diff --git a/#U4f7f#U7528#U9700#U9075#U5b88#U7684#U534f#U8bae-LICENSE.txt b/#U4f7f#U7528#U9700#U9075#U5b88#U7684#U534f#U8bae-LICENSE.txt
new file mode 100644
index 0000000000000000000000000000000000000000..0dca58d6cb0300a0e94bdd588dd7b87990b8adfd
--- /dev/null
+++ b/#U4f7f#U7528#U9700#U9075#U5b88#U7684#U534f#U8bae-LICENSE.txt
@@ -0,0 +1,50 @@
+MIT License
+
+Copyright (c) 2023 liujing04
+Copyright (c) 2023 源文雨
+
+ 本软件及其相关代码以MIT协议开源，作者不对软件具备任何控制力，使用软件者、传播软件导出的声音者自负全责。
+ 如不认可该条款，则不能使用或引用软件包内任何代码和文件。
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+特此授予任何获得本软件和相关文档文件（以下简称“软件”）副本的人免费使用、复制、修改、合并、出版、分发、再授权和/或销售本软件的权利，以及授予本软件所提供的人使用本软件的权利，但须符合以下条件：
+上述版权声明和本许可声明应包含在软件的所有副本或实质部分中。
+软件是“按原样”提供的，没有任何明示或暗示的保证，包括但不限于适销性、适用于特定目的和不侵权的保证。在任何情况下，作者或版权持有人均不承担因软件或软件的使用或其他交易而产生、产生或与之相关的任何索赔、损害赔偿或其他责任，无论是在合同诉讼、侵权诉讼还是其他诉讼中。
+
+相关引用库协议如下：
+#################
+ContentVec
+https://github.com/auspicious3000/contentvec/blob/main/LICENSE
+MIT License
+#################
+VITS
+https://github.com/jaywalnut310/vits/blob/main/LICENSE
+MIT License
+#################
+HIFIGAN
+https://github.com/jik876/hifi-gan/blob/master/LICENSE
+MIT License
+#################
+gradio
+https://github.com/gradio-app/gradio/blob/main/LICENSE
+Apache License 2.0
+#################
+ffmpeg
+https://github.com/FFmpeg/FFmpeg/blob/master/COPYING.LGPLv3
+https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2021-02-28-12-32/ffmpeg-n4.3.2-160-gfbb9368226-win64-lgpl-4.3.zip
+LPGLv3 License
+MIT License
+#################
+ultimatevocalremovergui
+https://github.com/Anjok07/ultimatevocalremovergui/blob/master/LICENSE
+https://github.com/yang123qwe/vocal_separation_by_uvr5
+MIT License
+#################
+audio-slicer
+https://github.com/openvpi/audio-slicer/blob/main/LICENSE
+MIT License
diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..b11eb0ff10845ec23055078b9d4257d5d467c519
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+logs/added_IVF2225_Flat_nprobe_1_simple-guitar-crepe-guolv_v2.index filter=lfs diff=lfs merge=lfs -text
+ffmpeg filter=lfs diff=lfs merge=lfs -text
diff --git a/Changelog_CN.md b/Changelog_CN.md
new file mode 100644
index 0000000000000000000000000000000000000000..0d66e5e331a0f566f31967ba767f7655de1e884b
--- /dev/null
+++ b/Changelog_CN.md
@@ -0,0 +1,68 @@
+### 20230528更新
+- 增加v2的jupyter notebook，韩文changelog，增加一些环境依赖
+- 增加呼吸、清辅音、齿音保护模式
+- 支持crepe-full推理
+- UVR5人声伴奏分离加上3个去延迟模型和MDX-Net去混响模型，增加HP3人声提取模型
+- 索引名称增加版本和实验名称
+- 人声伴奏分离、推理批量导出增加音频导出格式选项
+- 废弃32k模型的训练
+
+todolist：
+- 特征检索增加时序维度
+- 特征检索增加pre-kmeans可选项
+- 特征检索增加PCAR降维可选项
+- 支持onnx推理（附带仅推理的小压缩包）
+- 训练时在音高、gender、eq、噪声等方面对输入进行随机增强
+- 补全v2版本的48k预训练模型
+
+
+### 20230513更新
+- 清除一键包内部老版本runtime内残留的infer_pack和uvr5_pack
+- 修复训练集预处理伪多进程的bug
+- 增加harvest识别音高可选通过中值滤波削弱哑音现象，可调整中值滤波半径
+- 导出音频增加后处理重采样
+- 训练n_cpu进程数从"仅调整f0提取"改为"调整数据预处理和f0提取"
+- 自动检测logs文件夹下的index路径，提供下拉列表功能
+- tab页增加"常见问题解答"（也可参考github-rvc-wiki）
+- 相同路径的输入音频推理增加了音高缓存（用途：使用harvest音高提取，整个pipeline会经历漫长且重复的音高提取过程，如果不使用缓存，实验不同音色、索引、音高中值滤波半径参数的用户在第一次测试后的等待结果会非常痛苦）
+
+### 20230514更新
+- 音量包络对齐输入混合（可以缓解“输入静音输出小幅度噪声”的问题。如果输入音频背景底噪大则不建议开启，默认不开启（值为1可视为不开启））
+- 支持按照指定频率保存提取的小模型（假如你想尝试不同epoch下的推理效果，但是不想保存所有大checkpoint并且每次都要ckpt手工处理提取小模型，这项功能会非常实用）
+- 通过设置环境变量解决服务端开了系统全局代理导致浏览器连接错误的问题
+- 支持v2预训练模型（目前只公开了40k版本进行测试，另外2个采样率还没有训练完全）
+- 推理前限制超过1的过大音量
+- 微调数据预处理参数
+
+
+### 20230409更新
+- 修正训练参数，提升显卡平均利用率，A100最高从25%提升至90%左右，V100:50%->90%左右，2060S:60%->85%左右，P40:25%->95%左右，训练速度显著提升
+- 修正参数：总batch_size改为每张卡的batch_size
+- 修正total_epoch：最大限制100解锁至1000；默认10提升至默认20
+- 修复ckpt提取识别是否带音高错误导致推理异常的问题
+- 修复分布式训练每个rank都保存一次ckpt的问题
+- 特征提取进行nan特征过滤
+- 修复静音输入输出随机辅音or噪声的问题（老版模型需要重做训练集重训）
+
+### 20230416更新
+- 新增本地实时变声迷你GUI，双击go-realtime-gui.bat启动
+- 训练推理均对<50Hz的频段进行滤波过滤
+- 训练推理音高提取pyworld最低音高从默认80下降至50,50-80hz间的男声低音不会哑
+- WebUI支持根据系统区域变更语言（现支持en_US，ja_JP，zh_CN，zh_HK，zh_SG，zh_TW，不支持的默认en_US）
+- 修正部分显卡识别（例如V100-16G识别失败，P4识别失败）
+
+### 20230428更新
+- 升级faiss索引设置，速度更快，质量更高
+- 取消total_npy依赖，后续分享模型不再需要填写total_npy
+- 解锁16系限制。4G显存GPU给到4G的推理设置。
+- 修复部分音频格式下UVR5人声伴奏分离的bug
+- 实时变声迷你gui增加对非40k与不懈怠音高模型的支持
+
+### 后续计划：
+功能：
+- 支持多人训练选项卡（至多4人）
+
+底模：
+- 收集呼吸wav加入训练集修正呼吸变声电音的问题
+- 我们正在训练增加了歌声训练集的底模，未来会公开
+
diff --git a/Changelog_EN.md b/Changelog_EN.md
new file mode 100644
index 0000000000000000000000000000000000000000..0881006728615b332cfe8f7ccd79ff94738caed3
--- /dev/null
+++ b/Changelog_EN.md
@@ -0,0 +1,72 @@
+### 2023-05-28
+- Add v2 jupyter notebook, korean changelog, fix some environment requirments
+- Add voiceless consonant and breath protection mode
+- Support crepe-full pitch detect
+- UVR5 vocal separation: support dereverb models and de-echo models
+- Add experiment name and version on the name of index
+- Support users to manually select export format of output audios when batch voice conversion processing and UVR5 vocal separation
+- 32k model training is no more supported
+
+todolist：
+- Feature retrieval: add temporal feature retrieval
+- Feature retrieval: add pre-kmeans option
+- Feature retrieval: add PCAR dimensionality reduction
+- Add onnx inference support
+- Random data augmentation when training: pitch, gender, eq, noise
+- Add v2 version pretrained-models
+
+### 2023-05-13
+- Clear the redundant codes in the old version of runtime in the one-click-package: infer_pack and uvr5_pack
+- Fix pseudo multiprocessing bug in training set preprocessing
+- Adding median filtering radius adjustment for harvest pitch recognize algorithm
+- Support post processing resampling for exporting audio
+- Multi processing "n_cpu" setting for training is changed from "f0 extraction" to "data preprocessing and f0 extraction"
+- Automatically detect the index paths under the logs folder and provide a drop-down list function
+- Add "Frequently Asked Questions and Answers" on the tab page (you can also refer to github RVC wiki)
+- When inference, harvest pitch is cached when using same input audio path (purpose: using harvest pitch extraction, the entire pipeline will go through a long and repetitive pitch extraction process. If caching is not used, users who experiment with different timbre, index, and pitch median filtering radius settings will experience a very painful waiting process after the first inference)
+
+### 2023-05-14
+- Use volume envelope of input to mix or replace the volume envelope of output (can alleviate the problem of "input muting and output small amplitude noise". If the input audio background noise is high, it is not recommended to turn it on, and it is not turned on by default (1 can be considered as not turned on)
+- Support saving extracted small models at a specified frequency (if you want to see the performance under different epochs, but do not want to save all large checkpoints and manually extract small models by ckpt-processing every time, this feature will be very practical)
+- Resolve the issue of "connection errors" caused by the server's global proxy by setting environment variables
+- Supports pre-trained v2 models (currently only 40k versions are publicly available for testing, and the other two sampling rates have not been fully trained yet)
+- Limit excessive volume exceeding 1 before inference
+- Slightly adjusted the settings of training-set preprocessing
+
+
+#######################
+
+History changelogs:
+
+### 2023-04-09
+- Fixed training parameters to improve GPU utilization rate: A100 increased from 25% to around 90%, V100: 50% to around 90%, 2060S: 60% to around 85%, P40: 25% to around 95%; significantly improved training speed
+- Changed parameter: total batch_size is now per GPU batch_size
+- Changed total_epoch: maximum limit increased from 100 to 1000; default increased from 10 to 20
+- Fixed issue of ckpt extraction recognizing pitch incorrectly, causing abnormal inference
+- Fixed issue of distributed training saving ckpt for each rank
+- Applied nan feature filtering for feature extraction
+- Fixed issue with silent input/output producing random consonants or noise (old models need to retrain with a new dataset)
+
+### 2023-04-16 Update
+- Added local real-time voice changing mini-GUI, start by double-clicking go-realtime-gui.bat
+- Applied filtering for frequency bands below 50Hz during training and inference
+- Lowered the minimum pitch extraction of pyworld from the default 80 to 50 for training and inference, allowing male low-pitched voices between 50-80Hz not to be muted
+- WebUI supports changing languages according to system locale (currently supporting en_US, ja_JP, zh_CN, zh_HK, zh_SG, zh_TW; defaults to en_US if not supported)
+- Fixed recognition of some GPUs (e.g., V100-16G recognition failure, P4 recognition failure)
+
+### 2023-04-28 Update
+- Upgraded faiss index settings for faster speed and higher quality
+- Removed dependency on total_npy; future model sharing will not require total_npy input
+- Unlocked restrictions for the 16-series GPUs, providing 4GB inference settings for 4GB VRAM GPUs
+- Fixed bug in UVR5 vocal accompaniment separation for certain audio formats
+- Real-time voice changing mini-GUI now supports non-40k and non-lazy pitch models
+
+### Future Plans:
+Features:
+- Add option: extract small models for each epoch save
+- Add option: export additional mp3 to the specified path during inference
+- Support multi-person training tab (up to 4 people)
+
+Base model:
+- Collect breathing wav files to add to the training dataset to fix the issue of distorted breath sounds
+- We are currently training a base model with an extended singing dataset, which will be released in the future
diff --git a/Changelog_KO.md b/Changelog_KO.md
new file mode 100644
index 0000000000000000000000000000000000000000..fc782a7df3558883fa8c43b49d3fd8054a32113a
--- /dev/null
+++ b/Changelog_KO.md
@@ -0,0 +1,77 @@
+### 2023년 5월 28일 업데이트
+
+- v2 jupyter notebook 추가, 한국어 업데이트 로그 추가, 의존성 모듈 일부 수정.
+- 무성음 및 숨소리 보호 모드 추가.
+- crepe-full pitch 감지 지원.
+- UVR5 보컬 분리: 디버브 및 디-에코 모델 지원.
+- index 이름에 experiment 이름과 버전 추가.
+- 배치 음성 변환 처리 및 UVR5 보컬 분리 시, 사용자가 수동으로 출력 오디오의 내보내기(export) 형식을 선택할 수 있도록 지원.
+- 32k 훈련 모델 지원 종료.
+
+추후 업데이트 목록:
+
+- 특징 검색: 시간적 특징 검색 추가.
+- 특징 검색: pre-kmeans 옵션 추가.
+- 특징 검색: PCAR 차원 축소 추가.
+- onnx 추론 지원 추가.
+- 학습 시 랜덤 데이터 증강: 음고, 성별, eq, 잡음.
+- v2 버전 사전 훈련된 모델 추가.
+
+### 2023년 5월 13일 업데이트
+
+- 원클릭 패키지의 이전 버전 런타임 내, 불필요한 코드(infer_pack 및 uvr5_pack) 제거.
+- 훈련 세트 전처리의 유사 다중 처리 버그 수정.
+- Harvest 피치 인식 알고리즘에 대한 중위수 필터링 반경 조정 추가.
+- 오디오 내보낼 때, 후처리 리샘플링 지원.
+- 훈련에 대한 다중 처리 "n_cpu" 설정이 "f0 추출"에서 "데이터 전처리 및 f0 추출"로 변경.
+- logs 폴더 하의 인덱스 경로를 자동으로 감지 및 드롭다운 목록 기능 제공.
+- 탭 페이지에 "자주 묻는 질문과 답변" 추가. (github RVC wiki 참조 가능)
+- 동일한 입력 오디오 경로를 사용할 때 추론, Harvest 피치를 캐시.
+ (주의: Harvest 피치 추출을 사용하면 전체 파이프라인은 길고 반복적인 피치 추출 과정을 거치게됩니다. 캐싱을 하지 않는다면, 첫 inference 이후의 단계에서 timbre, 인덱스, 피치 중위수 필터링 반경 설정 등 대기시간이 엄청나게 길어집니다!)
+
+### 2023년 5월 14일 업데이트
+
+- 입력의 볼륨 캡슐을 사용하여 출력의 볼륨 캡슐을 혼합하거나 대체. (입력이 무음이거나 출력의 노이즈 문제를 최소화 할 수 있습니다. 입력 오디오의 배경 노이즈(소음)가 큰 경우 해당 기능을 사용하지 않는 것이 좋습니다. 기본적으로 비활성화 되어있는 옵션입니다. (1: 비활성화 상태))
+- 추출된 소형 모델을 지정된 빈도로 저장하는 기능을 지원. (다양한 에폭 하에서의 성능을 보려고 하지만 모든 대형 체크포인트를 저장하고 매번 ckpt 처리를 통해 소형 모델을 수동으로 추출하고 싶지 않은 경우 이 기능은 매우 유용합니다)
+- 환경 변수를 설정하여 서버의 전역 프록시로 인한 "연결 오류" 문제 해결.
+- 사전 훈련된 v2 모델 지원. (현재 40k 버전만 테스트를 위해 공개적으로 사용 가능하며, 다른 두 개의 샘플링 비율은 아직 완전히 훈련되지 않아 보류되었습니다.)
+- 추론 전, 1을 초과하는 과도한 볼륨 제한.
+- 데이터 전처리 매개변수 미세 조정.
+
+### 2023년 4월 9일 업데이트
+
+- GPU 이용률 향상을 위해 훈련 파라미터 수정: A100은 25%에서 약 90%로 증가, V100: 50%에서 약 90%로 증가, 2060S: 60%에서 약 85%로 증가, P40: 25%에서 약 95%로 증가.
+ 훈련 속도가 크게 향상.
+- 매개변수 기준 변경: total batch_size는 GPU당 batch_size를 의미.
+- total_epoch 변경: 최대 한도가 100에서 1000으로 증가. 기본값이 10에서 20으로 증가.
+- ckpt 추출이 피치를 잘못 인식하여 비정상적인 추론을 유발하는 문제 수정.
+- 분산 훈련 과정에서 각 랭크마다 ckpt를 저장하는 문제 수정.
+- 특성 추출 과정에 나노 특성 필터링 적용.
+- 무음 입력/출력이 랜덤하게 소음을 생성하는 문제 수정. (이전 모델은 새 데이터셋으로 다시 훈련해야 합니다)
+
+### 2023년 4월 16일 업데이트
+
+- 로컬 실시간 음성 변경 미니-GUI 추가, go-realtime-gui.bat를 더블 클릭하여 시작.
+- 훈련 및 추론 중 50Hz 이하의 주파수 대역에 대해 필터링 적용.
+- 훈련 및 추론의 pyworld 최소 피치 추출을 기본 80에서 50으로 낮춤. 이로 인해, 50-80Hz 사이의 남성 저음이 무음화되지 않습니다.
+- 시스템 지역에 따른 WebUI 언어 변경 지원. (현재 en_US, ja_JP, zh_CN, zh_HK, zh_SG, zh_TW를 지원하며, 지원되지 않는 경우 기본값은 en_US)
+- 일부 GPU의 인식 수정. (예: V100-16G 인식 실패, P4 인식 실패)
+
+### 2023년 4월 28일 업데이트
+
+- Faiss 인덱스 설정 업그레이드로 속도가 더 빨라지고 품질이 향상.
+- total_npy에 대한 의존성 제거. 추후의 모델 공유는 total_npy 입력을 필요로 하지 않습니다.
+- 16 시리즈 GPU에 대한 제한 해제, 4GB VRAM GPU에 대한 4GB 추론 설정 제공.
+- 일부 오디오 형식에 대한 UVR5 보컬 동반 분리에서의 버그 수정.
+- 실시간 음성 변경 미니-GUI는 이제 non-40k 및 non-lazy 피치 모델을 지원합니다.
+
+### 추후 계획
+
+Features:
+
+- 다중 사용자 훈련 탭 지원.(최대 4명)
+
+Base model:
+
+- 훈련 데이터셋에 숨소리 wav 파일을 추가하여, 보컬의 호흡이 노이즈로 변환되는 문제 수정.
+- 보컬 훈련 세트의 기본 모델을 추가하기 위한 작업을 진행중이며, 이는 향후에 발표될 예정.
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..49f62d5f9c0901931de6523721b3a97b40f34219
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,13 @@
+# syntax=docker/dockerfile:1
+
+FROM python:3.10-bullseye
+
+EXPOSE 7865
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip3 install -r requirements.txt
+
+CMD ["python3", "infer-web.py"]
\ No newline at end of file
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000000000000000000000000000000000000..8af94bd3569d2c96a532e51f4e3ea32261bc80a6
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 liujing04
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
diff --git a/MDXNet.py b/MDXNet.py
new file mode 100644
index 0000000000000000000000000000000000000000..99780afb2266a058a172e13c74e63c92b115e8c2
--- /dev/null
+++ b/MDXNet.py
@@ -0,0 +1,274 @@
+import soundfile as sf
+import torch, pdb, time, argparse, os, warnings, sys, librosa
+import numpy as np
+import onnxruntime as ort
+from scipy.io.wavfile import write
+from tqdm import tqdm
+import torch
+import torch.nn as nn
+
+dim_c = 4
+
+
+class Conv_TDF_net_trim:
+ def __init__(
+ self, device, model_name, target_name, L, dim_f, dim_t, n_fft, hop=1024
+ ):
+ super(Conv_TDF_net_trim, self).__init__()
+
+ self.dim_f = dim_f
+ self.dim_t = 2**dim_t
+ self.n_fft = n_fft
+ self.hop = hop
+ self.n_bins = self.n_fft // 2 + 1
+ self.chunk_size = hop * (self.dim_t - 1)
+ self.window = torch.hann_window(window_length=self.n_fft, periodic=True).to(
+ device
+ )
+ self.target_name = target_name
+ self.blender = "blender" in model_name
+
+ out_c = dim_c * 4 if target_name == "*" else dim_c
+ self.freq_pad = torch.zeros(
+ [1, out_c, self.n_bins - self.dim_f, self.dim_t]
+ ).to(device)
+
+ self.n = L // 2
+
+ def stft(self, x):
+ x = x.reshape([-1, self.chunk_size])
+ x = torch.stft(
+ x,
+ n_fft=self.n_fft,
+ hop_length=self.hop,
+ window=self.window,
+ center=True,
+ return_complex=True,
+ )
+ x = torch.view_as_real(x)
+ x = x.permute([0, 3, 1, 2])
+ x = x.reshape([-1, 2, 2, self.n_bins, self.dim_t]).reshape(
+ [-1, dim_c, self.n_bins, self.dim_t]
+ )
+ return x[:, :, : self.dim_f]
+
+ def istft(self, x, freq_pad=None):
+ freq_pad = (
+ self.freq_pad.repeat([x.shape[0], 1, 1, 1])
+ if freq_pad is None
+ else freq_pad
+ )
+ x = torch.cat([x, freq_pad], -2)
+ c = 4 * 2 if self.target_name == "*" else 2
+ x = x.reshape([-1, c, 2, self.n_bins, self.dim_t]).reshape(
+ [-1, 2, self.n_bins, self.dim_t]
+ )
+ x = x.permute([0, 2, 3, 1])
+ x = x.contiguous()
+ x = torch.view_as_complex(x)
+ x = torch.istft(
+ x, n_fft=self.n_fft, hop_length=self.hop, window=self.window, center=True
+ )
+ return x.reshape([-1, c, self.chunk_size])
+
+
+def get_models(device, dim_f, dim_t, n_fft):
+ return Conv_TDF_net_trim(
+ device=device,
+ model_name="Conv-TDF",
+ target_name="vocals",
+ L=11,
+ dim_f=dim_f,
+ dim_t=dim_t,
+ n_fft=n_fft,
+ )
+
+
+warnings.filterwarnings("ignore")
+cpu = torch.device("cpu")
+if torch.cuda.is_available():
+ device = torch.device("cuda:0")
+elif torch.backends.mps.is_available():
+ device = torch.device("mps")
+else:
+ device = torch.device("cpu")
+
+
+class Predictor:
+ def __init__(self, args):
+ self.args = args
+ self.model_ = get_models(
+ device=cpu, dim_f=args.dim_f, dim_t=args.dim_t, n_fft=args.n_fft
+ )
+ self.model = ort.InferenceSession(
+ os.path.join(args.onnx, self.model_.target_name + ".onnx"),
+ providers=["CUDAExecutionProvider", "CPUExecutionProvider"],
+ )
+ print("onnx load done")
+
+ def demix(self, mix):
+ samples = mix.shape[-1]
+ margin = self.args.margin
+ chunk_size = self.args.chunks * 44100
+ assert not margin == 0, "margin cannot be zero!"
+ if margin > chunk_size:
+ margin = chunk_size
+
+ segmented_mix = {}
+
+ if self.args.chunks == 0 or samples < chunk_size:
+ chunk_size = samples
+
+ counter = -1
+ for skip in range(0, samples, chunk_size):
+ counter += 1
+
+ s_margin = 0 if counter == 0 else margin
+ end = min(skip + chunk_size + margin, samples)
+
+ start = skip - s_margin
+
+ segmented_mix[skip] = mix[:, start:end].copy()
+ if end == samples:
+ break
+
+ sources = self.demix_base(segmented_mix, margin_size=margin)
+ """
+ mix:(2,big_sample)
+ segmented_mix:offset->(2,small_sample)
+ sources:(1,2,big_sample)
+ """
+ return sources
+
+ def demix_base(self, mixes, margin_size):
+ chunked_sources = []
+ progress_bar = tqdm(total=len(mixes))
+ progress_bar.set_description("Processing")
+ for mix in mixes:
+ cmix = mixes[mix]
+ sources = []
+ n_sample = cmix.shape[1]
+ model = self.model_
+ trim = model.n_fft // 2
+ gen_size = model.chunk_size - 2 * trim
+ pad = gen_size - n_sample % gen_size
+ mix_p = np.concatenate(
+ (np.zeros((2, trim)), cmix, np.zeros((2, pad)), np.zeros((2, trim))), 1
+ )
+ mix_waves = []
+ i = 0
+ while i < n_sample + pad:
+ waves = np.array(mix_p[:, i : i + model.chunk_size])
+ mix_waves.append(waves)
+ i += gen_size
+ mix_waves = torch.tensor(mix_waves, dtype=torch.float32).to(cpu)
+ with torch.no_grad():
+ _ort = self.model
+ spek = model.stft(mix_waves)
+ if self.args.denoise:
+ spec_pred = (
+ -_ort.run(None, {"input": -spek.cpu().numpy()})[0] * 0.5
+ + _ort.run(None, {"input": spek.cpu().numpy()})[0] * 0.5
+ )
+ tar_waves = model.istft(torch.tensor(spec_pred))
+ else:
+ tar_waves = model.istft(
+ torch.tensor(_ort.run(None, {"input": spek.cpu().numpy()})[0])
+ )
+ tar_signal = (
+ tar_waves[:, :, trim:-trim]
+ .transpose(0, 1)
+ .reshape(2, -1)
+ .numpy()[:, :-pad]
+ )
+
+ start = 0 if mix == 0 else margin_size
+ end = None if mix == list(mixes.keys())[::-1][0] else -margin_size
+ if margin_size == 0:
+ end = None
+ sources.append(tar_signal[:, start:end])
+
+ progress_bar.update(1)
+
+ chunked_sources.append(sources)
+ _sources = np.concatenate(chunked_sources, axis=-1)
+ # del self.model
+ progress_bar.close()
+ return _sources
+
+ def prediction(self, m, vocal_root, others_root, format):
+ os.makedirs(vocal_root, exist_ok=True)
+ os.makedirs(others_root, exist_ok=True)
+ basename = os.path.basename(m)
+ mix, rate = librosa.load(m, mono=False, sr=44100)
+ if mix.ndim == 1:
+ mix = np.asfortranarray([mix, mix])
+ mix = mix.T
+ sources = self.demix(mix.T)
+ opt = sources[0].T
+ if format in ["wav", "flac"]:
+ sf.write(
+ "%s/%s_main_vocal.%s" % (vocal_root, basename, format), mix - opt, rate
+ )
+ sf.write("%s/%s_others.%s" % (others_root, basename, format), opt, rate)
+ else:
+ path_vocal = "%s/%s_main_vocal.wav" % (vocal_root, basename)
+ path_other = "%s/%s_others.wav" % (others_root, basename)
+ sf.write(path_vocal, mix - opt, rate)
+ sf.write(path_other, opt, rate)
+ if os.path.exists(path_vocal):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path_vocal, path_vocal[:-4] + ".%s" % format)
+ )
+ if os.path.exists(path_other):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path_other, path_other[:-4] + ".%s" % format)
+ )
+
+
+class MDXNetDereverb:
+ def __init__(self, chunks):
+ self.onnx = "uvr5_weights/onnx_dereverb_By_FoxJoy"
+ self.shifts = 10 #'Predict with randomised equivariant stabilisation'
+ self.mixing = "min_mag" # ['default','min_mag','max_mag']
+ self.chunks = chunks
+ self.margin = 44100
+ self.dim_t = 9
+ self.dim_f = 3072
+ self.n_fft = 6144
+ self.denoise = True
+ self.pred = Predictor(self)
+
+ def _path_audio_(self, input, vocal_root, others_root, format):
+ self.pred.prediction(input, vocal_root, others_root, format)
+
+
+if __name__ == "__main__":
+ dereverb = MDXNetDereverb(15)
+ from time import time as ttime
+
+ t0 = ttime()
+ dereverb._path_audio_(
+ "雪雪伴奏对消HP5.wav",
+ "vocal",
+ "others",
+ )
+ t1 = ttime()
+ print(t1 - t0)
+
+
+"""
+
+runtime\python.exe MDXNet.py
+
+6G:
+15/9:0.8G->6.8G
+14:0.8G->6.5G
+25:炸
+
+half15:0.7G->6.6G,22.69s
+fp32-15:0.7G->6.6G,20.85s
+
+"""
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b7c03e1a5b01250d0d837e9676286cd569a1b2a1
--- /dev/null
+++ b/README.md
@@ -0,0 +1,14 @@
+---
+title: Vocal2guitar
+emoji: 🏃
+colorFrom: indigo
+colorTo: red
+sdk: gradio
+sdk_version: 3.34.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: lj1995/vocal2guitar
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/Retrieval_based_Voice_Conversion_WebUI.ipynb b/Retrieval_based_Voice_Conversion_WebUI.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..956fed9bcf94bef47e527d1dea85c1831687a4bc
--- /dev/null
+++ b/Retrieval_based_Voice_Conversion_WebUI.ipynb
@@ -0,0 +1,381 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "private_outputs": true,
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "accelerator": "GPU",
+ "gpuClass": "standard"
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"
+ ],
+ "metadata": {
+ "id": "ZFFCx5J80SGa"
+ }
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "GmFP6bN9dvOq"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 查看显卡\n",
+ "!nvidia-smi"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 安装依赖\n",
+ "!apt-get -y install build-essential python3-dev ffmpeg\n",
+ "!pip3 install --upgrade setuptools wheel\n",
+ "!pip3 install --upgrade pip\n",
+ "!pip3 install faiss-gpu fairseq gradio ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
+ ],
+ "metadata": {
+ "id": "wjddIFr1oS3W"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 克隆仓库\n",
+ "\n",
+ "!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
+ "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+ "!mkdir -p pretrained uvr5_weights"
+ ],
+ "metadata": {
+ "id": "ge_97mfpgqTm"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 更新仓库（一般无需执行）\n",
+ "!git pull"
+ ],
+ "metadata": {
+ "id": "BLDEZADkvlw1"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 安装aria2\n",
+ "!apt -y install -qq aria2"
+ ],
+ "metadata": {
+ "id": "pqE0PrnuRqI2"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 下载底模\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth"
+ ],
+ "metadata": {
+ "id": "UG3XpUwEomUz"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 下载人声分离模型\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+ ],
+ "metadata": {
+ "id": "HugjmZqZRuiF"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 下载hubert_base\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+ ],
+ "metadata": {
+ "id": "2RCaT9FTR0ej"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 挂载谷歌云盘\n",
+ "\n",
+ "from google.colab import drive\n",
+ "drive.mount('/content/drive')"
+ ],
+ "metadata": {
+ "id": "jwu07JgqoFON"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
+ "\n",
+ "#@markdown 数据集位置\n",
+ "DATASET = \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\" #@param {type:\"string\"}\n",
+ "\n",
+ "!mkdir -p /content/dataset\n",
+ "!unzip -d /content/dataset -B {DATASET}"
+ ],
+ "metadata": {
+ "id": "Mwk7Q0Loqzjx"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 重命名数据集中的重名文件\n",
+ "!ls -a /content/dataset/\n",
+ "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
+ ],
+ "metadata": {
+ "id": "PDlFxWHWEynD"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 启动web\n",
+ "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+ "# %load_ext tensorboard\n",
+ "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
+ "!python3 infer-web.py --colab --pycmd python3"
+ ],
+ "metadata": {
+ "id": "7vh6vphDwO0b"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 手动将训练后的模型文件备份到谷歌云盘\n",
+ "#@markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+ "\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 模型epoch\n",
+ "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
+ "\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
+ "\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
+ ],
+ "metadata": {
+ "id": "FgJuNeAwx5Y_"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 从谷歌云盘恢复pth\n",
+ "#@markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+ "\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 模型epoch\n",
+ "MODELEPOCH = 7500 #@param {type:\"integer\"}\n",
+ "\n",
+ "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+ "\n",
+ "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+ "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+ "!cp /content/drive/MyDrive/*.index /content/\n",
+ "!cp /content/drive/MyDrive/*.npy /content/\n",
+ "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
+ ],
+ "metadata": {
+ "id": "OVQoLQJXS7WX"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 手动预处理（不推荐）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 采样率\n",
+ "BITRATE = 48000 #@param {type:\"integer\"}\n",
+ "#@markdown 使用的进程数\n",
+ "THREADCOUNT = 8 #@param {type:\"integer\"}\n",
+ "\n",
+ "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True\n"
+ ],
+ "metadata": {
+ "id": "ZKAyuKb9J6dz"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 手动提取特征（不推荐）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 使用的进程数\n",
+ "THREADCOUNT = 8 #@param {type:\"integer\"}\n",
+ "#@markdown 音高提取算法\n",
+ "ALGO = \"harvest\" #@param {type:\"string\"}\n",
+ "\n",
+ "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+ "\n",
+ "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}\n"
+ ],
+ "metadata": {
+ "id": "CrxJqzAUKmPJ"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 手动训练（不推荐）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 使用的GPU\n",
+ "USEGPU = \"0\" #@param {type:\"string\"}\n",
+ "#@markdown 批大小\n",
+ "BATCHSIZE = 32 #@param {type:\"integer\"}\n",
+ "#@markdown 停止的epoch\n",
+ "MODELEPOCH = 3200 #@param {type:\"integer\"}\n",
+ "#@markdown 保存epoch间隔\n",
+ "EPOCHSAVE = 100 #@param {type:\"integer\"}\n",
+ "#@markdown 采样率\n",
+ "MODELSAMPLE = \"48k\" #@param {type:\"string\"}\n",
+ "#@markdown 是否缓存训练集\n",
+ "CACHEDATA = 1 #@param {type:\"integer\"}\n",
+ "#@markdown 是否仅保存最新的ckpt文件\n",
+ "ONLYLATEST = 0 #@param {type:\"integer\"}\n",
+ "\n",
+ "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}\n"
+ ],
+ "metadata": {
+ "id": "IMLPLKOaKj58"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 选中模型epoch\n",
+ "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
+ "\n",
+ "!echo \"备份选中的模型。。。\"\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"正在删除。。。\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+ "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
+ "\n",
+ "!echo \"恢复选中的模型。。。\"\n",
+ "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth \n",
+ "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"删除完成\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+ ],
+ "metadata": {
+ "id": "haYA81hySuDl"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#@title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 选中模型epoch\n",
+ "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
+ "\n",
+ "!echo \"备份选中的模型。。。\"\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"正在删除。。。\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+ "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
+ "\n",
+ "!echo \"恢复选中的模型。。。\"\n",
+ "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth \n",
+ "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"删除完成\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+ ],
+ "metadata": {
+ "id": "QhSiPTVPoIRh"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
diff --git a/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb b/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..cf9b34966b1c622e2291e54a78a278f79c25e730
--- /dev/null
+++ b/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb
@@ -0,0 +1,401 @@
+{
+ "cells": [
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "ZFFCx5J80SGa"
+ },
+ "source": [
+ "[](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "GmFP6bN9dvOq"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 查看显卡\n",
+ "!nvidia-smi"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "wjddIFr1oS3W"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 安装依赖\n",
+ "!apt-get -y install build-essential python3-dev ffmpeg\n",
+ "!pip3 install --upgrade setuptools wheel\n",
+ "!pip3 install --upgrade pip\n",
+ "!pip3 install faiss-gpu fairseq gradio ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "ge_97mfpgqTm"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 克隆仓库\n",
+ "\n",
+ "!mkdir Retrieval-based-Voice-Conversion-WebUI\n",
+ "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+ "!git init\n",
+ "!git remote add origin https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git\n",
+ "!git fetch origin cfd984812804ddc9247d65b14c82cd32e56c1133 --depth=1 \n",
+ "!git reset --hard FETCH_HEAD"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "BLDEZADkvlw1"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 更新仓库（一般无需执行）\n",
+ "!git pull"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "pqE0PrnuRqI2"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 安装aria2\n",
+ "!apt -y install -qq aria2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "UG3XpUwEomUz"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 下载底模\n",
+ "\n",
+ "# v1\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth\n",
+ "\n",
+ "#v2\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D40k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D48k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G40k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G48k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D40k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D48k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G32k.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G40k.pth\n",
+ "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G48k.pth"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "HugjmZqZRuiF"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 下载人声分离模型\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "2RCaT9FTR0ej"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 下载hubert_base\n",
+ "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "jwu07JgqoFON"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 挂载谷歌云盘\n",
+ "\n",
+ "from google.colab import drive\n",
+ "drive.mount('/content/drive')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Mwk7Q0Loqzjx"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
+ "\n",
+ "#@markdown 数据集位置\n",
+ "DATASET = \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\" #@param {type:\"string\"}\n",
+ "\n",
+ "!mkdir -p /content/dataset\n",
+ "!unzip -d /content/dataset -B {DATASET}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "PDlFxWHWEynD"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 重命名数据集中的重名文件\n",
+ "!ls -a /content/dataset/\n",
+ "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "7vh6vphDwO0b"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 启动web\n",
+ "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+ "# %load_ext tensorboard\n",
+ "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
+ "!python3 infer-web.py --colab --pycmd python3"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "FgJuNeAwx5Y_"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 手动将训练后的模型文件备份到谷歌云盘\n",
+ "#@markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+ "\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 模型epoch\n",
+ "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
+ "\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
+ "\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "OVQoLQJXS7WX"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 从谷歌云盘恢复pth\n",
+ "#@markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+ "\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 模型epoch\n",
+ "MODELEPOCH = 7500 #@param {type:\"integer\"}\n",
+ "\n",
+ "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+ "\n",
+ "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+ "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+ "!cp /content/drive/MyDrive/*.index /content/\n",
+ "!cp /content/drive/MyDrive/*.npy /content/\n",
+ "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "ZKAyuKb9J6dz"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 手动预处理（不推荐）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 采样率\n",
+ "BITRATE = 48000 #@param {type:\"integer\"}\n",
+ "#@markdown 使用的进程数\n",
+ "THREADCOUNT = 8 #@param {type:\"integer\"}\n",
+ "\n",
+ "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "CrxJqzAUKmPJ"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 手动提取特征（不推荐）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 使用的进程数\n",
+ "THREADCOUNT = 8 #@param {type:\"integer\"}\n",
+ "#@markdown 音高提取算法\n",
+ "ALGO = \"harvest\" #@param {type:\"string\"}\n",
+ "\n",
+ "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+ "\n",
+ "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "IMLPLKOaKj58"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 手动训练（不推荐）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 使用的GPU\n",
+ "USEGPU = \"0\" #@param {type:\"string\"}\n",
+ "#@markdown 批大小\n",
+ "BATCHSIZE = 32 #@param {type:\"integer\"}\n",
+ "#@markdown 停止的epoch\n",
+ "MODELEPOCH = 3200 #@param {type:\"integer\"}\n",
+ "#@markdown 保存epoch间隔\n",
+ "EPOCHSAVE = 100 #@param {type:\"integer\"}\n",
+ "#@markdown 采样率\n",
+ "MODELSAMPLE = \"48k\" #@param {type:\"string\"}\n",
+ "#@markdown 是否缓存训练集\n",
+ "CACHEDATA = 1 #@param {type:\"integer\"}\n",
+ "#@markdown 是否仅保存最新的ckpt文件\n",
+ "ONLYLATEST = 0 #@param {type:\"integer\"}\n",
+ "\n",
+ "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "haYA81hySuDl"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 选中模型epoch\n",
+ "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
+ "\n",
+ "!echo \"备份选中的模型。。。\"\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"正在删除。。。\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+ "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
+ "\n",
+ "!echo \"恢复选中的模型。。。\"\n",
+ "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth \n",
+ "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"删除完成\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "QhSiPTVPoIRh"
+ },
+ "outputs": [],
+ "source": [
+ "#@title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
+ "#@markdown 模型名\n",
+ "MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
+ "#@markdown 选中模型epoch\n",
+ "MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
+ "\n",
+ "!echo \"备份选中的模型。。。\"\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+ "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"正在删除。。。\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+ "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
+ "\n",
+ "!echo \"恢复选中的模型。。。\"\n",
+ "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth \n",
+ "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+ "\n",
+ "!echo \"删除完成\"\n",
+ "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+ ]
+ }
+ ],
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "private_outputs": true,
+ "provenance": []
+ },
+ "gpuClass": "standard",
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/__pycache__/config.cpython-39.pyc b/__pycache__/config.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..094f2835122f2a692adf2f3b08eeb0d283194f7a
Binary files /dev/null and b/__pycache__/config.cpython-39.pyc differ
diff --git a/__pycache__/i18n.cpython-39.pyc b/__pycache__/i18n.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..a684b2b86d4df0d66d81405117c1a3a6af3ab757
Binary files /dev/null and b/__pycache__/i18n.cpython-39.pyc differ
diff --git a/__pycache__/my_utils.cpython-39.pyc b/__pycache__/my_utils.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..0730e3c094425bffb78463ac5becc2a94a0ef2f4
Binary files /dev/null and b/__pycache__/my_utils.cpython-39.pyc differ
diff --git a/__pycache__/vc_infer_pipeline.cpython-39.pyc b/__pycache__/vc_infer_pipeline.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..88f22097fc810f10d90f898c2a140a30b999ec14
Binary files /dev/null and b/__pycache__/vc_infer_pipeline.cpython-39.pyc differ
diff --git a/app.py b/app.py
new file mode 100644
index 0000000000000000000000000000000000000000..83b12007eed88489cc12d07b40654320c40da573
--- /dev/null
+++ b/app.py
@@ -0,0 +1,163 @@
+import io
+import os
+os.system("chmod 777 ffmpeg")
+import torch
+import gradio as gr
+import librosa
+import numpy as np
+import soundfile
+import logging
+from fairseq import checkpoint_utils
+from my_utils import load_audio
+from vc_infer_pipeline import VC
+import traceback
+from config import Config
+from infer_pack.models import (
+ SynthesizerTrnMs256NSFsid,
+ SynthesizerTrnMs256NSFsid_nono,
+ SynthesizerTrnMs768NSFsid,
+ SynthesizerTrnMs768NSFsid_nono,
+)
+from i18n import I18nAuto
+
+logging.getLogger("numba").setLevel(logging.WARNING)
+logging.getLogger("markdown_it").setLevel(logging.WARNING)
+logging.getLogger("urllib3").setLevel(logging.WARNING)
+logging.getLogger("matplotlib").setLevel(logging.WARNING)
+
+i18n = I18nAuto()
+i18n.print()
+
+config = Config()
+
+models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
+ ["hubert_base.pt"],
+ suffix="",
+)
+hubert_model = models[0]
+hubert_model = hubert_model.to(config.device)
+hubert_model = hubert_model.float()
+hubert_model.eval()
+
+global n_spk, tgt_sr, net_g, vc, cpt, version
+person = "weights/simple-guitar-crepe-guolv_e1000.pth"
+print("loading %s" % person)
+cpt = torch.load(person, map_location="cpu")
+tgt_sr = cpt["config"][-1]
+cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
+net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=False)
+del net_g.enc_q
+print(net_g.load_state_dict(cpt["weight"], strict=False))
+net_g.eval().to(config.device)
+net_g = net_g.float()
+vc = VC(tgt_sr, config)
+n_spk = cpt["config"][-3]
+version="v2"
+
+default_audio=load_audio("logs/mute/1_16k_wavs/mute.wav",16000)
+def vc_single(
+ # sid=0,
+ input_audio_path,#待选取
+ f0_up_key,#待选取
+ f0_method,
+ file_index="logs/added_IVF2225_Flat_nprobe_1_simple-guitar-crepe-guolv_v2.index",#写死
+ index_rate=1,#写死1
+ filter_radius=3,#不需要，随便写，3
+ resample_sr=0,#写死0不需要
+ rms_mix_rate=1,#写死1不需要
+ protect=0.5,#写死0.5不需要
+):
+ global tgt_sr, net_g, vc, hubert_model, version
+ if input_audio_path is None:
+ return "You need to upload an audio", None
+ f0_up_key = int(f0_up_key)
+ try:
+ audio = input_audio_path[1] / 32768.0
+ if len(audio.shape) == 2:
+ audio = np.mean(audio, -1)
+ audio = librosa.resample(audio, orig_sr=input_audio_path[0], target_sr=16000)
+ audio_max = np.abs(audio).max() / 0.95
+ if audio_max > 1:
+ audio /= audio_max
+ times = [0, 0, 0]
+ audio_opt = vc.pipeline(
+ model=hubert_model,
+ net_g=net_g,
+ sid=0,
+ audio=audio,
+ input_audio_path="123",
+ times=times,
+ f0_up_key=f0_up_key,
+ f0_method=f0_method,
+ file_index=file_index,
+ index_rate=index_rate,
+ if_f0=1,
+ filter_radius=filter_radius,
+ tgt_sr=tgt_sr,
+ resample_sr=resample_sr,
+ rms_mix_rate=rms_mix_rate,
+ version="v2",
+ protect=protect,
+ f0_file=None,
+ )
+ if resample_sr >= 16000 and tgt_sr != resample_sr:
+ tgt_sr = resample_sr
+ index_info = (
+ "Using index:%s." % file_index
+ if os.path.exists(file_index)
+ else "Index not used."
+ )
+ return "Success.\n %s\nTime:\n npy:%ss, f0:%ss, infer:%ss" % (
+ index_info,
+ times[0],
+ times[1],
+ times[2],
+ ), (tgt_sr, audio_opt)
+ except:
+ info = traceback.format_exc()
+ print(info)
+ return "报错了！信息如下：%s"%info, (16000, default_audio)
+
+app = gr.Blocks()
+with app:
+ with gr.Tabs():
+ with gr.TabItem("人声转吉他极简在线demo"):
+ gr.Markdown(
+ value="""
+ 变调越高吉他音越细，越低越沉闷
+ """
+ )
+ vc_input = gr.Audio(label="上传音频")
+ with gr.Column():
+ with gr.Row():
+ vc_transform = gr.Slider(
+ minimum=-12,
+ maximum=12,
+ label="变调(半音数量,升八度12降八度-12)",
+ value=0,
+ step=1,
+ interactive=True,
+ )
+ f0method = gr.Radio(
+ label=i18n(
+ "选择音高提取算法:语音推荐dio歌声推荐pm"
+ ),
+ choices=["pm", "dio"],
+ value="dio",
+ interactive=True,
+ )
+ with gr.Row():
+ but = gr.Button(i18n("转换"), variant="primary")
+ vc_output1 = gr.Textbox(label=i18n("输出信息"))
+ vc_output2 = gr.Audio(label=i18n("输出音频(右下角三个点,点了可以下载)"))
+ but.click(
+ vc_single,
+ [
+ vc_input,
+ vc_transform,
+ f0method
+ ],
+ [vc_output1, vc_output2],
+ )
+
+app.launch(server_name="0.0.0.0",quiet=True)
diff --git a/config.py b/config.py
new file mode 100644
index 0000000000000000000000000000000000000000..426994f4700f3b46c82deebc8acaec60b7570e5b
--- /dev/null
+++ b/config.py
@@ -0,0 +1,110 @@
+import argparse
+import torch
+from multiprocessing import cpu_count
+
+
+def config_file_change_fp32():
+ for config_file in ["32k.json", "40k.json", "48k.json"]:
+ with open(f"configs/{config_file}", "r") as f:
+ strr = f.read().replace("true", "false")
+ with open(f"configs/{config_file}", "w") as f:
+ f.write(strr)
+ with open("trainset_preprocess_pipeline_print.py", "r") as f:
+ strr = f.read().replace("3.7", "3.0")
+ with open("trainset_preprocess_pipeline_print.py", "w") as f:
+ f.write(strr)
+
+
+class Config:
+ def __init__(self):
+ self.device = "cuda:0"
+ self.is_half = True
+ self.n_cpu = 0
+ self.gpu_name = None
+ self.gpu_mem = None
+ (
+ self.python_cmd,
+ self.listen_port,
+ self.iscolab,
+ self.noparallel,
+ self.noautoopen,
+ ) = self.arg_parse()
+ self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
+
+ @staticmethod
+ def arg_parse() -> tuple:
+ parser = argparse.ArgumentParser()
+ parser.add_argument("--port", type=int, default=7865, help="Listen port")
+ parser.add_argument(
+ "--pycmd", type=str, default="python", help="Python command"
+ )
+ parser.add_argument("--colab", action="store_true", help="Launch in colab")
+ parser.add_argument(
+ "--noparallel", action="store_true", help="Disable parallel processing"
+ )
+ parser.add_argument(
+ "--noautoopen",
+ action="store_true",
+ help="Do not open in browser automatically",
+ )
+ cmd_opts = parser.parse_args()
+
+ cmd_opts.port = cmd_opts.port if 0 <= cmd_opts.port <= 65535 else 7865
+
+ return (
+ cmd_opts.pycmd,
+ cmd_opts.port,
+ cmd_opts.colab,
+ cmd_opts.noparallel,
+ cmd_opts.noautoopen,
+ )
+
+ def device_config(self) -> tuple:
+ if torch.cuda.is_available():
+ i_device = int(self.device.split(":")[-1])
+ self.gpu_name = torch.cuda.get_device_name(i_device)
+ if (
+ ("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
+ or "P40" in self.gpu_name.upper()
+ or "1060" in self.gpu_name
+ or "1070" in self.gpu_name
+ or "1080" in self.gpu_name
+ ):
+ print("16系/10系显卡和P40强制单精度")
+ self.is_half = False
+ config_file_change_fp32()
+ else:
+ self.gpu_name = None
+ self.gpu_mem = int(
+ torch.cuda.get_device_properties(i_device).total_memory
+ / 1024
+ / 1024
+ / 1024
+ + 0.4
+ )
+ if self.gpu_mem <= 4:
+ with open("trainset_preprocess_pipeline_print.py", "r") as f:
+ strr = f.read().replace("3.7", "3.0")
+ with open("trainset_preprocess_pipeline_print.py", "w") as f:
+ f.write(strr)
+ elif torch.backends.mps.is_available():
+ print("没有发现支持的N卡, 使用MPS进行推理")
+ self.device = "mps"
+ self.is_half = False
+ config_file_change_fp32()
+ else:
+ print("没有发现支持的N卡, 使用CPU进行推理")
+ self.device = "cpu"
+ self.is_half = False
+ config_file_change_fp32()
+
+ if self.n_cpu == 0:
+ self.n_cpu = cpu_count()
+
+ x_pad = 0.1
+ x_query = 4
+ x_center = 20
+ x_max = 22
+ self.is_half=False
+ self.device="cpu"
+ return x_pad, x_query, x_center, x_max
diff --git a/configs/32k.json b/configs/32k.json
new file mode 100644
index 0000000000000000000000000000000000000000..d5f16d691ed798f4c974b431167c36269b2ce7d2
--- /dev/null
+++ b/configs/32k.json
@@ -0,0 +1,46 @@
+{
+ "train": {
+ "log_interval": 200,
+ "seed": 1234,
+ "epochs": 20000,
+ "learning_rate": 1e-4,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "fp16_run": true,
+ "lr_decay": 0.999875,
+ "segment_size": 12800,
+ "init_lr_ratio": 1,
+ "warmup_epochs": 0,
+ "c_mel": 45,
+ "c_kl": 1.0
+ },
+ "data": {
+ "max_wav_value": 32768.0,
+ "sampling_rate": 32000,
+ "filter_length": 1024,
+ "hop_length": 320,
+ "win_length": 1024,
+ "n_mel_channels": 80,
+ "mel_fmin": 0.0,
+ "mel_fmax": null
+ },
+ "model": {
+ "inter_channels": 192,
+ "hidden_channels": 192,
+ "filter_channels": 768,
+ "n_heads": 2,
+ "n_layers": 6,
+ "kernel_size": 3,
+ "p_dropout": 0,
+ "resblock": "1",
+ "resblock_kernel_sizes": [3,7,11],
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+ "upsample_rates": [10,4,2,2,2],
+ "upsample_initial_channel": 512,
+ "upsample_kernel_sizes": [16,16,4,4,4],
+ "use_spectral_norm": false,
+ "gin_channels": 256,
+ "spk_embed_dim": 109
+ }
+}
diff --git a/configs/40k.json b/configs/40k.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ffc87b9e9725fcd59d81a68d41a61962213b777
--- /dev/null
+++ b/configs/40k.json
@@ -0,0 +1,46 @@
+{
+ "train": {
+ "log_interval": 200,
+ "seed": 1234,
+ "epochs": 20000,
+ "learning_rate": 1e-4,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "fp16_run": true,
+ "lr_decay": 0.999875,
+ "segment_size": 12800,
+ "init_lr_ratio": 1,
+ "warmup_epochs": 0,
+ "c_mel": 45,
+ "c_kl": 1.0
+ },
+ "data": {
+ "max_wav_value": 32768.0,
+ "sampling_rate": 40000,
+ "filter_length": 2048,
+ "hop_length": 400,
+ "win_length": 2048,
+ "n_mel_channels": 125,
+ "mel_fmin": 0.0,
+ "mel_fmax": null
+ },
+ "model": {
+ "inter_channels": 192,
+ "hidden_channels": 192,
+ "filter_channels": 768,
+ "n_heads": 2,
+ "n_layers": 6,
+ "kernel_size": 3,
+ "p_dropout": 0,
+ "resblock": "1",
+ "resblock_kernel_sizes": [3,7,11],
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+ "upsample_rates": [10,10,2,2],
+ "upsample_initial_channel": 512,
+ "upsample_kernel_sizes": [16,16,4,4],
+ "use_spectral_norm": false,
+ "gin_channels": 256,
+ "spk_embed_dim": 109
+ }
+}
diff --git a/configs/48k.json b/configs/48k.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d0e05beb794f6f61b769b48c7ae728bf59e6335
--- /dev/null
+++ b/configs/48k.json
@@ -0,0 +1,46 @@
+{
+ "train": {
+ "log_interval": 200,
+ "seed": 1234,
+ "epochs": 20000,
+ "learning_rate": 1e-4,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "fp16_run": true,
+ "lr_decay": 0.999875,
+ "segment_size": 11520,
+ "init_lr_ratio": 1,
+ "warmup_epochs": 0,
+ "c_mel": 45,
+ "c_kl": 1.0
+ },
+ "data": {
+ "max_wav_value": 32768.0,
+ "sampling_rate": 48000,
+ "filter_length": 2048,
+ "hop_length": 480,
+ "win_length": 2048,
+ "n_mel_channels": 128,
+ "mel_fmin": 0.0,
+ "mel_fmax": null
+ },
+ "model": {
+ "inter_channels": 192,
+ "hidden_channels": 192,
+ "filter_channels": 768,
+ "n_heads": 2,
+ "n_layers": 6,
+ "kernel_size": 3,
+ "p_dropout": 0,
+ "resblock": "1",
+ "resblock_kernel_sizes": [3,7,11],
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+ "upsample_rates": [10,6,2,2,2],
+ "upsample_initial_channel": 512,
+ "upsample_kernel_sizes": [16,16,4,4,4],
+ "use_spectral_norm": false,
+ "gin_channels": 256,
+ "spk_embed_dim": 109
+ }
+}
diff --git a/docs/#U5c0f#U767d#U7b80#U6613#U6559#U7a0b.doc b/docs/#U5c0f#U767d#U7b80#U6613#U6559#U7a0b.doc
new file mode 100644
index 0000000000000000000000000000000000000000..2e291891303f0f805c36a463a3fecbde8d82c4de
Binary files /dev/null and b/docs/#U5c0f#U767d#U7b80#U6613#U6559#U7a0b.doc differ
diff --git a/docs/README.en.md b/docs/README.en.md
new file mode 100644
index 0000000000000000000000000000000000000000..1df5839ad420e5bbcb564c92853ec415bee7da44
--- /dev/null
+++ b/docs/README.en.md
@@ -0,0 +1,104 @@
+
+
+
Retrieval-based-Voice-Conversion-WebUI
+An easy-to-use Voice Conversion framework based on VITS.
+
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI)
+
+
+
+[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+
+[](https://discord.gg/HcsmBBGyVk)
+
+
+
+
diff --git a/docs/README.ja.md b/docs/README.ja.md
new file mode 100644
index 0000000000000000000000000000000000000000..cf47bd5be4652c7fb3738090fc3e3e75c09e703f
--- /dev/null
+++ b/docs/README.ja.md
@@ -0,0 +1,104 @@
+
+
+
Retrieval-based-Voice-Conversion-WebUI
+VITSに基づく使いやすい音声変換（voice changer）framework
+
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI)
+
+
+
+[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+
+[](https://discord.gg/HcsmBBGyVk)
+
+
+
+
Retrieval-based-Voice-Conversion-WebUI
+VITS基盤의 簡單하고使用하기 쉬운音聲變換틀
+
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI)
+
+
+
+[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+
+[](https://discord.gg/HcsmBBGyVk)
+
+
+
+
Retrieval-based-Voice-Conversion-WebUI
+VITS 기반의 간단하고 사용하기 쉬운 음성 변환 프레임워크.
+
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI)
+
+
+
+[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
+[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+
+[](https://discord.gg/HcsmBBGyVk)
+
+
+ffmpeg读取路径带空格、()等特殊符号，可能出现ffmpeg error；训练集音频带中文路径，在写入filelist.txt的时候可能出现utf8 error；
+
+## Q2:一键训练结束没有索引
+
+显示"Training is done. The program is closed."则模型训练成功，后续紧邻的报错是假的；
+
+一键训练结束完成没有added开头的索引文件，可能是因为训练集太大卡住了添加索引的步骤；已通过批处理add索引解决内存add索引对内存需求过大的问题。临时可尝试再次点击"训练索引"按钮。
+
+## Q3:训练结束推理没看到训练集的音色
+点刷新音色再看看，如果还没有看看训练有没有报错，控制台和webui的截图，logs/实验名下的log，都可以发给开发者看看。
+
+## Q4:如何分享模型
+ rvc_root/logs/实验名 下面存储的pth不是用来分享模型用来推理的，而是为了存储实验状态供复现，以及继续训练用的。用来分享的模型应该是weights文件夹下大小为60+MB的pth文件；
+ 后续将把weights/exp_name.pth和logs/exp_name/added_xxx.index合并打包成weights/exp_name.zip省去填写index的步骤，那么zip文件用来分享，不要分享pth文件，除非是想换机器继续训练；
+ 如果你把logs文件夹下的几百MB的pth文件复制/分享到weights文件夹下强行用于推理，可能会出现f0，tgt_sr等各种key不存在的报错。你需要用ckpt选项卡最下面，手工或自动（本地logs下如果能找到相关信息则会自动）选择是否携带音高、目标音频采样率的选项后进行ckpt小模型提取（输入路径填G开头的那个），提取完在weights文件夹下会出现60+MB的pth文件，刷新音色后可以选择使用。
+
+## Q5:Connection Error.
+也许你关闭了控制台（黑色窗口）。
+
+## Q6:WebUI弹出Expecting value: line 1 column 1 (char 0).
+请关闭系统局域网代理/全局代理。
+
+这个不仅是客户端的代理，也包括服务端的代理（例如你使用autodl设置了http_proxy和https_proxy学术加速，使用时也需要unset关掉）
+
+## Q7:不用WebUI如何通过命令训练推理
+训练脚本：
+可先跑通WebUI，消息窗内会显示数据集处理和训练用命令行；
+
+推理脚本：
+https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py
+
+例子：
+
+runtime\python.exe myinfer.py 0 "E:\codes\py39\RVC-beta\todo-songs\1111.wav" "E:\codes\py39\logs\mi-test\added_IVF677_Flat_nprobe_7.index" harvest "test.wav" "weights/mi-test.pth" 0.6 cuda:0 True
+
+f0up_key=sys.argv[1]
+input_path=sys.argv[2]
+index_path=sys.argv[3]
+f0method=sys.argv[4]#harvest or pm
+opt_path=sys.argv[5]
+model_path=sys.argv[6]
+index_rate=float(sys.argv[7])
+device=sys.argv[8]
+is_half=bool(sys.argv[9])
+
+## Q8:Cuda error/Cuda out of memory.
+小概率是cuda配置问题、设备不支持；大概率是显存不够（out of memory）；
+
+训练的话缩小batch size（如果缩小到1还不够只能更换显卡训练），推理的话酌情缩小config.py结尾的x_pad，x_query，x_center，x_max。4G以下显存（例如1060（3G）和各种2G显卡）可以直接放弃，4G显存显卡还有救。
+
+## Q9:total_epoch调多少比较好
+
+如果训练集音质差底噪大，20~30足够了，调太高，底模音质无法带高你的低音质训练集
+如果训练集音质高底噪低时长多，可以调高，200是ok的（训练速度很快，既然你有条件准备高音质训练集，显卡想必条件也不错，肯定不在乎多一些训练时间）
+
+## Q10:需要多少训练集时长
+ 推荐10min至50min
+ 保证音质高底噪低的情况下，如果有个人特色的音色统一，则多多益善
+ 高水平的训练集（精简+音色有特色），5min至10min也是ok的，仓库作者本人就经常这么玩
+ 也有人拿1min至2min的数据来训练并且训练成功的，但是成功经验是其他人不可复现的，不太具备参考价值。这要求训练集音色特色非常明显（比如说高频气声较明显的萝莉少女音），且音质高；
+ 1min以下时长数据目前没见有人尝试（成功）过。不建议进行这种鬼畜行为。
+
+## Q11:index rate干嘛用的，怎么调（科普）
+ 如果底模和推理源的音质高于训练集的音质，他们可以带高推理结果的音质，但代价可能是音色往底模/推理源的音色靠，这种现象叫做"音色泄露"；
+ index rate用来削减/解决音色泄露问题。调到1，则理论上不存在推理源的音色泄露问题，但音质更倾向于训练集。如果训练集音质比推理源低，则index rate调高可能降低音质。调到0，则不具备利用检索混合来保护训练集音色的效果；
+ 如果训练集优质时长多，可调高total_epoch，此时模型本身不太会引用推理源和底模的音色，很少存在"音色泄露"问题，此时index_rate不重要，你甚至可以不建立/分享index索引文件。
+
+## Q11:推理怎么选gpu
+config.py文件里device cuda:后面选择卡号；
+卡号和显卡的映射关系，在训练选项卡的显卡信息栏里能看到。
+
+## Q12:如何推理训练中间保存的pth
+通过ckpt选项卡最下面提取小模型。
+
+
+## Q13:如何中断和继续训练
+现阶段只能关闭WebUI控制台双击go-web.bat重启程序。网页参数也要刷新重新填写；
+继续训练：相同网页参数点训练模型，就会接着上次的checkpoint继续训练。
+
+## Q14:训练时出现文件页面/内存error
+进程开太多了，内存炸了。你可能可以通过如下方式解决
+1、"提取音高和处理数据使用的CPU进程数" 酌情拉低；
+2、训练集音频手工切一下，不要太长。
+
+
+
diff --git a/docs/faq_en.md b/docs/faq_en.md
new file mode 100644
index 0000000000000000000000000000000000000000..05f03ec0467706c319c0c19c83c200f43eb8f4a0
--- /dev/null
+++ b/docs/faq_en.md
@@ -0,0 +1,95 @@
+## Q1:ffmpeg error/utf8 error.
+It is most likely not a FFmpeg issue, but rather an audio path issue;
+
+FFmpeg may encounter an error when reading paths containing special characters like spaces and (), which may cause an FFmpeg error; and when the training set's audio contains Chinese paths, writing it into filelist.txt may cause a utf8 error.
+
+## Q2:Cannot find index file after "One-click Training".
+If it displays "Training is done. The program is closed," then the model has been trained successfully, and the subsequent errors are fake;
+
+The lack of an 'added' index file after One-click training may be due to the training set being too large, causing the addition of the index to get stuck; this has been resolved by using batch processing to add the index, which solves the problem of memory overload when adding the index. As a temporary solution, try clicking the "Train Index" button again.
+
+## Q3:Cannot find the model in “Inferencing timbre” after training
+Click “Refresh timbre list” and check again; if still not visible, check if there are any errors during training and send screenshots of the console, web UI, and logs/experiment_name/*.log to the developers for further analysis.
+
+## Q4:How to share a model/How to use others' models?
+The pth files stored in rvc_root/logs/experiment_name are not meant for sharing or inference, but for storing the experiment checkpoits for reproducibility and further training. The model to be shared should be the 60+MB pth file in the weights folder;
+
+In the future, weights/exp_name.pth and logs/exp_name/added_xxx.index will be merged into a single weights/exp_name.zip file to eliminate the need for manual index input; so share the zip file, not the pth file, unless you want to continue training on a different machine;
+
+Copying/sharing the several hundred MB pth files from the logs folder to the weights folder for forced inference may result in errors such as missing f0, tgt_sr, or other keys. You need to use the ckpt tab at the bottom to manually or automatically (if the information is found in the logs/exp_name), select whether to include pitch infomation and target audio sampling rate options and then extract the smaller model. After extraction, there will be a 60+ MB pth file in the weights folder, and you can refresh the voices to use it.
+
+## Q5:Connection Error.
+You may have closed the console (black command line window).
+
+## Q6:WebUI popup 'Expecting value: line 1 column 1 (char 0)'.
+Please disable system LAN proxy/global proxy and then refresh.
+
+## Q7:How to train and infer without the WebUI?
+Training script:
+You can run training in WebUI first, and the command-line versions of dataset preprocessing and training will be displayed in the message window.
+
+Inference script:
+https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py
+
+
+e.g.
+
+runtime\python.exe myinfer.py 0 "E:\codes\py39\RVC-beta\todo-songs\1111.wav" "E:\codes\py39\logs\mi-test\added_IVF677_Flat_nprobe_7.index" harvest "test.wav" "weights/mi-test.pth" 0.6 cuda:0 True
+
+
+f0up_key=sys.argv[1]
+input_path=sys.argv[2]
+index_path=sys.argv[3]
+f0method=sys.argv[4]#harvest or pm
+opt_path=sys.argv[5]
+model_path=sys.argv[6]
+index_rate=float(sys.argv[7])
+device=sys.argv[8]
+is_half=bool(sys.argv[9])
+
+## Q8:Cuda error/Cuda out of memory.
+There is a small chance that there is a problem with the CUDA configuration or the device is not supported; more likely, there is not enough memory (out of memory).
+
+For training, reduce the batch size (if reducing to 1 is still not enough, you may need to change the graphics card); for inference, adjust the x_pad, x_query, x_center, and x_max settings in the config.py file as needed. 4G or lower memory cards (e.g. 1060(3G) and various 2G cards) can be abandoned, while 4G memory cards still have a chance.
+
+## Q9:How many total_epoch are optimal?
+If the training dataset's audio quality is poor and the noise floor is high, 20-30 epochs are sufficient. Setting it too high won't improve the audio quality of your low-quality training set.
+
+If the training set audio quality is high, the noise floor is low, and there is sufficient duration, you can increase it. 200 is acceptable (since training is fast, and if you're able to prepare a high-quality training set, your GPU likely can handle a longer training duration without issue).
+
+## Q10:How much training set duration is needed?
+
+A dataset of around 10min to 50min is recommended.
+
+With guaranteed high sound quality and low bottom noise, more can be added if the dataset's timbre is uniform.
+
+For a high-level training set (lean + distinctive tone), 5min to 10min is fine.
+
+There are some people who have trained successfully with 1min to 2min data, but the success is not reproducible by others and is not very informative.
This requires that the training set has a very distinctive timbre (e.g. a high-frequency airy anime girl sound) and the quality of the audio is high;
+Data of less than 1min duration has not been successfully attempted so far. This is not recommended.
+
+
+## Q11:What is the index rate for and how to adjust it?
+If the tone quality of the pre-trained model and inference source is higher than that of the training set, they can bring up the tone quality of the inference result, but at the cost of a possible tone bias towards the tone of the underlying model/inference source rather than the tone of the training set, which is generally referred to as "tone leakage".
+
+The index rate is used to reduce/resolve the timbre leakage problem. If the index rate is set to 1, theoretically there is no timbre leakage from the inference source and the timbre quality is more biased towards the training set. If the training set has a lower sound quality than the inference source, then a higher index rate may reduce the sound quality. Turning it down to 0 does not have the effect of using retrieval blending to protect the training set tones.
+
+If the training set has good audio quality and long duration, turn up the total_epoch, when the model itself is less likely to refer to the inferred source and the pretrained underlying model, and there is little "tone leakage", the index_rate is not important and you can even not create/share the index file.
+
+## Q12:How to choose the gpu when inferring?
+In the config.py file, select the card number after "device cuda:".
+
+The mapping between card number and graphics card can be seen in the graphics card information section of the training tab.
+
+## Q13:How to use the model saved in the middle of training?
+Save via model extraction at the bottom of the ckpt processing tab.
+
+## Q14:File/memory error(when training)?
+Too many processes and your memory is not enough. You may fix it by:
+
+1、decrease the input in field "Threads of CPU".
+
+2、pre-cut trainset to shorter audio files.
+
+
+
diff --git a/docs/training_tips_en.md b/docs/training_tips_en.md
new file mode 100644
index 0000000000000000000000000000000000000000..ab9b1f8764285757a4fb3d06be7c647887bdad10
--- /dev/null
+++ b/docs/training_tips_en.md
@@ -0,0 +1,65 @@
+Instructions and tips for RVC training
+======================================
+This TIPS explains how data training is done.
+
+# Training flow
+I will explain along the steps in the training tab of the GUI.
+
+## step1
+Set the experiment name here.
+
+You can also set here whether the model should take pitch into account.
+If the model doesn't consider pitch, the model will be lighter, but not suitable for singing.
+
+Data for each experiment is placed in `/logs/your-experiment-name/`.
+
+## step2a
+Loads and preprocesses audio.
+
+### load audio
+If you specify a folder with audio, the audio files in that folder will be read automatically.
+For example, if you specify `C:Users\hoge\voices`, `C:Users\hoge\voices\voice.mp3` will be loaded, but `C:Users\hoge\voices\dir\voice.mp3` will Not loaded.
+
+Since ffmpeg is used internally for reading audio, if the extension is supported by ffmpeg, it will be read automatically.
+After converting to int16 with ffmpeg, convert to float32 and normalize between -1 to 1.
+
+### denoising
+The audio is smoothed by scipy's filtfilt.
+
+### Audio Split
+First, the input audio is divided by detecting parts of silence that last longer than a certain period (max_sil_kept=5 seconds?). After splitting the audio on silence, split the audio every 4 seconds with an overlap of 0.3 seconds. For audio separated within 4 seconds, after normalizing the volume, convert the wav file to `/logs/your-experiment-name/0_gt_wavs` and then convert it to 16k sampling rate to `/logs/your-experiment-name/1_16k_wavs ` as a wav file.
+
+## step2b
+### Extract pitch
+Extract pitch information from wav files. Extract the pitch information (=f0) using the method built into parselmouth or pyworld and save it in `/logs/your-experiment-name/2a_f0`. Then logarithmically convert the pitch information to an integer between 1 and 255 and save it in `/logs/your-experiment-name/2b-f0nsf`.
+
+### Extract feature_print
+Convert the wav file to embedding in advance using HuBERT. Read the wav file saved in `/logs/your-experiment-name/1_16k_wavs`, convert the wav file to 256-dimensional features with HuBERT, and save in npy format in `/logs/your-experiment-name/3_feature256`.
+
+## step3
+train the model.
+### Glossary for Beginners
+In deep learning, the data set is divided and the learning proceeds little by little. In one model update (step), batch_size data are retrieved and predictions and error corrections are performed. Doing this once for a dataset counts as one epoch.
+
+Therefore, the learning time is the learning time per step x (the number of data in the dataset / batch size) x the number of epochs. In general, the larger the batch size, the more stable the learning becomes (learning time per step ÷ batch size) becomes smaller, but it uses more GPU memory. GPU RAM can be checked with the nvidia-smi command. Learning can be done in a short time by increasing the batch size as much as possible according to the machine of the execution environment.
+
+### Specify pretrained model
+RVC starts training the model from pretrained weights instead of from 0, so it can be trained with a small dataset.
+
+By default
+
+- If you consider pitch, it loads `rvc-location/pretrained/f0G40k.pth` and `rvc-location/pretrained/f0D40k.pth`.
+- If you don't consider pitch, it loads `rvc-location/pretrained/f0G40k.pth` and `rvc-location/pretrained/f0D40k.pth`.
+
+When learning, model parameters are saved in `logs/your-experiment-name/G_{}.pth` and `logs/your-experiment-name/D_{}.pth` for each save_every_epoch, but by specifying this path, you can start learning. You can restart or start training from model weights learned in a different experiment.
+
+### learning index
+RVC saves the HuBERT feature values used during training, and during inference, searches for feature values that are similar to the feature values used during learning to perform inference. In order to perform this search at high speed, the index is learned in advance.
+For index learning, we use the approximate neighborhood search library faiss. Read the feature value of `logs/your-experiment-name/3_feature256` and use it to learn the index, and save it as `logs/your-experiment-name/add_XXX.index`.
+
+(From the 20230428update version, it is read from the index, and saving / specifying is no longer necessary.)
+
+### Button description
+- Train model: After executing step2b, press this button to train the model.
+- Train feature index: After training the model, perform index learning.
+- One-click training: step2b, model training and feature index training all at once.
\ No newline at end of file
diff --git a/docs/training_tips_ja.md b/docs/training_tips_ja.md
new file mode 100644
index 0000000000000000000000000000000000000000..c5b06f2fdaa603a690c51ee2b79daecc4305fbd5
--- /dev/null
+++ b/docs/training_tips_ja.md
@@ -0,0 +1,64 @@
+RVCの訓練における説明、およびTIPS
+===============================
+本TIPSではどのようにデータの訓練が行われているかを説明します。
+
+# 訓練の流れ
+GUIの訓練タブのstepに沿って説明します。
+
+## step1
+実験名の設定を行います。
+
+また、モデルに音高ガイド(ピッチ)を考慮させるかもここで設定できます。考慮させない場合はモデルは軽量になりますが、歌唱には向かなくなります。
+
+各実験のデータは`/logs/実験名/`に配置されます。
+
+## step2a
+音声の読み込みと前処理を行います。
+
+### load audio
+音声のあるフォルダを指定すると、そのフォルダ内にある音声ファイルを自動で読み込みます。
+例えば`C:Users\hoge\voices`を指定した場合、`C:Users\hoge\voices\voice.mp3`は読み込まれますが、`C:Users\hoge\voices\dir\voice.mp3`は読み込まれません。
+
+音声の読み込みには内部でffmpegを利用しているので、ffmpegで対応している拡張子であれば自動的に読み込まれます。
+ffmpegでint16に変換した後、float32に変換し、-1 ~ 1の間に正規化されます。
+
+### denoising
+音声についてscipyのfiltfiltによる平滑化を行います。
+
+### 音声の分割
+入力した音声はまず、一定期間(max_sil_kept=5秒?)より長く無音が続く部分を検知して音声を分割します。無音で音声を分割した後は、0.3秒のoverlapを含む4秒ごとに音声を分割します。4秒以内に区切られた音声は、音量の正規化を行った後wavファイルを`/logs/実験名/0_gt_wavs`に、そこから16kのサンプリングレートに変換して`/logs/実験名/1_16k_wavs`にwavファイルで保存します。
+
+## step2b
+### ピッチの抽出
+wavファイルからピッチ(音の高低)の情報を抽出します。parselmouthやpyworldに内蔵されている手法でピッチ情報(=f0)を抽出し、`/logs/実験名/2a_f0`に保存します。その後、ピッチ情報を対数で変換して1~255の整数に変換し、`/logs/実験名/2b-f0nsf`に保存します。
+
+### feature_printの抽出
+HuBERTを用いてwavファイルを事前にembeddingに変換します。`/logs/実験名/1_16k_wavs`に保存したwavファイルを読み込み、HuBERTでwavファイルを256次元の特徴量に変換し、npy形式で`/logs/実験名/3_feature256`に保存します。
+
+## step3
+モデルのトレーニングを行います。
+### 初心者向け用語解説
+深層学習ではデータセットを分割し、少しずつ学習を進めていきます。一回のモデルの更新(step)では、batch_size個のデータを取り出し予測と誤差の修正を行います。これをデータセットに対して一通り行うと一epochと数えます。
+
+そのため、学習時間は 1step当たりの学習時間 x (データセット内のデータ数 ÷ バッチサイズ) x epoch数 かかります。一般にバッチサイズを大きくするほど学習は安定し、(1step当たりの学習時間÷バッチサイズ)は小さくなりますが、その分GPUのメモリを多く使用します。GPUのRAMはnvidia-smiコマンド等で確認できます。実行環境のマシンに合わせてバッチサイズをできるだけ大きくするとより短時間で学習が可能です。
+
+### pretrained modelの指定
+RVCではモデルの訓練を0からではなく、事前学習済みの重みから開始するため、少ないデータセットで学習を行えます。
+
+デフォルトでは
+
+- 音高ガイドを考慮する場合、`RVCのある場所/pretrained/f0G40k.pth`と`RVCのある場所/pretrained/f0D40k.pth`を読み込みます。
+- 音高ガイドを考慮しない場合、`RVCのある場所/pretrained/G40k.pth`と`RVCのある場所/pretrained/D40k.pth`を読み込みます。
+
+学習時はsave_every_epochごとにモデルのパラメータが`logs/実験名/G_{}.pth`と`logs/実験名/D_{}.pth`に保存されますが、このパスを指定することで学習を再開したり、もしくは違う実験で学習したモデルの重みから学習を開始できます。
+
+### indexの学習
+RVCでは学習時に使われたHuBERTの特徴量を保存し、推論時は学習時の特徴量から近い特徴量を探してきて推論を行います。この検索を高速に行うために事前にindexの学習を行います。
+indexの学習には近似近傍探索ライブラリのfaissを用います。`/logs/実験名/3_feature256`の特徴量を読み込み、それを用いて学習したindexを`/logs/実験名/add_XXX.index`として保存します。
+(20230428updateよりtotal_fea.npyはindexから読み込むので不要になりました。)
+
+### ボタンの説明
+- モデルのトレーニング: step2bまでを実行した後、このボタンを押すとモデルの学習を行います。
+- 特徴インデックスのトレーニング: モデルのトレーニング後、indexの学習を行います。
+- ワンクリックトレーニング: step2bまでとモデルのトレーニング、特徴インデックスのトレーニングを一括で行います。
+
diff --git a/docs/training_tips_ko.md b/docs/training_tips_ko.md
new file mode 100644
index 0000000000000000000000000000000000000000..8b3b6245862aef69480f57263d268c94d5e843ca
--- /dev/null
+++ b/docs/training_tips_ko.md
@@ -0,0 +1,53 @@
+RVC 훈련에 대한 설명과 팁들
+======================================
+본 팁에서는 어떻게 데이터 훈련이 이루어지고 있는지 설명합니다.
+
+# 훈련의 흐름
+GUI의 훈련 탭의 단계를 따라 설명합니다.
+
+## step1
+실험 이름을 지정합니다. 또한, 모델이 피치(소리의 높낮이)를 고려해야 하는지 여부를 여기에서 설정할 수도 있습니다..
+각 실험을 위한 데이터는 `/logs/experiment name/`에 배치됩니다..
+
+## step2a
+음성 파일을 불러오고 전처리합니다.
+
+### 음성 파일 불러오기
+음성 파일이 있는 폴더를 지정하면 해당 폴더에 있는 음성 파일이 자동으로 가져와집니다.
+예를 들어 `C:Users\hoge\voices`를 지정하면 `C:Users\hoge\voices\voice.mp3`가 읽히지만 `C:Users\hoge\voices\dir\voice.mp3`는 읽히지 않습니다.
+
+음성 로드에는 내부적으로 ffmpeg를 이용하고 있으므로, ffmpeg로 대응하고 있는 확장자라면 자동적으로 읽힙니다.
+ffmpeg에서 int16으로 변환한 후 float32로 변환하고 -1과 1 사이에 정규화됩니다.
+
+### 잡음 제거
+음성 파일에 대해 scipy의 filtfilt를 이용하여 잡음을 처리합니다.
+
+### 음성 분할
+입력한 음성 파일은 먼저 일정 기간(max_sil_kept=5초?)보다 길게 무음이 지속되는 부분을 감지하여 음성을 분할합니다.무음으로 음성을 분할한 후에는 0.3초의 overlap을 포함하여 4초마다 음성을 분할합니다.4초 이내에 구분된 음성은 음량의 정규화를 실시한 후 wav 파일을 `/logs/실험명/0_gt_wavs`로, 거기에서 16k의 샘플링 레이트로 변환해 `/logs/실험명/1_16k_wavs`에 wav 파일로 저장합니다.
+
+## step2b
+### 피치 추출
+wav 파일에서 피치(소리의 높낮이) 정보를 추출합니다. parselmouth나 pyworld에 내장되어 있는 메서드으로 피치 정보(=f0)를 추출해, `/logs/실험명/2a_f0`에 저장합니다. 그 후 피치 정보를 로그로 변환하여 1~255 정수로 변환하고 `/logs/실험명/2b-f0nsf`에 저장합니다.
+
+### feature_print 추출
+HuBERT를 이용하여 wav 파일을 미리 embedding으로 변환합니다. `/logs/실험명/1_16k_wavs`에 저장한 wav 파일을 읽고 HuBERT에서 wav 파일을 256차원 feature들로 변환한 후 npy 형식으로 `/logs/실험명/3_feature256`에 저장합니다.
+
+## step3
+모델의 훈련을 진행합니다.
+
+### 초보자용 용어 해설
+심층학습(딥러닝)에서는 데이터셋을 분할하여 조금씩 학습을 진행합니다.한 번의 모델 업데이트(step) 단계 당 batch_size개의 데이터를 탐색하여 예측과 오차를 수정합니다. 데이터셋 전부에 대해 이 작업을 한 번 수행하는 이를 하나의 epoch라고 계산합니다.
+
+따라서 학습 시간은 단계당 학습 시간 x (데이터셋 내 데이터의 수 / batch size) x epoch 수가 소요됩니다. 일반적으로 batch size가 클수록 학습이 안정적이게 됩니다. (step당 학습 시간 ÷ batch size)는 작아지지만 GPU 메모리를 더 많이 사용합니다. GPU RAM은 nvidia-smi 명령어를 통해 확인할 수 있습니다. 실행 환경에 따라 배치 크기를 최대한 늘리면 짧은 시간 내에 학습이 가능합니다.
+
+### 사전 학습된 모델 지정
+RVC는 적은 데이터셋으로도 훈련이 가능하도록 사전 훈련된 가중치에서 모델 훈련을 시작합니다. 기본적으로 `rvc-location/pretrained/f0G40k.pth` 및 `rvc-location/pretrained/f0D40k.pth`를 불러옵니다. 학습을 할 시에, 모델 파라미터는 각 save_every_epoch별로 `logs/experiment name/G_{}.pth` 와 `logs/experiment name/D_{}.pth`로 저장이 되는데, 이 경로를 지정함으로써 학습을 재개하거나, 다른 실험에서 학습한 모델의 가중치에서 학습을 시작할 수 있습니다.
+
+### index의 학습
+RVC에서는 학습시에 사용된 HuBERT의 feature값을 저장하고, 추론 시에는 학습 시 사용한 feature값과 유사한 feature 값을 탐색해 추론을 진행합니다. 이 탐색을 고속으로 수행하기 위해 사전에 index을 학습하게 됩니다.
+Index 학습에는 근사 근접 탐색법 라이브러리인 Faiss를 사용하게 됩니다. `/logs/실험명/3_feature256`의 feature값을 불러와, 이를 모두 결합시킨 feature값을 `/logs/실험명/total_fea.npy`로서 저장, 그것을 사용해 학습한 index를`/logs/실험명/add_XXX.index`로 저장합니다.
+
+### 버튼 설명
+- モデルのトレーニング (모델 학습): step2b까지 실행한 후, 이 버튼을 눌러 모델을 학습합니다.
+- 特徴インデックスのトレーニング (특징 지수 훈련): 모델의 훈련 후, index를 학습합니다.
+- ワンクリックトレーニング (원클릭 트레이닝): step2b까지의 모델 훈련, feature index 훈련을 일괄로 실시합니다.
\ No newline at end of file
diff --git a/envfilescheck.bat b/envfilescheck.bat
new file mode 100644
index 0000000000000000000000000000000000000000..547f2aef8621821b86e4d9898f86e0128f55500e
--- /dev/null
+++ b/envfilescheck.bat
@@ -0,0 +1,348 @@
+@echo off && chcp 65001
+
+echo working dir is %cd%
+echo downloading requirement aria2 check.
+echo=
+dir /a:d/b | findstr "aria2" > flag.txt
+findstr "aria2" flag.txt >nul
+if %errorlevel% ==0 (
+ echo aria2 checked.
+ echo=
+) else (
+ echo failed. please downloading aria2 from webpage!
+ echo unzip it and put in this directory!
+ timeout /T 5
+ start https://github.com/aria2/aria2/releases/tag/release-1.36.0
+ echo=
+ goto end
+)
+
+echo envfiles checking start.
+echo=
+
+for /f %%x in ('findstr /i /c:"aria2" "flag.txt"') do (set aria2=%%x)&goto endSch
+:endSch
+
+set d32=f0D32k.pth
+set d40=f0D40k.pth
+set d48=f0D48k.pth
+set g32=f0G32k.pth
+set g40=f0G40k.pth
+set g48=f0G48k.pth
+
+set d40v2=f0D40k.pth
+set g40v2=f0G40k.pth
+
+set dld32=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth
+set dld40=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth
+set dld48=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth
+set dlg32=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth
+set dlg40=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth
+set dlg48=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth
+
+set dld40v2=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth
+set dlg40v2=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth
+
+set hp2_all=HP2_all_vocals.pth
+set hp3_all=HP3_all_vocals.pth
+set hp5_only=HP5_only_main_vocal.pth
+set VR_DeEchoAggressive=VR-DeEchoAggressive.pth
+set VR_DeEchoDeReverb=VR-DeEchoDeReverb.pth
+set VR_DeEchoNormal=VR-DeEchoNormal.pth
+set onnx_dereverb=vocals.onnx
+
+set dlhp2_all=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2_all_vocals.pth
+set dlhp3_all=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP3_all_vocals.pth
+set dlhp5_only=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5_only_main_vocal.pth
+set dlVR_DeEchoAggressive=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoAggressive.pth
+set dlVR_DeEchoDeReverb=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoDeReverb.pth
+set dlVR_DeEchoNormal=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoNormal.pth
+set dlonnx_dereverb=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx
+
+set hb=hubert_base.pt
+
+set dlhb=https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt
+
+echo dir check start.
+echo=
+
+if exist "%~dp0pretrained" (
+ echo dir .\pretrained checked.
+ ) else (
+ echo failed. generating dir .\pretrained.
+ mkdir pretrained
+ )
+if exist "%~dp0pretrained_v2" (
+ echo dir .\pretrained_v2 checked.
+ ) else (
+ echo failed. generating dir .\pretrained_v2.
+ mkdir pretrained_v2
+ )
+if exist "%~dp0uvr5_weights" (
+ echo dir .\uvr5_weights checked.
+ ) else (
+ echo failed. generating dir .\uvr5_weights.
+ mkdir uvr5_weights
+ )
+if exist "%~dp0uvr5_weights\onnx_dereverb_By_FoxJoy" (
+ echo dir .\uvr5_weights\onnx_dereverb_By_FoxJoy checked.
+ ) else (
+ echo failed. generating dir .\uvr5_weights\onnx_dereverb_By_FoxJoy.
+ mkdir uvr5_weights\onnx_dereverb_By_FoxJoy
+ )
+
+echo=
+echo dir check finished.
+
+echo=
+echo required files check start.
+
+echo checking D32k.pth
+if exist "%~dp0pretrained\D32k.pth" (
+ echo D32k.pth in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d %~dp0pretrained -o D32k.pth
+ if exist "%~dp0pretrained\D32k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking D40k.pth
+if exist "%~dp0pretrained\D40k.pth" (
+ echo D40k.pth in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d %~dp0pretrained -o D40k.pth
+ if exist "%~dp0pretrained\D40k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking D40k.pth
+if exist "%~dp0pretrained_v2\D40k.pth" (
+ echo D40k.pth in .\pretrained_v2 checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d %~dp0pretrained_v2 -o D40k.pth
+ if exist "%~dp0pretrained_v2\D40k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking D48k.pth
+if exist "%~dp0pretrained\D48k.pth" (
+ echo D48k.pth in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d %~dp0pretrained -o D48k.pth
+ if exist "%~dp0pretrained\D48k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking G32k.pth
+if exist "%~dp0pretrained\G32k.pth" (
+ echo G32k.pth in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d %~dp0pretrained -o G32k.pth
+ if exist "%~dp0pretrained\G32k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking G40k.pth
+if exist "%~dp0pretrained\G40k.pth" (
+ echo G40k.pth in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d %~dp0pretrained -o G40k.pth
+ if exist "%~dp0pretrained\G40k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking G40k.pth
+if exist "%~dp0pretrained_v2\G40k.pth" (
+ echo G40k.pth in .\pretrained_v2 checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d %~dp0pretrained_v2 -o G40k.pth
+ if exist "%~dp0pretrained_v2\G40k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking G48k.pth
+if exist "%~dp0pretrained\G48k.pth" (
+ echo G48k.pth in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d %~dp0pretrained -o G48k.pth
+ if exist "%~dp0pretrained\G48k.pth" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+
+echo checking %d32%
+if exist "%~dp0pretrained\%d32%" (
+ echo %d32% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dld32% -d %~dp0pretrained -o %d32%
+ if exist "%~dp0pretrained\%d32%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %d40%
+if exist "%~dp0pretrained\%d40%" (
+ echo %d40% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dld40% -d %~dp0pretrained -o %d40%
+ if exist "%~dp0pretrained\%d40%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %d40v2%
+if exist "%~dp0pretrained_v2\%d40v2%" (
+ echo %d40v2% in .\pretrained_v2 checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dld40v2% -d %~dp0pretrained_v2 -o %d40v2%
+ if exist "%~dp0pretrained_v2\%d40v2%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %d48%
+if exist "%~dp0pretrained\%d48%" (
+ echo %d48% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dld48% -d %~dp0pretrained -o %d48%
+ if exist "%~dp0pretrained\%d48%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %g32%
+if exist "%~dp0pretrained\%g32%" (
+ echo %g32% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlg32% -d %~dp0pretrained -o %g32%
+ if exist "%~dp0pretrained\%g32%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %g40%
+if exist "%~dp0pretrained\%g40%" (
+ echo %g40% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlg40% -d %~dp0pretrained -o %g40%
+ if exist "%~dp0pretrained\%g40%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %g40v2%
+if exist "%~dp0pretrained_v2\%g40v2%" (
+ echo %g40v2% in .\pretrained_v2 checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlg40v2% -d %~dp0pretrained_v2 -o %g40v2%
+ if exist "%~dp0pretrained_v2\%g40v2%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %g48%
+if exist "%~dp0pretrained\%g48%" (
+ echo %g48% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlg48% -d %~dp0\pretrained -o %g48%
+ if exist "%~dp0pretrained\%g48%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+
+echo checking %hp2_all%
+if exist "%~dp0uvr5_weights\%hp2_all%" (
+ echo %hp2_all% in .\uvr5_weights checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlhp2_all% -d %~dp0\uvr5_weights -o %hp2_all%
+ if exist "%~dp0uvr5_weights\%hp2_all%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %hp3_all%
+if exist "%~dp0uvr5_weights\%hp3_all%" (
+ echo %hp3_all% in .\uvr5_weights checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlhp3_all% -d %~dp0\uvr5_weights -o %hp3_all%
+ if exist "%~dp0uvr5_weights\%hp3_all%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %hp5_only%
+if exist "%~dp0uvr5_weights\%hp5_only%" (
+ echo %hp5_only% in .\uvr5_weights checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlhp5_only% -d %~dp0\uvr5_weights -o %hp5_only%
+ if exist "%~dp0uvr5_weights\%hp5_only%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %VR_DeEchoAggressive%
+if exist "%~dp0uvr5_weights\%VR_DeEchoAggressive%" (
+ echo %VR_DeEchoAggressive% in .\uvr5_weights checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlVR_DeEchoAggressive% -d %~dp0\uvr5_weights -o %VR_DeEchoAggressive%
+ if exist "%~dp0uvr5_weights\%VR_DeEchoAggressive%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %VR_DeEchoDeReverb%
+if exist "%~dp0uvr5_weights\%VR_DeEchoDeReverb%" (
+ echo %VR_DeEchoDeReverb% in .\uvr5_weights checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlVR_DeEchoDeReverb% -d %~dp0\uvr5_weights -o %VR_DeEchoDeReverb%
+ if exist "%~dp0uvr5_weights\%VR_DeEchoDeReverb%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %VR_DeEchoNormal%
+if exist "%~dp0uvr5_weights\%VR_DeEchoNormal%" (
+ echo %VR_DeEchoNormal% in .\uvr5_weights checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlVR_DeEchoNormal% -d %~dp0\uvr5_weights -o %VR_DeEchoNormal%
+ if exist "%~dp0uvr5_weights\%VR_DeEchoNormal%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+echo checking %onnx_dereverb%
+if exist "%~dp0uvr5_weights\onnx_dereverb_By_FoxJoy\%onnx_dereverb%" (
+ echo %onnx_dereverb% in .\uvr5_weights\onnx_dereverb_By_FoxJoy checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlonnx_dereverb% -d %~dp0\uvr5_weights\onnx_dereverb_By_FoxJoy -o %onnx_dereverb%
+ if exist "%~dp0uvr5_weights\onnx_dereverb_By_FoxJoy\%onnx_dereverb%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+
+echo checking %hb%
+if exist "%~dp0%hb%" (
+ echo %hb% in .\pretrained checked.
+ echo=
+ ) else (
+ echo failed. starting download from huggingface.
+ %~dp0%aria2%\aria2c --console-log-level=error -c -x 16 -s 16 -k 1M %dlhb% -d %~dp0 -o %hb%
+ if exist "%~dp0%hb%" (echo download successful.) else (echo please try again!
+ echo=)
+ )
+
+echo required files check finished.
+echo envfiles check complete.
+pause
+:end
+del flag.txt
diff --git a/export_onnx.py b/export_onnx.py
new file mode 100644
index 0000000000000000000000000000000000000000..95376d4294ebc4d8972c5ab4a72454419f3e8cdf
--- /dev/null
+++ b/export_onnx.py
@@ -0,0 +1,54 @@
+from infer_pack.models_onnx import SynthesizerTrnMsNSFsidM
+import torch
+
+if __name__ == "__main__":
+ MoeVS = True # 模型是否为MoeVoiceStudio（原MoeSS）使用
+
+ ModelPath = "Shiroha/shiroha.pth" # 模型路径
+ ExportedPath = "model.onnx" # 输出路径
+ hidden_channels = 256 # hidden_channels，为768Vec做准备
+ cpt = torch.load(ModelPath, map_location="cpu")
+ cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
+ print(*cpt["config"])
+
+ test_phone = torch.rand(1, 200, hidden_channels) # hidden unit
+ test_phone_lengths = torch.tensor([200]).long() # hidden unit 长度（貌似没啥用）
+ test_pitch = torch.randint(size=(1, 200), low=5, high=255) # 基频（单位赫兹）
+ test_pitchf = torch.rand(1, 200) # nsf基频
+ test_ds = torch.LongTensor([0]) # 说话人ID
+ test_rnd = torch.rand(1, 192, 200) # 噪声（加入随机因子）
+
+ device = "cpu" # 导出时设备（不影响使用模型）
+
+ net_g = SynthesizerTrnMsNSFsidM(
+ *cpt["config"], is_half=False
+ ) # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
+ net_g.load_state_dict(cpt["weight"], strict=False)
+ input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
+ output_names = [
+ "audio",
+ ]
+ # net_g.construct_spkmixmap(n_speaker) 多角色混合轨道导出
+ torch.onnx.export(
+ net_g,
+ (
+ test_phone.to(device),
+ test_phone_lengths.to(device),
+ test_pitch.to(device),
+ test_pitchf.to(device),
+ test_ds.to(device),
+ test_rnd.to(device),
+ ),
+ ExportedPath,
+ dynamic_axes={
+ "phone": [1],
+ "pitch": [1],
+ "pitchf": [1],
+ "rnd": [2],
+ },
+ do_constant_folding=False,
+ opset_version=16,
+ verbose=False,
+ input_names=input_names,
+ output_names=output_names,
+ )
diff --git a/extract_f0_print.py b/extract_f0_print.py
new file mode 100644
index 0000000000000000000000000000000000000000..8efe8a4345b942bd93306c3491588ed7edcb6c80
--- /dev/null
+++ b/extract_f0_print.py
@@ -0,0 +1,160 @@
+import os, traceback, sys, parselmouth
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+from my_utils import load_audio
+import pyworld
+from scipy.io import wavfile
+import numpy as np, logging
+
+logging.getLogger("numba").setLevel(logging.WARNING)
+from multiprocessing import Process
+
+exp_dir = sys.argv[1]
+f = open("%s/extract_f0_feature.log" % exp_dir, "a+")
+
+
+def printt(strr):
+ print(strr)
+ f.write("%s\n" % strr)
+ f.flush()
+
+
+n_p = int(sys.argv[2])
+f0method = sys.argv[3]
+
+
+class FeatureInput(object):
+ def __init__(self, samplerate=16000, hop_size=160):
+ self.fs = samplerate
+ self.hop = hop_size
+
+ self.f0_bin = 256
+ self.f0_max = 1100.0
+ self.f0_min = 50.0
+ self.f0_mel_min = 1127 * np.log(1 + self.f0_min / 700)
+ self.f0_mel_max = 1127 * np.log(1 + self.f0_max / 700)
+
+ def compute_f0(self, path, f0_method):
+ x = load_audio(path, self.fs)
+ p_len = x.shape[0] // self.hop
+ if f0_method == "pm":
+ time_step = 160 / 16000 * 1000
+ f0_min = 50
+ f0_max = 1100
+ f0 = (
+ parselmouth.Sound(x, self.fs)
+ .to_pitch_ac(
+ time_step=time_step / 1000,
+ voicing_threshold=0.6,
+ pitch_floor=f0_min,
+ pitch_ceiling=f0_max,
+ )
+ .selected_array["frequency"]
+ )
+ pad_size = (p_len - len(f0) + 1) // 2
+ if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+ f0 = np.pad(
+ f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
+ )
+ elif f0_method == "harvest":
+ f0, t = pyworld.harvest(
+ x.astype(np.double),
+ fs=self.fs,
+ f0_ceil=self.f0_max,
+ f0_floor=self.f0_min,
+ frame_period=1000 * self.hop / self.fs,
+ )
+ f0 = pyworld.stonemask(x.astype(np.double), f0, t, self.fs)
+ elif f0_method == "dio":
+ f0, t = pyworld.dio(
+ x.astype(np.double),
+ fs=self.fs,
+ f0_ceil=self.f0_max,
+ f0_floor=self.f0_min,
+ frame_period=1000 * self.hop / self.fs,
+ )
+ f0 = pyworld.stonemask(x.astype(np.double), f0, t, self.fs)
+ return f0
+
+ def coarse_f0(self, f0):
+ f0_mel = 1127 * np.log(1 + f0 / 700)
+ f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - self.f0_mel_min) * (
+ self.f0_bin - 2
+ ) / (self.f0_mel_max - self.f0_mel_min) + 1
+
+ # use 0 or 1
+ f0_mel[f0_mel <= 1] = 1
+ f0_mel[f0_mel > self.f0_bin - 1] = self.f0_bin - 1
+ f0_coarse = np.rint(f0_mel).astype(int)
+ assert f0_coarse.max() <= 255 and f0_coarse.min() >= 1, (
+ f0_coarse.max(),
+ f0_coarse.min(),
+ )
+ return f0_coarse
+
+ def go(self, paths, f0_method):
+ if len(paths) == 0:
+ printt("no-f0-todo")
+ else:
+ printt("todo-f0-%s" % len(paths))
+ n = max(len(paths) // 5, 1) # 每个进程最多打印5条
+ for idx, (inp_path, opt_path1, opt_path2) in enumerate(paths):
+ try:
+ if idx % n == 0:
+ printt("f0ing,now-%s,all-%s,-%s" % (idx, len(paths), inp_path))
+ if (
+ os.path.exists(opt_path1 + ".npy") == True
+ and os.path.exists(opt_path2 + ".npy") == True
+ ):
+ continue
+ featur_pit = self.compute_f0(inp_path, f0_method)
+ np.save(
+ opt_path2,
+ featur_pit,
+ allow_pickle=False,
+ ) # nsf
+ coarse_pit = self.coarse_f0(featur_pit)
+ np.save(
+ opt_path1,
+ coarse_pit,
+ allow_pickle=False,
+ ) # ori
+ except:
+ printt("f0fail-%s-%s-%s" % (idx, inp_path, traceback.format_exc()))
+
+
+if __name__ == "__main__":
+ # exp_dir=r"E:\codes\py39\dataset\mi-test"
+ # n_p=16
+ # f = open("%s/log_extract_f0.log"%exp_dir, "w")
+ printt(sys.argv)
+ featureInput = FeatureInput()
+ paths = []
+ inp_root = "%s/1_16k_wavs" % (exp_dir)
+ opt_root1 = "%s/2a_f0" % (exp_dir)
+ opt_root2 = "%s/2b-f0nsf" % (exp_dir)
+
+ os.makedirs(opt_root1, exist_ok=True)
+ os.makedirs(opt_root2, exist_ok=True)
+ for name in sorted(list(os.listdir(inp_root))):
+ inp_path = "%s/%s" % (inp_root, name)
+ if "spec" in inp_path:
+ continue
+ opt_path1 = "%s/%s" % (opt_root1, name)
+ opt_path2 = "%s/%s" % (opt_root2, name)
+ paths.append([inp_path, opt_path1, opt_path2])
+
+ ps = []
+ for i in range(n_p):
+ p = Process(
+ target=featureInput.go,
+ args=(
+ paths[i::n_p],
+ f0method,
+ ),
+ )
+ ps.append(p)
+ p.start()
+ for i in range(n_p):
+ ps[i].join()
diff --git a/extract_feature_print.py b/extract_feature_print.py
new file mode 100644
index 0000000000000000000000000000000000000000..ab9b67520198aa50972a734020c9f8c87ae42505
--- /dev/null
+++ b/extract_feature_print.py
@@ -0,0 +1,116 @@
+import os, sys, traceback
+
+# device=sys.argv[1]
+n_part = int(sys.argv[2])
+i_part = int(sys.argv[3])
+if len(sys.argv) == 5:
+ exp_dir = sys.argv[4]
+ version = sys.argv[5]
+else:
+ i_gpu = sys.argv[4]
+ exp_dir = sys.argv[5]
+ os.environ["CUDA_VISIBLE_DEVICES"] = str(i_gpu)
+ version = sys.argv[6]
+import torch
+import torch.nn.functional as F
+import soundfile as sf
+import numpy as np
+from fairseq import checkpoint_utils
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+if torch.cuda.is_available():
+ device = "cuda"
+elif torch.backends.mps.is_available():
+ device = "mps"
+else:
+ device = "cpu"
+
+f = open("%s/extract_f0_feature.log" % exp_dir, "a+")
+
+
+def printt(strr):
+ print(strr)
+ f.write("%s\n" % strr)
+ f.flush()
+
+
+printt(sys.argv)
+model_path = "hubert_base.pt"
+
+printt(exp_dir)
+wavPath = "%s/1_16k_wavs" % exp_dir
+outPath = (
+ "%s/3_feature256" % exp_dir if version == "v1" else "%s/3_feature768" % exp_dir
+)
+os.makedirs(outPath, exist_ok=True)
+
+
+# wave must be 16k, hop_size=320
+def readwave(wav_path, normalize=False):
+ wav, sr = sf.read(wav_path)
+ assert sr == 16000
+ feats = torch.from_numpy(wav).float()
+ if feats.dim() == 2: # double channels
+ feats = feats.mean(-1)
+ assert feats.dim() == 1, feats.dim()
+ if normalize:
+ with torch.no_grad():
+ feats = F.layer_norm(feats, feats.shape)
+ feats = feats.view(1, -1)
+ return feats
+
+
+# HuBERT model
+printt("load model(s) from {}".format(model_path))
+models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
+ [model_path],
+ suffix="",
+)
+model = models[0]
+model = model.to(device)
+printt("move model to %s" % device)
+if device not in ["mps", "cpu"]:
+ model = model.half()
+model.eval()
+
+todo = sorted(list(os.listdir(wavPath)))[i_part::n_part]
+n = max(1, len(todo) // 10) # 最多打印十条
+if len(todo) == 0:
+ printt("no-feature-todo")
+else:
+ printt("all-feature-%s" % len(todo))
+ for idx, file in enumerate(todo):
+ try:
+ if file.endswith(".wav"):
+ wav_path = "%s/%s" % (wavPath, file)
+ out_path = "%s/%s" % (outPath, file.replace("wav", "npy"))
+
+ if os.path.exists(out_path):
+ continue
+
+ feats = readwave(wav_path, normalize=saved_cfg.task.normalize)
+ padding_mask = torch.BoolTensor(feats.shape).fill_(False)
+ inputs = {
+ "source": feats.half().to(device)
+ if device not in ["mps", "cpu"]
+ else feats.to(device),
+ "padding_mask": padding_mask.to(device),
+ "output_layer": 9 if version == "v1" else 12, # layer 9
+ }
+ with torch.no_grad():
+ logits = model.extract_features(**inputs)
+ feats = (
+ model.final_proj(logits[0]) if version == "v1" else logits[0]
+ )
+
+ feats = feats.squeeze(0).float().cpu().numpy()
+ if np.isnan(feats).sum() == 0:
+ np.save(out_path, feats, allow_pickle=False)
+ else:
+ printt("%s-contains nan" % file)
+ if idx % n == 0:
+ printt("now-%s,all-%s,%s,%s" % (len(todo), idx, file, feats.shape))
+ except:
+ printt(traceback.format_exc())
+ printt("all-feature-done")
diff --git a/extract_locale.py b/extract_locale.py
new file mode 100644
index 0000000000000000000000000000000000000000..c42bda59d3b620590d77e1819b31eefd275d5d87
--- /dev/null
+++ b/extract_locale.py
@@ -0,0 +1,31 @@
+import json
+import re
+
+# Define regular expression patterns
+pattern = r"""i18n\([\s\n\t]*(["'][^"']+["'])[\s\n\t]*\)"""
+
+# Initialize the dictionary to store key-value pairs
+data = {}
+
+
+def process(fn: str):
+ global data
+ with open(fn, "r", encoding="utf-8") as f:
+ contents = f.read()
+ matches = re.findall(pattern, contents)
+ for key in matches:
+ key = eval(key)
+ print("extract:", key)
+ data[key] = key
+
+
+print("processing infer-web.py")
+process("infer-web.py")
+
+print("processing gui.py")
+process("gui.py")
+
+# Save as a JSON file
+with open("./i18n/zh_CN.json", "w", encoding="utf-8") as f:
+ json.dump(data, f, ensure_ascii=False, indent=4)
+ f.write("\n")
diff --git a/ffmpeg b/ffmpeg
new file mode 100644
index 0000000000000000000000000000000000000000..4cd4c5eb25a0ef9b1d917f410fc3bc471688dc48
--- /dev/null
+++ b/ffmpeg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e8c9eb308f6161d33e16ecf6fa09884f36bdf5ca1bd4abbbcf20a0fb3145eb
+size 91584056
diff --git a/go-realtime-gui.bat b/go-realtime-gui.bat
new file mode 100644
index 0000000000000000000000000000000000000000..835543f5d4845f4b9dae70c1cf1855cce3ce6c0b
--- /dev/null
+++ b/go-realtime-gui.bat
@@ -0,0 +1,2 @@
+runtime\python.exe gui.py
+pause
diff --git a/go-web.bat b/go-web.bat
new file mode 100644
index 0000000000000000000000000000000000000000..db1dec52006bc631e4e68bafd619a3a65f202532
--- /dev/null
+++ b/go-web.bat
@@ -0,0 +1,2 @@
+runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
+pause
diff --git a/gui.py b/gui.py
new file mode 100644
index 0000000000000000000000000000000000000000..754d95b47cc3abc80166c63d2ecc1e69ce38ce41
--- /dev/null
+++ b/gui.py
@@ -0,0 +1,681 @@
+"""
+0416后的更新：
+ 引入config中half
+ 重建npy而不用填写
+ v2支持
+ 无f0模型支持
+ 修复
+
+ int16：
+ 增加无索引支持
+ f0算法改harvest(怎么看就只有这个会影响CPU占用)，但是不这么改效果不好
+"""
+import os, sys, traceback
+
+import json
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+from config import Config
+
+Config = Config()
+import PySimpleGUI as sg
+import sounddevice as sd
+import noisereduce as nr
+import numpy as np
+from fairseq import checkpoint_utils
+import librosa, torch, pyworld, faiss, time, threading
+import torch.nn.functional as F
+import torchaudio.transforms as tat
+import scipy.signal as signal
+
+
+# import matplotlib.pyplot as plt
+from infer_pack.models import (
+ SynthesizerTrnMs256NSFsid,
+ SynthesizerTrnMs256NSFsid_nono,
+ SynthesizerTrnMs768NSFsid,
+ SynthesizerTrnMs768NSFsid_nono,
+)
+from i18n import I18nAuto
+
+i18n = I18nAuto()
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+current_dir = os.getcwd()
+
+
+class RVC:
+ def __init__(
+ self, key, hubert_path, pth_path, index_path, npy_path, index_rate
+ ) -> None:
+ """
+ 初始化
+ """
+ try:
+ self.f0_up_key = key
+ self.time_step = 160 / 16000 * 1000
+ self.f0_min = 50
+ self.f0_max = 1100
+ self.f0_mel_min = 1127 * np.log(1 + self.f0_min / 700)
+ self.f0_mel_max = 1127 * np.log(1 + self.f0_max / 700)
+ self.sr = 16000
+ self.window = 160
+ if index_rate != 0:
+ self.index = faiss.read_index(index_path)
+ # self.big_npy = np.load(npy_path)
+ self.big_npy = self.index.reconstruct_n(0, self.index.ntotal)
+ print("index search enabled")
+ self.index_rate = index_rate
+ model_path = hubert_path
+ print("load model(s) from {}".format(model_path))
+ models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
+ [model_path],
+ suffix="",
+ )
+ self.model = models[0]
+ self.model = self.model.to(device)
+ if Config.is_half:
+ self.model = self.model.half()
+ else:
+ self.model = self.model.float()
+ self.model.eval()
+ cpt = torch.load(pth_path, map_location="cpu")
+ self.tgt_sr = cpt["config"][-1]
+ cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
+ self.if_f0 = cpt.get("f0", 1)
+ self.version = cpt.get("version", "v1")
+ if self.version == "v1":
+ if self.if_f0 == 1:
+ self.net_g = SynthesizerTrnMs256NSFsid(
+ *cpt["config"], is_half=Config.is_half
+ )
+ else:
+ self.net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
+ elif self.version == "v2":
+ if self.if_f0 == 1:
+ self.net_g = SynthesizerTrnMs768NSFsid(
+ *cpt["config"], is_half=Config.is_half
+ )
+ else:
+ self.net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
+ del self.net_g.enc_q
+ print(self.net_g.load_state_dict(cpt["weight"], strict=False))
+ self.net_g.eval().to(device)
+ if Config.is_half:
+ self.net_g = self.net_g.half()
+ else:
+ self.net_g = self.net_g.float()
+ except:
+ print(traceback.format_exc())
+
+ def get_f0(self, x, f0_up_key, inp_f0=None):
+ x_pad = 1
+ f0_min = 50
+ f0_max = 1100
+ f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+ f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+ f0, t = pyworld.harvest(
+ x.astype(np.double),
+ fs=self.sr,
+ f0_ceil=f0_max,
+ f0_floor=f0_min,
+ frame_period=10,
+ )
+ f0 = pyworld.stonemask(x.astype(np.double), f0, t, self.sr)
+ f0 = signal.medfilt(f0, 3)
+ f0 *= pow(2, f0_up_key / 12)
+ # with open("test.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+ tf0 = self.sr // self.window # 每秒f0点数
+ if inp_f0 is not None:
+ delta_t = np.round(
+ (inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1
+ ).astype("int16")
+ replace_f0 = np.interp(
+ list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1]
+ )
+ shape = f0[x_pad * tf0 : x_pad * tf0 + len(replace_f0)].shape[0]
+ f0[x_pad * tf0 : x_pad * tf0 + len(replace_f0)] = replace_f0[:shape]
+ # with open("test_opt.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+ f0bak = f0.copy()
+ f0_mel = 1127 * np.log(1 + f0 / 700)
+ f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+ f0_mel_max - f0_mel_min
+ ) + 1
+ f0_mel[f0_mel <= 1] = 1
+ f0_mel[f0_mel > 255] = 255
+ f0_coarse = np.rint(f0_mel).astype(np.int)
+ return f0_coarse, f0bak # 1-0
+
+ def infer(self, feats: torch.Tensor) -> np.ndarray:
+ """
+ 推理函数
+ """
+ audio = feats.clone().cpu().numpy()
+ assert feats.dim() == 1, feats.dim()
+ feats = feats.view(1, -1)
+ padding_mask = torch.BoolTensor(feats.shape).fill_(False)
+ if Config.is_half:
+ feats = feats.half()
+ else:
+ feats = feats.float()
+ inputs = {
+ "source": feats.to(device),
+ "padding_mask": padding_mask.to(device),
+ "output_layer": 9 if self.version == "v1" else 12,
+ }
+ torch.cuda.synchronize()
+ with torch.no_grad():
+ logits = self.model.extract_features(**inputs)
+ feats = (
+ self.model.final_proj(logits[0]) if self.version == "v1" else logits[0]
+ )
+
+ ####索引优化
+ try:
+ if (
+ hasattr(self, "index")
+ and hasattr(self, "big_npy")
+ and self.index_rate != 0
+ ):
+ npy = feats[0].cpu().numpy().astype("float32")
+ score, ix = self.index.search(npy, k=8)
+ weight = np.square(1 / score)
+ weight /= weight.sum(axis=1, keepdims=True)
+ npy = np.sum(self.big_npy[ix] * np.expand_dims(weight, axis=2), axis=1)
+ if Config.is_half:
+ npy = npy.astype("float16")
+ feats = (
+ torch.from_numpy(npy).unsqueeze(0).to(device) * self.index_rate
+ + (1 - self.index_rate) * feats
+ )
+ else:
+ print("index search FAIL or disabled")
+ except:
+ traceback.print_exc()
+ print("index search FAIL")
+ feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
+ torch.cuda.synchronize()
+ print(feats.shape)
+ if self.if_f0 == 1:
+ pitch, pitchf = self.get_f0(audio, self.f0_up_key)
+ p_len = min(feats.shape[1], 13000, pitch.shape[0]) # 太大了爆显存
+ else:
+ pitch, pitchf = None, None
+ p_len = min(feats.shape[1], 13000) # 太大了爆显存
+ torch.cuda.synchronize()
+ # print(feats.shape,pitch.shape)
+ feats = feats[:, :p_len, :]
+ if self.if_f0 == 1:
+ pitch = pitch[:p_len]
+ pitchf = pitchf[:p_len]
+ pitch = torch.LongTensor(pitch).unsqueeze(0).to(device)
+ pitchf = torch.FloatTensor(pitchf).unsqueeze(0).to(device)
+ p_len = torch.LongTensor([p_len]).to(device)
+ ii = 0 # sid
+ sid = torch.LongTensor([ii]).to(device)
+ with torch.no_grad():
+ if self.if_f0 == 1:
+ infered_audio = (
+ self.net_g.infer(feats, p_len, pitch, pitchf, sid)[0][0, 0]
+ .data.cpu()
+ .float()
+ )
+ else:
+ infered_audio = (
+ self.net_g.infer(feats, p_len, sid)[0][0, 0].data.cpu().float()
+ )
+ torch.cuda.synchronize()
+ return infered_audio
+
+
+class GUIConfig:
+ def __init__(self) -> None:
+ self.hubert_path: str = ""
+ self.pth_path: str = ""
+ self.index_path: str = ""
+ self.npy_path: str = ""
+ self.pitch: int = 12
+ self.samplerate: int = 44100
+ self.block_time: float = 1.0 # s
+ self.buffer_num: int = 1
+ self.threhold: int = -30
+ self.crossfade_time: float = 0.08
+ self.extra_time: float = 0.04
+ self.I_noise_reduce = False
+ self.O_noise_reduce = False
+ self.index_rate = 0.3
+
+
+class GUI:
+ def __init__(self) -> None:
+ self.config = GUIConfig()
+ self.flag_vc = False
+
+ self.launcher()
+
+ def load(self):
+ input_devices, output_devices, _, _ = self.get_devices()
+ try:
+ with open("values1.json", "r") as j:
+ data = json.load(j)
+ except:
+ with open("values1.json", "w") as j:
+ data = {
+ "pth_path": " ",
+ "index_path": " ",
+ "sg_input_device": input_devices[sd.default.device[0]],
+ "sg_output_device": output_devices[sd.default.device[1]],
+ "threhold": "-45",
+ "pitch": "0",
+ "index_rate": "0",
+ "block_time": "1",
+ "crossfade_length": "0.04",
+ "extra_time": "1",
+ }
+ return data
+
+ def launcher(self):
+ data = self.load()
+ sg.theme("LightBlue3")
+ input_devices, output_devices, _, _ = self.get_devices()
+ layout = [
+ [
+ sg.Frame(
+ title=i18n("加载模型"),
+ layout=[
+ [
+ sg.Input(
+ default_text="hubert_base.pt",
+ key="hubert_path",
+ disabled=True,
+ ),
+ sg.FileBrowse(
+ i18n("Hubert模型"),
+ initial_folder=os.path.join(os.getcwd()),
+ file_types=((". pt"),),
+ ),
+ ],
+ [
+ sg.Input(
+ default_text=data.get("pth_path", ""),
+ key="pth_path",
+ ),
+ sg.FileBrowse(
+ i18n("选择.pth文件"),
+ initial_folder=os.path.join(os.getcwd(), "weights"),
+ file_types=((". pth"),),
+ ),
+ ],
+ [
+ sg.Input(
+ default_text=data.get("index_path", ""),
+ key="index_path",
+ ),
+ sg.FileBrowse(
+ i18n("选择.index文件"),
+ initial_folder=os.path.join(os.getcwd(), "logs"),
+ file_types=((". index"),),
+ ),
+ ],
+ [
+ sg.Input(
+ default_text="你不需要填写这个You don't need write this.",
+ key="npy_path",
+ disabled=True,
+ ),
+ sg.FileBrowse(
+ i18n("选择.npy文件"),
+ initial_folder=os.path.join(os.getcwd(), "logs"),
+ file_types=((". npy"),),
+ ),
+ ],
+ ],
+ )
+ ],
+ [
+ sg.Frame(
+ layout=[
+ [
+ sg.Text(i18n("输入设备")),
+ sg.Combo(
+ input_devices,
+ key="sg_input_device",
+ default_value=data.get("sg_input_device", ""),
+ ),
+ ],
+ [
+ sg.Text(i18n("输出设备")),
+ sg.Combo(
+ output_devices,
+ key="sg_output_device",
+ default_value=data.get("sg_output_device", ""),
+ ),
+ ],
+ ],
+ title=i18n("音频设备(请使用同种类驱动)"),
+ )
+ ],
+ [
+ sg.Frame(
+ layout=[
+ [
+ sg.Text(i18n("响应阈值")),
+ sg.Slider(
+ range=(-60, 0),
+ key="threhold",
+ resolution=1,
+ orientation="h",
+ default_value=data.get("threhold", ""),
+ ),
+ ],
+ [
+ sg.Text(i18n("音调设置")),
+ sg.Slider(
+ range=(-24, 24),
+ key="pitch",
+ resolution=1,
+ orientation="h",
+ default_value=data.get("pitch", ""),
+ ),
+ ],
+ [
+ sg.Text(i18n("Index Rate")),
+ sg.Slider(
+ range=(0.0, 1.0),
+ key="index_rate",
+ resolution=0.01,
+ orientation="h",
+ default_value=data.get("index_rate", ""),
+ ),
+ ],
+ ],
+ title=i18n("常规设置"),
+ ),
+ sg.Frame(
+ layout=[
+ [
+ sg.Text(i18n("采样长度")),
+ sg.Slider(
+ range=(0.1, 3.0),
+ key="block_time",
+ resolution=0.1,
+ orientation="h",
+ default_value=data.get("block_time", ""),
+ ),
+ ],
+ [
+ sg.Text(i18n("淡入淡出长度")),
+ sg.Slider(
+ range=(0.01, 0.15),
+ key="crossfade_length",
+ resolution=0.01,
+ orientation="h",
+ default_value=data.get("crossfade_length", ""),
+ ),
+ ],
+ [
+ sg.Text(i18n("额外推理时长")),
+ sg.Slider(
+ range=(0.05, 3.00),
+ key="extra_time",
+ resolution=0.01,
+ orientation="h",
+ default_value=data.get("extra_time", ""),
+ ),
+ ],
+ [
+ sg.Checkbox(i18n("输入降噪"), key="I_noise_reduce"),
+ sg.Checkbox(i18n("输出降噪"), key="O_noise_reduce"),
+ ],
+ ],
+ title=i18n("性能设置"),
+ ),
+ ],
+ [
+ sg.Button(i18n("开始音频转换"), key="start_vc"),
+ sg.Button(i18n("停止音频转换"), key="stop_vc"),
+ sg.Text(i18n("推理时间(ms):")),
+ sg.Text("0", key="infer_time"),
+ ],
+ ]
+ self.window = sg.Window("RVC - GUI", layout=layout)
+ self.event_handler()
+
+ def event_handler(self):
+ while True:
+ event, values = self.window.read()
+ if event == sg.WINDOW_CLOSED:
+ self.flag_vc = False
+ exit()
+ if event == "start_vc" and self.flag_vc == False:
+ self.set_values(values)
+ print("using_cuda:" + str(torch.cuda.is_available()))
+ self.start_vc()
+ settings = {
+ "pth_path": values["pth_path"],
+ "index_path": values["index_path"],
+ "sg_input_device": values["sg_input_device"],
+ "sg_output_device": values["sg_output_device"],
+ "threhold": values["threhold"],
+ "pitch": values["pitch"],
+ "index_rate": values["index_rate"],
+ "block_time": values["block_time"],
+ "crossfade_length": values["crossfade_length"],
+ "extra_time": values["extra_time"],
+ }
+ with open("values1.json", "w") as j:
+ json.dump(settings, j)
+ if event == "stop_vc" and self.flag_vc == True:
+ self.flag_vc = False
+
+ def set_values(self, values):
+ self.set_devices(values["sg_input_device"], values["sg_output_device"])
+ self.config.hubert_path = os.path.join(current_dir, "hubert_base.pt")
+ self.config.pth_path = values["pth_path"]
+ self.config.index_path = values["index_path"]
+ self.config.npy_path = values["npy_path"]
+ self.config.threhold = values["threhold"]
+ self.config.pitch = values["pitch"]
+ self.config.block_time = values["block_time"]
+ self.config.crossfade_time = values["crossfade_length"]
+ self.config.extra_time = values["extra_time"]
+ self.config.I_noise_reduce = values["I_noise_reduce"]
+ self.config.O_noise_reduce = values["O_noise_reduce"]
+ self.config.index_rate = values["index_rate"]
+
+ def start_vc(self):
+ torch.cuda.empty_cache()
+ self.flag_vc = True
+ self.block_frame = int(self.config.block_time * self.config.samplerate)
+ self.crossfade_frame = int(self.config.crossfade_time * self.config.samplerate)
+ self.sola_search_frame = int(0.012 * self.config.samplerate)
+ self.delay_frame = int(0.01 * self.config.samplerate) # 往前预留0.02s
+ self.extra_frame = int(self.config.extra_time * self.config.samplerate)
+ self.rvc = None
+ self.rvc = RVC(
+ self.config.pitch,
+ self.config.hubert_path,
+ self.config.pth_path,
+ self.config.index_path,
+ self.config.npy_path,
+ self.config.index_rate,
+ )
+ self.input_wav: np.ndarray = np.zeros(
+ self.extra_frame
+ + self.crossfade_frame
+ + self.sola_search_frame
+ + self.block_frame,
+ dtype="float32",
+ )
+ self.output_wav: torch.Tensor = torch.zeros(
+ self.block_frame, device=device, dtype=torch.float32
+ )
+ self.sola_buffer: torch.Tensor = torch.zeros(
+ self.crossfade_frame, device=device, dtype=torch.float32
+ )
+ self.fade_in_window: torch.Tensor = torch.linspace(
+ 0.0, 1.0, steps=self.crossfade_frame, device=device, dtype=torch.float32
+ )
+ self.fade_out_window: torch.Tensor = 1 - self.fade_in_window
+ self.resampler1 = tat.Resample(
+ orig_freq=self.config.samplerate, new_freq=16000, dtype=torch.float32
+ )
+ self.resampler2 = tat.Resample(
+ orig_freq=self.rvc.tgt_sr,
+ new_freq=self.config.samplerate,
+ dtype=torch.float32,
+ )
+ thread_vc = threading.Thread(target=self.soundinput)
+ thread_vc.start()
+
+ def soundinput(self):
+ """
+ 接受音频输入
+ """
+ with sd.Stream(
+ callback=self.audio_callback,
+ blocksize=self.block_frame,
+ samplerate=self.config.samplerate,
+ dtype="float32",
+ ):
+ while self.flag_vc:
+ time.sleep(self.config.block_time)
+ print("Audio block passed.")
+ print("ENDing VC")
+
+ def audio_callback(
+ self, indata: np.ndarray, outdata: np.ndarray, frames, times, status
+ ):
+ """
+ 音频处理
+ """
+ start_time = time.perf_counter()
+ indata = librosa.to_mono(indata.T)
+ if self.config.I_noise_reduce:
+ indata[:] = nr.reduce_noise(y=indata, sr=self.config.samplerate)
+
+ """noise gate"""
+ frame_length = 2048
+ hop_length = 1024
+ rms = librosa.feature.rms(
+ y=indata, frame_length=frame_length, hop_length=hop_length
+ )
+ db_threhold = librosa.amplitude_to_db(rms, ref=1.0)[0] < self.config.threhold
+ # print(rms.shape,db.shape,db)
+ for i in range(db_threhold.shape[0]):
+ if db_threhold[i]:
+ indata[i * hop_length : (i + 1) * hop_length] = 0
+ self.input_wav[:] = np.append(self.input_wav[self.block_frame :], indata)
+
+ # infer
+ print("input_wav:" + str(self.input_wav.shape))
+ # print('infered_wav:'+str(infer_wav.shape))
+ infer_wav: torch.Tensor = self.resampler2(
+ self.rvc.infer(self.resampler1(torch.from_numpy(self.input_wav)))
+ )[-self.crossfade_frame - self.sola_search_frame - self.block_frame :].to(
+ device
+ )
+ print("infer_wav:" + str(infer_wav.shape))
+
+ # SOLA algorithm from https://github.com/yxlllc/DDSP-SVC
+ cor_nom = F.conv1d(
+ infer_wav[None, None, : self.crossfade_frame + self.sola_search_frame],
+ self.sola_buffer[None, None, :],
+ )
+ cor_den = torch.sqrt(
+ F.conv1d(
+ infer_wav[None, None, : self.crossfade_frame + self.sola_search_frame]
+ ** 2,
+ torch.ones(1, 1, self.crossfade_frame, device=device),
+ )
+ + 1e-8
+ )
+ sola_offset = torch.argmax(cor_nom[0, 0] / cor_den[0, 0])
+ print("sola offset: " + str(int(sola_offset)))
+
+ # crossfade
+ self.output_wav[:] = infer_wav[sola_offset : sola_offset + self.block_frame]
+ self.output_wav[: self.crossfade_frame] *= self.fade_in_window
+ self.output_wav[: self.crossfade_frame] += self.sola_buffer[:]
+ if sola_offset < self.sola_search_frame:
+ self.sola_buffer[:] = (
+ infer_wav[
+ -self.sola_search_frame
+ - self.crossfade_frame
+ + sola_offset : -self.sola_search_frame
+ + sola_offset
+ ]
+ * self.fade_out_window
+ )
+ else:
+ self.sola_buffer[:] = (
+ infer_wav[-self.crossfade_frame :] * self.fade_out_window
+ )
+
+ if self.config.O_noise_reduce:
+ outdata[:] = np.tile(
+ nr.reduce_noise(
+ y=self.output_wav[:].cpu().numpy(), sr=self.config.samplerate
+ ),
+ (2, 1),
+ ).T
+ else:
+ outdata[:] = self.output_wav[:].repeat(2, 1).t().cpu().numpy()
+ total_time = time.perf_counter() - start_time
+ self.window["infer_time"].update(int(total_time * 1000))
+ print("infer time:" + str(total_time))
+
+ def get_devices(self, update: bool = True):
+ """获取设备列表"""
+ if update:
+ sd._terminate()
+ sd._initialize()
+ devices = sd.query_devices()
+ hostapis = sd.query_hostapis()
+ for hostapi in hostapis:
+ for device_idx in hostapi["devices"]:
+ devices[device_idx]["hostapi_name"] = hostapi["name"]
+ input_devices = [
+ f"{d['name']} ({d['hostapi_name']})"
+ for d in devices
+ if d["max_input_channels"] > 0
+ ]
+ output_devices = [
+ f"{d['name']} ({d['hostapi_name']})"
+ for d in devices
+ if d["max_output_channels"] > 0
+ ]
+ input_devices_indices = [
+ d["index"] if "index" in d else d["name"]
+ for d in devices
+ if d["max_input_channels"] > 0
+ ]
+ output_devices_indices = [
+ d["index"] if "index" in d else d["name"]
+ for d in devices
+ if d["max_output_channels"] > 0
+ ]
+ return (
+ input_devices,
+ output_devices,
+ input_devices_indices,
+ output_devices_indices,
+ )
+
+ def set_devices(self, input_device, output_device):
+ """设置输出设备"""
+ (
+ input_devices,
+ output_devices,
+ input_device_indices,
+ output_device_indices,
+ ) = self.get_devices()
+ sd.default.device[0] = input_device_indices[input_devices.index(input_device)]
+ sd.default.device[1] = output_device_indices[
+ output_devices.index(output_device)
+ ]
+ print("input device:" + str(sd.default.device[0]) + ":" + str(input_device))
+ print("output device:" + str(sd.default.device[1]) + ":" + str(output_device))
+
+
+gui = GUI()
diff --git a/hubert_base.pt b/hubert_base.pt
new file mode 100644
index 0000000000000000000000000000000000000000..72f47ab58564f01d5cc8b05c63bdf96d944551ff
--- /dev/null
+++ b/hubert_base.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96
+size 189507909
diff --git a/i18n.py b/i18n.py
new file mode 100644
index 0000000000000000000000000000000000000000..37f310fadd0b48b2f364877158fb2105d645fc03
--- /dev/null
+++ b/i18n.py
@@ -0,0 +1,28 @@
+import locale
+import json
+import os
+
+
+def load_language_list(language):
+ with open(f"./i18n/{language}.json", "r", encoding="utf-8") as f:
+ language_list = json.load(f)
+ return language_list
+
+
+class I18nAuto:
+ def __init__(self, language=None):
+ if language in ["Auto", None]:
+ language = locale.getdefaultlocale()[
+ 0
+ ] # getlocale can't identify the system's language ((None, None))
+ if not os.path.exists(f"./i18n/{language}.json"):
+ language = "en_US"
+ self.language = language
+ # print("Use Language:", language)
+ self.language_map = load_language_list(language)
+
+ def __call__(self, key):
+ return self.language_map.get(key, key)
+
+ def print(self):
+ print("Use Language:", self.language)
diff --git a/i18n/en_US.json b/i18n/en_US.json
new file mode 100644
index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b
--- /dev/null
+++ b/i18n/en_US.json
@@ -0,0 +1 @@
+{}
\ No newline at end of file
diff --git a/i18n/es_ES.json b/i18n/es_ES.json
new file mode 100644
index 0000000000000000000000000000000000000000..2a7c54f12107df8c25cb8986f4b13753e4d20edd
--- /dev/null
+++ b/i18n/es_ES.json
@@ -0,0 +1,123 @@
+{
+ "很遗憾您这没有能用的显卡来支持您训练": "很遗憾您这没有能用的显卡来支持您训练",
+ "是": "是",
+ "step1:正在处理数据": "step1:正在处理数据",
+ "step2a:无需提取音高": "step2a:无需提取音高",
+ "step2b:正在提取特征": "step2b:正在提取特征",
+ "step3a:正在训练模型": "step3a:正在训练模型",
+ "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+ "全流程结束！": "全流程结束！",
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.": "Este software es de código abierto bajo la licencia MIT, el autor no tiene ningún control sobre el software, y aquellos que usan el software y difunden los sonidos exportados por el software son los únicos responsables.
Si no está de acuerdo con esta cláusula , no puede utilizar ni citar ningún código ni archivo del paquete de software Consulte el directorio raíz Agreement-LICENSE.txt para obtener más información.",
+ "模型推理": "inferencia del modelo",
+ "推理音色": "inferencia de voz",
+ "刷新音色列表和索引路径": "刷新音色列表和索引路径",
+ "卸载音色省显存": "Descargue la voz para ahorrar memoria GPU",
+ "请选择说话人id": "seleccione una identificación de altavoz",
+ "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Tecla +12 recomendada para conversión de voz de hombre a mujer, tecla -12 para conversión de voz de mujer a hombre. Si el rango de tono es demasiado amplio y causa distorsión, ajústelo usted mismo a un rango adecuado.",
+ "变调(整数, 半音数量, 升八度12降八度-12)": "Cambio de tono (entero, número de semitonos, subir una octava +12 o bajar una octava -12)",
+ "输入待处理音频文件路径(默认是正确格式示例)": "Ingrese la ruta del archivo del audio que se procesará (el formato predeterminado es el ejemplo correcto)",
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU": "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU",
+ ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音": ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音",
+ "特征检索库文件路径,为空则使用下拉的选择结果": "特征检索库文件路径,为空则使用下拉的选择结果",
+ "自动检测index路径,下拉式选择(dropdown)": "自动检测index路径,下拉式选择(dropdown)",
+ "特征文件路径": "Ruta del archivo de características",
+ "检索特征占比": "Proporción de función de búsqueda",
+ "后处理重采样至最终采样率，0为不进行重采样": "后处理重采样至最终采样率，0为不进行重采样",
+ "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络": "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络",
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果": "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果",
+ "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调": "Archivo de curva F0, opcional, un tono por línea, en lugar de F0 predeterminado y cambio de tono",
+ "转换": "Conversión",
+ "输出信息": "Información de salida",
+ "输出音频(右下角三个点,点了可以下载)": "Salida de audio (haga clic en los tres puntos en la esquina inferior derecha para descargar)",
+ "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ": "Conversión por lotes, ingrese la carpeta que contiene los archivos de audio para convertir o cargue varios archivos de audio. El audio convertido se emitirá en la carpeta especificada (opción predeterminada).",
+ "指定输出文件夹": "Especificar carpeta de salida",
+ "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)": "Ingrese la ruta a la carpeta de audio que se procesará (simplemente cópiela desde la barra de direcciones del administrador de archivos)",
+ "也可批量输入音频文件, 二选一, 优先读文件夹": "También se pueden ingresar múltiples archivos de audio, cualquiera de las dos opciones, con prioridad dada a la carpeta",
+ "导出文件格式": "导出文件格式",
+ "伴奏人声分离&去混响&去回声": "伴奏人声分离&去混响&去回声",
+ "输入待处理音频文件夹路径": "Ingrese la ruta a la carpeta de audio que se procesará",
+ "模型": "Modelo",
+ "指定输出主人声文件夹": "指定输出主人声文件夹",
+ "指定输出非主人声文件夹": "指定输出非主人声文件夹",
+ "训练": "Entrenamiento",
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ": "paso 1: Complete la configuración del experimento. Los datos del experimento se almacenan en el directorio 'logs', con cada experimento en una carpeta separada. La ruta del nombre del experimento debe ingresarse manualmente y debe contener la configuración del experimento, los registros y los archivos del modelo entrenado.",
+ "输入实验名": "Ingrese el nombre del modelo",
+ "目标采样率": "Tasa de muestreo objetivo",
+ "模型是否带音高指导(唱歌一定要, 语音可以不要)": "Si el modelo tiene guía de tono (necesaria para cantar, pero no para hablar)",
+ "版本(目前仅40k支持了v2)": "版本(目前仅40k支持了v2)",
+ "提取音高和处理数据使用的CPU进程数": "提取音高和处理数据使用的CPU进程数",
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ": "paso 2a: recorra automáticamente la carpeta de capacitación y corte y normalice todos los archivos de audio que se pueden decodificar en audio. Se generarán dos carpetas 'wav' en el directorio del experimento. Actualmente, solo se admite la capacitación de una sola persona.",
+ "输入训练文件夹路径": "Introduzca la ruta de la carpeta de entrenamiento",
+ "请指定说话人id": "Especifique el ID del hablante",
+ "处理数据": "Procesar datos",
+ "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)": "paso 2b: use la CPU para extraer el tono (si el modelo tiene guía de tono) y la GPU para extraer características (seleccione el número de tarjeta).",
+ "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2": "Separe los números de identificación de la GPU con '-' al ingresarlos. Por ejemplo, '0-1-2' significa usar GPU 0, GPU 1 y GPU 2.",
+ "显卡信息": "información de la GPU",
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "Seleccione el algoritmo de extracción de tono: utilice 'pm' para un procesamiento más rápido de la voz cantada, 'dio' para un discurso de alta calidad pero un procesamiento más lento y 'cosecha' para obtener la mejor calidad pero un procesamiento más lento.",
+ "特征提取": "Extracción de características",
+ "step3: 填写训练设置, 开始训练模型和索引": "Paso 3: complete la configuración de entrenamiento y comience a entrenar el modelo y el índice.",
+ "保存频率save_every_epoch": "Frecuencia de guardado (save_every_epoch)",
+ "总训练轮数total_epoch": "Total de épocas de entrenamiento (total_epoch)",
+ "每张显卡的batch_size": "每张显卡的batch_size",
+ "是否仅保存最新的ckpt文件以节省硬盘空间": "Si guardar solo el archivo ckpt más reciente para ahorrar espacio en disco",
+ "否": "否",
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速": "Si almacenar en caché todos los conjuntos de entrenamiento en la memoria de la GPU. Los conjuntos de datos pequeños (menos de 10 minutos) se pueden almacenar en caché para acelerar el entrenamiento, pero el almacenamiento en caché de conjuntos de datos grandes puede causar errores de memoria en la GPU y no aumenta la velocidad de manera significativa.",
+ "是否在每次保存时间点将最终小模型保存至weights文件夹": "是否在每次保存时间点将最终小模型保存至weights文件夹",
+ "加载预训练底模G路径": "Cargue la ruta G del modelo base preentrenada.",
+ "加载预训练底模D路径": "Cargue la ruta del modelo D base preentrenada.",
+ "训练模型": "Entrenar Modelo",
+ "训练特征索引": "Índice de características del Entrenamiento",
+ "一键训练": "Entrenamiento con un clic.",
+ "ckpt处理": "Procesamiento de recibos",
+ "模型融合, 可用于测试音色融合": "Fusión de modelos, se puede utilizar para fusionar diferentes voces",
+ "A模型路径": "Modelo A ruta.",
+ "B模型路径": "Modelo B ruta.",
+ "A模型权重": "Un peso modelo para el modelo A.",
+ "模型是否带音高指导": "Si el modelo tiene guía de tono.",
+ "要置入的模型信息": "Información del modelo a colocar.",
+ "保存的模型名不带后缀": "Nombre del modelo guardado sin extensión.",
+ "模型版本型号": "模型版本型号",
+ "融合": "Fusión.",
+ "修改模型信息(仅支持weights文件夹下提取的小模型文件)": "Modificar la información del modelo (solo admite archivos de modelos pequeños extraídos en la carpeta de pesos).",
+ "模型路径": "Ruta del modelo",
+ "要改的模型信息": "Información del modelo a modificar",
+ "保存的文件名, 默认空为和源文件同名": "Nombre del archivo que se guardará, el valor predeterminado es el mismo que el nombre del archivo de origen",
+ "修改": "Modificar",
+ "查看模型信息(仅支持weights文件夹下提取的小模型文件)": "Ver información del modelo (solo aplicable a archivos de modelos pequeños extraídos de la carpeta 'pesos')",
+ "查看": "Ver",
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "Extracción de modelo (ingrese la ruta de un archivo de modelo grande en la carpeta 'logs'), aplicable cuando desea extraer un archivo de modelo pequeño después de entrenar a mitad de camino y no se guardó automáticamente, o cuando desea probar un modelo intermedio",
+ "保存名": "Guardar nombre",
+ "模型是否带音高指导,1是0否": "Si el modelo tiene guía de tono, 1 para sí, 0 para no",
+ "提取": "Extracter",
+ "Onnx导出": "Onnx导出",
+ "RVC模型路径": "RVC模型路径",
+ "Onnx输出路径": "Onnx输出路径",
+ "MoeVS模型": "MoeVS模型",
+ "导出Onnx模型": "导出Onnx模型",
+ "常见问题解答": "常见问题解答",
+ "招募音高曲线前端编辑器": "Reclutar editores front-end para curvas de tono",
+ "加开发群联系我xxxxx": "Únase al grupo de desarrollo para contactarme en xxxxx",
+ "点击查看交流、问题反馈群号": "Haga clic para ver el número de grupo de comunicación y comentarios sobre problemas",
+ "xxxxx": "xxxxx",
+ "加载模型": "Cargar modelo",
+ "Hubert模型": "Modelo de Hubert ",
+ "选择.pth文件": "Seleccionar archivo .pth",
+ "选择.index文件": "Select .index file",
+ "选择.npy文件": "Seleccionar archivo .npy",
+ "输入设备": "Dispositivo de entrada",
+ "输出设备": "Dispositivo de salida",
+ "音频设备(请使用同种类驱动)": "Dispositivo de audio (utilice el mismo tipo de controlador)",
+ "响应阈值": "Umbral de respuesta",
+ "音调设置": "Ajuste de tono",
+ "Index Rate": "Tasa de índice",
+ "常规设置": "Configuración general",
+ "采样长度": "Longitud de muestreo",
+ "淡入淡出长度": "Duración del fundido de entrada/salida",
+ "额外推理时长": "Tiempo de inferencia adicional",
+ "输入降噪": "Reducción de ruido de entrada",
+ "输出降噪": "Reducción de ruido de salida",
+ "性能设置": "Configuración de rendimiento",
+ "开始音频转换": "Iniciar conversión de audio",
+ "停止音频转换": "Detener la conversión de audio",
+ "推理时间(ms):": "Inferir tiempo (ms):"
+}
diff --git a/i18n/ja_JP.json b/i18n/ja_JP.json
new file mode 100644
index 0000000000000000000000000000000000000000..dce800285d8f42abb6da006e421e5503bb2cbbd5
--- /dev/null
+++ b/i18n/ja_JP.json
@@ -0,0 +1,123 @@
+{
+ "很遗憾您这没有能用的显卡来支持您训练": "トレーニングに対応したGPUが動作しないのは残念です。",
+ "是": "はい",
+ "step1:正在处理数据": "step1:処理中のデータ",
+ "step2a:无需提取音高": "step2a:ピッチの抽出は不要",
+ "step2b:正在提取特征": "step2b:抽出される特徴量",
+ "step3a:正在训练模型": "step3a:トレーニング中のモデル",
+ "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "トレーニング終了時に、トレーニングログやフォルダ内のtrain.logを確認することができます",
+ "全流程结束！": "全工程が完了！",
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.": "本ソフトウェアはMITライセンスに基づくオープンソースであり、作者は本ソフトウェアに対していかなる強制力も持ちません。本ソフトウェアの利用者および本ソフトウェアから派生した音源(成果物)を配布する者は、本ソフトウェアに対して自身で責任を負うものとします。
この条項に同意しない場合、パッケージ内のコードやファイルを使用や参照を禁じます。詳しくは使用需遵守的协议-LICENSE.txtをご覧ください.",
+ "模型推理": "モデル推論",
+ "推理音色": "音源推論",
+ "刷新音色列表和索引路径": "音源リストとインデックスパスの更新",
+ "卸载音色省显存": "音源を削除してメモリを節約",
+ "请选择说话人id": "話者IDを選択してください",
+ "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性から女性へは+12キーをお勧めします。女性から男性へは-12キーをお勧めします。音域が広すぎて音質が劣化した場合は、適切な音域に自分で調整することもできます。",
+ "变调(整数, 半音数量, 升八度12降八度-12)": "ピッチ変更(整数、半音数、上下オクターブ12-12)",
+ "输入待处理音频文件路径(默认是正确格式示例)": "処理対象音声ファイルのパスを入力してください(デフォルトは正しいフォーマットの例です)",
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU": "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU",
+ ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音": ">=3 次に、harvestピッチの認識結果に対してメディアンフィルタを使用します。値はフィルター半径で、ミュートを減衰させるために使用します。",
+ "特征检索库文件路径,为空则使用下拉的选择结果": "特徴検索ライブラリへのパス 空の場合はドロップダウンで選択",
+ "自动检测index路径,下拉式选择(dropdown)": "インデックスパスの自動検出 ドロップダウンで選択",
+ "特征文件路径": "特徴量ファイルのパス",
+ "检索特征占比": "検索特徴率",
+ "后处理重采样至最终采样率，0为不进行重采样": "最終的なサンプリングレートへのポストプロセッシングのリサンプリング リサンプリングしない場合は0",
+ "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络": "入力ソースの音量エンベロープと出力音量エンベロープの融合率 1に近づくほど、出力音量エンベロープの割合が高くなる",
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果": "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果",
+ "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调": "F0(最低共振周波数)カーブファイル(オプション、1行に1ピッチ、デフォルトのF0(最低共振周波数)とエレベーションを置き換えます。)",
+ "转换": "変換",
+ "输出信息": "出力情報",
+ "输出音频(右下角三个点,点了可以下载)": "出力音声(右下の三点をクリックしてダウンロードできます)",
+ "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ": "一括変換、変換する音声フォルダを入力、または複数の音声ファイルをアップロードし、指定したフォルダ(デフォルトのopt)に変換した音声を出力します。",
+ "指定输出文件夹": "出力フォルダを指定してください",
+ "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)": "処理対象音声フォルダーのパスを入力してください(ファイルマネージャのアドレスバーからコピーしてください)",
+ "也可批量输入音频文件, 二选一, 优先读文件夹": "複数の音声ファイルを一括で入力することもできますが、フォルダーを優先して読み込みます",
+ "导出文件格式": "导出文件格式",
+ "伴奏人声分离&去混响&去回声": "伴奏人声分离&去混响&去回声",
+ "输入待处理音频文件夹路径": "処理するオーディオファイルのフォルダパスを入力してください",
+ "模型": "モデル",
+ "指定输出主人声文件夹": "指定输出主人声文件夹",
+ "指定输出非主人声文件夹": "指定输出非主人声文件夹",
+ "训练": "トレーニング",
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ": "ステップ1:実験設定を入力します。実験データはlogsに保存され、各実験にはフォルダーがあります。実験名のパスを手動で入力する必要があり、実験設定、ログ、トレーニングされたモデルファイルが含まれます。",
+ "输入实验名": "モデル名",
+ "目标采样率": "目標サンプリングレート",
+ "模型是否带音高指导(唱歌一定要, 语音可以不要)": "モデルに音高ガイドがあるかどうか(歌唱には必要ですが、音声には必要ありません)",
+ "版本(目前仅40k支持了v2)": "バージョン（現在v2をサポートしているのは40kのみ）",
+ "提取音高和处理数据使用的CPU进程数": "ピッチの抽出やデータ処理に使用するCPUスレッド数",
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ": "ステップ2a: 訓練フォルダー内のすべての音声ファイルを自動的に探索し、スライスと正規化を行い、2つのwavフォルダーを実験ディレクトリに生成します。現在は一人でのトレーニングのみをサポートしています。",
+ "输入训练文件夹路径": "トレーニング用フォルダのパスを入力してください",
+ "请指定说话人id": "話者IDを指定してください",
+ "处理数据": "データ処理",
+ "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)": "ステップ2b: CPUを使用して音高を抽出する(モデルに音高がある場合)、GPUを使用して特徴を抽出する(GPUの番号を選択する)",
+ "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2": "ハイフンで区切って使用するGPUの番号を入力します。例えば0-1-2はGPU0、GPU1、GPU2を使用します",
+ "显卡信息": "GPU情報",
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "音高抽出アルゴリズムの選択:歌声を入力する場合は、pmを使用して速度を上げることができます。CPUが低い場合はdioを使用して速度を上げることができます。harvestは品質が高く、精度が高いですが、遅いです。",
+ "特征提取": "特徴抽出",
+ "step3: 填写训练设置, 开始训练模型和索引": "ステップ3: トレーニング設定を入力して、モデルとインデックスのトレーニングを開始します",
+ "保存频率save_every_epoch": "エポックごとの保存頻度",
+ "总训练轮数total_epoch": "総エポック数",
+ "每张显卡的batch_size": "GPUごとのバッチサイズ",
+ "是否仅保存最新的ckpt文件以节省硬盘空间": "ハードディスク容量を節約するため、最新のckptファイルのみを保存するかどうか",
+ "否": "いいえ",
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速": "すべてのトレーニングデータをメモリにキャッシュするかどうか。10分以下の小さなデータはキャッシュしてトレーニングを高速化できますが、大きなデータをキャッシュするとメモリが破裂し、あまり速度が上がりません。",
+ "是否在每次保存时间点将最终小模型保存至weights文件夹": "各保存時点の小モデルを全部weightsフォルダに保存するかどうか",
+ "加载预训练底模G路径": "事前学習済みのGモデルのパス",
+ "加载预训练底模D路径": "事前学習済みのDモデルのパス",
+ "训练模型": "モデルのトレーニング",
+ "训练特征索引": "特徴インデックスのトレーニング",
+ "一键训练": "ワンクリックトレーニング",
+ "ckpt处理": "ckptファイルの処理",
+ "模型融合, 可用于测试音色融合": "モデルのマージ、音源のマージテストに使用できます",
+ "A模型路径": "Aモデルのパス",
+ "B模型路径": "Bモデルのパス",
+ "A模型权重": "Aモデルの重み",
+ "模型是否带音高指导": "モデルに音高ガイドを付けるかどうか",
+ "要置入的模型信息": "挿入するモデル情報",
+ "保存的模型名不带后缀": "拡張子のない保存するモデル名",
+ "模型版本型号": "モデルのバージョン",
+ "融合": "フュージョン",
+ "修改模型信息(仅支持weights文件夹下提取的小模型文件)": "モデル情報の修正(weightsフォルダから抽出された小さなモデルファイルのみ対応)",
+ "模型路径": "モデルパス",
+ "要改的模型信息": "変更するモデル情報",
+ "保存的文件名, 默认空为和源文件同名": "保存するファイル名、デフォルトでは空欄で元のファイル名と同じ名前になります",
+ "修改": "変更",
+ "查看模型信息(仅支持weights文件夹下提取的小模型文件)": "モデル情報を表示する(小さいモデルファイルはweightsフォルダーからのみサポートされています)",
+ "查看": "表示",
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "モデル抽出(ログフォルダー内の大きなファイルのモデルパスを入力)、モデルを半分までトレーニングし、自動的に小さいファイルモデルを保存しなかったり、中間モデルをテストしたい場合に適用されます。",
+ "保存名": "保存ファイル名",
+ "模型是否带音高指导,1是0否": "モデルに音高ガイドを付けるかどうか、1は付ける、0は付けない",
+ "提取": "抽出",
+ "Onnx导出": "Onnx",
+ "RVC模型路径": "RVCモデルパス",
+ "Onnx输出路径": "Onnx出力パス",
+ "MoeVS模型": "MoeSS？",
+ "导出Onnx模型": "Onnxに変換",
+ "常见问题解答": "よくある質問",
+ "招募音高曲线前端编辑器": "音高曲線フロントエンドエディターを募集",
+ "加开发群联系我xxxxx": "開発グループに参加して私に連絡してくださいxxxxx",
+ "点击查看交流、问题反馈群号": "クリックして交流、問題フィードバックグループ番号を表示",
+ "xxxxx": "xxxxx",
+ "加载模型": "モデルをロード",
+ "Hubert模型": "Hubertモデル",
+ "选择.pth文件": ".pthファイルを選択",
+ "选择.index文件": ".indexファイルを選択",
+ "选择.npy文件": ".npyファイルを選択",
+ "输入设备": "入力デバイス",
+ "输出设备": "出力デバイス",
+ "音频设备(请使用同种类驱动)": "オーディオデバイス(同じ種類のドライバーを使用してください)",
+ "响应阈值": "反応閾値",
+ "音调设置": "音程設定",
+ "Index Rate": "Index Rate",
+ "常规设置": "一般設定",
+ "采样长度": "サンプル長",
+ "淡入淡出长度": "フェードイン/フェードアウト長",
+ "额外推理时长": "追加推論時間",
+ "输入降噪": "入力ノイズの低減",
+ "输出降噪": "出力ノイズの低減",
+ "性能设置": "パフォーマンス設定",
+ "开始音频转换": "音声変換を開始",
+ "停止音频转换": "音声変換を停止",
+ "推理时间(ms):": "推論時間(ms):"
+}
diff --git a/i18n/locale_diff.py b/i18n/locale_diff.py
new file mode 100644
index 0000000000000000000000000000000000000000..257277965e0866a86d0361863a8f1b408c4f71ab
--- /dev/null
+++ b/i18n/locale_diff.py
@@ -0,0 +1,45 @@
+import json
+import os
+from collections import OrderedDict
+
+# Define the standard file name
+standard_file = "zh_CN.json"
+
+# Find all JSON files in the directory
+dir_path = "./"
+languages = [
+ f for f in os.listdir(dir_path) if f.endswith(".json") and f != standard_file
+]
+
+# Load the standard file
+with open(standard_file, "r", encoding="utf-8") as f:
+ standard_data = json.load(f, object_pairs_hook=OrderedDict)
+
+# Loop through each language file
+for lang_file in languages:
+ # Load the language file
+ with open(lang_file, "r", encoding="utf-8") as f:
+ lang_data = json.load(f, object_pairs_hook=OrderedDict)
+
+ # Find the difference between the language file and the standard file
+ diff = set(standard_data.keys()) - set(lang_data.keys())
+
+ miss = set(lang_data.keys()) - set(standard_data.keys())
+
+ # Add any missing keys to the language file
+ for key in diff:
+ lang_data[key] = key
+
+ # Del any extra keys to the language file
+ for key in miss:
+ del lang_data[key]
+
+ # Sort the keys of the language file to match the order of the standard file
+ lang_data = OrderedDict(
+ sorted(lang_data.items(), key=lambda x: list(standard_data.keys()).index(x[0]))
+ )
+
+ # Save the updated language file
+ with open(lang_file, "w", encoding="utf-8") as f:
+ json.dump(lang_data, f, ensure_ascii=False, indent=4)
+ f.write("\n")
diff --git a/i18n/zh_CN.json b/i18n/zh_CN.json
new file mode 100644
index 0000000000000000000000000000000000000000..f12f47ba9ed86c0616d0e1dd481b39ea438f18ee
--- /dev/null
+++ b/i18n/zh_CN.json
@@ -0,0 +1,123 @@
+{
+ "很遗憾您这没有能用的显卡来支持您训练": "很遗憾您这没有能用的显卡来支持您训练",
+ "是": "是",
+ "step1:正在处理数据": "step1:正在处理数据",
+ "step2a:无需提取音高": "step2a:无需提取音高",
+ "step2b:正在提取特征": "step2b:正在提取特征",
+ "step3a:正在训练模型": "step3a:正在训练模型",
+ "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+ "全流程结束！": "全流程结束！",
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.": "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.",
+ "模型推理": "模型推理",
+ "推理音色": "推理音色",
+ "刷新音色列表和索引路径": "刷新音色列表和索引路径",
+ "卸载音色省显存": "卸载音色省显存",
+ "请选择说话人id": "请选择说话人id",
+ "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ",
+ "变调(整数, 半音数量, 升八度12降八度-12)": "变调(整数, 半音数量, 升八度12降八度-12)",
+ "输入待处理音频文件路径(默认是正确格式示例)": "输入待处理音频文件路径(默认是正确格式示例)",
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU": "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU",
+ ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音": ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音",
+ "特征检索库文件路径,为空则使用下拉的选择结果": "特征检索库文件路径,为空则使用下拉的选择结果",
+ "自动检测index路径,下拉式选择(dropdown)": "自动检测index路径,下拉式选择(dropdown)",
+ "特征文件路径": "特征文件路径",
+ "检索特征占比": "检索特征占比",
+ "后处理重采样至最终采样率，0为不进行重采样": "后处理重采样至最终采样率，0为不进行重采样",
+ "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络": "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络",
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果": "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果",
+ "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调": "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调",
+ "转换": "转换",
+ "输出信息": "输出信息",
+ "输出音频(右下角三个点,点了可以下载)": "输出音频(右下角三个点,点了可以下载)",
+ "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ": "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ",
+ "指定输出文件夹": "指定输出文件夹",
+ "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)": "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)",
+ "也可批量输入音频文件, 二选一, 优先读文件夹": "也可批量输入音频文件, 二选一, 优先读文件夹",
+ "导出文件格式": "导出文件格式",
+ "伴奏人声分离&去混响&去回声": "伴奏人声分离&去混响&去回声",
+ "输入待处理音频文件夹路径": "输入待处理音频文件夹路径",
+ "模型": "模型",
+ "指定输出主人声文件夹": "指定输出主人声文件夹",
+ "指定输出非主人声文件夹": "指定输出非主人声文件夹",
+ "训练": "训练",
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ": "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ",
+ "输入实验名": "输入实验名",
+ "目标采样率": "目标采样率",
+ "模型是否带音高指导(唱歌一定要, 语音可以不要)": "模型是否带音高指导(唱歌一定要, 语音可以不要)",
+ "版本(目前仅40k支持了v2)": "版本(目前仅40k支持了v2)",
+ "提取音高和处理数据使用的CPU进程数": "提取音高和处理数据使用的CPU进程数",
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ": "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ",
+ "输入训练文件夹路径": "输入训练文件夹路径",
+ "请指定说话人id": "请指定说话人id",
+ "处理数据": "处理数据",
+ "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)": "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)",
+ "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2": "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2",
+ "显卡信息": "显卡信息",
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢",
+ "特征提取": "特征提取",
+ "step3: 填写训练设置, 开始训练模型和索引": "step3: 填写训练设置, 开始训练模型和索引",
+ "保存频率save_every_epoch": "保存频率save_every_epoch",
+ "总训练轮数total_epoch": "总训练轮数total_epoch",
+ "每张显卡的batch_size": "每张显卡的batch_size",
+ "是否仅保存最新的ckpt文件以节省硬盘空间": "是否仅保存最新的ckpt文件以节省硬盘空间",
+ "否": "否",
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速": "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速",
+ "是否在每次保存时间点将最终小模型保存至weights文件夹": "是否在每次保存时间点将最终小模型保存至weights文件夹",
+ "加载预训练底模G路径": "加载预训练底模G路径",
+ "加载预训练底模D路径": "加载预训练底模D路径",
+ "训练模型": "训练模型",
+ "训练特征索引": "训练特征索引",
+ "一键训练": "一键训练",
+ "ckpt处理": "ckpt处理",
+ "模型融合, 可用于测试音色融合": "模型融合, 可用于测试音色融合",
+ "A模型路径": "A模型路径",
+ "B模型路径": "B模型路径",
+ "A模型权重": "A模型权重",
+ "模型是否带音高指导": "模型是否带音高指导",
+ "要置入的模型信息": "要置入的模型信息",
+ "保存的模型名不带后缀": "保存的模型名不带后缀",
+ "模型版本型号": "模型版本型号",
+ "融合": "融合",
+ "修改模型信息(仅支持weights文件夹下提取的小模型文件)": "修改模型信息(仅支持weights文件夹下提取的小模型文件)",
+ "模型路径": "模型路径",
+ "要改的模型信息": "要改的模型信息",
+ "保存的文件名, 默认空为和源文件同名": "保存的文件名, 默认空为和源文件同名",
+ "修改": "修改",
+ "查看模型信息(仅支持weights文件夹下提取的小模型文件)": "查看模型信息(仅支持weights文件夹下提取的小模型文件)",
+ "查看": "查看",
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况",
+ "保存名": "保存名",
+ "模型是否带音高指导,1是0否": "模型是否带音高指导,1是0否",
+ "提取": "提取",
+ "Onnx导出": "Onnx导出",
+ "RVC模型路径": "RVC模型路径",
+ "Onnx输出路径": "Onnx输出路径",
+ "MoeVS模型": "MoeVS模型",
+ "导出Onnx模型": "导出Onnx模型",
+ "常见问题解答": "常见问题解答",
+ "招募音高曲线前端编辑器": "招募音高曲线前端编辑器",
+ "加开发群联系我xxxxx": "加开发群联系我xxxxx",
+ "点击查看交流、问题反馈群号": "点击查看交流、问题反馈群号",
+ "xxxxx": "xxxxx",
+ "加载模型": "加载模型",
+ "Hubert模型": "Hubert模型",
+ "选择.pth文件": "选择.pth文件",
+ "选择.index文件": "选择.index文件",
+ "选择.npy文件": "选择.npy文件",
+ "输入设备": "输入设备",
+ "输出设备": "输出设备",
+ "音频设备(请使用同种类驱动)": "音频设备(请使用同种类驱动)",
+ "响应阈值": "响应阈值",
+ "音调设置": "音调设置",
+ "Index Rate": "Index Rate",
+ "常规设置": "常规设置",
+ "采样长度": "采样长度",
+ "淡入淡出长度": "淡入淡出长度",
+ "额外推理时长": "额外推理时长",
+ "输入降噪": "输入降噪",
+ "输出降噪": "输出降噪",
+ "性能设置": "性能设置",
+ "开始音频转换": "开始音频转换",
+ "停止音频转换": "停止音频转换",
+ "推理时间(ms):": "推理时间(ms):"
+}
diff --git a/i18n/zh_HK.json b/i18n/zh_HK.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca0dbc0a5d21c5664d6aeaa39d06a2379188f91d
--- /dev/null
+++ b/i18n/zh_HK.json
@@ -0,0 +1,123 @@
+{
+ "很遗憾您这没有能用的显卡来支持您训练": "很遗憾您这没有能用的显卡来支持您训练",
+ "是": "是",
+ "step1:正在处理数据": "step1:正在处理数据",
+ "step2a:无需提取音高": "step2a:无需提取音高",
+ "step2b:正在提取特征": "step2b:正在提取特征",
+ "step3a:正在训练模型": "step3a:正在训练模型",
+ "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+ "全流程结束！": "全流程结束！",
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.": "本軟體以MIT協議開源，作者不對軟體具備任何控制力，使用軟體者、傳播軟體導出的聲音者自負全責。
如不認可該條款，則不能使用或引用軟體包內任何程式碼和檔案。詳見根目錄使用需遵守的協議-LICENSE.txt。",
+ "模型推理": "模型推理",
+ "推理音色": "推理音色",
+ "刷新音色列表和索引路径": "刷新音色列表和索引路徑",
+ "卸载音色省显存": "卸載音色節省 VRAM",
+ "请选择说话人id": "請選擇說話人ID",
+ "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性轉女性推薦+12key，女性轉男性推薦-12key，如果音域爆炸導致音色失真也可以自己調整到合適音域。",
+ "变调(整数, 半音数量, 升八度12降八度-12)": "變調(整數、半音數量、升八度12降八度-12)",
+ "输入待处理音频文件路径(默认是正确格式示例)": "輸入待處理音頻檔案路徑（預設是正確格式示例）",
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU": "選擇音高提取演算法,輸入歌聲可用pm提速,harvest低音好但巨慢無比,crepe效果好但吃GPU",
+ ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音": ">=3則使用對harvest音高識別的結果使用中值濾波，數值為濾波半徑，使用可以削弱啞音",
+ "特征检索库文件路径,为空则使用下拉的选择结果": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果",
+ "自动检测index路径,下拉式选择(dropdown)": "自動檢測index路徑,下拉式選擇(dropdown)",
+ "特征文件路径": "特徵檔案路徑",
+ "检索特征占比": "檢索特徵佔比",
+ "后处理重采样至最终采样率，0为不进行重采样": "後處理重採樣至最終採樣率，0為不進行重採樣",
+ "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络": "輸入源音量包絡替換輸出音量包絡融合比例，越靠近1越使用輸出包絡",
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果": "保護清輔音和呼吸聲，防止電音撕裂等artifact，拉滿0.5不開啟，調低加大保護力度但可能降低索引效果",
+ "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调": "F0曲線檔案，可選，一行一個音高，代替預設的F0及升降調",
+ "转换": "轉換",
+ "输出信息": "輸出訊息",
+ "输出音频(右下角三个点,点了可以下载)": "輸出音頻(右下角三個點，點了可以下載)",
+ "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ": "批量轉換，輸入待轉換音頻資料夾，或上傳多個音頻檔案，在指定資料夾(默認opt)下輸出轉換的音頻。",
+ "指定输出文件夹": "指定輸出資料夾",
+ "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)": "輸入待處理音頻資料夾路徑(去檔案管理器地址欄拷貝即可)",
+ "也可批量输入音频文件, 二选一, 优先读文件夹": "也可批量輸入音頻檔案，二選一，優先讀資料夾",
+ "导出文件格式": "導出檔格式",
+ "伴奏人声分离&去混响&去回声": "伴奏人声分离&去混响&去回声",
+ "输入待处理音频文件夹路径": "輸入待處理音頻資料夾路徑",
+ "模型": "模型",
+ "指定输出主人声文件夹": "指定输出主人声文件夹",
+ "指定输出非主人声文件夹": "指定输出非主人声文件夹",
+ "训练": "訓練",
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ": "step1：填寫實驗配置。實驗數據放在logs下，每個實驗一個資料夾，需手動輸入實驗名路徑，內含實驗配置、日誌、訓練得到的模型檔案。",
+ "输入实验名": "輸入實驗名稱",
+ "目标采样率": "目標取樣率",
+ "模型是否带音高指导(唱歌一定要, 语音可以不要)": "模型是否帶音高指導（唱歌一定要，語音可以不要）",
+ "版本(目前仅40k支持了v2)": "版本(目前僅40k支持了v2)",
+ "提取音高和处理数据使用的CPU进程数": "提取音高和處理數據使用的CPU進程數",
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ": "step2a：自動遍歷訓練資料夾下所有可解碼成音頻的檔案並進行切片歸一化，在實驗目錄下生成2個wav資料夾；暫時只支援單人訓練。",
+ "输入训练文件夹路径": "輸入訓練檔案夾路徑",
+ "请指定说话人id": "請指定說話人id",
+ "处理数据": "處理資料",
+ "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)": "步驟2b: 使用CPU提取音高(如果模型帶音高), 使用GPU提取特徵(選擇卡號)",
+ "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2": "以-分隔輸入使用的卡號, 例如 0-1-2 使用卡0和卡1和卡2",
+ "显卡信息": "顯示卡資訊",
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "選擇音高提取算法:輸入歌聲可用pm提速,高品質語音但CPU差可用dio提速,harvest品質更好但較慢",
+ "特征提取": "特徵提取",
+ "step3: 填写训练设置, 开始训练模型和索引": "步驟3: 填寫訓練設定, 開始訓練模型和索引",
+ "保存频率save_every_epoch": "保存頻率save_every_epoch",
+ "总训练轮数total_epoch": "總訓練輪數total_epoch",
+ "每张显卡的batch_size": "每张显卡的batch_size",
+ "是否仅保存最新的ckpt文件以节省硬盘空间": "是否僅保存最新的ckpt檔案以節省硬碟空間",
+ "否": "否",
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速": "是否緩存所有訓練集至 VRAM。小於10分鐘的小數據可緩存以加速訓練，大數據緩存會爆 VRAM 也加不了多少速度",
+ "是否在每次保存时间点将最终小模型保存至weights文件夹": "是否在每次保存時間點將最終小模型保存至weights檔夾",
+ "加载预训练底模G路径": "加載預訓練底模G路徑",
+ "加载预训练底模D路径": "加載預訓練底模D路徑",
+ "训练模型": "訓練模型",
+ "训练特征索引": "訓練特徵索引",
+ "一键训练": "一鍵訓練",
+ "ckpt处理": "ckpt處理",
+ "模型融合, 可用于测试音色融合": "模型融合，可用於測試音色融合",
+ "A模型路径": "A模型路徑",
+ "B模型路径": "B模型路徑",
+ "A模型权重": "A模型權重",
+ "模型是否带音高指导": "模型是否帶音高指導",
+ "要置入的模型信息": "要置入的模型資訊",
+ "保存的模型名不带后缀": "儲存的模型名不帶副檔名",
+ "模型版本型号": "模型版本型號",
+ "融合": "融合",
+ "修改模型信息(仅支持weights文件夹下提取的小模型文件)": "修改模型資訊(僅支援weights資料夾下提取的小模型檔案)",
+ "模型路径": "模型路徑",
+ "要改的模型信息": "要改的模型資訊",
+ "保存的文件名, 默认空为和源文件同名": "儲存的檔案名，預設空為與來源檔案同名",
+ "修改": "修改",
+ "查看模型信息(仅支持weights文件夹下提取的小模型文件)": "查看模型資訊(僅支援weights資料夾下提取的小模型檔案)",
+ "查看": "查看",
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "模型提取(輸入logs資料夾下大檔案模型路徑)，適用於訓一半不想訓了模型沒有自動提取儲存小檔案模型，或者想測試中間模型的情況",
+ "保存名": "儲存名",
+ "模型是否带音高指导,1是0否": "模型是否帶音高指導，1是0否",
+ "提取": "提取",
+ "Onnx导出": "Onnx导出",
+ "RVC模型路径": "RVC模型路径",
+ "Onnx输出路径": "Onnx输出路径",
+ "MoeVS模型": "MoeSS模型",
+ "导出Onnx模型": "导出Onnx模型",
+ "常见问题解答": "常見問題解答",
+ "招募音高曲线前端编辑器": "招募音高曲線前端編輯器",
+ "加开发群联系我xxxxx": "加開發群聯繫我xxxxx",
+ "点击查看交流、问题反馈群号": "點擊查看交流、問題反饋群號",
+ "xxxxx": "xxxxx",
+ "加载模型": "載入模型",
+ "Hubert模型": "Hubert 模型",
+ "选择.pth文件": "選擇 .pth 檔案",
+ "选择.index文件": "選擇 .index 檔案",
+ "选择.npy文件": "選擇 .npy 檔案",
+ "输入设备": "輸入設備",
+ "输出设备": "輸出設備",
+ "音频设备(请使用同种类驱动)": "音訊設備 (請使用同種類驅動)",
+ "响应阈值": "響應閾值",
+ "音调设置": "音調設定",
+ "Index Rate": "Index Rate",
+ "常规设置": "一般設定",
+ "采样长度": "取樣長度",
+ "淡入淡出长度": "淡入淡出長度",
+ "额外推理时长": "額外推理時長",
+ "输入降噪": "輸入降噪",
+ "输出降噪": "輸出降噪",
+ "性能设置": "效能設定",
+ "开始音频转换": "開始音訊轉換",
+ "停止音频转换": "停止音訊轉換",
+ "推理时间(ms):": "推理時間(ms):"
+}
diff --git a/i18n/zh_SG.json b/i18n/zh_SG.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca0dbc0a5d21c5664d6aeaa39d06a2379188f91d
--- /dev/null
+++ b/i18n/zh_SG.json
@@ -0,0 +1,123 @@
+{
+ "很遗憾您这没有能用的显卡来支持您训练": "很遗憾您这没有能用的显卡来支持您训练",
+ "是": "是",
+ "step1:正在处理数据": "step1:正在处理数据",
+ "step2a:无需提取音高": "step2a:无需提取音高",
+ "step2b:正在提取特征": "step2b:正在提取特征",
+ "step3a:正在训练模型": "step3a:正在训练模型",
+ "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+ "全流程结束！": "全流程结束！",
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.": "本軟體以MIT協議開源，作者不對軟體具備任何控制力，使用軟體者、傳播軟體導出的聲音者自負全責。
如不認可該條款，則不能使用或引用軟體包內任何程式碼和檔案。詳見根目錄使用需遵守的協議-LICENSE.txt。",
+ "模型推理": "模型推理",
+ "推理音色": "推理音色",
+ "刷新音色列表和索引路径": "刷新音色列表和索引路徑",
+ "卸载音色省显存": "卸載音色節省 VRAM",
+ "请选择说话人id": "請選擇說話人ID",
+ "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性轉女性推薦+12key，女性轉男性推薦-12key，如果音域爆炸導致音色失真也可以自己調整到合適音域。",
+ "变调(整数, 半音数量, 升八度12降八度-12)": "變調(整數、半音數量、升八度12降八度-12)",
+ "输入待处理音频文件路径(默认是正确格式示例)": "輸入待處理音頻檔案路徑（預設是正確格式示例）",
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU": "選擇音高提取演算法,輸入歌聲可用pm提速,harvest低音好但巨慢無比,crepe效果好但吃GPU",
+ ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音": ">=3則使用對harvest音高識別的結果使用中值濾波，數值為濾波半徑，使用可以削弱啞音",
+ "特征检索库文件路径,为空则使用下拉的选择结果": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果",
+ "自动检测index路径,下拉式选择(dropdown)": "自動檢測index路徑,下拉式選擇(dropdown)",
+ "特征文件路径": "特徵檔案路徑",
+ "检索特征占比": "檢索特徵佔比",
+ "后处理重采样至最终采样率，0为不进行重采样": "後處理重採樣至最終採樣率，0為不進行重採樣",
+ "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络": "輸入源音量包絡替換輸出音量包絡融合比例，越靠近1越使用輸出包絡",
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果": "保護清輔音和呼吸聲，防止電音撕裂等artifact，拉滿0.5不開啟，調低加大保護力度但可能降低索引效果",
+ "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调": "F0曲線檔案，可選，一行一個音高，代替預設的F0及升降調",
+ "转换": "轉換",
+ "输出信息": "輸出訊息",
+ "输出音频(右下角三个点,点了可以下载)": "輸出音頻(右下角三個點，點了可以下載)",
+ "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ": "批量轉換，輸入待轉換音頻資料夾，或上傳多個音頻檔案，在指定資料夾(默認opt)下輸出轉換的音頻。",
+ "指定输出文件夹": "指定輸出資料夾",
+ "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)": "輸入待處理音頻資料夾路徑(去檔案管理器地址欄拷貝即可)",
+ "也可批量输入音频文件, 二选一, 优先读文件夹": "也可批量輸入音頻檔案，二選一，優先讀資料夾",
+ "导出文件格式": "導出檔格式",
+ "伴奏人声分离&去混响&去回声": "伴奏人声分离&去混响&去回声",
+ "输入待处理音频文件夹路径": "輸入待處理音頻資料夾路徑",
+ "模型": "模型",
+ "指定输出主人声文件夹": "指定输出主人声文件夹",
+ "指定输出非主人声文件夹": "指定输出非主人声文件夹",
+ "训练": "訓練",
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ": "step1：填寫實驗配置。實驗數據放在logs下，每個實驗一個資料夾，需手動輸入實驗名路徑，內含實驗配置、日誌、訓練得到的模型檔案。",
+ "输入实验名": "輸入實驗名稱",
+ "目标采样率": "目標取樣率",
+ "模型是否带音高指导(唱歌一定要, 语音可以不要)": "模型是否帶音高指導（唱歌一定要，語音可以不要）",
+ "版本(目前仅40k支持了v2)": "版本(目前僅40k支持了v2)",
+ "提取音高和处理数据使用的CPU进程数": "提取音高和處理數據使用的CPU進程數",
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ": "step2a：自動遍歷訓練資料夾下所有可解碼成音頻的檔案並進行切片歸一化，在實驗目錄下生成2個wav資料夾；暫時只支援單人訓練。",
+ "输入训练文件夹路径": "輸入訓練檔案夾路徑",
+ "请指定说话人id": "請指定說話人id",
+ "处理数据": "處理資料",
+ "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)": "步驟2b: 使用CPU提取音高(如果模型帶音高), 使用GPU提取特徵(選擇卡號)",
+ "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2": "以-分隔輸入使用的卡號, 例如 0-1-2 使用卡0和卡1和卡2",
+ "显卡信息": "顯示卡資訊",
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "選擇音高提取算法:輸入歌聲可用pm提速,高品質語音但CPU差可用dio提速,harvest品質更好但較慢",
+ "特征提取": "特徵提取",
+ "step3: 填写训练设置, 开始训练模型和索引": "步驟3: 填寫訓練設定, 開始訓練模型和索引",
+ "保存频率save_every_epoch": "保存頻率save_every_epoch",
+ "总训练轮数total_epoch": "總訓練輪數total_epoch",
+ "每张显卡的batch_size": "每张显卡的batch_size",
+ "是否仅保存最新的ckpt文件以节省硬盘空间": "是否僅保存最新的ckpt檔案以節省硬碟空間",
+ "否": "否",
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速": "是否緩存所有訓練集至 VRAM。小於10分鐘的小數據可緩存以加速訓練，大數據緩存會爆 VRAM 也加不了多少速度",
+ "是否在每次保存时间点将最终小模型保存至weights文件夹": "是否在每次保存時間點將最終小模型保存至weights檔夾",
+ "加载预训练底模G路径": "加載預訓練底模G路徑",
+ "加载预训练底模D路径": "加載預訓練底模D路徑",
+ "训练模型": "訓練模型",
+ "训练特征索引": "訓練特徵索引",
+ "一键训练": "一鍵訓練",
+ "ckpt处理": "ckpt處理",
+ "模型融合, 可用于测试音色融合": "模型融合，可用於測試音色融合",
+ "A模型路径": "A模型路徑",
+ "B模型路径": "B模型路徑",
+ "A模型权重": "A模型權重",
+ "模型是否带音高指导": "模型是否帶音高指導",
+ "要置入的模型信息": "要置入的模型資訊",
+ "保存的模型名不带后缀": "儲存的模型名不帶副檔名",
+ "模型版本型号": "模型版本型號",
+ "融合": "融合",
+ "修改模型信息(仅支持weights文件夹下提取的小模型文件)": "修改模型資訊(僅支援weights資料夾下提取的小模型檔案)",
+ "模型路径": "模型路徑",
+ "要改的模型信息": "要改的模型資訊",
+ "保存的文件名, 默认空为和源文件同名": "儲存的檔案名，預設空為與來源檔案同名",
+ "修改": "修改",
+ "查看模型信息(仅支持weights文件夹下提取的小模型文件)": "查看模型資訊(僅支援weights資料夾下提取的小模型檔案)",
+ "查看": "查看",
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "模型提取(輸入logs資料夾下大檔案模型路徑)，適用於訓一半不想訓了模型沒有自動提取儲存小檔案模型，或者想測試中間模型的情況",
+ "保存名": "儲存名",
+ "模型是否带音高指导,1是0否": "模型是否帶音高指導，1是0否",
+ "提取": "提取",
+ "Onnx导出": "Onnx导出",
+ "RVC模型路径": "RVC模型路径",
+ "Onnx输出路径": "Onnx输出路径",
+ "MoeVS模型": "MoeSS模型",
+ "导出Onnx模型": "导出Onnx模型",
+ "常见问题解答": "常見問題解答",
+ "招募音高曲线前端编辑器": "招募音高曲線前端編輯器",
+ "加开发群联系我xxxxx": "加開發群聯繫我xxxxx",
+ "点击查看交流、问题反馈群号": "點擊查看交流、問題反饋群號",
+ "xxxxx": "xxxxx",
+ "加载模型": "載入模型",
+ "Hubert模型": "Hubert 模型",
+ "选择.pth文件": "選擇 .pth 檔案",
+ "选择.index文件": "選擇 .index 檔案",
+ "选择.npy文件": "選擇 .npy 檔案",
+ "输入设备": "輸入設備",
+ "输出设备": "輸出設備",
+ "音频设备(请使用同种类驱动)": "音訊設備 (請使用同種類驅動)",
+ "响应阈值": "響應閾值",
+ "音调设置": "音調設定",
+ "Index Rate": "Index Rate",
+ "常规设置": "一般設定",
+ "采样长度": "取樣長度",
+ "淡入淡出长度": "淡入淡出長度",
+ "额外推理时长": "額外推理時長",
+ "输入降噪": "輸入降噪",
+ "输出降噪": "輸出降噪",
+ "性能设置": "效能設定",
+ "开始音频转换": "開始音訊轉換",
+ "停止音频转换": "停止音訊轉換",
+ "推理时间(ms):": "推理時間(ms):"
+}
diff --git a/i18n/zh_TW.json b/i18n/zh_TW.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca0dbc0a5d21c5664d6aeaa39d06a2379188f91d
--- /dev/null
+++ b/i18n/zh_TW.json
@@ -0,0 +1,123 @@
+{
+ "很遗憾您这没有能用的显卡来支持您训练": "很遗憾您这没有能用的显卡来支持您训练",
+ "是": "是",
+ "step1:正在处理数据": "step1:正在处理数据",
+ "step2a:无需提取音高": "step2a:无需提取音高",
+ "step2b:正在提取特征": "step2b:正在提取特征",
+ "step3a:正在训练模型": "step3a:正在训练模型",
+ "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+ "全流程结束！": "全流程结束！",
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt.": "本軟體以MIT協議開源，作者不對軟體具備任何控制力，使用軟體者、傳播軟體導出的聲音者自負全責。
如不認可該條款，則不能使用或引用軟體包內任何程式碼和檔案。詳見根目錄使用需遵守的協議-LICENSE.txt。",
+ "模型推理": "模型推理",
+ "推理音色": "推理音色",
+ "刷新音色列表和索引路径": "刷新音色列表和索引路徑",
+ "卸载音色省显存": "卸載音色節省 VRAM",
+ "请选择说话人id": "請選擇說話人ID",
+ "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性轉女性推薦+12key，女性轉男性推薦-12key，如果音域爆炸導致音色失真也可以自己調整到合適音域。",
+ "变调(整数, 半音数量, 升八度12降八度-12)": "變調(整數、半音數量、升八度12降八度-12)",
+ "输入待处理音频文件路径(默认是正确格式示例)": "輸入待處理音頻檔案路徑（預設是正確格式示例）",
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU": "選擇音高提取演算法,輸入歌聲可用pm提速,harvest低音好但巨慢無比,crepe效果好但吃GPU",
+ ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音": ">=3則使用對harvest音高識別的結果使用中值濾波，數值為濾波半徑，使用可以削弱啞音",
+ "特征检索库文件路径,为空则使用下拉的选择结果": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果",
+ "自动检测index路径,下拉式选择(dropdown)": "自動檢測index路徑,下拉式選擇(dropdown)",
+ "特征文件路径": "特徵檔案路徑",
+ "检索特征占比": "檢索特徵佔比",
+ "后处理重采样至最终采样率，0为不进行重采样": "後處理重採樣至最終採樣率，0為不進行重採樣",
+ "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络": "輸入源音量包絡替換輸出音量包絡融合比例，越靠近1越使用輸出包絡",
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果": "保護清輔音和呼吸聲，防止電音撕裂等artifact，拉滿0.5不開啟，調低加大保護力度但可能降低索引效果",
+ "F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调": "F0曲線檔案，可選，一行一個音高，代替預設的F0及升降調",
+ "转换": "轉換",
+ "输出信息": "輸出訊息",
+ "输出音频(右下角三个点,点了可以下载)": "輸出音頻(右下角三個點，點了可以下載)",
+ "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ": "批量轉換，輸入待轉換音頻資料夾，或上傳多個音頻檔案，在指定資料夾(默認opt)下輸出轉換的音頻。",
+ "指定输出文件夹": "指定輸出資料夾",
+ "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)": "輸入待處理音頻資料夾路徑(去檔案管理器地址欄拷貝即可)",
+ "也可批量输入音频文件, 二选一, 优先读文件夹": "也可批量輸入音頻檔案，二選一，優先讀資料夾",
+ "导出文件格式": "導出檔格式",
+ "伴奏人声分离&去混响&去回声": "伴奏人声分离&去混响&去回声",
+ "输入待处理音频文件夹路径": "輸入待處理音頻資料夾路徑",
+ "模型": "模型",
+ "指定输出主人声文件夹": "指定输出主人声文件夹",
+ "指定输出非主人声文件夹": "指定输出非主人声文件夹",
+ "训练": "訓練",
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. ": "step1：填寫實驗配置。實驗數據放在logs下，每個實驗一個資料夾，需手動輸入實驗名路徑，內含實驗配置、日誌、訓練得到的模型檔案。",
+ "输入实验名": "輸入實驗名稱",
+ "目标采样率": "目標取樣率",
+ "模型是否带音高指导(唱歌一定要, 语音可以不要)": "模型是否帶音高指導（唱歌一定要，語音可以不要）",
+ "版本(目前仅40k支持了v2)": "版本(目前僅40k支持了v2)",
+ "提取音高和处理数据使用的CPU进程数": "提取音高和處理數據使用的CPU進程數",
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. ": "step2a：自動遍歷訓練資料夾下所有可解碼成音頻的檔案並進行切片歸一化，在實驗目錄下生成2個wav資料夾；暫時只支援單人訓練。",
+ "输入训练文件夹路径": "輸入訓練檔案夾路徑",
+ "请指定说话人id": "請指定說話人id",
+ "处理数据": "處理資料",
+ "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)": "步驟2b: 使用CPU提取音高(如果模型帶音高), 使用GPU提取特徵(選擇卡號)",
+ "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2": "以-分隔輸入使用的卡號, 例如 0-1-2 使用卡0和卡1和卡2",
+ "显卡信息": "顯示卡資訊",
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢": "選擇音高提取算法:輸入歌聲可用pm提速,高品質語音但CPU差可用dio提速,harvest品質更好但較慢",
+ "特征提取": "特徵提取",
+ "step3: 填写训练设置, 开始训练模型和索引": "步驟3: 填寫訓練設定, 開始訓練模型和索引",
+ "保存频率save_every_epoch": "保存頻率save_every_epoch",
+ "总训练轮数total_epoch": "總訓練輪數total_epoch",
+ "每张显卡的batch_size": "每张显卡的batch_size",
+ "是否仅保存最新的ckpt文件以节省硬盘空间": "是否僅保存最新的ckpt檔案以節省硬碟空間",
+ "否": "否",
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速": "是否緩存所有訓練集至 VRAM。小於10分鐘的小數據可緩存以加速訓練，大數據緩存會爆 VRAM 也加不了多少速度",
+ "是否在每次保存时间点将最终小模型保存至weights文件夹": "是否在每次保存時間點將最終小模型保存至weights檔夾",
+ "加载预训练底模G路径": "加載預訓練底模G路徑",
+ "加载预训练底模D路径": "加載預訓練底模D路徑",
+ "训练模型": "訓練模型",
+ "训练特征索引": "訓練特徵索引",
+ "一键训练": "一鍵訓練",
+ "ckpt处理": "ckpt處理",
+ "模型融合, 可用于测试音色融合": "模型融合，可用於測試音色融合",
+ "A模型路径": "A模型路徑",
+ "B模型路径": "B模型路徑",
+ "A模型权重": "A模型權重",
+ "模型是否带音高指导": "模型是否帶音高指導",
+ "要置入的模型信息": "要置入的模型資訊",
+ "保存的模型名不带后缀": "儲存的模型名不帶副檔名",
+ "模型版本型号": "模型版本型號",
+ "融合": "融合",
+ "修改模型信息(仅支持weights文件夹下提取的小模型文件)": "修改模型資訊(僅支援weights資料夾下提取的小模型檔案)",
+ "模型路径": "模型路徑",
+ "要改的模型信息": "要改的模型資訊",
+ "保存的文件名, 默认空为和源文件同名": "儲存的檔案名，預設空為與來源檔案同名",
+ "修改": "修改",
+ "查看模型信息(仅支持weights文件夹下提取的小模型文件)": "查看模型資訊(僅支援weights資料夾下提取的小模型檔案)",
+ "查看": "查看",
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况": "模型提取(輸入logs資料夾下大檔案模型路徑)，適用於訓一半不想訓了模型沒有自動提取儲存小檔案模型，或者想測試中間模型的情況",
+ "保存名": "儲存名",
+ "模型是否带音高指导,1是0否": "模型是否帶音高指導，1是0否",
+ "提取": "提取",
+ "Onnx导出": "Onnx导出",
+ "RVC模型路径": "RVC模型路径",
+ "Onnx输出路径": "Onnx输出路径",
+ "MoeVS模型": "MoeSS模型",
+ "导出Onnx模型": "导出Onnx模型",
+ "常见问题解答": "常見問題解答",
+ "招募音高曲线前端编辑器": "招募音高曲線前端編輯器",
+ "加开发群联系我xxxxx": "加開發群聯繫我xxxxx",
+ "点击查看交流、问题反馈群号": "點擊查看交流、問題反饋群號",
+ "xxxxx": "xxxxx",
+ "加载模型": "載入模型",
+ "Hubert模型": "Hubert 模型",
+ "选择.pth文件": "選擇 .pth 檔案",
+ "选择.index文件": "選擇 .index 檔案",
+ "选择.npy文件": "選擇 .npy 檔案",
+ "输入设备": "輸入設備",
+ "输出设备": "輸出設備",
+ "音频设备(请使用同种类驱动)": "音訊設備 (請使用同種類驅動)",
+ "响应阈值": "響應閾值",
+ "音调设置": "音調設定",
+ "Index Rate": "Index Rate",
+ "常规设置": "一般設定",
+ "采样长度": "取樣長度",
+ "淡入淡出长度": "淡入淡出長度",
+ "额外推理时长": "額外推理時長",
+ "输入降噪": "輸入降噪",
+ "输出降噪": "輸出降噪",
+ "性能设置": "效能設定",
+ "开始音频转换": "開始音訊轉換",
+ "停止音频转换": "停止音訊轉換",
+ "推理时间(ms):": "推理時間(ms):"
+}
diff --git a/infer-web.py b/infer-web.py
new file mode 100644
index 0000000000000000000000000000000000000000..21efc811ba35fe80fd91a5521fc687f3eff0995b
--- /dev/null
+++ b/infer-web.py
@@ -0,0 +1,1856 @@
+import torch, os, traceback, sys, warnings, shutil, numpy as np
+
+os.environ["no_proxy"] = "localhost, 127.0.0.1, ::1"
+import threading
+from time import sleep
+from subprocess import Popen
+import faiss
+from random import shuffle
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+tmp = os.path.join(now_dir, "TEMP")
+shutil.rmtree(tmp, ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/infer_pack" % (now_dir), ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/uvr5_pack" % (now_dir), ignore_errors=True)
+os.makedirs(tmp, exist_ok=True)
+os.makedirs(os.path.join(now_dir, "logs"), exist_ok=True)
+os.makedirs(os.path.join(now_dir, "weights"), exist_ok=True)
+os.environ["TEMP"] = tmp
+warnings.filterwarnings("ignore")
+torch.manual_seed(114514)
+from i18n import I18nAuto
+import ffmpeg
+from MDXNet import MDXNetDereverb
+
+i18n = I18nAuto()
+i18n.print()
+# 判断是否有能用来训练和加速推理的N卡
+ngpu = torch.cuda.device_count()
+gpu_infos = []
+mem = []
+if (not torch.cuda.is_available()) or ngpu == 0:
+ if_gpu_ok = False
+else:
+ if_gpu_ok = False
+ for i in range(ngpu):
+ gpu_name = torch.cuda.get_device_name(i)
+ if (
+ "10" in gpu_name
+ or "16" in gpu_name
+ or "20" in gpu_name
+ or "30" in gpu_name
+ or "40" in gpu_name
+ or "A2" in gpu_name.upper()
+ or "A3" in gpu_name.upper()
+ or "A4" in gpu_name.upper()
+ or "P4" in gpu_name.upper()
+ or "A50" in gpu_name.upper()
+ or "A60" in gpu_name.upper()
+ or "70" in gpu_name
+ or "80" in gpu_name
+ or "90" in gpu_name
+ or "M4" in gpu_name.upper()
+ or "T4" in gpu_name.upper()
+ or "TITAN" in gpu_name.upper()
+ ): # A10#A100#V100#A40#P40#M40#K80#A4500
+ if_gpu_ok = True # 至少有一张能用的N卡
+ gpu_infos.append("%s\t%s" % (i, gpu_name))
+ mem.append(
+ int(
+ torch.cuda.get_device_properties(i).total_memory
+ / 1024
+ / 1024
+ / 1024
+ + 0.4
+ )
+ )
+if if_gpu_ok == True and len(gpu_infos) > 0:
+ gpu_info = "\n".join(gpu_infos)
+ default_batch_size = min(mem) // 2
+else:
+ gpu_info = i18n("很遗憾您这没有能用的显卡来支持您训练")
+ default_batch_size = 1
+gpus = "-".join([i[0] for i in gpu_infos])
+from infer_pack.models import (
+ SynthesizerTrnMs256NSFsid,
+ SynthesizerTrnMs256NSFsid_nono,
+ SynthesizerTrnMs768NSFsid,
+ SynthesizerTrnMs768NSFsid_nono,
+)
+import soundfile as sf
+from fairseq import checkpoint_utils
+import gradio as gr
+import logging
+from vc_infer_pipeline import VC
+from config import Config
+from infer_uvr5 import _audio_pre_, _audio_pre_new
+from my_utils import load_audio
+from train.process_ckpt import show_info, change_info, merge, extract_small_model
+
+config = Config()
+# from trainset_preprocess_pipeline import PreProcess
+logging.getLogger("numba").setLevel(logging.WARNING)
+
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+ """Small button with single emoji as text, fits inside gradio forms"""
+
+ def __init__(self, **kwargs):
+ super().__init__(variant="tool", **kwargs)
+
+ def get_block_name(self):
+ return "button"
+
+
+hubert_model = None
+
+
+def load_hubert():
+ global hubert_model
+ models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
+ ["hubert_base.pt"],
+ suffix="",
+ )
+ hubert_model = models[0]
+ hubert_model = hubert_model.to(config.device)
+ if config.is_half:
+ hubert_model = hubert_model.half()
+ else:
+ hubert_model = hubert_model.float()
+ hubert_model.eval()
+
+
+weight_root = "weights"
+weight_uvr5_root = "uvr5_weights"
+index_root = "logs"
+names = []
+for name in os.listdir(weight_root):
+ if name.endswith(".pth"):
+ names.append(name)
+index_paths = []
+for root, dirs, files in os.walk(index_root, topdown=False):
+ for name in files:
+ if name.endswith(".index") and "trained" not in name:
+ index_paths.append("%s/%s" % (root, name))
+uvr5_names = []
+for name in os.listdir(weight_uvr5_root):
+ if name.endswith(".pth") or "onnx" in name:
+ uvr5_names.append(name.replace(".pth", ""))
+
+
+def vc_single(
+ sid,
+ input_audio_path,
+ f0_up_key,
+ f0_file,
+ f0_method,
+ file_index,
+ file_index2,
+ # file_big_npy,
+ index_rate,
+ filter_radius,
+ resample_sr,
+ rms_mix_rate,
+ protect,
+): # spk_item, input_audio0, vc_transform0,f0_file,f0method0
+ global tgt_sr, net_g, vc, hubert_model, version
+ if input_audio_path is None:
+ return "You need to upload an audio", None
+ f0_up_key = int(f0_up_key)
+ try:
+ audio = load_audio(input_audio_path, 16000)
+ audio_max = np.abs(audio).max() / 0.95
+ if audio_max > 1:
+ audio /= audio_max
+ times = [0, 0, 0]
+ if hubert_model == None:
+ load_hubert()
+ if_f0 = cpt.get("f0", 1)
+ file_index = (
+ (
+ file_index.strip(" ")
+ .strip('"')
+ .strip("\n")
+ .strip('"')
+ .strip(" ")
+ .replace("trained", "added")
+ )
+ if file_index != ""
+ else file_index2
+ ) # 防止小白写错，自动帮他替换掉
+ # file_big_npy = (
+ # file_big_npy.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ # )
+ audio_opt = vc.pipeline(
+ hubert_model,
+ net_g,
+ sid,
+ audio,
+ input_audio_path,
+ times,
+ f0_up_key,
+ f0_method,
+ file_index,
+ # file_big_npy,
+ index_rate,
+ if_f0,
+ filter_radius,
+ tgt_sr,
+ resample_sr,
+ rms_mix_rate,
+ version,
+ protect,
+ f0_file=f0_file,
+ )
+ if resample_sr >= 16000 and tgt_sr != resample_sr:
+ tgt_sr = resample_sr
+ index_info = (
+ "Using index:%s." % file_index
+ if os.path.exists(file_index)
+ else "Index not used."
+ )
+ return "Success.\n %s\nTime:\n npy:%ss, f0:%ss, infer:%ss" % (
+ index_info,
+ times[0],
+ times[1],
+ times[2],
+ ), (tgt_sr, audio_opt)
+ except:
+ info = traceback.format_exc()
+ print(info)
+ return info, (None, None)
+
+
+def vc_multi(
+ sid,
+ dir_path,
+ opt_root,
+ paths,
+ f0_up_key,
+ f0_method,
+ file_index,
+ file_index2,
+ # file_big_npy,
+ index_rate,
+ filter_radius,
+ resample_sr,
+ rms_mix_rate,
+ protect,
+ format1,
+):
+ try:
+ dir_path = (
+ dir_path.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ ) # 防止小白拷路径头尾带了空格和"和回车
+ opt_root = opt_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ os.makedirs(opt_root, exist_ok=True)
+ try:
+ if dir_path != "":
+ paths = [os.path.join(dir_path, name) for name in os.listdir(dir_path)]
+ else:
+ paths = [path.name for path in paths]
+ except:
+ traceback.print_exc()
+ paths = [path.name for path in paths]
+ infos = []
+ for path in paths:
+ info, opt = vc_single(
+ sid,
+ path,
+ f0_up_key,
+ None,
+ f0_method,
+ file_index,
+ file_index2,
+ # file_big_npy,
+ index_rate,
+ filter_radius,
+ resample_sr,
+ rms_mix_rate,
+ protect,
+ )
+ if "Success" in info:
+ try:
+ tgt_sr, audio_opt = opt
+ if format1 in ["wav", "flac"]:
+ sf.write(
+ "%s/%s.%s" % (opt_root, os.path.basename(path), format1),
+ audio_opt,
+ tgt_sr,
+ )
+ else:
+ path = "%s/%s.wav" % (opt_root, os.path.basename(path))
+ sf.write(
+ path,
+ audio_opt,
+ tgt_sr,
+ )
+ if os.path.exists(path):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path, path[:-4] + ".%s" % format1)
+ )
+ except:
+ info += traceback.format_exc()
+ infos.append("%s->%s" % (os.path.basename(path), info))
+ yield "\n".join(infos)
+ yield "\n".join(infos)
+ except:
+ yield traceback.format_exc()
+
+
+def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format0):
+ infos = []
+ try:
+ inp_root = inp_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ save_root_vocal = (
+ save_root_vocal.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ )
+ save_root_ins = (
+ save_root_ins.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ )
+ if model_name == "onnx_dereverb_By_FoxJoy":
+ pre_fun = MDXNetDereverb(15)
+ else:
+ func = _audio_pre_ if "DeEcho" not in model_name else _audio_pre_new
+ pre_fun = func(
+ agg=int(agg),
+ model_path=os.path.join(weight_uvr5_root, model_name + ".pth"),
+ device=config.device,
+ is_half=config.is_half,
+ )
+ if inp_root != "":
+ paths = [os.path.join(inp_root, name) for name in os.listdir(inp_root)]
+ else:
+ paths = [path.name for path in paths]
+ for path in paths:
+ inp_path = os.path.join(inp_root, path)
+ need_reformat = 1
+ done = 0
+ try:
+ info = ffmpeg.probe(inp_path, cmd="ffprobe")
+ if (
+ info["streams"][0]["channels"] == 2
+ and info["streams"][0]["sample_rate"] == "44100"
+ ):
+ need_reformat = 0
+ pre_fun._path_audio_(
+ inp_path, save_root_ins, save_root_vocal, format0
+ )
+ done = 1
+ except:
+ need_reformat = 1
+ traceback.print_exc()
+ if need_reformat == 1:
+ tmp_path = "%s/%s.reformatted.wav" % (tmp, os.path.basename(inp_path))
+ os.system(
+ "ffmpeg -i %s -vn -acodec pcm_s16le -ac 2 -ar 44100 %s -y"
+ % (inp_path, tmp_path)
+ )
+ inp_path = tmp_path
+ try:
+ if done == 0:
+ pre_fun._path_audio_(
+ inp_path, save_root_ins, save_root_vocal, format0
+ )
+ infos.append("%s->Success" % (os.path.basename(inp_path)))
+ yield "\n".join(infos)
+ except:
+ infos.append(
+ "%s->%s" % (os.path.basename(inp_path), traceback.format_exc())
+ )
+ yield "\n".join(infos)
+ except:
+ infos.append(traceback.format_exc())
+ yield "\n".join(infos)
+ finally:
+ try:
+ if model_name == "onnx_dereverb_By_FoxJoy":
+ del pre_fun.pred.model
+ del pre_fun.pred.model_
+ else:
+ del pre_fun.model
+ del pre_fun
+ except:
+ traceback.print_exc()
+ print("clean_empty_cache")
+ if torch.cuda.is_available():
+ torch.cuda.empty_cache()
+ yield "\n".join(infos)
+
+
+# 一个选项卡全局只能有一个音色
+def get_vc(sid):
+ global n_spk, tgt_sr, net_g, vc, cpt, version
+ if sid == "" or sid == []:
+ global hubert_model
+ if hubert_model != None: # 考虑到轮询, 需要加个判断看是否 sid 是由有模型切换到无模型的
+ print("clean_empty_cache")
+ del net_g, n_spk, vc, hubert_model, tgt_sr # ,cpt
+ hubert_model = net_g = n_spk = vc = hubert_model = tgt_sr = None
+ if torch.cuda.is_available():
+ torch.cuda.empty_cache()
+ ###楼下不这么折腾清理不干净
+ if_f0 = cpt.get("f0", 1)
+ version = cpt.get("version", "v1")
+ if version == "v1":
+ if if_f0 == 1:
+ net_g = SynthesizerTrnMs256NSFsid(
+ *cpt["config"], is_half=config.is_half
+ )
+ else:
+ net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
+ elif version == "v2":
+ if if_f0 == 1:
+ net_g = SynthesizerTrnMs768NSFsid(
+ *cpt["config"], is_half=config.is_half
+ )
+ else:
+ net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
+ del net_g, cpt
+ if torch.cuda.is_available():
+ torch.cuda.empty_cache()
+ cpt = None
+ return {"visible": False, "__type__": "update"}
+ person = "%s/%s" % (weight_root, sid)
+ print("loading %s" % person)
+ cpt = torch.load(person, map_location="cpu")
+ tgt_sr = cpt["config"][-1]
+ cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
+ if_f0 = cpt.get("f0", 1)
+ version = cpt.get("version", "v1")
+ if version == "v1":
+ if if_f0 == 1:
+ net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=config.is_half)
+ else:
+ net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
+ elif version == "v2":
+ if if_f0 == 1:
+ net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=config.is_half)
+ else:
+ net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
+ del net_g.enc_q
+ print(net_g.load_state_dict(cpt["weight"], strict=False))
+ net_g.eval().to(config.device)
+ if config.is_half:
+ net_g = net_g.half()
+ else:
+ net_g = net_g.float()
+ vc = VC(tgt_sr, config)
+ n_spk = cpt["config"][-3]
+ return {"visible": True, "maximum": n_spk, "__type__": "update"}
+
+
+def change_choices():
+ names = []
+ for name in os.listdir(weight_root):
+ if name.endswith(".pth"):
+ names.append(name)
+ index_paths = []
+ for root, dirs, files in os.walk(index_root, topdown=False):
+ for name in files:
+ if name.endswith(".index") and "trained" not in name:
+ index_paths.append("%s/%s" % (root, name))
+ return {"choices": sorted(names), "__type__": "update"}, {
+ "choices": sorted(index_paths),
+ "__type__": "update",
+ }
+
+
+def clean():
+ return {"value": "", "__type__": "update"}
+
+
+sr_dict = {
+ "32k": 32000,
+ "40k": 40000,
+ "48k": 48000,
+}
+
+
+def if_done(done, p):
+ while 1:
+ if p.poll() == None:
+ sleep(0.5)
+ else:
+ break
+ done[0] = True
+
+
+def if_done_multi(done, ps):
+ while 1:
+ # poll==None代表进程未结束
+ # 只要有一个进程未结束都不停
+ flag = 1
+ for p in ps:
+ if p.poll() == None:
+ flag = 0
+ sleep(0.5)
+ break
+ if flag == 1:
+ break
+ done[0] = True
+
+
+def preprocess_dataset(trainset_dir, exp_dir, sr, n_p):
+ sr = sr_dict[sr]
+ os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+ f = open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "w")
+ f.close()
+ cmd = (
+ config.python_cmd
+ + " trainset_preprocess_pipeline_print.py %s %s %s %s/logs/%s "
+ % (trainset_dir, sr, n_p, now_dir, exp_dir)
+ + str(config.noparallel)
+ )
+ print(cmd)
+ p = Popen(cmd, shell=True) # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir
+ ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+ done = [False]
+ threading.Thread(
+ target=if_done,
+ args=(
+ done,
+ p,
+ ),
+ ).start()
+ while 1:
+ with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+ yield (f.read())
+ sleep(1)
+ if done[0] == True:
+ break
+ with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+ log = f.read()
+ print(log)
+ yield log
+
+
+# but2.click(extract_f0,[gpus6,np7,f0method8,if_f0_3,trainset_dir4],[info2])
+def extract_f0_feature(gpus, n_p, f0method, if_f0, exp_dir, version19):
+ gpus = gpus.split("-")
+ os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+ f = open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "w")
+ f.close()
+ if if_f0:
+ cmd = config.python_cmd + " extract_f0_print.py %s/logs/%s %s %s" % (
+ now_dir,
+ exp_dir,
+ n_p,
+ f0method,
+ )
+ print(cmd)
+ p = Popen(cmd, shell=True, cwd=now_dir) # , stdin=PIPE, stdout=PIPE,stderr=PIPE
+ ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+ done = [False]
+ threading.Thread(
+ target=if_done,
+ args=(
+ done,
+ p,
+ ),
+ ).start()
+ while 1:
+ with open(
+ "%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r"
+ ) as f:
+ yield (f.read())
+ sleep(1)
+ if done[0] == True:
+ break
+ with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+ log = f.read()
+ print(log)
+ yield log
+ ####对不同part分别开多进程
+ """
+ n_part=int(sys.argv[1])
+ i_part=int(sys.argv[2])
+ i_gpu=sys.argv[3]
+ exp_dir=sys.argv[4]
+ os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu)
+ """
+ leng = len(gpus)
+ ps = []
+ for idx, n_g in enumerate(gpus):
+ cmd = (
+ config.python_cmd
+ + " extract_feature_print.py %s %s %s %s %s/logs/%s %s"
+ % (
+ config.device,
+ leng,
+ idx,
+ n_g,
+ now_dir,
+ exp_dir,
+ version19,
+ )
+ )
+ print(cmd)
+ p = Popen(
+ cmd, shell=True, cwd=now_dir
+ ) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+ ps.append(p)
+ ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+ done = [False]
+ threading.Thread(
+ target=if_done_multi,
+ args=(
+ done,
+ ps,
+ ),
+ ).start()
+ while 1:
+ with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+ yield (f.read())
+ sleep(1)
+ if done[0] == True:
+ break
+ with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+ log = f.read()
+ print(log)
+ yield log
+
+
+def change_sr2(sr2, if_f0_3, version19):
+ vis_v = True if sr2 == "40k" else False
+ if sr2 != "40k":
+ version19 = "v1"
+ path_str = "" if version19 == "v1" else "_v2"
+ version_state = {"visible": vis_v, "__type__": "update"}
+ if vis_v == False:
+ version_state["value"] = "v1"
+ f0_str = "f0" if if_f0_3 else ""
+ return (
+ "pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2),
+ "pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2),
+ version_state,
+ )
+
+
+def change_version19(sr2, if_f0_3, version19):
+ path_str = "" if version19 == "v1" else "_v2"
+ f0_str = "f0" if if_f0_3 else ""
+ return "pretrained%s/%sG%s.pth" % (
+ path_str,
+ f0_str,
+ sr2,
+ ), "pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2)
+
+
+def change_f0(if_f0_3, sr2, version19): # f0method8,pretrained_G14,pretrained_D15
+ path_str = "" if version19 == "v1" else "_v2"
+ if if_f0_3:
+ return (
+ {"visible": True, "__type__": "update"},
+ "pretrained%s/f0G%s.pth" % (path_str, sr2),
+ "pretrained%s/f0D%s.pth" % (path_str, sr2),
+ )
+ return (
+ {"visible": False, "__type__": "update"},
+ "pretrained%s/G%s.pth" % (path_str, sr2),
+ "pretrained%s/D%s.pth" % (path_str, sr2),
+ )
+
+
+# but3.click(click_train,[exp_dir1,sr2,if_f0_3,save_epoch10,total_epoch11,batch_size12,if_save_latest13,pretrained_G14,pretrained_D15,gpus16])
+def click_train(
+ exp_dir1,
+ sr2,
+ if_f0_3,
+ spk_id5,
+ save_epoch10,
+ total_epoch11,
+ batch_size12,
+ if_save_latest13,
+ pretrained_G14,
+ pretrained_D15,
+ gpus16,
+ if_cache_gpu17,
+ if_save_every_weights18,
+ version19,
+):
+ # 生成filelist
+ exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+ os.makedirs(exp_dir, exist_ok=True)
+ gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir)
+ feature_dir = (
+ "%s/3_feature256" % (exp_dir)
+ if version19 == "v1"
+ else "%s/3_feature768" % (exp_dir)
+ )
+ if if_f0_3:
+ f0_dir = "%s/2a_f0" % (exp_dir)
+ f0nsf_dir = "%s/2b-f0nsf" % (exp_dir)
+ names = (
+ set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
+ & set([name.split(".")[0] for name in os.listdir(feature_dir)])
+ & set([name.split(".")[0] for name in os.listdir(f0_dir)])
+ & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
+ )
+ else:
+ names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
+ [name.split(".")[0] for name in os.listdir(feature_dir)]
+ )
+ opt = []
+ for name in names:
+ if if_f0_3:
+ opt.append(
+ "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
+ % (
+ gt_wavs_dir.replace("\\", "\\\\"),
+ name,
+ feature_dir.replace("\\", "\\\\"),
+ name,
+ f0_dir.replace("\\", "\\\\"),
+ name,
+ f0nsf_dir.replace("\\", "\\\\"),
+ name,
+ spk_id5,
+ )
+ )
+ else:
+ opt.append(
+ "%s/%s.wav|%s/%s.npy|%s"
+ % (
+ gt_wavs_dir.replace("\\", "\\\\"),
+ name,
+ feature_dir.replace("\\", "\\\\"),
+ name,
+ spk_id5,
+ )
+ )
+ fea_dim = 256 if version19 == "v1" else 768
+ if if_f0_3:
+ for _ in range(2):
+ opt.append(
+ "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
+ % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
+ )
+ else:
+ for _ in range(2):
+ opt.append(
+ "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
+ % (now_dir, sr2, now_dir, fea_dim, spk_id5)
+ )
+ shuffle(opt)
+ with open("%s/filelist.txt" % exp_dir, "w") as f:
+ f.write("\n".join(opt))
+ print("write filelist done")
+ # 生成config#无需生成config
+ # cmd = python_cmd + " train_nsf_sim_cache_sid_load_pretrain.py -e mi-test -sr 40k -f0 1 -bs 4 -g 0 -te 10 -se 5 -pg pretrained/f0G40k.pth -pd pretrained/f0D40k.pth -l 1 -c 0"
+ print("use gpus:", gpus16)
+ if gpus16:
+ cmd = (
+ config.python_cmd
+ + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -g %s -te %s -se %s -pg %s -pd %s -l %s -c %s -sw %s -v %s"
+ % (
+ exp_dir1,
+ sr2,
+ 1 if if_f0_3 else 0,
+ batch_size12,
+ gpus16,
+ total_epoch11,
+ save_epoch10,
+ pretrained_G14,
+ pretrained_D15,
+ 1 if if_save_latest13 == i18n("是") else 0,
+ 1 if if_cache_gpu17 == i18n("是") else 0,
+ 1 if if_save_every_weights18 == i18n("是") else 0,
+ version19,
+ )
+ )
+ else:
+ cmd = (
+ config.python_cmd
+ + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -te %s -se %s -pg %s -pd %s -l %s -c %s -sw %s -v %s"
+ % (
+ exp_dir1,
+ sr2,
+ 1 if if_f0_3 else 0,
+ batch_size12,
+ total_epoch11,
+ save_epoch10,
+ pretrained_G14,
+ pretrained_D15,
+ 1 if if_save_latest13 == i18n("是") else 0,
+ 1 if if_cache_gpu17 == i18n("是") else 0,
+ 1 if if_save_every_weights18 == i18n("是") else 0,
+ version19,
+ )
+ )
+ print(cmd)
+ p = Popen(cmd, shell=True, cwd=now_dir)
+ p.wait()
+ return "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"
+
+
+# but4.click(train_index, [exp_dir1], info3)
+def train_index(exp_dir1, version19):
+ exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+ os.makedirs(exp_dir, exist_ok=True)
+ feature_dir = (
+ "%s/3_feature256" % (exp_dir)
+ if version19 == "v1"
+ else "%s/3_feature768" % (exp_dir)
+ )
+ if os.path.exists(feature_dir) == False:
+ return "请先进行特征提取!"
+ listdir_res = list(os.listdir(feature_dir))
+ if len(listdir_res) == 0:
+ return "请先进行特征提取！"
+ npys = []
+ for name in sorted(listdir_res):
+ phone = np.load("%s/%s" % (feature_dir, name))
+ npys.append(phone)
+ big_npy = np.concatenate(npys, 0)
+ big_npy_idx = np.arange(big_npy.shape[0])
+ np.random.shuffle(big_npy_idx)
+ big_npy = big_npy[big_npy_idx]
+ np.save("%s/total_fea.npy" % exp_dir, big_npy)
+ # n_ivf = big_npy.shape[0] // 39
+ n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+ infos = []
+ infos.append("%s,%s" % (big_npy.shape, n_ivf))
+ yield "\n".join(infos)
+ index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
+ # index = faiss.index_factory(256if version19=="v1"else 768, "IVF%s,PQ128x4fs,RFlat"%n_ivf)
+ infos.append("training")
+ yield "\n".join(infos)
+ index_ivf = faiss.extract_index_ivf(index) #
+ index_ivf.nprobe = 1
+ index.train(big_npy)
+ faiss.write_index(
+ index,
+ "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
+ % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+ )
+ # faiss.write_index(index, '%s/trained_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19))
+ infos.append("adding")
+ yield "\n".join(infos)
+ batch_size_add = 8192
+ for i in range(0, big_npy.shape[0], batch_size_add):
+ index.add(big_npy[i : i + batch_size_add])
+ faiss.write_index(
+ index,
+ "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+ % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+ )
+ infos.append(
+ "成功构建索引，added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+ % (n_ivf, index_ivf.nprobe, exp_dir1, version19)
+ )
+ # faiss.write_index(index, '%s/added_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19))
+ # infos.append("成功构建索引，added_IVF%s_Flat_FastScan_%s.index"%(n_ivf,version19))
+ yield "\n".join(infos)
+
+
+# but5.click(train1key, [exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, gpus6, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17], info3)
+def train1key(
+ exp_dir1,
+ sr2,
+ if_f0_3,
+ trainset_dir4,
+ spk_id5,
+ np7,
+ f0method8,
+ save_epoch10,
+ total_epoch11,
+ batch_size12,
+ if_save_latest13,
+ pretrained_G14,
+ pretrained_D15,
+ gpus16,
+ if_cache_gpu17,
+ if_save_every_weights18,
+ version19,
+):
+ infos = []
+
+ def get_info_str(strr):
+ infos.append(strr)
+ return "\n".join(infos)
+
+ model_log_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+ preprocess_log_path = "%s/preprocess.log" % model_log_dir
+ extract_f0_feature_log_path = "%s/extract_f0_feature.log" % model_log_dir
+ gt_wavs_dir = "%s/0_gt_wavs" % model_log_dir
+ feature_dir = (
+ "%s/3_feature256" % model_log_dir
+ if version19 == "v1"
+ else "%s/3_feature768" % model_log_dir
+ )
+
+ os.makedirs(model_log_dir, exist_ok=True)
+ #########step1:处理数据
+ open(preprocess_log_path, "w").close()
+ cmd = (
+ config.python_cmd
+ + " trainset_preprocess_pipeline_print.py %s %s %s %s "
+ % (trainset_dir4, sr_dict[sr2], np7, model_log_dir)
+ + str(config.noparallel)
+ )
+ yield get_info_str(i18n("step1:正在处理数据"))
+ yield get_info_str(cmd)
+ p = Popen(cmd, shell=True)
+ p.wait()
+ with open(preprocess_log_path, "r") as f:
+ print(f.read())
+ #########step2a:提取音高
+ open(extract_f0_feature_log_path, "w")
+ if if_f0_3:
+ yield get_info_str("step2a:正在提取音高")
+ cmd = config.python_cmd + " extract_f0_print.py %s %s %s" % (
+ model_log_dir,
+ np7,
+ f0method8,
+ )
+ yield get_info_str(cmd)
+ p = Popen(cmd, shell=True, cwd=now_dir)
+ p.wait()
+ with open(extract_f0_feature_log_path, "r") as f:
+ print(f.read())
+ else:
+ yield get_info_str(i18n("step2a:无需提取音高"))
+ #######step2b:提取特征
+ yield get_info_str(i18n("step2b:正在提取特征"))
+ gpus = gpus16.split("-")
+ leng = len(gpus)
+ ps = []
+ for idx, n_g in enumerate(gpus):
+ cmd = config.python_cmd + " extract_feature_print.py %s %s %s %s %s %s" % (
+ config.device,
+ leng,
+ idx,
+ n_g,
+ model_log_dir,
+ version19,
+ )
+ yield get_info_str(cmd)
+ p = Popen(
+ cmd, shell=True, cwd=now_dir
+ ) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+ ps.append(p)
+ for p in ps:
+ p.wait()
+ with open(extract_f0_feature_log_path, "r") as f:
+ print(f.read())
+ #######step3a:训练模型
+ yield get_info_str(i18n("step3a:正在训练模型"))
+ # 生成filelist
+ if if_f0_3:
+ f0_dir = "%s/2a_f0" % model_log_dir
+ f0nsf_dir = "%s/2b-f0nsf" % model_log_dir
+ names = (
+ set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
+ & set([name.split(".")[0] for name in os.listdir(feature_dir)])
+ & set([name.split(".")[0] for name in os.listdir(f0_dir)])
+ & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
+ )
+ else:
+ names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
+ [name.split(".")[0] for name in os.listdir(feature_dir)]
+ )
+ opt = []
+ for name in names:
+ if if_f0_3:
+ opt.append(
+ "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
+ % (
+ gt_wavs_dir.replace("\\", "\\\\"),
+ name,
+ feature_dir.replace("\\", "\\\\"),
+ name,
+ f0_dir.replace("\\", "\\\\"),
+ name,
+ f0nsf_dir.replace("\\", "\\\\"),
+ name,
+ spk_id5,
+ )
+ )
+ else:
+ opt.append(
+ "%s/%s.wav|%s/%s.npy|%s"
+ % (
+ gt_wavs_dir.replace("\\", "\\\\"),
+ name,
+ feature_dir.replace("\\", "\\\\"),
+ name,
+ spk_id5,
+ )
+ )
+ fea_dim = 256 if version19 == "v1" else 768
+ if if_f0_3:
+ for _ in range(2):
+ opt.append(
+ "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
+ % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
+ )
+ else:
+ for _ in range(2):
+ opt.append(
+ "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
+ % (now_dir, sr2, now_dir, fea_dim, spk_id5)
+ )
+ shuffle(opt)
+ with open("%s/filelist.txt" % model_log_dir, "w") as f:
+ f.write("\n".join(opt))
+ yield get_info_str("write filelist done")
+ if gpus16:
+ cmd = (
+ config.python_cmd
+ + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -g %s -te %s -se %s -pg %s -pd %s -l %s -c %s -sw %s -v %s"
+ % (
+ exp_dir1,
+ sr2,
+ 1 if if_f0_3 else 0,
+ batch_size12,
+ gpus16,
+ total_epoch11,
+ save_epoch10,
+ pretrained_G14,
+ pretrained_D15,
+ 1 if if_save_latest13 == i18n("是") else 0,
+ 1 if if_cache_gpu17 == i18n("是") else 0,
+ 1 if if_save_every_weights18 == i18n("是") else 0,
+ version19,
+ )
+ )
+ else:
+ cmd = (
+ config.python_cmd
+ + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -te %s -se %s -pg %s -pd %s -l %s -c %s -sw %s -v %s"
+ % (
+ exp_dir1,
+ sr2,
+ 1 if if_f0_3 else 0,
+ batch_size12,
+ total_epoch11,
+ save_epoch10,
+ pretrained_G14,
+ pretrained_D15,
+ 1 if if_save_latest13 == i18n("是") else 0,
+ 1 if if_cache_gpu17 == i18n("是") else 0,
+ 1 if if_save_every_weights18 == i18n("是") else 0,
+ version19,
+ )
+ )
+ yield get_info_str(cmd)
+ p = Popen(cmd, shell=True, cwd=now_dir)
+ p.wait()
+ yield get_info_str(i18n("训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"))
+ #######step3b:训练索引
+ npys = []
+ listdir_res = list(os.listdir(feature_dir))
+ for name in sorted(listdir_res):
+ phone = np.load("%s/%s" % (feature_dir, name))
+ npys.append(phone)
+ big_npy = np.concatenate(npys, 0)
+
+ big_npy_idx = np.arange(big_npy.shape[0])
+ np.random.shuffle(big_npy_idx)
+ big_npy = big_npy[big_npy_idx]
+ np.save("%s/total_fea.npy" % model_log_dir, big_npy)
+
+ # n_ivf = big_npy.shape[0] // 39
+ n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+ yield get_info_str("%s,%s" % (big_npy.shape, n_ivf))
+ index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
+ yield get_info_str("training index")
+ index_ivf = faiss.extract_index_ivf(index) #
+ index_ivf.nprobe = 1
+ index.train(big_npy)
+ faiss.write_index(
+ index,
+ "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
+ % (model_log_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+ )
+ yield get_info_str("adding index")
+ batch_size_add = 8192
+ for i in range(0, big_npy.shape[0], batch_size_add):
+ index.add(big_npy[i : i + batch_size_add])
+ faiss.write_index(
+ index,
+ "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+ % (model_log_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+ )
+ yield get_info_str(
+ "成功构建索引, added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+ % (n_ivf, index_ivf.nprobe, exp_dir1, version19)
+ )
+ yield get_info_str(i18n("全流程结束！"))
+
+
+# ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__])
+def change_info_(ckpt_path):
+ if (
+ os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log"))
+ == False
+ ):
+ return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+ try:
+ with open(
+ ckpt_path.replace(os.path.basename(ckpt_path), "train.log"), "r"
+ ) as f:
+ info = eval(f.read().strip("\n").split("\n")[0].split("\t")[-1])
+ sr, f0 = info["sample_rate"], info["if_f0"]
+ version = "v2" if ("version" in info and info["version"] == "v2") else "v1"
+ return sr, str(f0), version
+ except:
+ traceback.print_exc()
+ return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+
+
+from infer_pack.models_onnx import SynthesizerTrnMsNSFsidM
+
+
+def export_onnx(ModelPath, ExportedPath, MoeVS=True):
+ cpt = torch.load(ModelPath, map_location="cpu")
+ cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
+ hidden_channels = cpt["config"][-2] # hidden_channels，为768Vec做准备
+
+ test_phone = torch.rand(1, 200, hidden_channels) # hidden unit
+ test_phone_lengths = torch.tensor([200]).long() # hidden unit 长度（貌似没啥用）
+ test_pitch = torch.randint(size=(1, 200), low=5, high=255) # 基频（单位赫兹）
+ test_pitchf = torch.rand(1, 200) # nsf基频
+ test_ds = torch.LongTensor([0]) # 说话人ID
+ test_rnd = torch.rand(1, 192, 200) # 噪声（加入随机因子）
+
+ device = "cpu" # 导出时设备（不影响使用模型）
+
+ net_g = SynthesizerTrnMsNSFsidM(
+ *cpt["config"], is_half=False
+ ) # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
+ net_g.load_state_dict(cpt["weight"], strict=False)
+ input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
+ output_names = [
+ "audio",
+ ]
+ # net_g.construct_spkmixmap(n_speaker) 多角色混合轨道导出
+ torch.onnx.export(
+ net_g,
+ (
+ test_phone.to(device),
+ test_phone_lengths.to(device),
+ test_pitch.to(device),
+ test_pitchf.to(device),
+ test_ds.to(device),
+ test_rnd.to(device),
+ ),
+ ExportedPath,
+ dynamic_axes={
+ "phone": [1],
+ "pitch": [1],
+ "pitchf": [1],
+ "rnd": [2],
+ },
+ do_constant_folding=False,
+ opset_version=16,
+ verbose=False,
+ input_names=input_names,
+ output_names=output_names,
+ )
+ return "Finished"
+
+
+with gr.Blocks() as app:
+ gr.Markdown(
+ value=i18n(
+ "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录使用需遵守的协议-LICENSE.txt."
+ )
+ )
+ with gr.Tabs():
+ with gr.TabItem(i18n("模型推理")):
+ with gr.Row():
+ sid0 = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names))
+ refresh_button = gr.Button(i18n("刷新音色列表和索引路径"), variant="primary")
+ clean_button = gr.Button(i18n("卸载音色省显存"), variant="primary")
+ spk_item = gr.Slider(
+ minimum=0,
+ maximum=2333,
+ step=1,
+ label=i18n("请选择说话人id"),
+ value=0,
+ visible=False,
+ interactive=True,
+ )
+ clean_button.click(fn=clean, inputs=[], outputs=[sid0])
+ sid0.change(
+ fn=get_vc,
+ inputs=[sid0],
+ outputs=[spk_item],
+ )
+ with gr.Group():
+ gr.Markdown(
+ value=i18n("男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ")
+ )
+ with gr.Row():
+ with gr.Column():
+ vc_transform0 = gr.Number(
+ label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+ )
+ input_audio0 = gr.Textbox(
+ label=i18n("输入待处理音频文件路径(默认是正确格式示例)"),
+ value="E:\\codes\\py39\\test-20230416b\\todo-songs\\冬之花clip1.wav",
+ )
+ f0method0 = gr.Radio(
+ label=i18n(
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU"
+ ),
+ choices=["pm", "harvest", "crepe"],
+ value="pm",
+ interactive=True,
+ )
+ filter_radius0 = gr.Slider(
+ minimum=0,
+ maximum=7,
+ label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+ value=3,
+ step=1,
+ interactive=True,
+ )
+ with gr.Column():
+ file_index1 = gr.Textbox(
+ label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+ value="",
+ interactive=True,
+ )
+ file_index2 = gr.Dropdown(
+ label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+ choices=sorted(index_paths),
+ interactive=True,
+ )
+ refresh_button.click(
+ fn=change_choices, inputs=[], outputs=[sid0, file_index2]
+ )
+ # file_big_npy1 = gr.Textbox(
+ # label=i18n("特征文件路径"),
+ # value="E:\\codes\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+ # interactive=True,
+ # )
+ index_rate1 = gr.Slider(
+ minimum=0,
+ maximum=1,
+ label=i18n("检索特征占比"),
+ value=0.88,
+ interactive=True,
+ )
+ with gr.Column():
+ resample_sr0 = gr.Slider(
+ minimum=0,
+ maximum=48000,
+ label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+ value=0,
+ step=1,
+ interactive=True,
+ )
+ rms_mix_rate0 = gr.Slider(
+ minimum=0,
+ maximum=1,
+ label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+ value=1,
+ interactive=True,
+ )
+ protect0 = gr.Slider(
+ minimum=0,
+ maximum=0.5,
+ label=i18n(
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+ ),
+ value=0.33,
+ step=0.01,
+ interactive=True,
+ )
+ f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"))
+ but0 = gr.Button(i18n("转换"), variant="primary")
+ with gr.Row():
+ vc_output1 = gr.Textbox(label=i18n("输出信息"))
+ vc_output2 = gr.Audio(label=i18n("输出音频(右下角三个点,点了可以下载)"))
+ but0.click(
+ vc_single,
+ [
+ spk_item,
+ input_audio0,
+ vc_transform0,
+ f0_file,
+ f0method0,
+ file_index1,
+ file_index2,
+ # file_big_npy1,
+ index_rate1,
+ filter_radius0,
+ resample_sr0,
+ rms_mix_rate0,
+ protect0,
+ ],
+ [vc_output1, vc_output2],
+ )
+ with gr.Group():
+ gr.Markdown(
+ value=i18n("批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ")
+ )
+ with gr.Row():
+ with gr.Column():
+ vc_transform1 = gr.Number(
+ label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+ )
+ opt_input = gr.Textbox(label=i18n("指定输出文件夹"), value="opt")
+ f0method1 = gr.Radio(
+ label=i18n(
+ "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU"
+ ),
+ choices=["pm", "harvest", "crepe"],
+ value="pm",
+ interactive=True,
+ )
+ filter_radius1 = gr.Slider(
+ minimum=0,
+ maximum=7,
+ label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+ value=3,
+ step=1,
+ interactive=True,
+ )
+ with gr.Column():
+ file_index3 = gr.Textbox(
+ label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+ value="",
+ interactive=True,
+ )
+ file_index4 = gr.Dropdown(
+ label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+ choices=sorted(index_paths),
+ interactive=True,
+ )
+ refresh_button.click(
+ fn=lambda: change_choices()[1],
+ inputs=[],
+ outputs=file_index4,
+ )
+ # file_big_npy2 = gr.Textbox(
+ # label=i18n("特征文件路径"),
+ # value="E:\\codes\\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+ # interactive=True,
+ # )
+ index_rate2 = gr.Slider(
+ minimum=0,
+ maximum=1,
+ label=i18n("检索特征占比"),
+ value=1,
+ interactive=True,
+ )
+ with gr.Column():
+ resample_sr1 = gr.Slider(
+ minimum=0,
+ maximum=48000,
+ label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+ value=0,
+ step=1,
+ interactive=True,
+ )
+ rms_mix_rate1 = gr.Slider(
+ minimum=0,
+ maximum=1,
+ label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+ value=1,
+ interactive=True,
+ )
+ protect1 = gr.Slider(
+ minimum=0,
+ maximum=0.5,
+ label=i18n(
+ "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+ ),
+ value=0.33,
+ step=0.01,
+ interactive=True,
+ )
+ with gr.Column():
+ dir_input = gr.Textbox(
+ label=i18n("输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)"),
+ value="E:\codes\py39\\test-20230416b\\todo-songs",
+ )
+ inputs = gr.File(
+ file_count="multiple", label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹")
+ )
+ with gr.Row():
+ format1 = gr.Radio(
+ label=i18n("导出文件格式"),
+ choices=["wav", "flac", "mp3", "m4a"],
+ value="flac",
+ interactive=True,
+ )
+ but1 = gr.Button(i18n("转换"), variant="primary")
+ vc_output3 = gr.Textbox(label=i18n("输出信息"))
+ but1.click(
+ vc_multi,
+ [
+ spk_item,
+ dir_input,
+ opt_input,
+ inputs,
+ vc_transform1,
+ f0method1,
+ file_index3,
+ file_index4,
+ # file_big_npy2,
+ index_rate2,
+ filter_radius1,
+ resample_sr1,
+ rms_mix_rate1,
+ protect1,
+ format1,
+ ],
+ [vc_output3],
+ )
+ with gr.TabItem(i18n("伴奏人声分离&去混响&去回声")):
+ with gr.Group():
+ gr.Markdown(
+ value=i18n(
+ "人声伴奏分离批量处理， 使用UVR5模型。
"
+ "合格的文件夹路径格式举例： E:\\codes\\py39\\vits_vc_gpu\\白鹭霜华测试样例(去文件管理器地址栏拷就行了)。
"
+ "模型分为三类：
"
+ "1、保留人声：不带和声的音频选这个，对主人声保留比HP5更好。内置HP2和HP3两个模型，HP3可能轻微漏伴奏但对主人声保留比HP2稍微好一丁点；
"
+ "2、仅保留主人声：带和声的音频选这个，对主人声可能有削弱。内置HP5一个模型；
"
+ "3、去混响、去延迟模型（by FoxJoy）：
"
+ " (1)MDX-Net(onnx_dereverb):对于双通道混响是最好的选择，不能去除单通道混响；
"
+ " (234)DeEcho:去除延迟效果。Aggressive比Normal去除得更彻底，DeReverb额外去除混响，可去除单声道混响，但是对高频重的板式混响去不干净。
"
+ "去混响/去延迟，附：
"
+ "1、DeEcho-DeReverb模型的耗时是另外2个DeEcho模型的接近2倍；
"
+ "2、MDX-Net-Dereverb模型挺慢的；
"
+ "3、个人推荐的最干净的配置是先MDX-Net再DeEcho-Aggressive。"
+ )
+ )
+ with gr.Row():
+ with gr.Column():
+ dir_wav_input = gr.Textbox(
+ label=i18n("输入待处理音频文件夹路径"),
+ value="E:\\codes\\py39\\test-20230416b\\todo-songs\\todo-songs",
+ )
+ wav_inputs = gr.File(
+ file_count="multiple", label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹")
+ )
+ with gr.Column():
+ model_choose = gr.Dropdown(label=i18n("模型"), choices=uvr5_names)
+ agg = gr.Slider(
+ minimum=0,
+ maximum=20,
+ step=1,
+ label="人声提取激进程度",
+ value=10,
+ interactive=True,
+ visible=False, # 先不开放调整
+ )
+ opt_vocal_root = gr.Textbox(
+ label=i18n("指定输出主人声文件夹"), value="opt"
+ )
+ opt_ins_root = gr.Textbox(
+ label=i18n("指定输出非主人声文件夹"), value="opt"
+ )
+ format0 = gr.Radio(
+ label=i18n("导出文件格式"),
+ choices=["wav", "flac", "mp3", "m4a"],
+ value="flac",
+ interactive=True,
+ )
+ but2 = gr.Button(i18n("转换"), variant="primary")
+ vc_output4 = gr.Textbox(label=i18n("输出信息"))
+ but2.click(
+ uvr,
+ [
+ model_choose,
+ dir_wav_input,
+ opt_vocal_root,
+ wav_inputs,
+ opt_ins_root,
+ agg,
+ format0,
+ ],
+ [vc_output4],
+ )
+ with gr.TabItem(i18n("训练")):
+ gr.Markdown(
+ value=i18n(
+ "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. "
+ )
+ )
+ with gr.Row():
+ exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="mi-test")
+ sr2 = gr.Radio(
+ label=i18n("目标采样率"),
+ choices=["40k", "48k"],
+ value="40k",
+ interactive=True,
+ )
+ if_f0_3 = gr.Radio(
+ label=i18n("模型是否带音高指导(唱歌一定要, 语音可以不要)"),
+ choices=[True, False],
+ value=True,
+ interactive=True,
+ )
+ version19 = gr.Radio(
+ label=i18n("版本(目前仅40k支持了v2)"),
+ choices=["v1", "v2"],
+ value="v1",
+ interactive=True,
+ visible=True,
+ )
+ np7 = gr.Slider(
+ minimum=0,
+ maximum=config.n_cpu,
+ step=1,
+ label=i18n("提取音高和处理数据使用的CPU进程数"),
+ value=config.n_cpu,
+ interactive=True,
+ )
+ with gr.Group(): # 暂时单人的, 后面支持最多4人的#数据处理
+ gr.Markdown(
+ value=i18n(
+ "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. "
+ )
+ )
+ with gr.Row():
+ trainset_dir4 = gr.Textbox(
+ label=i18n("输入训练文件夹路径"), value="E:\\语音音频+标注\\米津玄师\\src"
+ )
+ spk_id5 = gr.Slider(
+ minimum=0,
+ maximum=4,
+ step=1,
+ label=i18n("请指定说话人id"),
+ value=0,
+ interactive=True,
+ )
+ but1 = gr.Button(i18n("处理数据"), variant="primary")
+ info1 = gr.Textbox(label=i18n("输出信息"), value="")
+ but1.click(
+ preprocess_dataset, [trainset_dir4, exp_dir1, sr2, np7], [info1]
+ )
+ with gr.Group():
+ gr.Markdown(value=i18n("step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)"))
+ with gr.Row():
+ with gr.Column():
+ gpus6 = gr.Textbox(
+ label=i18n("以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2"),
+ value=gpus,
+ interactive=True,
+ )
+ gpu_info9 = gr.Textbox(label=i18n("显卡信息"), value=gpu_info)
+ with gr.Column():
+ f0method8 = gr.Radio(
+ label=i18n(
+ "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢"
+ ),
+ choices=["pm", "harvest", "dio"],
+ value="harvest",
+ interactive=True,
+ )
+ but2 = gr.Button(i18n("特征提取"), variant="primary")
+ info2 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+ but2.click(
+ extract_f0_feature,
+ [gpus6, np7, f0method8, if_f0_3, exp_dir1, version19],
+ [info2],
+ )
+ with gr.Group():
+ gr.Markdown(value=i18n("step3: 填写训练设置, 开始训练模型和索引"))
+ with gr.Row():
+ save_epoch10 = gr.Slider(
+ minimum=0,
+ maximum=50,
+ step=1,
+ label=i18n("保存频率save_every_epoch"),
+ value=5,
+ interactive=True,
+ )
+ total_epoch11 = gr.Slider(
+ minimum=0,
+ maximum=1000,
+ step=1,
+ label=i18n("总训练轮数total_epoch"),
+ value=20,
+ interactive=True,
+ )
+ batch_size12 = gr.Slider(
+ minimum=1,
+ maximum=40,
+ step=1,
+ label=i18n("每张显卡的batch_size"),
+ value=default_batch_size,
+ interactive=True,
+ )
+ if_save_latest13 = gr.Radio(
+ label=i18n("是否仅保存最新的ckpt文件以节省硬盘空间"),
+ choices=[i18n("是"), i18n("否")],
+ value=i18n("否"),
+ interactive=True,
+ )
+ if_cache_gpu17 = gr.Radio(
+ label=i18n(
+ "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速"
+ ),
+ choices=[i18n("是"), i18n("否")],
+ value=i18n("否"),
+ interactive=True,
+ )
+ if_save_every_weights18 = gr.Radio(
+ label=i18n("是否在每次保存时间点将最终小模型保存至weights文件夹"),
+ choices=[i18n("是"), i18n("否")],
+ value=i18n("否"),
+ interactive=True,
+ )
+ with gr.Row():
+ pretrained_G14 = gr.Textbox(
+ label=i18n("加载预训练底模G路径"),
+ value="pretrained/f0G40k.pth",
+ interactive=True,
+ )
+ pretrained_D15 = gr.Textbox(
+ label=i18n("加载预训练底模D路径"),
+ value="pretrained/f0D40k.pth",
+ interactive=True,
+ )
+ sr2.change(
+ change_sr2,
+ [sr2, if_f0_3, version19],
+ [pretrained_G14, pretrained_D15, version19],
+ )
+ version19.change(
+ change_version19,
+ [sr2, if_f0_3, version19],
+ [pretrained_G14, pretrained_D15],
+ )
+ if_f0_3.change(
+ change_f0,
+ [if_f0_3, sr2, version19],
+ [f0method8, pretrained_G14, pretrained_D15],
+ )
+ gpus16 = gr.Textbox(
+ label=i18n("以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2"),
+ value=gpus,
+ interactive=True,
+ )
+ but3 = gr.Button(i18n("训练模型"), variant="primary")
+ but4 = gr.Button(i18n("训练特征索引"), variant="primary")
+ but5 = gr.Button(i18n("一键训练"), variant="primary")
+ info3 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=10)
+ but3.click(
+ click_train,
+ [
+ exp_dir1,
+ sr2,
+ if_f0_3,
+ spk_id5,
+ save_epoch10,
+ total_epoch11,
+ batch_size12,
+ if_save_latest13,
+ pretrained_G14,
+ pretrained_D15,
+ gpus16,
+ if_cache_gpu17,
+ if_save_every_weights18,
+ version19,
+ ],
+ info3,
+ )
+ but4.click(train_index, [exp_dir1, version19], info3)
+ but5.click(
+ train1key,
+ [
+ exp_dir1,
+ sr2,
+ if_f0_3,
+ trainset_dir4,
+ spk_id5,
+ np7,
+ f0method8,
+ save_epoch10,
+ total_epoch11,
+ batch_size12,
+ if_save_latest13,
+ pretrained_G14,
+ pretrained_D15,
+ gpus16,
+ if_cache_gpu17,
+ if_save_every_weights18,
+ version19,
+ ],
+ info3,
+ )
+
+ with gr.TabItem(i18n("ckpt处理")):
+ with gr.Group():
+ gr.Markdown(value=i18n("模型融合, 可用于测试音色融合"))
+ with gr.Row():
+ ckpt_a = gr.Textbox(label=i18n("A模型路径"), value="", interactive=True)
+ ckpt_b = gr.Textbox(label=i18n("B模型路径"), value="", interactive=True)
+ alpha_a = gr.Slider(
+ minimum=0,
+ maximum=1,
+ label=i18n("A模型权重"),
+ value=0.5,
+ interactive=True,
+ )
+ with gr.Row():
+ sr_ = gr.Radio(
+ label=i18n("目标采样率"),
+ choices=["32k", "40k", "48k"],
+ value="40k",
+ interactive=True,
+ )
+ if_f0_ = gr.Radio(
+ label=i18n("模型是否带音高指导"),
+ choices=[i18n("是"), i18n("否")],
+ value=i18n("是"),
+ interactive=True,
+ )
+ info__ = gr.Textbox(
+ label=i18n("要置入的模型信息"), value="", max_lines=8, interactive=True
+ )
+ name_to_save0 = gr.Textbox(
+ label=i18n("保存的模型名不带后缀"),
+ value="",
+ max_lines=1,
+ interactive=True,
+ )
+ version_2 = gr.Radio(
+ label=i18n("模型版本型号"),
+ choices=["v1", "v2"],
+ value="v1",
+ interactive=True,
+ )
+ with gr.Row():
+ but6 = gr.Button(i18n("融合"), variant="primary")
+ info4 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+ but6.click(
+ merge,
+ [
+ ckpt_a,
+ ckpt_b,
+ alpha_a,
+ sr_,
+ if_f0_,
+ info__,
+ name_to_save0,
+ version_2,
+ ],
+ info4,
+ ) # def merge(path1,path2,alpha1,sr,f0,info):
+ with gr.Group():
+ gr.Markdown(value=i18n("修改模型信息(仅支持weights文件夹下提取的小模型文件)"))
+ with gr.Row():
+ ckpt_path0 = gr.Textbox(
+ label=i18n("模型路径"), value="", interactive=True
+ )
+ info_ = gr.Textbox(
+ label=i18n("要改的模型信息"), value="", max_lines=8, interactive=True
+ )
+ name_to_save1 = gr.Textbox(
+ label=i18n("保存的文件名, 默认空为和源文件同名"),
+ value="",
+ max_lines=8,
+ interactive=True,
+ )
+ with gr.Row():
+ but7 = gr.Button(i18n("修改"), variant="primary")
+ info5 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+ but7.click(change_info, [ckpt_path0, info_, name_to_save1], info5)
+ with gr.Group():
+ gr.Markdown(value=i18n("查看模型信息(仅支持weights文件夹下提取的小模型文件)"))
+ with gr.Row():
+ ckpt_path1 = gr.Textbox(
+ label=i18n("模型路径"), value="", interactive=True
+ )
+ but8 = gr.Button(i18n("查看"), variant="primary")
+ info6 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+ but8.click(show_info, [ckpt_path1], info6)
+ with gr.Group():
+ gr.Markdown(
+ value=i18n(
+ "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况"
+ )
+ )
+ with gr.Row():
+ ckpt_path2 = gr.Textbox(
+ label=i18n("模型路径"),
+ value="E:\\codes\\py39\\logs\\mi-test_f0_48k\\G_23333.pth",
+ interactive=True,
+ )
+ save_name = gr.Textbox(
+ label=i18n("保存名"), value="", interactive=True
+ )
+ sr__ = gr.Radio(
+ label=i18n("目标采样率"),
+ choices=["32k", "40k", "48k"],
+ value="40k",
+ interactive=True,
+ )
+ if_f0__ = gr.Radio(
+ label=i18n("模型是否带音高指导,1是0否"),
+ choices=["1", "0"],
+ value="1",
+ interactive=True,
+ )
+ version_1 = gr.Radio(
+ label=i18n("模型版本型号"),
+ choices=["v1", "v2"],
+ value="v1",
+ interactive=True,
+ )
+ info___ = gr.Textbox(
+ label=i18n("要置入的模型信息"), value="", max_lines=8, interactive=True
+ )
+ but9 = gr.Button(i18n("提取"), variant="primary")
+ info7 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+ ckpt_path2.change(
+ change_info_, [ckpt_path2], [sr__, if_f0__, version_1]
+ )
+ but9.click(
+ extract_small_model,
+ [ckpt_path2, save_name, sr__, if_f0__, info___, version_1],
+ info7,
+ )
+
+ with gr.TabItem(i18n("Onnx导出")):
+ with gr.Row():
+ ckpt_dir = gr.Textbox(label=i18n("RVC模型路径"), value="", interactive=True)
+ with gr.Row():
+ onnx_dir = gr.Textbox(
+ label=i18n("Onnx输出路径"), value="", interactive=True
+ )
+ with gr.Row():
+ moevs = gr.Checkbox(label=i18n("MoeVS模型"), value=True)
+ infoOnnx = gr.Label(label="Null")
+ with gr.Row():
+ butOnnx = gr.Button(i18n("导出Onnx模型"), variant="primary")
+ butOnnx.click(export_onnx, [ckpt_dir, onnx_dir, moevs], infoOnnx)
+
+ tab_faq = i18n("常见问题解答")
+ with gr.TabItem(tab_faq):
+ try:
+ if tab_faq == "常见问题解答":
+ with open("docs/faq.md", "r", encoding="utf8") as f:
+ info = f.read()
+ else:
+ with open("docs/faq_en.md", "r", encoding="utf8") as f:
+ info = f.read()
+ gr.Markdown(value=info)
+ except:
+ gr.Markdown(traceback.format_exc())
+
+ # with gr.TabItem(i18n("招募音高曲线前端编辑器")):
+ # gr.Markdown(value=i18n("加开发群联系我xxxxx"))
+ # with gr.TabItem(i18n("点击查看交流、问题反馈群号")):
+ # gr.Markdown(value=i18n("xxxxx"))
+
+ if config.iscolab:
+ app.queue(concurrency_count=511, max_size=1022).launch(share=True)
+ else:
+ app.queue(concurrency_count=511, max_size=1022).launch(
+ server_name="0.0.0.0",
+ inbrowser=not config.noautoopen,
+ server_port=config.listen_port,
+ quiet=True,
+ )
diff --git a/infer/infer-pm-index256.py b/infer/infer-pm-index256.py
new file mode 100644
index 0000000000000000000000000000000000000000..66e38d49071994e9c850f7d75d0a3b2e5c79b0da
--- /dev/null
+++ b/infer/infer-pm-index256.py
@@ -0,0 +1,199 @@
+"""
+
+对源特征进行检索
+"""
+import torch, pdb, os, parselmouth
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+import numpy as np
+import soundfile as sf
+
+# from models import SynthesizerTrn256#hifigan_nonsf
+# from infer_pack.models import SynthesizerTrn256NSF as SynthesizerTrn256#hifigan_nsf
+from infer_pack.models import (
+ SynthesizerTrnMs256NSFsid as SynthesizerTrn256,
+) # hifigan_nsf
+
+# from infer_pack.models import SynthesizerTrnMs256NSFsid_sim as SynthesizerTrn256#hifigan_nsf
+# from models import SynthesizerTrn256NSFsim as SynthesizerTrn256#hifigan_nsf
+# from models import SynthesizerTrn256NSFsimFlow as SynthesizerTrn256#hifigan_nsf
+
+
+from scipy.io import wavfile
+from fairseq import checkpoint_utils
+
+# import pyworld
+import librosa
+import torch.nn.functional as F
+import scipy.signal as signal
+
+# import torchcrepe
+from time import time as ttime
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model_path = r"E:\codes\py39\vits_vc_gpu_train\hubert_base.pt" #
+print("load model(s) from {}".format(model_path))
+models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
+ [model_path],
+ suffix="",
+)
+model = models[0]
+model = model.to(device)
+model = model.half()
+model.eval()
+
+# net_g = SynthesizerTrn256(1025,32,192,192,768,2,6,3,0.1,"1", [3,7,11],[[1,3,5], [1,3,5], [1,3,5]],[10,10,2,2],512,[16,16,4,4],183,256,is_half=True)#hifigan#512#256
+# net_g = SynthesizerTrn256(1025,32,192,192,768,2,6,3,0.1,"1", [3,7,11],[[1,3,5], [1,3,5], [1,3,5]],[10,10,2,2],512,[16,16,4,4],109,256,is_half=True)#hifigan#512#256
+net_g = SynthesizerTrn256(
+ 1025,
+ 32,
+ 192,
+ 192,
+ 768,
+ 2,
+ 6,
+ 3,
+ 0,
+ "1",
+ [3, 7, 11],
+ [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+ [10, 10, 2, 2],
+ 512,
+ [16, 16, 4, 4],
+ 183,
+ 256,
+ is_half=True,
+) # hifigan#512#256#no_dropout
+# net_g = SynthesizerTrn256(1025,32,192,192,768,2,3,3,0.1,"1", [3,7,11],[[1,3,5], [1,3,5], [1,3,5]],[10,10,2,2],512,[16,16,4,4],0)#ts3
+# net_g = SynthesizerTrn256(1025,32,192,192,768,2,6,3,0.1,"1", [3,7,11],[[1,3,5], [1,3,5], [1,3,5]],[10,10,2],512,[16,16,4],0)#hifigan-ps-sr
+#
+# net_g = SynthesizerTrn(1025, 32, 192, 192, 768, 2, 6, 3, 0.1, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [5,5], 512, [15,15], 0)#ms
+# net_g = SynthesizerTrn(1025, 32, 192, 192, 768, 2, 6, 3, 0.1, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10,10], 512, [16,16], 0)#idwt2
+
+# weights=torch.load("infer/ft-mi_1k-noD.pt")
+# weights=torch.load("infer/ft-mi-freeze-vocoder-flow-enc_q_1k.pt")
+# weights=torch.load("infer/ft-mi-freeze-vocoder_true_1k.pt")
+# weights=torch.load("infer/ft-mi-sim1k.pt")
+weights = torch.load("infer/ft-mi-no_opt-no_dropout.pt")
+print(net_g.load_state_dict(weights, strict=True))
+
+net_g.eval().to(device)
+net_g.half()
+
+
+def get_f0(x, p_len, f0_up_key=0):
+ time_step = 160 / 16000 * 1000
+ f0_min = 50
+ f0_max = 1100
+ f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+ f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+
+ f0 = (
+ parselmouth.Sound(x, 16000)
+ .to_pitch_ac(
+ time_step=time_step / 1000,
+ voicing_threshold=0.6,
+ pitch_floor=f0_min,
+ pitch_ceiling=f0_max,
+ )
+ .selected_array["frequency"]
+ )
+
+ pad_size = (p_len - len(f0) + 1) // 2
+ if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+ f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+ f0 *= pow(2, f0_up_key / 12)
+ f0bak = f0.copy()
+
+ f0_mel = 1127 * np.log(1 + f0 / 700)
+ f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+ f0_mel_max - f0_mel_min
+ ) + 1
+ f0_mel[f0_mel <= 1] = 1
+ f0_mel[f0_mel > 255] = 255
+ # f0_mel[f0_mel > 188] = 188
+ f0_coarse = np.rint(f0_mel).astype(np.int)
+ return f0_coarse, f0bak
+
+
+import faiss
+
+index = faiss.read_index("infer/added_IVF512_Flat_mi_baseline_src_feat.index")
+big_npy = np.load("infer/big_src_feature_mi.npy")
+ta0 = ta1 = ta2 = 0
+for idx, name in enumerate(
+ [
+ "冬之花clip1.wav",
+ ]
+): ##
+ wav_path = "todo-songs/%s" % name #
+ f0_up_key = -2 #
+ audio, sampling_rate = sf.read(wav_path)
+ if len(audio.shape) > 1:
+ audio = librosa.to_mono(audio.transpose(1, 0))
+ if sampling_rate != 16000:
+ audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
+
+ feats = torch.from_numpy(audio).float()
+ if feats.dim() == 2: # double channels
+ feats = feats.mean(-1)
+ assert feats.dim() == 1, feats.dim()
+ feats = feats.view(1, -1)
+ padding_mask = torch.BoolTensor(feats.shape).fill_(False)
+ inputs = {
+ "source": feats.half().to(device),
+ "padding_mask": padding_mask.to(device),
+ "output_layer": 9, # layer 9
+ }
+ if torch.cuda.is_available():
+ torch.cuda.synchronize()
+ t0 = ttime()
+ with torch.no_grad():
+ logits = model.extract_features(**inputs)
+ feats = model.final_proj(logits[0])
+
+ ####索引优化
+ npy = feats[0].cpu().numpy().astype("float32")
+ D, I = index.search(npy, 1)
+ feats = (
+ torch.from_numpy(big_npy[I.squeeze()].astype("float16")).unsqueeze(0).to(device)
+ )
+
+ feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
+ if torch.cuda.is_available():
+ torch.cuda.synchronize()
+ t1 = ttime()
+ # p_len = min(feats.shape[1],10000,pitch.shape[0])#太大了爆显存
+ p_len = min(feats.shape[1], 10000) #
+ pitch, pitchf = get_f0(audio, p_len, f0_up_key)
+ p_len = min(feats.shape[1], 10000, pitch.shape[0]) # 太大了爆显存
+ if torch.cuda.is_available():
+ torch.cuda.synchronize()
+ t2 = ttime()
+ feats = feats[:, :p_len, :]
+ pitch = pitch[:p_len]
+ pitchf = pitchf[:p_len]
+ p_len = torch.LongTensor([p_len]).to(device)
+ pitch = torch.LongTensor(pitch).unsqueeze(0).to(device)
+ sid = torch.LongTensor([0]).to(device)
+ pitchf = torch.FloatTensor(pitchf).unsqueeze(0).to(device)
+ with torch.no_grad():
+ audio = (
+ net_g.infer(feats, p_len, pitch, pitchf, sid)[0][0, 0]
+ .data.cpu()
+ .float()
+ .numpy()
+ ) # nsf
+ if torch.cuda.is_available():
+ torch.cuda.synchronize()
+ t3 = ttime()
+ ta0 += t1 - t0
+ ta1 += t2 - t1
+ ta2 += t3 - t2
+ # wavfile.write("ft-mi_1k-index256-noD-%s.wav"%name, 40000, audio)##
+ # wavfile.write("ft-mi-freeze-vocoder-flow-enc_q_1k-%s.wav"%name, 40000, audio)##
+ # wavfile.write("ft-mi-sim1k-%s.wav"%name, 40000, audio)##
+ wavfile.write("ft-mi-no_opt-no_dropout-%s.wav" % name, 40000, audio) ##
+
+
+print(ta0, ta1, ta2) #
diff --git a/infer/train-index -v2.py b/infer/train-index -v2.py
new file mode 100644
index 0000000000000000000000000000000000000000..bb24eeab7106b7489e66123cb6530e6306f2ed7a
--- /dev/null
+++ b/infer/train-index -v2.py
@@ -0,0 +1,44 @@
+"""
+格式：直接cid为自带的index位；aid放不下了，通过字典来查，反正就5w个
+"""
+import faiss, numpy as np, os
+
+# ###########如果是原始特征要先写save
+inp_root = r"./logs/nene/3_feature768"
+npys = []
+listdir_res = list(os.listdir(inp_root))
+for name in sorted(listdir_res):
+ phone = np.load("%s/%s" % (inp_root, name))
+ npys.append(phone)
+big_npy = np.concatenate(npys, 0)
+big_npy_idx = np.arange(big_npy.shape[0])
+np.random.shuffle(big_npy_idx)
+big_npy = big_npy[big_npy_idx]
+print(big_npy.shape) # (6196072, 192)#fp32#4.43G
+np.save("infer/big_src_feature_mi.npy", big_npy)
+
+##################train+add
+# big_npy=np.load("/bili-coeus/jupyter/jupyterhub-liujing04/vits_ch/inference_f0/big_src_feature_mi.npy")
+n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+index = faiss.index_factory(768, "IVF%s,Flat" % n_ivf) # mi
+print("training")
+index_ivf = faiss.extract_index_ivf(index) #
+index_ivf.nprobe = 1
+index.train(big_npy)
+faiss.write_index(
+ index, "infer/trained_IVF%s_Flat_baseline_src_feat_v2.index" % (n_ivf)
+)
+print("adding")
+batch_size_add = 8192
+for i in range(0, big_npy.shape[0], batch_size_add):
+ index.add(big_npy[i : i + batch_size_add])
+faiss.write_index(index, "infer/added_IVF%s_Flat_mi_baseline_src_feat.index" % (n_ivf))
+"""
+大小（都是FP32）
+big_src_feature 2.95G
+ (3098036, 256)
+big_emb 4.43G
+ (6196072, 192)
+big_emb双倍是因为求特征要repeat后再加pitch
+
+"""
diff --git a/infer/train-index.py b/infer/train-index.py
new file mode 100644
index 0000000000000000000000000000000000000000..04396a2241ed27c999a6687aa7b9880941edbcf3
--- /dev/null
+++ b/infer/train-index.py
@@ -0,0 +1,36 @@
+"""
+格式：直接cid为自带的index位；aid放不下了，通过字典来查，反正就5w个
+"""
+import faiss, numpy as np, os
+
+# ###########如果是原始特征要先写save
+inp_root = r"E:\codes\py39\dataset\mi\2-co256"
+npys = []
+for name in sorted(list(os.listdir(inp_root))):
+ phone = np.load("%s/%s" % (inp_root, name))
+ npys.append(phone)
+big_npy = np.concatenate(npys, 0)
+print(big_npy.shape) # (6196072, 192)#fp32#4.43G
+np.save("infer/big_src_feature_mi.npy", big_npy)
+
+##################train+add
+# big_npy=np.load("/bili-coeus/jupyter/jupyterhub-liujing04/vits_ch/inference_f0/big_src_feature_mi.npy")
+print(big_npy.shape)
+index = faiss.index_factory(256, "IVF512,Flat") # mi
+print("training")
+index_ivf = faiss.extract_index_ivf(index) #
+index_ivf.nprobe = 9
+index.train(big_npy)
+faiss.write_index(index, "infer/trained_IVF512_Flat_mi_baseline_src_feat.index")
+print("adding")
+index.add(big_npy)
+faiss.write_index(index, "infer/added_IVF512_Flat_mi_baseline_src_feat.index")
+"""
+大小（都是FP32）
+big_src_feature 2.95G
+ (3098036, 256)
+big_emb 4.43G
+ (6196072, 192)
+big_emb双倍是因为求特征要repeat后再加pitch
+
+"""
diff --git a/infer/trans_weights.py b/infer/trans_weights.py
new file mode 100644
index 0000000000000000000000000000000000000000..da0759627d3fee175a2311a5ac50ccb7f8db8ded
--- /dev/null
+++ b/infer/trans_weights.py
@@ -0,0 +1,16 @@
+import torch, pdb
+
+# a=torch.load(r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-suc\G_1000.pth")["model"]#sim_nsf#
+# a=torch.load(r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-freeze-vocoder-flow-enc_q\G_1000.pth")["model"]#sim_nsf#
+# a=torch.load(r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-freeze-vocoder\G_1000.pth")["model"]#sim_nsf#
+# a=torch.load(r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-test\G_1000.pth")["model"]#sim_nsf#
+a = torch.load(
+ r"E:\codes\py39\vits_vc_gpu_train\logs\ft-mi-no_opt-no_dropout\G_1000.pth"
+)[
+ "model"
+] # sim_nsf#
+for key in a.keys():
+ a[key] = a[key].half()
+# torch.save(a,"ft-mi-freeze-vocoder_true_1k.pt")#
+# torch.save(a,"ft-mi-sim1k.pt")#
+torch.save(a, "ft-mi-no_opt-no_dropout.pt") #
diff --git a/infer_pack/__pycache__/attentions.cpython-39.pyc b/infer_pack/__pycache__/attentions.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..cef736164b87199cfcf175c42d983057e33ad366
Binary files /dev/null and b/infer_pack/__pycache__/attentions.cpython-39.pyc differ
diff --git a/infer_pack/__pycache__/commons.cpython-39.pyc b/infer_pack/__pycache__/commons.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b43d90bf268c5a1c65820905555316021e8f37e7
Binary files /dev/null and b/infer_pack/__pycache__/commons.cpython-39.pyc differ
diff --git a/infer_pack/__pycache__/models.cpython-39.pyc b/infer_pack/__pycache__/models.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b926cf6b32ba68e4c6e4ad936a0a66db8aa603dc
Binary files /dev/null and b/infer_pack/__pycache__/models.cpython-39.pyc differ
diff --git a/infer_pack/__pycache__/modules.cpython-39.pyc b/infer_pack/__pycache__/modules.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..26808d244691b3c822a43382fdc315baf914e18b
Binary files /dev/null and b/infer_pack/__pycache__/modules.cpython-39.pyc differ
diff --git a/infer_pack/__pycache__/transforms.cpython-39.pyc b/infer_pack/__pycache__/transforms.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..38ad01f09a9d0ffcf8fc46d4fdb42637f6ab6fd3
Binary files /dev/null and b/infer_pack/__pycache__/transforms.cpython-39.pyc differ
diff --git a/infer_pack/attentions.py b/infer_pack/attentions.py
new file mode 100644
index 0000000000000000000000000000000000000000..77cb63ffccf3e33badf22d50862a64ba517b487f
--- /dev/null
+++ b/infer_pack/attentions.py
@@ -0,0 +1,417 @@
+import copy
+import math
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from infer_pack import commons
+from infer_pack import modules
+from infer_pack.modules import LayerNorm
+
+
+class Encoder(nn.Module):
+ def __init__(
+ self,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size=1,
+ p_dropout=0.0,
+ window_size=10,
+ **kwargs
+ ):
+ super().__init__()
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.window_size = window_size
+
+ self.drop = nn.Dropout(p_dropout)
+ self.attn_layers = nn.ModuleList()
+ self.norm_layers_1 = nn.ModuleList()
+ self.ffn_layers = nn.ModuleList()
+ self.norm_layers_2 = nn.ModuleList()
+ for i in range(self.n_layers):
+ self.attn_layers.append(
+ MultiHeadAttention(
+ hidden_channels,
+ hidden_channels,
+ n_heads,
+ p_dropout=p_dropout,
+ window_size=window_size,
+ )
+ )
+ self.norm_layers_1.append(LayerNorm(hidden_channels))
+ self.ffn_layers.append(
+ FFN(
+ hidden_channels,
+ hidden_channels,
+ filter_channels,
+ kernel_size,
+ p_dropout=p_dropout,
+ )
+ )
+ self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+ def forward(self, x, x_mask):
+ attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+ x = x * x_mask
+ for i in range(self.n_layers):
+ y = self.attn_layers[i](x, x, attn_mask)
+ y = self.drop(y)
+ x = self.norm_layers_1[i](x + y)
+
+ y = self.ffn_layers[i](x, x_mask)
+ y = self.drop(y)
+ x = self.norm_layers_2[i](x + y)
+ x = x * x_mask
+ return x
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size=1,
+ p_dropout=0.0,
+ proximal_bias=False,
+ proximal_init=True,
+ **kwargs
+ ):
+ super().__init__()
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.proximal_bias = proximal_bias
+ self.proximal_init = proximal_init
+
+ self.drop = nn.Dropout(p_dropout)
+ self.self_attn_layers = nn.ModuleList()
+ self.norm_layers_0 = nn.ModuleList()
+ self.encdec_attn_layers = nn.ModuleList()
+ self.norm_layers_1 = nn.ModuleList()
+ self.ffn_layers = nn.ModuleList()
+ self.norm_layers_2 = nn.ModuleList()
+ for i in range(self.n_layers):
+ self.self_attn_layers.append(
+ MultiHeadAttention(
+ hidden_channels,
+ hidden_channels,
+ n_heads,
+ p_dropout=p_dropout,
+ proximal_bias=proximal_bias,
+ proximal_init=proximal_init,
+ )
+ )
+ self.norm_layers_0.append(LayerNorm(hidden_channels))
+ self.encdec_attn_layers.append(
+ MultiHeadAttention(
+ hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout
+ )
+ )
+ self.norm_layers_1.append(LayerNorm(hidden_channels))
+ self.ffn_layers.append(
+ FFN(
+ hidden_channels,
+ hidden_channels,
+ filter_channels,
+ kernel_size,
+ p_dropout=p_dropout,
+ causal=True,
+ )
+ )
+ self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+ def forward(self, x, x_mask, h, h_mask):
+ """
+ x: decoder input
+ h: encoder output
+ """
+ self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(
+ device=x.device, dtype=x.dtype
+ )
+ encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+ x = x * x_mask
+ for i in range(self.n_layers):
+ y = self.self_attn_layers[i](x, x, self_attn_mask)
+ y = self.drop(y)
+ x = self.norm_layers_0[i](x + y)
+
+ y = self.encdec_attn_layers[i](x, h, encdec_attn_mask)
+ y = self.drop(y)
+ x = self.norm_layers_1[i](x + y)
+
+ y = self.ffn_layers[i](x, x_mask)
+ y = self.drop(y)
+ x = self.norm_layers_2[i](x + y)
+ x = x * x_mask
+ return x
+
+
+class MultiHeadAttention(nn.Module):
+ def __init__(
+ self,
+ channels,
+ out_channels,
+ n_heads,
+ p_dropout=0.0,
+ window_size=None,
+ heads_share=True,
+ block_length=None,
+ proximal_bias=False,
+ proximal_init=False,
+ ):
+ super().__init__()
+ assert channels % n_heads == 0
+
+ self.channels = channels
+ self.out_channels = out_channels
+ self.n_heads = n_heads
+ self.p_dropout = p_dropout
+ self.window_size = window_size
+ self.heads_share = heads_share
+ self.block_length = block_length
+ self.proximal_bias = proximal_bias
+ self.proximal_init = proximal_init
+ self.attn = None
+
+ self.k_channels = channels // n_heads
+ self.conv_q = nn.Conv1d(channels, channels, 1)
+ self.conv_k = nn.Conv1d(channels, channels, 1)
+ self.conv_v = nn.Conv1d(channels, channels, 1)
+ self.conv_o = nn.Conv1d(channels, out_channels, 1)
+ self.drop = nn.Dropout(p_dropout)
+
+ if window_size is not None:
+ n_heads_rel = 1 if heads_share else n_heads
+ rel_stddev = self.k_channels**-0.5
+ self.emb_rel_k = nn.Parameter(
+ torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
+ * rel_stddev
+ )
+ self.emb_rel_v = nn.Parameter(
+ torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
+ * rel_stddev
+ )
+
+ nn.init.xavier_uniform_(self.conv_q.weight)
+ nn.init.xavier_uniform_(self.conv_k.weight)
+ nn.init.xavier_uniform_(self.conv_v.weight)
+ if proximal_init:
+ with torch.no_grad():
+ self.conv_k.weight.copy_(self.conv_q.weight)
+ self.conv_k.bias.copy_(self.conv_q.bias)
+
+ def forward(self, x, c, attn_mask=None):
+ q = self.conv_q(x)
+ k = self.conv_k(c)
+ v = self.conv_v(c)
+
+ x, self.attn = self.attention(q, k, v, mask=attn_mask)
+
+ x = self.conv_o(x)
+ return x
+
+ def attention(self, query, key, value, mask=None):
+ # reshape [b, d, t] -> [b, n_h, t, d_k]
+ b, d, t_s, t_t = (*key.size(), query.size(2))
+ query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3)
+ key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+ value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+
+ scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1))
+ if self.window_size is not None:
+ assert (
+ t_s == t_t
+ ), "Relative attention is only available for self-attention."
+ key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s)
+ rel_logits = self._matmul_with_relative_keys(
+ query / math.sqrt(self.k_channels), key_relative_embeddings
+ )
+ scores_local = self._relative_position_to_absolute_position(rel_logits)
+ scores = scores + scores_local
+ if self.proximal_bias:
+ assert t_s == t_t, "Proximal bias is only available for self-attention."
+ scores = scores + self._attention_bias_proximal(t_s).to(
+ device=scores.device, dtype=scores.dtype
+ )
+ if mask is not None:
+ scores = scores.masked_fill(mask == 0, -1e4)
+ if self.block_length is not None:
+ assert (
+ t_s == t_t
+ ), "Local attention is only available for self-attention."
+ block_mask = (
+ torch.ones_like(scores)
+ .triu(-self.block_length)
+ .tril(self.block_length)
+ )
+ scores = scores.masked_fill(block_mask == 0, -1e4)
+ p_attn = F.softmax(scores, dim=-1) # [b, n_h, t_t, t_s]
+ p_attn = self.drop(p_attn)
+ output = torch.matmul(p_attn, value)
+ if self.window_size is not None:
+ relative_weights = self._absolute_position_to_relative_position(p_attn)
+ value_relative_embeddings = self._get_relative_embeddings(
+ self.emb_rel_v, t_s
+ )
+ output = output + self._matmul_with_relative_values(
+ relative_weights, value_relative_embeddings
+ )
+ output = (
+ output.transpose(2, 3).contiguous().view(b, d, t_t)
+ ) # [b, n_h, t_t, d_k] -> [b, d, t_t]
+ return output, p_attn
+
+ def _matmul_with_relative_values(self, x, y):
+ """
+ x: [b, h, l, m]
+ y: [h or 1, m, d]
+ ret: [b, h, l, d]
+ """
+ ret = torch.matmul(x, y.unsqueeze(0))
+ return ret
+
+ def _matmul_with_relative_keys(self, x, y):
+ """
+ x: [b, h, l, d]
+ y: [h or 1, m, d]
+ ret: [b, h, l, m]
+ """
+ ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1))
+ return ret
+
+ def _get_relative_embeddings(self, relative_embeddings, length):
+ max_relative_position = 2 * self.window_size + 1
+ # Pad first before slice to avoid using cond ops.
+ pad_length = max(length - (self.window_size + 1), 0)
+ slice_start_position = max((self.window_size + 1) - length, 0)
+ slice_end_position = slice_start_position + 2 * length - 1
+ if pad_length > 0:
+ padded_relative_embeddings = F.pad(
+ relative_embeddings,
+ commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]),
+ )
+ else:
+ padded_relative_embeddings = relative_embeddings
+ used_relative_embeddings = padded_relative_embeddings[
+ :, slice_start_position:slice_end_position
+ ]
+ return used_relative_embeddings
+
+ def _relative_position_to_absolute_position(self, x):
+ """
+ x: [b, h, l, 2*l-1]
+ ret: [b, h, l, l]
+ """
+ batch, heads, length, _ = x.size()
+ # Concat columns of pad to shift from relative to absolute indexing.
+ x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]]))
+
+ # Concat extra elements so to add up to shape (len+1, 2*len-1).
+ x_flat = x.view([batch, heads, length * 2 * length])
+ x_flat = F.pad(
+ x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [0, length - 1]])
+ )
+
+ # Reshape and slice out the padded elements.
+ x_final = x_flat.view([batch, heads, length + 1, 2 * length - 1])[
+ :, :, :length, length - 1 :
+ ]
+ return x_final
+
+ def _absolute_position_to_relative_position(self, x):
+ """
+ x: [b, h, l, l]
+ ret: [b, h, l, 2*l-1]
+ """
+ batch, heads, length, _ = x.size()
+ # padd along column
+ x = F.pad(
+ x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length - 1]])
+ )
+ x_flat = x.view([batch, heads, length**2 + length * (length - 1)])
+ # add 0's in the beginning that will skew the elements after reshape
+ x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]]))
+ x_final = x_flat.view([batch, heads, length, 2 * length])[:, :, :, 1:]
+ return x_final
+
+ def _attention_bias_proximal(self, length):
+ """Bias for self-attention to encourage attention to close positions.
+ Args:
+ length: an integer scalar.
+ Returns:
+ a Tensor with shape [1, 1, length, length]
+ """
+ r = torch.arange(length, dtype=torch.float32)
+ diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1)
+ return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0)
+
+
+class FFN(nn.Module):
+ def __init__(
+ self,
+ in_channels,
+ out_channels,
+ filter_channels,
+ kernel_size,
+ p_dropout=0.0,
+ activation=None,
+ causal=False,
+ ):
+ super().__init__()
+ self.in_channels = in_channels
+ self.out_channels = out_channels
+ self.filter_channels = filter_channels
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.activation = activation
+ self.causal = causal
+
+ if causal:
+ self.padding = self._causal_padding
+ else:
+ self.padding = self._same_padding
+
+ self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size)
+ self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size)
+ self.drop = nn.Dropout(p_dropout)
+
+ def forward(self, x, x_mask):
+ x = self.conv_1(self.padding(x * x_mask))
+ if self.activation == "gelu":
+ x = x * torch.sigmoid(1.702 * x)
+ else:
+ x = torch.relu(x)
+ x = self.drop(x)
+ x = self.conv_2(self.padding(x * x_mask))
+ return x * x_mask
+
+ def _causal_padding(self, x):
+ if self.kernel_size == 1:
+ return x
+ pad_l = self.kernel_size - 1
+ pad_r = 0
+ padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+ x = F.pad(x, commons.convert_pad_shape(padding))
+ return x
+
+ def _same_padding(self, x):
+ if self.kernel_size == 1:
+ return x
+ pad_l = (self.kernel_size - 1) // 2
+ pad_r = self.kernel_size // 2
+ padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+ x = F.pad(x, commons.convert_pad_shape(padding))
+ return x
diff --git a/infer_pack/commons.py b/infer_pack/commons.py
new file mode 100644
index 0000000000000000000000000000000000000000..54470986f37825b35d90d7efa7437d1c26b87215
--- /dev/null
+++ b/infer_pack/commons.py
@@ -0,0 +1,166 @@
+import math
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+
+def init_weights(m, mean=0.0, std=0.01):
+ classname = m.__class__.__name__
+ if classname.find("Conv") != -1:
+ m.weight.data.normal_(mean, std)
+
+
+def get_padding(kernel_size, dilation=1):
+ return int((kernel_size * dilation - dilation) / 2)
+
+
+def convert_pad_shape(pad_shape):
+ l = pad_shape[::-1]
+ pad_shape = [item for sublist in l for item in sublist]
+ return pad_shape
+
+
+def kl_divergence(m_p, logs_p, m_q, logs_q):
+ """KL(P||Q)"""
+ kl = (logs_q - logs_p) - 0.5
+ kl += (
+ 0.5 * (torch.exp(2.0 * logs_p) + ((m_p - m_q) ** 2)) * torch.exp(-2.0 * logs_q)
+ )
+ return kl
+
+
+def rand_gumbel(shape):
+ """Sample from the Gumbel distribution, protect from overflows."""
+ uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
+ return -torch.log(-torch.log(uniform_samples))
+
+
+def rand_gumbel_like(x):
+ g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
+ return g
+
+
+def slice_segments(x, ids_str, segment_size=4):
+ ret = torch.zeros_like(x[:, :, :segment_size])
+ for i in range(x.size(0)):
+ idx_str = ids_str[i]
+ idx_end = idx_str + segment_size
+ ret[i] = x[i, :, idx_str:idx_end]
+ return ret
+
+
+def slice_segments2(x, ids_str, segment_size=4):
+ ret = torch.zeros_like(x[:, :segment_size])
+ for i in range(x.size(0)):
+ idx_str = ids_str[i]
+ idx_end = idx_str + segment_size
+ ret[i] = x[i, idx_str:idx_end]
+ return ret
+
+
+def rand_slice_segments(x, x_lengths=None, segment_size=4):
+ b, d, t = x.size()
+ if x_lengths is None:
+ x_lengths = t
+ ids_str_max = x_lengths - segment_size + 1
+ ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
+ ret = slice_segments(x, ids_str, segment_size)
+ return ret, ids_str
+
+
+def get_timing_signal_1d(length, channels, min_timescale=1.0, max_timescale=1.0e4):
+ position = torch.arange(length, dtype=torch.float)
+ num_timescales = channels // 2
+ log_timescale_increment = math.log(float(max_timescale) / float(min_timescale)) / (
+ num_timescales - 1
+ )
+ inv_timescales = min_timescale * torch.exp(
+ torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment
+ )
+ scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
+ signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
+ signal = F.pad(signal, [0, 0, 0, channels % 2])
+ signal = signal.view(1, channels, length)
+ return signal
+
+
+def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
+ b, channels, length = x.size()
+ signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
+ return x + signal.to(dtype=x.dtype, device=x.device)
+
+
+def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
+ b, channels, length = x.size()
+ signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
+ return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)
+
+
+def subsequent_mask(length):
+ mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
+ return mask
+
+
+@torch.jit.script
+def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
+ n_channels_int = n_channels[0]
+ in_act = input_a + input_b
+ t_act = torch.tanh(in_act[:, :n_channels_int, :])
+ s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
+ acts = t_act * s_act
+ return acts
+
+
+def convert_pad_shape(pad_shape):
+ l = pad_shape[::-1]
+ pad_shape = [item for sublist in l for item in sublist]
+ return pad_shape
+
+
+def shift_1d(x):
+ x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
+ return x
+
+
+def sequence_mask(length, max_length=None):
+ if max_length is None:
+ max_length = length.max()
+ x = torch.arange(max_length, dtype=length.dtype, device=length.device)
+ return x.unsqueeze(0) < length.unsqueeze(1)
+
+
+def generate_path(duration, mask):
+ """
+ duration: [b, 1, t_x]
+ mask: [b, 1, t_y, t_x]
+ """
+ device = duration.device
+
+ b, _, t_y, t_x = mask.shape
+ cum_duration = torch.cumsum(duration, -1)
+
+ cum_duration_flat = cum_duration.view(b * t_x)
+ path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
+ path = path.view(b, t_x, t_y)
+ path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
+ path = path.unsqueeze(1).transpose(2, 3) * mask
+ return path
+
+
+def clip_grad_value_(parameters, clip_value, norm_type=2):
+ if isinstance(parameters, torch.Tensor):
+ parameters = [parameters]
+ parameters = list(filter(lambda p: p.grad is not None, parameters))
+ norm_type = float(norm_type)
+ if clip_value is not None:
+ clip_value = float(clip_value)
+
+ total_norm = 0
+ for p in parameters:
+ param_norm = p.grad.data.norm(norm_type)
+ total_norm += param_norm.item() ** norm_type
+ if clip_value is not None:
+ p.grad.data.clamp_(min=-clip_value, max=clip_value)
+ total_norm = total_norm ** (1.0 / norm_type)
+ return total_norm
diff --git a/infer_pack/models.py b/infer_pack/models.py
new file mode 100644
index 0000000000000000000000000000000000000000..5e4b2e72383efaee1fae4f5c42e3db2c627e4190
--- /dev/null
+++ b/infer_pack/models.py
@@ -0,0 +1,1124 @@
+import math, pdb, os
+from time import time as ttime
+import torch
+from torch import nn
+from torch.nn import functional as F
+from infer_pack import modules
+from infer_pack import attentions
+from infer_pack import commons
+from infer_pack.commons import init_weights, get_padding
+from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
+from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
+from infer_pack.commons import init_weights
+import numpy as np
+from infer_pack import commons
+
+
+class TextEncoder256(nn.Module):
+ def __init__(
+ self,
+ out_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ f0=True,
+ ):
+ super().__init__()
+ self.out_channels = out_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.emb_phone = nn.Linear(256, hidden_channels)
+ self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+ if f0 == True:
+ self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
+ self.encoder = attentions.Encoder(
+ hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+ )
+ self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+ def forward(self, phone, pitch, lengths):
+ if pitch == None:
+ x = self.emb_phone(phone)
+ else:
+ x = self.emb_phone(phone) + self.emb_pitch(pitch)
+ x = x * math.sqrt(self.hidden_channels) # [b, t, h]
+ x = self.lrelu(x)
+ x = torch.transpose(x, 1, -1) # [b, h, t]
+ x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+ x.dtype
+ )
+ x = self.encoder(x * x_mask, x_mask)
+ stats = self.proj(x) * x_mask
+
+ m, logs = torch.split(stats, self.out_channels, dim=1)
+ return m, logs, x_mask
+
+
+class TextEncoder768(nn.Module):
+ def __init__(
+ self,
+ out_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ f0=True,
+ ):
+ super().__init__()
+ self.out_channels = out_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.emb_phone = nn.Linear(768, hidden_channels)
+ self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+ if f0 == True:
+ self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
+ self.encoder = attentions.Encoder(
+ hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+ )
+ self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+ def forward(self, phone, pitch, lengths):
+ if pitch == None:
+ x = self.emb_phone(phone)
+ else:
+ x = self.emb_phone(phone) + self.emb_pitch(pitch)
+ x = x * math.sqrt(self.hidden_channels) # [b, t, h]
+ x = self.lrelu(x)
+ x = torch.transpose(x, 1, -1) # [b, h, t]
+ x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+ x.dtype
+ )
+ x = self.encoder(x * x_mask, x_mask)
+ stats = self.proj(x) * x_mask
+
+ m, logs = torch.split(stats, self.out_channels, dim=1)
+ return m, logs, x_mask
+
+
+class ResidualCouplingBlock(nn.Module):
+ def __init__(
+ self,
+ channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ n_flows=4,
+ gin_channels=0,
+ ):
+ super().__init__()
+ self.channels = channels
+ self.hidden_channels = hidden_channels
+ self.kernel_size = kernel_size
+ self.dilation_rate = dilation_rate
+ self.n_layers = n_layers
+ self.n_flows = n_flows
+ self.gin_channels = gin_channels
+
+ self.flows = nn.ModuleList()
+ for i in range(n_flows):
+ self.flows.append(
+ modules.ResidualCouplingLayer(
+ channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=gin_channels,
+ mean_only=True,
+ )
+ )
+ self.flows.append(modules.Flip())
+
+ def forward(self, x, x_mask, g=None, reverse=False):
+ if not reverse:
+ for flow in self.flows:
+ x, _ = flow(x, x_mask, g=g, reverse=reverse)
+ else:
+ for flow in reversed(self.flows):
+ x = flow(x, x_mask, g=g, reverse=reverse)
+ return x
+
+ def remove_weight_norm(self):
+ for i in range(self.n_flows):
+ self.flows[i * 2].remove_weight_norm()
+
+
+class PosteriorEncoder(nn.Module):
+ def __init__(
+ self,
+ in_channels,
+ out_channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=0,
+ ):
+ super().__init__()
+ self.in_channels = in_channels
+ self.out_channels = out_channels
+ self.hidden_channels = hidden_channels
+ self.kernel_size = kernel_size
+ self.dilation_rate = dilation_rate
+ self.n_layers = n_layers
+ self.gin_channels = gin_channels
+
+ self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
+ self.enc = modules.WN(
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=gin_channels,
+ )
+ self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+ def forward(self, x, x_lengths, g=None):
+ x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
+ x.dtype
+ )
+ x = self.pre(x) * x_mask
+ x = self.enc(x, x_mask, g=g)
+ stats = self.proj(x) * x_mask
+ m, logs = torch.split(stats, self.out_channels, dim=1)
+ z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
+ return z, m, logs, x_mask
+
+ def remove_weight_norm(self):
+ self.enc.remove_weight_norm()
+
+
+class Generator(torch.nn.Module):
+ def __init__(
+ self,
+ initial_channel,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=0,
+ ):
+ super(Generator, self).__init__()
+ self.num_kernels = len(resblock_kernel_sizes)
+ self.num_upsamples = len(upsample_rates)
+ self.conv_pre = Conv1d(
+ initial_channel, upsample_initial_channel, 7, 1, padding=3
+ )
+ resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+ self.ups = nn.ModuleList()
+ for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+ self.ups.append(
+ weight_norm(
+ ConvTranspose1d(
+ upsample_initial_channel // (2**i),
+ upsample_initial_channel // (2 ** (i + 1)),
+ k,
+ u,
+ padding=(k - u) // 2,
+ )
+ )
+ )
+
+ self.resblocks = nn.ModuleList()
+ for i in range(len(self.ups)):
+ ch = upsample_initial_channel // (2 ** (i + 1))
+ for j, (k, d) in enumerate(
+ zip(resblock_kernel_sizes, resblock_dilation_sizes)
+ ):
+ self.resblocks.append(resblock(ch, k, d))
+
+ self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+ self.ups.apply(init_weights)
+
+ if gin_channels != 0:
+ self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+ def forward(self, x, g=None):
+ x = self.conv_pre(x)
+ if g is not None:
+ x = x + self.cond(g)
+
+ for i in range(self.num_upsamples):
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ x = self.ups[i](x)
+ xs = None
+ for j in range(self.num_kernels):
+ if xs is None:
+ xs = self.resblocks[i * self.num_kernels + j](x)
+ else:
+ xs += self.resblocks[i * self.num_kernels + j](x)
+ x = xs / self.num_kernels
+ x = F.leaky_relu(x)
+ x = self.conv_post(x)
+ x = torch.tanh(x)
+
+ return x
+
+ def remove_weight_norm(self):
+ for l in self.ups:
+ remove_weight_norm(l)
+ for l in self.resblocks:
+ l.remove_weight_norm()
+
+
+class SineGen(torch.nn.Module):
+ """Definition of sine generator
+ SineGen(samp_rate, harmonic_num = 0,
+ sine_amp = 0.1, noise_std = 0.003,
+ voiced_threshold = 0,
+ flag_for_pulse=False)
+ samp_rate: sampling rate in Hz
+ harmonic_num: number of harmonic overtones (default 0)
+ sine_amp: amplitude of sine-wavefrom (default 0.1)
+ noise_std: std of Gaussian noise (default 0.003)
+ voiced_thoreshold: F0 threshold for U/V classification (default 0)
+ flag_for_pulse: this SinGen is used inside PulseGen (default False)
+ Note: when flag_for_pulse is True, the first time step of a voiced
+ segment is always sin(np.pi) or cos(0)
+ """
+
+ def __init__(
+ self,
+ samp_rate,
+ harmonic_num=0,
+ sine_amp=0.1,
+ noise_std=0.003,
+ voiced_threshold=0,
+ flag_for_pulse=False,
+ ):
+ super(SineGen, self).__init__()
+ self.sine_amp = sine_amp
+ self.noise_std = noise_std
+ self.harmonic_num = harmonic_num
+ self.dim = self.harmonic_num + 1
+ self.sampling_rate = samp_rate
+ self.voiced_threshold = voiced_threshold
+
+ def _f02uv(self, f0):
+ # generate uv signal
+ uv = torch.ones_like(f0)
+ uv = uv * (f0 > self.voiced_threshold)
+ return uv
+
+ def forward(self, f0, upp):
+ """sine_tensor, uv = forward(f0)
+ input F0: tensor(batchsize=1, length, dim=1)
+ f0 for unvoiced steps should be 0
+ output sine_tensor: tensor(batchsize=1, length, dim)
+ output uv: tensor(batchsize=1, length, 1)
+ """
+ with torch.no_grad():
+ f0 = f0[:, None].transpose(1, 2)
+ f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
+ # fundamental component
+ f0_buf[:, :, 0] = f0[:, :, 0]
+ for idx in np.arange(self.harmonic_num):
+ f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (
+ idx + 2
+ ) # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
+ rad_values = (f0_buf / self.sampling_rate) % 1 ###%1意味着n_har的乘积无法后处理优化
+ rand_ini = torch.rand(
+ f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device
+ )
+ rand_ini[:, 0] = 0
+ rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
+ tmp_over_one = torch.cumsum(rad_values, 1) # % 1 #####%1意味着后面的cumsum无法再优化
+ tmp_over_one *= upp
+ tmp_over_one = F.interpolate(
+ tmp_over_one.transpose(2, 1),
+ scale_factor=upp,
+ mode="linear",
+ align_corners=True,
+ ).transpose(2, 1)
+ rad_values = F.interpolate(
+ rad_values.transpose(2, 1), scale_factor=upp, mode="nearest"
+ ).transpose(
+ 2, 1
+ ) #######
+ tmp_over_one %= 1
+ tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
+ cumsum_shift = torch.zeros_like(rad_values)
+ cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
+ sine_waves = torch.sin(
+ torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * np.pi
+ )
+ sine_waves = sine_waves * self.sine_amp
+ uv = self._f02uv(f0)
+ uv = F.interpolate(
+ uv.transpose(2, 1), scale_factor=upp, mode="nearest"
+ ).transpose(2, 1)
+ noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
+ noise = noise_amp * torch.randn_like(sine_waves)
+ sine_waves = sine_waves * uv + noise
+ return sine_waves, uv, noise
+
+
+class SourceModuleHnNSF(torch.nn.Module):
+ """SourceModule for hn-nsf
+ SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
+ add_noise_std=0.003, voiced_threshod=0)
+ sampling_rate: sampling_rate in Hz
+ harmonic_num: number of harmonic above F0 (default: 0)
+ sine_amp: amplitude of sine source signal (default: 0.1)
+ add_noise_std: std of additive Gaussian noise (default: 0.003)
+ note that amplitude of noise in unvoiced is decided
+ by sine_amp
+ voiced_threshold: threhold to set U/V given F0 (default: 0)
+ Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
+ F0_sampled (batchsize, length, 1)
+ Sine_source (batchsize, length, 1)
+ noise_source (batchsize, length 1)
+ uv (batchsize, length, 1)
+ """
+
+ def __init__(
+ self,
+ sampling_rate,
+ harmonic_num=0,
+ sine_amp=0.1,
+ add_noise_std=0.003,
+ voiced_threshod=0,
+ is_half=True,
+ ):
+ super(SourceModuleHnNSF, self).__init__()
+
+ self.sine_amp = sine_amp
+ self.noise_std = add_noise_std
+ self.is_half = is_half
+ # to produce sine waveforms
+ self.l_sin_gen = SineGen(
+ sampling_rate, harmonic_num, sine_amp, add_noise_std, voiced_threshod
+ )
+
+ # to merge source harmonics into a single excitation
+ self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
+ self.l_tanh = torch.nn.Tanh()
+
+ def forward(self, x, upp=None):
+ sine_wavs, uv, _ = self.l_sin_gen(x, upp)
+ if self.is_half:
+ sine_wavs = sine_wavs.half()
+ sine_merge = self.l_tanh(self.l_linear(sine_wavs))
+ return sine_merge, None, None # noise, uv
+
+
+class GeneratorNSF(torch.nn.Module):
+ def __init__(
+ self,
+ initial_channel,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels,
+ sr,
+ is_half=False,
+ ):
+ super(GeneratorNSF, self).__init__()
+ self.num_kernels = len(resblock_kernel_sizes)
+ self.num_upsamples = len(upsample_rates)
+
+ self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(upsample_rates))
+ self.m_source = SourceModuleHnNSF(
+ sampling_rate=sr, harmonic_num=0, is_half=is_half
+ )
+ self.noise_convs = nn.ModuleList()
+ self.conv_pre = Conv1d(
+ initial_channel, upsample_initial_channel, 7, 1, padding=3
+ )
+ resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+ self.ups = nn.ModuleList()
+ for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+ c_cur = upsample_initial_channel // (2 ** (i + 1))
+ self.ups.append(
+ weight_norm(
+ ConvTranspose1d(
+ upsample_initial_channel // (2**i),
+ upsample_initial_channel // (2 ** (i + 1)),
+ k,
+ u,
+ padding=(k - u) // 2,
+ )
+ )
+ )
+ if i + 1 < len(upsample_rates):
+ stride_f0 = np.prod(upsample_rates[i + 1 :])
+ self.noise_convs.append(
+ Conv1d(
+ 1,
+ c_cur,
+ kernel_size=stride_f0 * 2,
+ stride=stride_f0,
+ padding=stride_f0 // 2,
+ )
+ )
+ else:
+ self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
+
+ self.resblocks = nn.ModuleList()
+ for i in range(len(self.ups)):
+ ch = upsample_initial_channel // (2 ** (i + 1))
+ for j, (k, d) in enumerate(
+ zip(resblock_kernel_sizes, resblock_dilation_sizes)
+ ):
+ self.resblocks.append(resblock(ch, k, d))
+
+ self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+ self.ups.apply(init_weights)
+
+ if gin_channels != 0:
+ self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+ self.upp = np.prod(upsample_rates)
+
+ def forward(self, x, f0, g=None):
+ har_source, noi_source, uv = self.m_source(f0, self.upp)
+ har_source = har_source.transpose(1, 2)
+ x = self.conv_pre(x)
+ if g is not None:
+ x = x + self.cond(g)
+
+ for i in range(self.num_upsamples):
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ x = self.ups[i](x)
+ x_source = self.noise_convs[i](har_source)
+ x = x + x_source
+ xs = None
+ for j in range(self.num_kernels):
+ if xs is None:
+ xs = self.resblocks[i * self.num_kernels + j](x)
+ else:
+ xs += self.resblocks[i * self.num_kernels + j](x)
+ x = xs / self.num_kernels
+ x = F.leaky_relu(x)
+ x = self.conv_post(x)
+ x = torch.tanh(x)
+ return x
+
+ def remove_weight_norm(self):
+ for l in self.ups:
+ remove_weight_norm(l)
+ for l in self.resblocks:
+ l.remove_weight_norm()
+
+
+sr2sr = {
+ "32k": 32000,
+ "40k": 40000,
+ "48k": 48000,
+}
+
+
+class SynthesizerTrnMs256NSFsid(nn.Module):
+ def __init__(
+ self,
+ spec_channels,
+ segment_size,
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ spk_embed_dim,
+ gin_channels,
+ sr,
+ **kwargs
+ ):
+ super().__init__()
+ if type(sr) == type("strr"):
+ sr = sr2sr[sr]
+ self.spec_channels = spec_channels
+ self.inter_channels = inter_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.resblock = resblock
+ self.resblock_kernel_sizes = resblock_kernel_sizes
+ self.resblock_dilation_sizes = resblock_dilation_sizes
+ self.upsample_rates = upsample_rates
+ self.upsample_initial_channel = upsample_initial_channel
+ self.upsample_kernel_sizes = upsample_kernel_sizes
+ self.segment_size = segment_size
+ self.gin_channels = gin_channels
+ # self.hop_length = hop_length#
+ self.spk_embed_dim = spk_embed_dim
+ self.enc_p = TextEncoder256(
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ )
+ self.dec = GeneratorNSF(
+ inter_channels,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=gin_channels,
+ sr=sr,
+ is_half=kwargs["is_half"],
+ )
+ self.enc_q = PosteriorEncoder(
+ spec_channels,
+ inter_channels,
+ hidden_channels,
+ 5,
+ 1,
+ 16,
+ gin_channels=gin_channels,
+ )
+ self.flow = ResidualCouplingBlock(
+ inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+ )
+ self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+ print("gin_channels:", gin_channels, "self.spk_embed_dim:", self.spk_embed_dim)
+
+ def remove_weight_norm(self):
+ self.dec.remove_weight_norm()
+ self.flow.remove_weight_norm()
+ self.enc_q.remove_weight_norm()
+
+ def forward(
+ self, phone, phone_lengths, pitch, pitchf, y, y_lengths, ds
+ ): # 这里ds是id，[bs,1]
+ # print(1,pitch.shape)#[bs,t]
+ g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
+ m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+ z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+ z_p = self.flow(z, y_mask, g=g)
+ z_slice, ids_slice = commons.rand_slice_segments(
+ z, y_lengths, self.segment_size
+ )
+ # print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
+ pitchf = commons.slice_segments2(pitchf, ids_slice, self.segment_size)
+ # print(-2,pitchf.shape,z_slice.shape)
+ o = self.dec(z_slice, pitchf, g=g)
+ return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+ def infer(self, phone, phone_lengths, pitch, nsff0, sid, max_len=None):
+ g = self.emb_g(sid).unsqueeze(-1)
+ m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+ z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+ z = self.flow(z_p, x_mask, g=g, reverse=True)
+ o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
+ return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class SynthesizerTrnMs768NSFsid(nn.Module):
+ def __init__(
+ self,
+ spec_channels,
+ segment_size,
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ spk_embed_dim,
+ gin_channels,
+ sr,
+ **kwargs
+ ):
+ super().__init__()
+ if type(sr) == type("strr"):
+ sr = sr2sr[sr]
+ self.spec_channels = spec_channels
+ self.inter_channels = inter_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.resblock = resblock
+ self.resblock_kernel_sizes = resblock_kernel_sizes
+ self.resblock_dilation_sizes = resblock_dilation_sizes
+ self.upsample_rates = upsample_rates
+ self.upsample_initial_channel = upsample_initial_channel
+ self.upsample_kernel_sizes = upsample_kernel_sizes
+ self.segment_size = segment_size
+ self.gin_channels = gin_channels
+ # self.hop_length = hop_length#
+ self.spk_embed_dim = spk_embed_dim
+ self.enc_p = TextEncoder768(
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ )
+ self.dec = GeneratorNSF(
+ inter_channels,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=gin_channels,
+ sr=sr,
+ is_half=kwargs["is_half"],
+ )
+ self.enc_q = PosteriorEncoder(
+ spec_channels,
+ inter_channels,
+ hidden_channels,
+ 5,
+ 1,
+ 16,
+ gin_channels=gin_channels,
+ )
+ self.flow = ResidualCouplingBlock(
+ inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+ )
+ self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+ print("gin_channels:", gin_channels, "self.spk_embed_dim:", self.spk_embed_dim)
+
+ def remove_weight_norm(self):
+ self.dec.remove_weight_norm()
+ self.flow.remove_weight_norm()
+ self.enc_q.remove_weight_norm()
+
+ def forward(
+ self, phone, phone_lengths, pitch, pitchf, y, y_lengths, ds
+ ): # 这里ds是id，[bs,1]
+ # print(1,pitch.shape)#[bs,t]
+ g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
+ m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+ z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+ z_p = self.flow(z, y_mask, g=g)
+ z_slice, ids_slice = commons.rand_slice_segments(
+ z, y_lengths, self.segment_size
+ )
+ # print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
+ pitchf = commons.slice_segments2(pitchf, ids_slice, self.segment_size)
+ # print(-2,pitchf.shape,z_slice.shape)
+ o = self.dec(z_slice, pitchf, g=g)
+ return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+ def infer(self, phone, phone_lengths, pitch, nsff0, sid, max_len=None):
+ g = self.emb_g(sid).unsqueeze(-1)
+ m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+ z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+ z = self.flow(z_p, x_mask, g=g, reverse=True)
+ o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
+ return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class SynthesizerTrnMs256NSFsid_nono(nn.Module):
+ def __init__(
+ self,
+ spec_channels,
+ segment_size,
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ spk_embed_dim,
+ gin_channels,
+ sr=None,
+ **kwargs
+ ):
+ super().__init__()
+ self.spec_channels = spec_channels
+ self.inter_channels = inter_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.resblock = resblock
+ self.resblock_kernel_sizes = resblock_kernel_sizes
+ self.resblock_dilation_sizes = resblock_dilation_sizes
+ self.upsample_rates = upsample_rates
+ self.upsample_initial_channel = upsample_initial_channel
+ self.upsample_kernel_sizes = upsample_kernel_sizes
+ self.segment_size = segment_size
+ self.gin_channels = gin_channels
+ # self.hop_length = hop_length#
+ self.spk_embed_dim = spk_embed_dim
+ self.enc_p = TextEncoder256(
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ f0=False,
+ )
+ self.dec = Generator(
+ inter_channels,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=gin_channels,
+ )
+ self.enc_q = PosteriorEncoder(
+ spec_channels,
+ inter_channels,
+ hidden_channels,
+ 5,
+ 1,
+ 16,
+ gin_channels=gin_channels,
+ )
+ self.flow = ResidualCouplingBlock(
+ inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+ )
+ self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+ print("gin_channels:", gin_channels, "self.spk_embed_dim:", self.spk_embed_dim)
+
+ def remove_weight_norm(self):
+ self.dec.remove_weight_norm()
+ self.flow.remove_weight_norm()
+ self.enc_q.remove_weight_norm()
+
+ def forward(self, phone, phone_lengths, y, y_lengths, ds): # 这里ds是id，[bs,1]
+ g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
+ m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+ z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+ z_p = self.flow(z, y_mask, g=g)
+ z_slice, ids_slice = commons.rand_slice_segments(
+ z, y_lengths, self.segment_size
+ )
+ o = self.dec(z_slice, g=g)
+ return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+ def infer(self, phone, phone_lengths, sid, max_len=None):
+ g = self.emb_g(sid).unsqueeze(-1)
+ m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+ z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+ z = self.flow(z_p, x_mask, g=g, reverse=True)
+ o = self.dec((z * x_mask)[:, :, :max_len], g=g)
+ return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class SynthesizerTrnMs768NSFsid_nono(nn.Module):
+ def __init__(
+ self,
+ spec_channels,
+ segment_size,
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ spk_embed_dim,
+ gin_channels,
+ sr=None,
+ **kwargs
+ ):
+ super().__init__()
+ self.spec_channels = spec_channels
+ self.inter_channels = inter_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.resblock = resblock
+ self.resblock_kernel_sizes = resblock_kernel_sizes
+ self.resblock_dilation_sizes = resblock_dilation_sizes
+ self.upsample_rates = upsample_rates
+ self.upsample_initial_channel = upsample_initial_channel
+ self.upsample_kernel_sizes = upsample_kernel_sizes
+ self.segment_size = segment_size
+ self.gin_channels = gin_channels
+ # self.hop_length = hop_length#
+ self.spk_embed_dim = spk_embed_dim
+ self.enc_p = TextEncoder768(
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ f0=False,
+ )
+ self.dec = Generator(
+ inter_channels,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=gin_channels,
+ )
+ self.enc_q = PosteriorEncoder(
+ spec_channels,
+ inter_channels,
+ hidden_channels,
+ 5,
+ 1,
+ 16,
+ gin_channels=gin_channels,
+ )
+ self.flow = ResidualCouplingBlock(
+ inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+ )
+ self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+ print("gin_channels:", gin_channels, "self.spk_embed_dim:", self.spk_embed_dim)
+
+ def remove_weight_norm(self):
+ self.dec.remove_weight_norm()
+ self.flow.remove_weight_norm()
+ self.enc_q.remove_weight_norm()
+
+ def forward(self, phone, phone_lengths, y, y_lengths, ds): # 这里ds是id，[bs,1]
+ g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
+ m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+ z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+ z_p = self.flow(z, y_mask, g=g)
+ z_slice, ids_slice = commons.rand_slice_segments(
+ z, y_lengths, self.segment_size
+ )
+ o = self.dec(z_slice, g=g)
+ return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+ def infer(self, phone, phone_lengths, sid, max_len=None):
+ g = self.emb_g(sid).unsqueeze(-1)
+ m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+ z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+ z = self.flow(z_p, x_mask, g=g, reverse=True)
+ o = self.dec((z * x_mask)[:, :, :max_len], g=g)
+ return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class MultiPeriodDiscriminator(torch.nn.Module):
+ def __init__(self, use_spectral_norm=False):
+ super(MultiPeriodDiscriminator, self).__init__()
+ periods = [2, 3, 5, 7, 11, 17]
+ # periods = [3, 5, 7, 11, 17, 23, 37]
+
+ discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+ discs = discs + [
+ DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+ ]
+ self.discriminators = nn.ModuleList(discs)
+
+ def forward(self, y, y_hat):
+ y_d_rs = [] #
+ y_d_gs = []
+ fmap_rs = []
+ fmap_gs = []
+ for i, d in enumerate(self.discriminators):
+ y_d_r, fmap_r = d(y)
+ y_d_g, fmap_g = d(y_hat)
+ # for j in range(len(fmap_r)):
+ # print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+ y_d_rs.append(y_d_r)
+ y_d_gs.append(y_d_g)
+ fmap_rs.append(fmap_r)
+ fmap_gs.append(fmap_g)
+
+ return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class MultiPeriodDiscriminatorV2(torch.nn.Module):
+ def __init__(self, use_spectral_norm=False):
+ super(MultiPeriodDiscriminatorV2, self).__init__()
+ # periods = [2, 3, 5, 7, 11, 17]
+ periods = [2, 3, 5, 7, 11, 17, 23, 37]
+
+ discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+ discs = discs + [
+ DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+ ]
+ self.discriminators = nn.ModuleList(discs)
+
+ def forward(self, y, y_hat):
+ y_d_rs = [] #
+ y_d_gs = []
+ fmap_rs = []
+ fmap_gs = []
+ for i, d in enumerate(self.discriminators):
+ y_d_r, fmap_r = d(y)
+ y_d_g, fmap_g = d(y_hat)
+ # for j in range(len(fmap_r)):
+ # print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+ y_d_rs.append(y_d_r)
+ y_d_gs.append(y_d_g)
+ fmap_rs.append(fmap_r)
+ fmap_gs.append(fmap_g)
+
+ return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class DiscriminatorS(torch.nn.Module):
+ def __init__(self, use_spectral_norm=False):
+ super(DiscriminatorS, self).__init__()
+ norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+ self.convs = nn.ModuleList(
+ [
+ norm_f(Conv1d(1, 16, 15, 1, padding=7)),
+ norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
+ norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
+ norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
+ norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
+ norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
+ ]
+ )
+ self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
+
+ def forward(self, x):
+ fmap = []
+
+ for l in self.convs:
+ x = l(x)
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ fmap.append(x)
+ x = self.conv_post(x)
+ fmap.append(x)
+ x = torch.flatten(x, 1, -1)
+
+ return x, fmap
+
+
+class DiscriminatorP(torch.nn.Module):
+ def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
+ super(DiscriminatorP, self).__init__()
+ self.period = period
+ self.use_spectral_norm = use_spectral_norm
+ norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+ self.convs = nn.ModuleList(
+ [
+ norm_f(
+ Conv2d(
+ 1,
+ 32,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 32,
+ 128,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 128,
+ 512,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 512,
+ 1024,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 1024,
+ 1024,
+ (kernel_size, 1),
+ 1,
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ ]
+ )
+ self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
+
+ def forward(self, x):
+ fmap = []
+
+ # 1d to 2d
+ b, c, t = x.shape
+ if t % self.period != 0: # pad first
+ n_pad = self.period - (t % self.period)
+ x = F.pad(x, (0, n_pad), "reflect")
+ t = t + n_pad
+ x = x.view(b, c, t // self.period, self.period)
+
+ for l in self.convs:
+ x = l(x)
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ fmap.append(x)
+ x = self.conv_post(x)
+ fmap.append(x)
+ x = torch.flatten(x, 1, -1)
+
+ return x, fmap
diff --git a/infer_pack/models_onnx.py b/infer_pack/models_onnx.py
new file mode 100644
index 0000000000000000000000000000000000000000..b945eac8e59aac38fbd166da49eda01e2b8f4bd4
--- /dev/null
+++ b/infer_pack/models_onnx.py
@@ -0,0 +1,818 @@
+import math, pdb, os
+from time import time as ttime
+import torch
+from torch import nn
+from torch.nn import functional as F
+from infer_pack import modules
+from infer_pack import attentions
+from infer_pack import commons
+from infer_pack.commons import init_weights, get_padding
+from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
+from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
+from infer_pack.commons import init_weights
+import numpy as np
+from infer_pack import commons
+
+
+class TextEncoder256(nn.Module):
+ def __init__(
+ self,
+ out_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ f0=True,
+ ):
+ super().__init__()
+ self.out_channels = out_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.emb_phone = nn.Linear(256, hidden_channels)
+ self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+ if f0 == True:
+ self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
+ self.encoder = attentions.Encoder(
+ hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+ )
+ self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+ def forward(self, phone, pitch, lengths):
+ if pitch == None:
+ x = self.emb_phone(phone)
+ else:
+ x = self.emb_phone(phone) + self.emb_pitch(pitch)
+ x = x * math.sqrt(self.hidden_channels) # [b, t, h]
+ x = self.lrelu(x)
+ x = torch.transpose(x, 1, -1) # [b, h, t]
+ x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+ x.dtype
+ )
+ x = self.encoder(x * x_mask, x_mask)
+ stats = self.proj(x) * x_mask
+
+ m, logs = torch.split(stats, self.out_channels, dim=1)
+ return m, logs, x_mask
+
+
+class TextEncoder768(nn.Module):
+ def __init__(
+ self,
+ out_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ f0=True,
+ ):
+ super().__init__()
+ self.out_channels = out_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.emb_phone = nn.Linear(768, hidden_channels)
+ self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+ if f0 == True:
+ self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
+ self.encoder = attentions.Encoder(
+ hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+ )
+ self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+ def forward(self, phone, pitch, lengths):
+ if pitch == None:
+ x = self.emb_phone(phone)
+ else:
+ x = self.emb_phone(phone) + self.emb_pitch(pitch)
+ x = x * math.sqrt(self.hidden_channels) # [b, t, h]
+ x = self.lrelu(x)
+ x = torch.transpose(x, 1, -1) # [b, h, t]
+ x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+ x.dtype
+ )
+ x = self.encoder(x * x_mask, x_mask)
+ stats = self.proj(x) * x_mask
+
+ m, logs = torch.split(stats, self.out_channels, dim=1)
+ return m, logs, x_mask
+
+
+class ResidualCouplingBlock(nn.Module):
+ def __init__(
+ self,
+ channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ n_flows=4,
+ gin_channels=0,
+ ):
+ super().__init__()
+ self.channels = channels
+ self.hidden_channels = hidden_channels
+ self.kernel_size = kernel_size
+ self.dilation_rate = dilation_rate
+ self.n_layers = n_layers
+ self.n_flows = n_flows
+ self.gin_channels = gin_channels
+
+ self.flows = nn.ModuleList()
+ for i in range(n_flows):
+ self.flows.append(
+ modules.ResidualCouplingLayer(
+ channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=gin_channels,
+ mean_only=True,
+ )
+ )
+ self.flows.append(modules.Flip())
+
+ def forward(self, x, x_mask, g=None, reverse=False):
+ if not reverse:
+ for flow in self.flows:
+ x, _ = flow(x, x_mask, g=g, reverse=reverse)
+ else:
+ for flow in reversed(self.flows):
+ x = flow(x, x_mask, g=g, reverse=reverse)
+ return x
+
+ def remove_weight_norm(self):
+ for i in range(self.n_flows):
+ self.flows[i * 2].remove_weight_norm()
+
+
+class PosteriorEncoder(nn.Module):
+ def __init__(
+ self,
+ in_channels,
+ out_channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=0,
+ ):
+ super().__init__()
+ self.in_channels = in_channels
+ self.out_channels = out_channels
+ self.hidden_channels = hidden_channels
+ self.kernel_size = kernel_size
+ self.dilation_rate = dilation_rate
+ self.n_layers = n_layers
+ self.gin_channels = gin_channels
+
+ self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
+ self.enc = modules.WN(
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=gin_channels,
+ )
+ self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+ def forward(self, x, x_lengths, g=None):
+ x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
+ x.dtype
+ )
+ x = self.pre(x) * x_mask
+ x = self.enc(x, x_mask, g=g)
+ stats = self.proj(x) * x_mask
+ m, logs = torch.split(stats, self.out_channels, dim=1)
+ z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
+ return z, m, logs, x_mask
+
+ def remove_weight_norm(self):
+ self.enc.remove_weight_norm()
+
+
+class Generator(torch.nn.Module):
+ def __init__(
+ self,
+ initial_channel,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=0,
+ ):
+ super(Generator, self).__init__()
+ self.num_kernels = len(resblock_kernel_sizes)
+ self.num_upsamples = len(upsample_rates)
+ self.conv_pre = Conv1d(
+ initial_channel, upsample_initial_channel, 7, 1, padding=3
+ )
+ resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+ self.ups = nn.ModuleList()
+ for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+ self.ups.append(
+ weight_norm(
+ ConvTranspose1d(
+ upsample_initial_channel // (2**i),
+ upsample_initial_channel // (2 ** (i + 1)),
+ k,
+ u,
+ padding=(k - u) // 2,
+ )
+ )
+ )
+
+ self.resblocks = nn.ModuleList()
+ for i in range(len(self.ups)):
+ ch = upsample_initial_channel // (2 ** (i + 1))
+ for j, (k, d) in enumerate(
+ zip(resblock_kernel_sizes, resblock_dilation_sizes)
+ ):
+ self.resblocks.append(resblock(ch, k, d))
+
+ self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+ self.ups.apply(init_weights)
+
+ if gin_channels != 0:
+ self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+ def forward(self, x, g=None):
+ x = self.conv_pre(x)
+ if g is not None:
+ x = x + self.cond(g)
+
+ for i in range(self.num_upsamples):
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ x = self.ups[i](x)
+ xs = None
+ for j in range(self.num_kernels):
+ if xs is None:
+ xs = self.resblocks[i * self.num_kernels + j](x)
+ else:
+ xs += self.resblocks[i * self.num_kernels + j](x)
+ x = xs / self.num_kernels
+ x = F.leaky_relu(x)
+ x = self.conv_post(x)
+ x = torch.tanh(x)
+
+ return x
+
+ def remove_weight_norm(self):
+ for l in self.ups:
+ remove_weight_norm(l)
+ for l in self.resblocks:
+ l.remove_weight_norm()
+
+
+class SineGen(torch.nn.Module):
+ """Definition of sine generator
+ SineGen(samp_rate, harmonic_num = 0,
+ sine_amp = 0.1, noise_std = 0.003,
+ voiced_threshold = 0,
+ flag_for_pulse=False)
+ samp_rate: sampling rate in Hz
+ harmonic_num: number of harmonic overtones (default 0)
+ sine_amp: amplitude of sine-wavefrom (default 0.1)
+ noise_std: std of Gaussian noise (default 0.003)
+ voiced_thoreshold: F0 threshold for U/V classification (default 0)
+ flag_for_pulse: this SinGen is used inside PulseGen (default False)
+ Note: when flag_for_pulse is True, the first time step of a voiced
+ segment is always sin(np.pi) or cos(0)
+ """
+
+ def __init__(
+ self,
+ samp_rate,
+ harmonic_num=0,
+ sine_amp=0.1,
+ noise_std=0.003,
+ voiced_threshold=0,
+ flag_for_pulse=False,
+ ):
+ super(SineGen, self).__init__()
+ self.sine_amp = sine_amp
+ self.noise_std = noise_std
+ self.harmonic_num = harmonic_num
+ self.dim = self.harmonic_num + 1
+ self.sampling_rate = samp_rate
+ self.voiced_threshold = voiced_threshold
+
+ def _f02uv(self, f0):
+ # generate uv signal
+ uv = torch.ones_like(f0)
+ uv = uv * (f0 > self.voiced_threshold)
+ return uv
+
+ def forward(self, f0, upp):
+ """sine_tensor, uv = forward(f0)
+ input F0: tensor(batchsize=1, length, dim=1)
+ f0 for unvoiced steps should be 0
+ output sine_tensor: tensor(batchsize=1, length, dim)
+ output uv: tensor(batchsize=1, length, 1)
+ """
+ with torch.no_grad():
+ f0 = f0[:, None].transpose(1, 2)
+ f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
+ # fundamental component
+ f0_buf[:, :, 0] = f0[:, :, 0]
+ for idx in np.arange(self.harmonic_num):
+ f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (
+ idx + 2
+ ) # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
+ rad_values = (f0_buf / self.sampling_rate) % 1 ###%1意味着n_har的乘积无法后处理优化
+ rand_ini = torch.rand(
+ f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device
+ )
+ rand_ini[:, 0] = 0
+ rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
+ tmp_over_one = torch.cumsum(rad_values, 1) # % 1 #####%1意味着后面的cumsum无法再优化
+ tmp_over_one *= upp
+ tmp_over_one = F.interpolate(
+ tmp_over_one.transpose(2, 1),
+ scale_factor=upp,
+ mode="linear",
+ align_corners=True,
+ ).transpose(2, 1)
+ rad_values = F.interpolate(
+ rad_values.transpose(2, 1), scale_factor=upp, mode="nearest"
+ ).transpose(
+ 2, 1
+ ) #######
+ tmp_over_one %= 1
+ tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
+ cumsum_shift = torch.zeros_like(rad_values)
+ cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
+ sine_waves = torch.sin(
+ torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * np.pi
+ )
+ sine_waves = sine_waves * self.sine_amp
+ uv = self._f02uv(f0)
+ uv = F.interpolate(
+ uv.transpose(2, 1), scale_factor=upp, mode="nearest"
+ ).transpose(2, 1)
+ noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
+ noise = noise_amp * torch.randn_like(sine_waves)
+ sine_waves = sine_waves * uv + noise
+ return sine_waves, uv, noise
+
+
+class SourceModuleHnNSF(torch.nn.Module):
+ """SourceModule for hn-nsf
+ SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
+ add_noise_std=0.003, voiced_threshod=0)
+ sampling_rate: sampling_rate in Hz
+ harmonic_num: number of harmonic above F0 (default: 0)
+ sine_amp: amplitude of sine source signal (default: 0.1)
+ add_noise_std: std of additive Gaussian noise (default: 0.003)
+ note that amplitude of noise in unvoiced is decided
+ by sine_amp
+ voiced_threshold: threhold to set U/V given F0 (default: 0)
+ Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
+ F0_sampled (batchsize, length, 1)
+ Sine_source (batchsize, length, 1)
+ noise_source (batchsize, length 1)
+ uv (batchsize, length, 1)
+ """
+
+ def __init__(
+ self,
+ sampling_rate,
+ harmonic_num=0,
+ sine_amp=0.1,
+ add_noise_std=0.003,
+ voiced_threshod=0,
+ is_half=True,
+ ):
+ super(SourceModuleHnNSF, self).__init__()
+
+ self.sine_amp = sine_amp
+ self.noise_std = add_noise_std
+ self.is_half = is_half
+ # to produce sine waveforms
+ self.l_sin_gen = SineGen(
+ sampling_rate, harmonic_num, sine_amp, add_noise_std, voiced_threshod
+ )
+
+ # to merge source harmonics into a single excitation
+ self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
+ self.l_tanh = torch.nn.Tanh()
+
+ def forward(self, x, upp=None):
+ sine_wavs, uv, _ = self.l_sin_gen(x, upp)
+ if self.is_half:
+ sine_wavs = sine_wavs.half()
+ sine_merge = self.l_tanh(self.l_linear(sine_wavs))
+ return sine_merge, None, None # noise, uv
+
+
+class GeneratorNSF(torch.nn.Module):
+ def __init__(
+ self,
+ initial_channel,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels,
+ sr,
+ is_half=False,
+ ):
+ super(GeneratorNSF, self).__init__()
+ self.num_kernels = len(resblock_kernel_sizes)
+ self.num_upsamples = len(upsample_rates)
+
+ self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(upsample_rates))
+ self.m_source = SourceModuleHnNSF(
+ sampling_rate=sr, harmonic_num=0, is_half=is_half
+ )
+ self.noise_convs = nn.ModuleList()
+ self.conv_pre = Conv1d(
+ initial_channel, upsample_initial_channel, 7, 1, padding=3
+ )
+ resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+ self.ups = nn.ModuleList()
+ for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+ c_cur = upsample_initial_channel // (2 ** (i + 1))
+ self.ups.append(
+ weight_norm(
+ ConvTranspose1d(
+ upsample_initial_channel // (2**i),
+ upsample_initial_channel // (2 ** (i + 1)),
+ k,
+ u,
+ padding=(k - u) // 2,
+ )
+ )
+ )
+ if i + 1 < len(upsample_rates):
+ stride_f0 = np.prod(upsample_rates[i + 1 :])
+ self.noise_convs.append(
+ Conv1d(
+ 1,
+ c_cur,
+ kernel_size=stride_f0 * 2,
+ stride=stride_f0,
+ padding=stride_f0 // 2,
+ )
+ )
+ else:
+ self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
+
+ self.resblocks = nn.ModuleList()
+ for i in range(len(self.ups)):
+ ch = upsample_initial_channel // (2 ** (i + 1))
+ for j, (k, d) in enumerate(
+ zip(resblock_kernel_sizes, resblock_dilation_sizes)
+ ):
+ self.resblocks.append(resblock(ch, k, d))
+
+ self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+ self.ups.apply(init_weights)
+
+ if gin_channels != 0:
+ self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+ self.upp = np.prod(upsample_rates)
+
+ def forward(self, x, f0, g=None):
+ har_source, noi_source, uv = self.m_source(f0, self.upp)
+ har_source = har_source.transpose(1, 2)
+ x = self.conv_pre(x)
+ if g is not None:
+ x = x + self.cond(g)
+
+ for i in range(self.num_upsamples):
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ x = self.ups[i](x)
+ x_source = self.noise_convs[i](har_source)
+ x = x + x_source
+ xs = None
+ for j in range(self.num_kernels):
+ if xs is None:
+ xs = self.resblocks[i * self.num_kernels + j](x)
+ else:
+ xs += self.resblocks[i * self.num_kernels + j](x)
+ x = xs / self.num_kernels
+ x = F.leaky_relu(x)
+ x = self.conv_post(x)
+ x = torch.tanh(x)
+ return x
+
+ def remove_weight_norm(self):
+ for l in self.ups:
+ remove_weight_norm(l)
+ for l in self.resblocks:
+ l.remove_weight_norm()
+
+
+sr2sr = {
+ "32k": 32000,
+ "40k": 40000,
+ "48k": 48000,
+}
+
+
+class SynthesizerTrnMsNSFsidM(nn.Module):
+ def __init__(
+ self,
+ spec_channels,
+ segment_size,
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ spk_embed_dim,
+ gin_channels,
+ sr,
+ **kwargs
+ ):
+ super().__init__()
+ if type(sr) == type("strr"):
+ sr = sr2sr[sr]
+ self.spec_channels = spec_channels
+ self.inter_channels = inter_channels
+ self.hidden_channels = hidden_channels
+ self.filter_channels = filter_channels
+ self.n_heads = n_heads
+ self.n_layers = n_layers
+ self.kernel_size = kernel_size
+ self.p_dropout = p_dropout
+ self.resblock = resblock
+ self.resblock_kernel_sizes = resblock_kernel_sizes
+ self.resblock_dilation_sizes = resblock_dilation_sizes
+ self.upsample_rates = upsample_rates
+ self.upsample_initial_channel = upsample_initial_channel
+ self.upsample_kernel_sizes = upsample_kernel_sizes
+ self.segment_size = segment_size
+ self.gin_channels = gin_channels
+ # self.hop_length = hop_length#
+ self.spk_embed_dim = spk_embed_dim
+ if self.gin_channels == 256:
+ self.enc_p = TextEncoder256(
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ )
+ else:
+ self.enc_p = TextEncoder768(
+ inter_channels,
+ hidden_channels,
+ filter_channels,
+ n_heads,
+ n_layers,
+ kernel_size,
+ p_dropout,
+ )
+ self.dec = GeneratorNSF(
+ inter_channels,
+ resblock,
+ resblock_kernel_sizes,
+ resblock_dilation_sizes,
+ upsample_rates,
+ upsample_initial_channel,
+ upsample_kernel_sizes,
+ gin_channels=gin_channels,
+ sr=sr,
+ is_half=kwargs["is_half"],
+ )
+ self.enc_q = PosteriorEncoder(
+ spec_channels,
+ inter_channels,
+ hidden_channels,
+ 5,
+ 1,
+ 16,
+ gin_channels=gin_channels,
+ )
+ self.flow = ResidualCouplingBlock(
+ inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+ )
+ self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+ self.speaker_map = None
+ print("gin_channels:", gin_channels, "self.spk_embed_dim:", self.spk_embed_dim)
+
+ def remove_weight_norm(self):
+ self.dec.remove_weight_norm()
+ self.flow.remove_weight_norm()
+ self.enc_q.remove_weight_norm()
+
+ def construct_spkmixmap(self, n_speaker):
+ self.speaker_map = torch.zeros((n_speaker, 1, 1, self.gin_channels))
+ for i in range(n_speaker):
+ self.speaker_map[i] = self.emb_g(torch.LongTensor([[i]]))
+ self.speaker_map = self.speaker_map.unsqueeze(0)
+
+ def forward(self, phone, phone_lengths, pitch, nsff0, g, rnd, max_len=None):
+ if self.speaker_map is not None: # [N, S] * [S, B, 1, H]
+ g = g.reshape((g.shape[0], g.shape[1], 1, 1, 1)) # [N, S, B, 1, 1]
+ g = g * self.speaker_map # [N, S, B, 1, H]
+ g = torch.sum(g, dim=1) # [N, 1, B, 1, H]
+ g = g.transpose(0, -1).transpose(0, -2).squeeze(0) # [B, H, N]
+ else:
+ g = g.unsqueeze(0)
+ g = self.emb_g(g).transpose(1, 2)
+
+ m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+ z_p = (m_p + torch.exp(logs_p) * rnd) * x_mask
+ z = self.flow(z_p, x_mask, g=g, reverse=True)
+ o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
+ return o
+
+
+class MultiPeriodDiscriminator(torch.nn.Module):
+ def __init__(self, use_spectral_norm=False):
+ super(MultiPeriodDiscriminator, self).__init__()
+ periods = [2, 3, 5, 7, 11, 17]
+ # periods = [3, 5, 7, 11, 17, 23, 37]
+
+ discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+ discs = discs + [
+ DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+ ]
+ self.discriminators = nn.ModuleList(discs)
+
+ def forward(self, y, y_hat):
+ y_d_rs = [] #
+ y_d_gs = []
+ fmap_rs = []
+ fmap_gs = []
+ for i, d in enumerate(self.discriminators):
+ y_d_r, fmap_r = d(y)
+ y_d_g, fmap_g = d(y_hat)
+ # for j in range(len(fmap_r)):
+ # print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+ y_d_rs.append(y_d_r)
+ y_d_gs.append(y_d_g)
+ fmap_rs.append(fmap_r)
+ fmap_gs.append(fmap_g)
+
+ return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class MultiPeriodDiscriminatorV2(torch.nn.Module):
+ def __init__(self, use_spectral_norm=False):
+ super(MultiPeriodDiscriminatorV2, self).__init__()
+ # periods = [2, 3, 5, 7, 11, 17]
+ periods = [2, 3, 5, 7, 11, 17, 23, 37]
+
+ discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+ discs = discs + [
+ DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+ ]
+ self.discriminators = nn.ModuleList(discs)
+
+ def forward(self, y, y_hat):
+ y_d_rs = [] #
+ y_d_gs = []
+ fmap_rs = []
+ fmap_gs = []
+ for i, d in enumerate(self.discriminators):
+ y_d_r, fmap_r = d(y)
+ y_d_g, fmap_g = d(y_hat)
+ # for j in range(len(fmap_r)):
+ # print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+ y_d_rs.append(y_d_r)
+ y_d_gs.append(y_d_g)
+ fmap_rs.append(fmap_r)
+ fmap_gs.append(fmap_g)
+
+ return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class DiscriminatorS(torch.nn.Module):
+ def __init__(self, use_spectral_norm=False):
+ super(DiscriminatorS, self).__init__()
+ norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+ self.convs = nn.ModuleList(
+ [
+ norm_f(Conv1d(1, 16, 15, 1, padding=7)),
+ norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
+ norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
+ norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
+ norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
+ norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
+ ]
+ )
+ self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
+
+ def forward(self, x):
+ fmap = []
+
+ for l in self.convs:
+ x = l(x)
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ fmap.append(x)
+ x = self.conv_post(x)
+ fmap.append(x)
+ x = torch.flatten(x, 1, -1)
+
+ return x, fmap
+
+
+class DiscriminatorP(torch.nn.Module):
+ def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
+ super(DiscriminatorP, self).__init__()
+ self.period = period
+ self.use_spectral_norm = use_spectral_norm
+ norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+ self.convs = nn.ModuleList(
+ [
+ norm_f(
+ Conv2d(
+ 1,
+ 32,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 32,
+ 128,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 128,
+ 512,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 512,
+ 1024,
+ (kernel_size, 1),
+ (stride, 1),
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ norm_f(
+ Conv2d(
+ 1024,
+ 1024,
+ (kernel_size, 1),
+ 1,
+ padding=(get_padding(kernel_size, 1), 0),
+ )
+ ),
+ ]
+ )
+ self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
+
+ def forward(self, x):
+ fmap = []
+
+ # 1d to 2d
+ b, c, t = x.shape
+ if t % self.period != 0: # pad first
+ n_pad = self.period - (t % self.period)
+ x = F.pad(x, (0, n_pad), "reflect")
+ t = t + n_pad
+ x = x.view(b, c, t // self.period, self.period)
+
+ for l in self.convs:
+ x = l(x)
+ x = F.leaky_relu(x, modules.LRELU_SLOPE)
+ fmap.append(x)
+ x = self.conv_post(x)
+ fmap.append(x)
+ x = torch.flatten(x, 1, -1)
+
+ return x, fmap
diff --git a/infer_pack/modules.py b/infer_pack/modules.py
new file mode 100644
index 0000000000000000000000000000000000000000..960481cedad9a6106f2bf0b9e86e82b120f7b33f
--- /dev/null
+++ b/infer_pack/modules.py
@@ -0,0 +1,522 @@
+import copy
+import math
+import numpy as np
+import scipy
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
+from torch.nn.utils import weight_norm, remove_weight_norm
+
+from infer_pack import commons
+from infer_pack.commons import init_weights, get_padding
+from infer_pack.transforms import piecewise_rational_quadratic_transform
+
+
+LRELU_SLOPE = 0.1
+
+
+class LayerNorm(nn.Module):
+ def __init__(self, channels, eps=1e-5):
+ super().__init__()
+ self.channels = channels
+ self.eps = eps
+
+ self.gamma = nn.Parameter(torch.ones(channels))
+ self.beta = nn.Parameter(torch.zeros(channels))
+
+ def forward(self, x):
+ x = x.transpose(1, -1)
+ x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
+ return x.transpose(1, -1)
+
+
+class ConvReluNorm(nn.Module):
+ def __init__(
+ self,
+ in_channels,
+ hidden_channels,
+ out_channels,
+ kernel_size,
+ n_layers,
+ p_dropout,
+ ):
+ super().__init__()
+ self.in_channels = in_channels
+ self.hidden_channels = hidden_channels
+ self.out_channels = out_channels
+ self.kernel_size = kernel_size
+ self.n_layers = n_layers
+ self.p_dropout = p_dropout
+ assert n_layers > 1, "Number of layers should be larger than 0."
+
+ self.conv_layers = nn.ModuleList()
+ self.norm_layers = nn.ModuleList()
+ self.conv_layers.append(
+ nn.Conv1d(
+ in_channels, hidden_channels, kernel_size, padding=kernel_size // 2
+ )
+ )
+ self.norm_layers.append(LayerNorm(hidden_channels))
+ self.relu_drop = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout))
+ for _ in range(n_layers - 1):
+ self.conv_layers.append(
+ nn.Conv1d(
+ hidden_channels,
+ hidden_channels,
+ kernel_size,
+ padding=kernel_size // 2,
+ )
+ )
+ self.norm_layers.append(LayerNorm(hidden_channels))
+ self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
+ self.proj.weight.data.zero_()
+ self.proj.bias.data.zero_()
+
+ def forward(self, x, x_mask):
+ x_org = x
+ for i in range(self.n_layers):
+ x = self.conv_layers[i](x * x_mask)
+ x = self.norm_layers[i](x)
+ x = self.relu_drop(x)
+ x = x_org + self.proj(x)
+ return x * x_mask
+
+
+class DDSConv(nn.Module):
+ """
+ Dialted and Depth-Separable Convolution
+ """
+
+ def __init__(self, channels, kernel_size, n_layers, p_dropout=0.0):
+ super().__init__()
+ self.channels = channels
+ self.kernel_size = kernel_size
+ self.n_layers = n_layers
+ self.p_dropout = p_dropout
+
+ self.drop = nn.Dropout(p_dropout)
+ self.convs_sep = nn.ModuleList()
+ self.convs_1x1 = nn.ModuleList()
+ self.norms_1 = nn.ModuleList()
+ self.norms_2 = nn.ModuleList()
+ for i in range(n_layers):
+ dilation = kernel_size**i
+ padding = (kernel_size * dilation - dilation) // 2
+ self.convs_sep.append(
+ nn.Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ groups=channels,
+ dilation=dilation,
+ padding=padding,
+ )
+ )
+ self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
+ self.norms_1.append(LayerNorm(channels))
+ self.norms_2.append(LayerNorm(channels))
+
+ def forward(self, x, x_mask, g=None):
+ if g is not None:
+ x = x + g
+ for i in range(self.n_layers):
+ y = self.convs_sep[i](x * x_mask)
+ y = self.norms_1[i](y)
+ y = F.gelu(y)
+ y = self.convs_1x1[i](y)
+ y = self.norms_2[i](y)
+ y = F.gelu(y)
+ y = self.drop(y)
+ x = x + y
+ return x * x_mask
+
+
+class WN(torch.nn.Module):
+ def __init__(
+ self,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ gin_channels=0,
+ p_dropout=0,
+ ):
+ super(WN, self).__init__()
+ assert kernel_size % 2 == 1
+ self.hidden_channels = hidden_channels
+ self.kernel_size = (kernel_size,)
+ self.dilation_rate = dilation_rate
+ self.n_layers = n_layers
+ self.gin_channels = gin_channels
+ self.p_dropout = p_dropout
+
+ self.in_layers = torch.nn.ModuleList()
+ self.res_skip_layers = torch.nn.ModuleList()
+ self.drop = nn.Dropout(p_dropout)
+
+ if gin_channels != 0:
+ cond_layer = torch.nn.Conv1d(
+ gin_channels, 2 * hidden_channels * n_layers, 1
+ )
+ self.cond_layer = torch.nn.utils.weight_norm(cond_layer, name="weight")
+
+ for i in range(n_layers):
+ dilation = dilation_rate**i
+ padding = int((kernel_size * dilation - dilation) / 2)
+ in_layer = torch.nn.Conv1d(
+ hidden_channels,
+ 2 * hidden_channels,
+ kernel_size,
+ dilation=dilation,
+ padding=padding,
+ )
+ in_layer = torch.nn.utils.weight_norm(in_layer, name="weight")
+ self.in_layers.append(in_layer)
+
+ # last one is not necessary
+ if i < n_layers - 1:
+ res_skip_channels = 2 * hidden_channels
+ else:
+ res_skip_channels = hidden_channels
+
+ res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
+ res_skip_layer = torch.nn.utils.weight_norm(res_skip_layer, name="weight")
+ self.res_skip_layers.append(res_skip_layer)
+
+ def forward(self, x, x_mask, g=None, **kwargs):
+ output = torch.zeros_like(x)
+ n_channels_tensor = torch.IntTensor([self.hidden_channels])
+
+ if g is not None:
+ g = self.cond_layer(g)
+
+ for i in range(self.n_layers):
+ x_in = self.in_layers[i](x)
+ if g is not None:
+ cond_offset = i * 2 * self.hidden_channels
+ g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
+ else:
+ g_l = torch.zeros_like(x_in)
+
+ acts = commons.fused_add_tanh_sigmoid_multiply(x_in, g_l, n_channels_tensor)
+ acts = self.drop(acts)
+
+ res_skip_acts = self.res_skip_layers[i](acts)
+ if i < self.n_layers - 1:
+ res_acts = res_skip_acts[:, : self.hidden_channels, :]
+ x = (x + res_acts) * x_mask
+ output = output + res_skip_acts[:, self.hidden_channels :, :]
+ else:
+ output = output + res_skip_acts
+ return output * x_mask
+
+ def remove_weight_norm(self):
+ if self.gin_channels != 0:
+ torch.nn.utils.remove_weight_norm(self.cond_layer)
+ for l in self.in_layers:
+ torch.nn.utils.remove_weight_norm(l)
+ for l in self.res_skip_layers:
+ torch.nn.utils.remove_weight_norm(l)
+
+
+class ResBlock1(torch.nn.Module):
+ def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
+ super(ResBlock1, self).__init__()
+ self.convs1 = nn.ModuleList(
+ [
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=dilation[0],
+ padding=get_padding(kernel_size, dilation[0]),
+ )
+ ),
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=dilation[1],
+ padding=get_padding(kernel_size, dilation[1]),
+ )
+ ),
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=dilation[2],
+ padding=get_padding(kernel_size, dilation[2]),
+ )
+ ),
+ ]
+ )
+ self.convs1.apply(init_weights)
+
+ self.convs2 = nn.ModuleList(
+ [
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=1,
+ padding=get_padding(kernel_size, 1),
+ )
+ ),
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=1,
+ padding=get_padding(kernel_size, 1),
+ )
+ ),
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=1,
+ padding=get_padding(kernel_size, 1),
+ )
+ ),
+ ]
+ )
+ self.convs2.apply(init_weights)
+
+ def forward(self, x, x_mask=None):
+ for c1, c2 in zip(self.convs1, self.convs2):
+ xt = F.leaky_relu(x, LRELU_SLOPE)
+ if x_mask is not None:
+ xt = xt * x_mask
+ xt = c1(xt)
+ xt = F.leaky_relu(xt, LRELU_SLOPE)
+ if x_mask is not None:
+ xt = xt * x_mask
+ xt = c2(xt)
+ x = xt + x
+ if x_mask is not None:
+ x = x * x_mask
+ return x
+
+ def remove_weight_norm(self):
+ for l in self.convs1:
+ remove_weight_norm(l)
+ for l in self.convs2:
+ remove_weight_norm(l)
+
+
+class ResBlock2(torch.nn.Module):
+ def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
+ super(ResBlock2, self).__init__()
+ self.convs = nn.ModuleList(
+ [
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=dilation[0],
+ padding=get_padding(kernel_size, dilation[0]),
+ )
+ ),
+ weight_norm(
+ Conv1d(
+ channels,
+ channels,
+ kernel_size,
+ 1,
+ dilation=dilation[1],
+ padding=get_padding(kernel_size, dilation[1]),
+ )
+ ),
+ ]
+ )
+ self.convs.apply(init_weights)
+
+ def forward(self, x, x_mask=None):
+ for c in self.convs:
+ xt = F.leaky_relu(x, LRELU_SLOPE)
+ if x_mask is not None:
+ xt = xt * x_mask
+ xt = c(xt)
+ x = xt + x
+ if x_mask is not None:
+ x = x * x_mask
+ return x
+
+ def remove_weight_norm(self):
+ for l in self.convs:
+ remove_weight_norm(l)
+
+
+class Log(nn.Module):
+ def forward(self, x, x_mask, reverse=False, **kwargs):
+ if not reverse:
+ y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
+ logdet = torch.sum(-y, [1, 2])
+ return y, logdet
+ else:
+ x = torch.exp(x) * x_mask
+ return x
+
+
+class Flip(nn.Module):
+ def forward(self, x, *args, reverse=False, **kwargs):
+ x = torch.flip(x, [1])
+ if not reverse:
+ logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
+ return x, logdet
+ else:
+ return x
+
+
+class ElementwiseAffine(nn.Module):
+ def __init__(self, channels):
+ super().__init__()
+ self.channels = channels
+ self.m = nn.Parameter(torch.zeros(channels, 1))
+ self.logs = nn.Parameter(torch.zeros(channels, 1))
+
+ def forward(self, x, x_mask, reverse=False, **kwargs):
+ if not reverse:
+ y = self.m + torch.exp(self.logs) * x
+ y = y * x_mask
+ logdet = torch.sum(self.logs * x_mask, [1, 2])
+ return y, logdet
+ else:
+ x = (x - self.m) * torch.exp(-self.logs) * x_mask
+ return x
+
+
+class ResidualCouplingLayer(nn.Module):
+ def __init__(
+ self,
+ channels,
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ p_dropout=0,
+ gin_channels=0,
+ mean_only=False,
+ ):
+ assert channels % 2 == 0, "channels should be divisible by 2"
+ super().__init__()
+ self.channels = channels
+ self.hidden_channels = hidden_channels
+ self.kernel_size = kernel_size
+ self.dilation_rate = dilation_rate
+ self.n_layers = n_layers
+ self.half_channels = channels // 2
+ self.mean_only = mean_only
+
+ self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
+ self.enc = WN(
+ hidden_channels,
+ kernel_size,
+ dilation_rate,
+ n_layers,
+ p_dropout=p_dropout,
+ gin_channels=gin_channels,
+ )
+ self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
+ self.post.weight.data.zero_()
+ self.post.bias.data.zero_()
+
+ def forward(self, x, x_mask, g=None, reverse=False):
+ x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
+ h = self.pre(x0) * x_mask
+ h = self.enc(h, x_mask, g=g)
+ stats = self.post(h) * x_mask
+ if not self.mean_only:
+ m, logs = torch.split(stats, [self.half_channels] * 2, 1)
+ else:
+ m = stats
+ logs = torch.zeros_like(m)
+
+ if not reverse:
+ x1 = m + x1 * torch.exp(logs) * x_mask
+ x = torch.cat([x0, x1], 1)
+ logdet = torch.sum(logs, [1, 2])
+ return x, logdet
+ else:
+ x1 = (x1 - m) * torch.exp(-logs) * x_mask
+ x = torch.cat([x0, x1], 1)
+ return x
+
+ def remove_weight_norm(self):
+ self.enc.remove_weight_norm()
+
+
+class ConvFlow(nn.Module):
+ def __init__(
+ self,
+ in_channels,
+ filter_channels,
+ kernel_size,
+ n_layers,
+ num_bins=10,
+ tail_bound=5.0,
+ ):
+ super().__init__()
+ self.in_channels = in_channels
+ self.filter_channels = filter_channels
+ self.kernel_size = kernel_size
+ self.n_layers = n_layers
+ self.num_bins = num_bins
+ self.tail_bound = tail_bound
+ self.half_channels = in_channels // 2
+
+ self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
+ self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.0)
+ self.proj = nn.Conv1d(
+ filter_channels, self.half_channels * (num_bins * 3 - 1), 1
+ )
+ self.proj.weight.data.zero_()
+ self.proj.bias.data.zero_()
+
+ def forward(self, x, x_mask, g=None, reverse=False):
+ x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
+ h = self.pre(x0)
+ h = self.convs(h, x_mask, g=g)
+ h = self.proj(h) * x_mask
+
+ b, c, t = x0.shape
+ h = h.reshape(b, c, -1, t).permute(0, 1, 3, 2) # [b, cx?, t] -> [b, c, t, ?]
+
+ unnormalized_widths = h[..., : self.num_bins] / math.sqrt(self.filter_channels)
+ unnormalized_heights = h[..., self.num_bins : 2 * self.num_bins] / math.sqrt(
+ self.filter_channels
+ )
+ unnormalized_derivatives = h[..., 2 * self.num_bins :]
+
+ x1, logabsdet = piecewise_rational_quadratic_transform(
+ x1,
+ unnormalized_widths,
+ unnormalized_heights,
+ unnormalized_derivatives,
+ inverse=reverse,
+ tails="linear",
+ tail_bound=self.tail_bound,
+ )
+
+ x = torch.cat([x0, x1], 1) * x_mask
+ logdet = torch.sum(logabsdet * x_mask, [1, 2])
+ if not reverse:
+ return x, logdet
+ else:
+ return x
diff --git a/infer_pack/modules/F0Predictor/DioF0Predictor.py b/infer_pack/modules/F0Predictor/DioF0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..eb60d8830714338448be009d1075e3594337db15
--- /dev/null
+++ b/infer_pack/modules/F0Predictor/DioF0Predictor.py
@@ -0,0 +1,90 @@
+from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+import pyworld
+import numpy as np
+
+
+class DioF0Predictor(F0Predictor):
+ def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+ self.hop_length = hop_length
+ self.f0_min = f0_min
+ self.f0_max = f0_max
+ self.sampling_rate = sampling_rate
+
+ def interpolate_f0(self, f0):
+ """
+ 对F0进行插值处理
+ """
+
+ data = np.reshape(f0, (f0.size, 1))
+
+ vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+ vuv_vector[data > 0.0] = 1.0
+ vuv_vector[data <= 0.0] = 0.0
+
+ ip_data = data
+
+ frame_number = data.size
+ last_value = 0.0
+ for i in range(frame_number):
+ if data[i] <= 0.0:
+ j = i + 1
+ for j in range(i + 1, frame_number):
+ if data[j] > 0.0:
+ break
+ if j < frame_number - 1:
+ if last_value > 0.0:
+ step = (data[j] - data[i - 1]) / float(j - i)
+ for k in range(i, j):
+ ip_data[k] = data[i - 1] + step * (k - i + 1)
+ else:
+ for k in range(i, j):
+ ip_data[k] = data[j]
+ else:
+ for k in range(i, frame_number):
+ ip_data[k] = last_value
+ else:
+ ip_data[i] = data[i] # 这里可能存在一个没有必要的拷贝
+ last_value = data[i]
+
+ return ip_data[:, 0], vuv_vector[:, 0]
+
+ def resize_f0(self, x, target_len):
+ source = np.array(x)
+ source[source < 0.001] = np.nan
+ target = np.interp(
+ np.arange(0, len(source) * target_len, len(source)) / target_len,
+ np.arange(0, len(source)),
+ source,
+ )
+ res = np.nan_to_num(target)
+ return res
+
+ def compute_f0(self, wav, p_len=None):
+ if p_len is None:
+ p_len = wav.shape[0] // self.hop_length
+ f0, t = pyworld.dio(
+ wav.astype(np.double),
+ fs=self.sampling_rate,
+ f0_floor=self.f0_min,
+ f0_ceil=self.f0_max,
+ frame_period=1000 * self.hop_length / self.sampling_rate,
+ )
+ f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+ for index, pitch in enumerate(f0):
+ f0[index] = round(pitch, 1)
+ return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
+
+ def compute_f0_uv(self, wav, p_len=None):
+ if p_len is None:
+ p_len = wav.shape[0] // self.hop_length
+ f0, t = pyworld.dio(
+ wav.astype(np.double),
+ fs=self.sampling_rate,
+ f0_floor=self.f0_min,
+ f0_ceil=self.f0_max,
+ frame_period=1000 * self.hop_length / self.sampling_rate,
+ )
+ f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+ for index, pitch in enumerate(f0):
+ f0[index] = round(pitch, 1)
+ return self.interpolate_f0(self.resize_f0(f0, p_len))
diff --git a/infer_pack/modules/F0Predictor/F0Predictor.py b/infer_pack/modules/F0Predictor/F0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..f56e49e7f0e6eab3babf0711cae2933371b9f9cc
--- /dev/null
+++ b/infer_pack/modules/F0Predictor/F0Predictor.py
@@ -0,0 +1,16 @@
+class F0Predictor(object):
+ def compute_f0(self, wav, p_len):
+ """
+ input: wav:[signal_length]
+ p_len:int
+ output: f0:[signal_length//hop_length]
+ """
+ pass
+
+ def compute_f0_uv(self, wav, p_len):
+ """
+ input: wav:[signal_length]
+ p_len:int
+ output: f0:[signal_length//hop_length],uv:[signal_length//hop_length]
+ """
+ pass
diff --git a/infer_pack/modules/F0Predictor/HarvestF0Predictor.py b/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..98d4e98b353008f81bde2c37e7da818763a992c9
--- /dev/null
+++ b/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
@@ -0,0 +1,86 @@
+from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+import pyworld
+import numpy as np
+
+
+class HarvestF0Predictor(F0Predictor):
+ def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+ self.hop_length = hop_length
+ self.f0_min = f0_min
+ self.f0_max = f0_max
+ self.sampling_rate = sampling_rate
+
+ def interpolate_f0(self, f0):
+ """
+ 对F0进行插值处理
+ """
+
+ data = np.reshape(f0, (f0.size, 1))
+
+ vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+ vuv_vector[data > 0.0] = 1.0
+ vuv_vector[data <= 0.0] = 0.0
+
+ ip_data = data
+
+ frame_number = data.size
+ last_value = 0.0
+ for i in range(frame_number):
+ if data[i] <= 0.0:
+ j = i + 1
+ for j in range(i + 1, frame_number):
+ if data[j] > 0.0:
+ break
+ if j < frame_number - 1:
+ if last_value > 0.0:
+ step = (data[j] - data[i - 1]) / float(j - i)
+ for k in range(i, j):
+ ip_data[k] = data[i - 1] + step * (k - i + 1)
+ else:
+ for k in range(i, j):
+ ip_data[k] = data[j]
+ else:
+ for k in range(i, frame_number):
+ ip_data[k] = last_value
+ else:
+ ip_data[i] = data[i] # 这里可能存在一个没有必要的拷贝
+ last_value = data[i]
+
+ return ip_data[:, 0], vuv_vector[:, 0]
+
+ def resize_f0(self, x, target_len):
+ source = np.array(x)
+ source[source < 0.001] = np.nan
+ target = np.interp(
+ np.arange(0, len(source) * target_len, len(source)) / target_len,
+ np.arange(0, len(source)),
+ source,
+ )
+ res = np.nan_to_num(target)
+ return res
+
+ def compute_f0(self, wav, p_len=None):
+ if p_len is None:
+ p_len = wav.shape[0] // self.hop_length
+ f0, t = pyworld.harvest(
+ wav.astype(np.double),
+ fs=self.hop_length,
+ f0_ceil=self.f0_max,
+ f0_floor=self.f0_min,
+ frame_period=1000 * self.hop_length / self.sampling_rate,
+ )
+ f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.fs)
+ return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
+
+ def compute_f0_uv(self, wav, p_len=None):
+ if p_len is None:
+ p_len = wav.shape[0] // self.hop_length
+ f0, t = pyworld.harvest(
+ wav.astype(np.double),
+ fs=self.sampling_rate,
+ f0_floor=self.f0_min,
+ f0_ceil=self.f0_max,
+ frame_period=1000 * self.hop_length / self.sampling_rate,
+ )
+ f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+ return self.interpolate_f0(self.resize_f0(f0, p_len))
diff --git a/infer_pack/modules/F0Predictor/PMF0Predictor.py b/infer_pack/modules/F0Predictor/PMF0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..ab523020325fa3f30676ad20125c6a9f059a9d84
--- /dev/null
+++ b/infer_pack/modules/F0Predictor/PMF0Predictor.py
@@ -0,0 +1,97 @@
+from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+import parselmouth
+import numpy as np
+
+
+class PMF0Predictor(F0Predictor):
+ def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+ self.hop_length = hop_length
+ self.f0_min = f0_min
+ self.f0_max = f0_max
+ self.sampling_rate = sampling_rate
+
+ def interpolate_f0(self, f0):
+ """
+ 对F0进行插值处理
+ """
+
+ data = np.reshape(f0, (f0.size, 1))
+
+ vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+ vuv_vector[data > 0.0] = 1.0
+ vuv_vector[data <= 0.0] = 0.0
+
+ ip_data = data
+
+ frame_number = data.size
+ last_value = 0.0
+ for i in range(frame_number):
+ if data[i] <= 0.0:
+ j = i + 1
+ for j in range(i + 1, frame_number):
+ if data[j] > 0.0:
+ break
+ if j < frame_number - 1:
+ if last_value > 0.0:
+ step = (data[j] - data[i - 1]) / float(j - i)
+ for k in range(i, j):
+ ip_data[k] = data[i - 1] + step * (k - i + 1)
+ else:
+ for k in range(i, j):
+ ip_data[k] = data[j]
+ else:
+ for k in range(i, frame_number):
+ ip_data[k] = last_value
+ else:
+ ip_data[i] = data[i] # 这里可能存在一个没有必要的拷贝
+ last_value = data[i]
+
+ return ip_data[:, 0], vuv_vector[:, 0]
+
+ def compute_f0(self, wav, p_len=None):
+ x = wav
+ if p_len is None:
+ p_len = x.shape[0] // self.hop_length
+ else:
+ assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
+ time_step = self.hop_length / self.sampling_rate * 1000
+ f0 = (
+ parselmouth.Sound(x, self.sampling_rate)
+ .to_pitch_ac(
+ time_step=time_step / 1000,
+ voicing_threshold=0.6,
+ pitch_floor=self.f0_min,
+ pitch_ceiling=self.f0_max,
+ )
+ .selected_array["frequency"]
+ )
+
+ pad_size = (p_len - len(f0) + 1) // 2
+ if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+ f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+ f0, uv = self.interpolate_f0(f0)
+ return f0
+
+ def compute_f0_uv(self, wav, p_len=None):
+ x = wav
+ if p_len is None:
+ p_len = x.shape[0] // self.hop_length
+ else:
+ assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
+ time_step = self.hop_length / self.sampling_rate * 1000
+ f0 = (
+ parselmouth.Sound(x, self.sampling_rate)
+ .to_pitch_ac(
+ time_step=time_step / 1000,
+ voicing_threshold=0.6,
+ pitch_floor=self.f0_min,
+ pitch_ceiling=self.f0_max,
+ )
+ .selected_array["frequency"]
+ )
+
+ pad_size = (p_len - len(f0) + 1) // 2
+ if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+ f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+ f0, uv = self.interpolate_f0(f0)
+ return f0, uv
diff --git a/infer_pack/modules/F0Predictor/__init__.py b/infer_pack/modules/F0Predictor/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/infer_pack/onnx_inference.py b/infer_pack/onnx_inference.py
new file mode 100644
index 0000000000000000000000000000000000000000..322572820dfc75d789e40ce5bbd9415066a03979
--- /dev/null
+++ b/infer_pack/onnx_inference.py
@@ -0,0 +1,139 @@
+import onnxruntime
+import librosa
+import numpy as np
+import soundfile
+
+
+class ContentVec:
+ def __init__(self, vec_path="pretrained/vec-768-layer-12.onnx", device=None):
+ print("load model(s) from {}".format(vec_path))
+ if device == "cpu" or device is None:
+ providers = ["CPUExecutionProvider"]
+ elif device == "cuda":
+ providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+ else:
+ raise RuntimeError("Unsportted Device")
+ self.model = onnxruntime.InferenceSession(vec_path, providers=providers)
+
+ def __call__(self, wav):
+ return self.forward(wav)
+
+ def forward(self, wav):
+ feats = wav
+ if feats.ndim == 2: # double channels
+ feats = feats.mean(-1)
+ assert feats.ndim == 1, feats.ndim
+ feats = np.expand_dims(np.expand_dims(feats, 0), 0)
+ onnx_input = {self.model.get_inputs()[0].name: feats}
+ logits = self.model.run(None, onnx_input)[0]
+ return logits.transpose(0, 2, 1)
+
+
+def get_f0_predictor(f0_predictor, hop_length, sampling_rate, **kargs):
+ if f0_predictor == "pm":
+ from infer_pack.modules.F0Predictor.PMF0Predictor import PMF0Predictor
+
+ f0_predictor_object = PMF0Predictor(
+ hop_length=hop_length, sampling_rate=sampling_rate
+ )
+ elif f0_predictor == "harvest":
+ from infer_pack.modules.F0Predictor.HarvestF0Predictor import HarvestF0Predictor
+
+ f0_predictor_object = HarvestF0Predictor(
+ hop_length=hop_length, sampling_rate=sampling_rate
+ )
+ elif f0_predictor == "dio":
+ from infer_pack.modules.F0Predictor.DioF0Predictor import DioF0Predictor
+
+ f0_predictor_object = DioF0Predictor(
+ hop_length=hop_length, sampling_rate=sampling_rate
+ )
+ else:
+ raise Exception("Unknown f0 predictor")
+ return f0_predictor_object
+
+
+class OnnxRVC:
+ def __init__(
+ self,
+ model_path,
+ sr=40000,
+ hop_size=512,
+ vec_path="vec-768-layer-12",
+ device="cpu",
+ ):
+ vec_path = f"pretrained/{vec_path}.onnx"
+ self.vec_model = ContentVec(vec_path, device)
+ if device == "cpu" or device is None:
+ providers = ["CPUExecutionProvider"]
+ elif device == "cuda":
+ providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+ else:
+ raise RuntimeError("Unsportted Device")
+ self.model = onnxruntime.InferenceSession(model_path, providers=providers)
+ self.sampling_rate = sr
+ self.hop_size = hop_size
+
+ def forward(self, hubert, hubert_length, pitch, pitchf, ds, rnd):
+ onnx_input = {
+ self.model.get_inputs()[0].name: hubert,
+ self.model.get_inputs()[1].name: hubert_length,
+ self.model.get_inputs()[2].name: pitch,
+ self.model.get_inputs()[3].name: pitchf,
+ self.model.get_inputs()[4].name: ds,
+ self.model.get_inputs()[5].name: rnd,
+ }
+ return (self.model.run(None, onnx_input)[0] * 32767).astype(np.int16)
+
+ def inference(
+ self,
+ raw_path,
+ sid,
+ f0_method="dio",
+ f0_up_key=0,
+ pad_time=0.5,
+ cr_threshold=0.02,
+ ):
+ f0_min = 50
+ f0_max = 1100
+ f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+ f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+ f0_predictor = get_f0_predictor(
+ f0_method,
+ hop_length=self.hop_size,
+ sampling_rate=self.sampling_rate,
+ threshold=cr_threshold,
+ )
+ wav, sr = librosa.load(raw_path, sr=self.sampling_rate)
+ org_length = len(wav)
+ if org_length / sr > 50.0:
+ raise RuntimeError("Reached Max Length")
+
+ wav16k = librosa.resample(wav, orig_sr=self.sampling_rate, target_sr=16000)
+ wav16k = wav16k
+
+ hubert = self.vec_model(wav16k)
+ hubert = np.repeat(hubert, 2, axis=2).transpose(0, 2, 1).astype(np.float32)
+ hubert_length = hubert.shape[1]
+
+ pitchf = f0_predictor.compute_f0(wav, hubert_length)
+ pitchf = pitchf * 2 ** (f0_up_key / 12)
+ pitch = pitchf.copy()
+ f0_mel = 1127 * np.log(1 + pitch / 700)
+ f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+ f0_mel_max - f0_mel_min
+ ) + 1
+ f0_mel[f0_mel <= 1] = 1
+ f0_mel[f0_mel > 255] = 255
+ pitch = np.rint(f0_mel).astype(np.int64)
+
+ pitchf = pitchf.reshape(1, len(pitchf)).astype(np.float32)
+ pitch = pitch.reshape(1, len(pitch))
+ ds = np.array([sid]).astype(np.int64)
+
+ rnd = np.random.randn(1, 192, hubert_length).astype(np.float32)
+ hubert_length = np.array([hubert_length]).astype(np.int64)
+
+ out_wav = self.forward(hubert, hubert_length, pitch, pitchf, ds, rnd).squeeze()
+ out_wav = np.pad(out_wav, (0, 2 * self.hop_size), "constant")
+ return out_wav[0:org_length]
diff --git a/infer_pack/transforms.py b/infer_pack/transforms.py
new file mode 100644
index 0000000000000000000000000000000000000000..a11f799e023864ff7082c1f49c0cc18351a13b47
--- /dev/null
+++ b/infer_pack/transforms.py
@@ -0,0 +1,209 @@
+import torch
+from torch.nn import functional as F
+
+import numpy as np
+
+
+DEFAULT_MIN_BIN_WIDTH = 1e-3
+DEFAULT_MIN_BIN_HEIGHT = 1e-3
+DEFAULT_MIN_DERIVATIVE = 1e-3
+
+
+def piecewise_rational_quadratic_transform(
+ inputs,
+ unnormalized_widths,
+ unnormalized_heights,
+ unnormalized_derivatives,
+ inverse=False,
+ tails=None,
+ tail_bound=1.0,
+ min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+ min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+ min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+ if tails is None:
+ spline_fn = rational_quadratic_spline
+ spline_kwargs = {}
+ else:
+ spline_fn = unconstrained_rational_quadratic_spline
+ spline_kwargs = {"tails": tails, "tail_bound": tail_bound}
+
+ outputs, logabsdet = spline_fn(
+ inputs=inputs,
+ unnormalized_widths=unnormalized_widths,
+ unnormalized_heights=unnormalized_heights,
+ unnormalized_derivatives=unnormalized_derivatives,
+ inverse=inverse,
+ min_bin_width=min_bin_width,
+ min_bin_height=min_bin_height,
+ min_derivative=min_derivative,
+ **spline_kwargs
+ )
+ return outputs, logabsdet
+
+
+def searchsorted(bin_locations, inputs, eps=1e-6):
+ bin_locations[..., -1] += eps
+ return torch.sum(inputs[..., None] >= bin_locations, dim=-1) - 1
+
+
+def unconstrained_rational_quadratic_spline(
+ inputs,
+ unnormalized_widths,
+ unnormalized_heights,
+ unnormalized_derivatives,
+ inverse=False,
+ tails="linear",
+ tail_bound=1.0,
+ min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+ min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+ min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+ inside_interval_mask = (inputs >= -tail_bound) & (inputs <= tail_bound)
+ outside_interval_mask = ~inside_interval_mask
+
+ outputs = torch.zeros_like(inputs)
+ logabsdet = torch.zeros_like(inputs)
+
+ if tails == "linear":
+ unnormalized_derivatives = F.pad(unnormalized_derivatives, pad=(1, 1))
+ constant = np.log(np.exp(1 - min_derivative) - 1)
+ unnormalized_derivatives[..., 0] = constant
+ unnormalized_derivatives[..., -1] = constant
+
+ outputs[outside_interval_mask] = inputs[outside_interval_mask]
+ logabsdet[outside_interval_mask] = 0
+ else:
+ raise RuntimeError("{} tails are not implemented.".format(tails))
+
+ (
+ outputs[inside_interval_mask],
+ logabsdet[inside_interval_mask],
+ ) = rational_quadratic_spline(
+ inputs=inputs[inside_interval_mask],
+ unnormalized_widths=unnormalized_widths[inside_interval_mask, :],
+ unnormalized_heights=unnormalized_heights[inside_interval_mask, :],
+ unnormalized_derivatives=unnormalized_derivatives[inside_interval_mask, :],
+ inverse=inverse,
+ left=-tail_bound,
+ right=tail_bound,
+ bottom=-tail_bound,
+ top=tail_bound,
+ min_bin_width=min_bin_width,
+ min_bin_height=min_bin_height,
+ min_derivative=min_derivative,
+ )
+
+ return outputs, logabsdet
+
+
+def rational_quadratic_spline(
+ inputs,
+ unnormalized_widths,
+ unnormalized_heights,
+ unnormalized_derivatives,
+ inverse=False,
+ left=0.0,
+ right=1.0,
+ bottom=0.0,
+ top=1.0,
+ min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+ min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+ min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+ if torch.min(inputs) < left or torch.max(inputs) > right:
+ raise ValueError("Input to a transform is not within its domain")
+
+ num_bins = unnormalized_widths.shape[-1]
+
+ if min_bin_width * num_bins > 1.0:
+ raise ValueError("Minimal bin width too large for the number of bins")
+ if min_bin_height * num_bins > 1.0:
+ raise ValueError("Minimal bin height too large for the number of bins")
+
+ widths = F.softmax(unnormalized_widths, dim=-1)
+ widths = min_bin_width + (1 - min_bin_width * num_bins) * widths
+ cumwidths = torch.cumsum(widths, dim=-1)
+ cumwidths = F.pad(cumwidths, pad=(1, 0), mode="constant", value=0.0)
+ cumwidths = (right - left) * cumwidths + left
+ cumwidths[..., 0] = left
+ cumwidths[..., -1] = right
+ widths = cumwidths[..., 1:] - cumwidths[..., :-1]
+
+ derivatives = min_derivative + F.softplus(unnormalized_derivatives)
+
+ heights = F.softmax(unnormalized_heights, dim=-1)
+ heights = min_bin_height + (1 - min_bin_height * num_bins) * heights
+ cumheights = torch.cumsum(heights, dim=-1)
+ cumheights = F.pad(cumheights, pad=(1, 0), mode="constant", value=0.0)
+ cumheights = (top - bottom) * cumheights + bottom
+ cumheights[..., 0] = bottom
+ cumheights[..., -1] = top
+ heights = cumheights[..., 1:] - cumheights[..., :-1]
+
+ if inverse:
+ bin_idx = searchsorted(cumheights, inputs)[..., None]
+ else:
+ bin_idx = searchsorted(cumwidths, inputs)[..., None]
+
+ input_cumwidths = cumwidths.gather(-1, bin_idx)[..., 0]
+ input_bin_widths = widths.gather(-1, bin_idx)[..., 0]
+
+ input_cumheights = cumheights.gather(-1, bin_idx)[..., 0]
+ delta = heights / widths
+ input_delta = delta.gather(-1, bin_idx)[..., 0]
+
+ input_derivatives = derivatives.gather(-1, bin_idx)[..., 0]
+ input_derivatives_plus_one = derivatives[..., 1:].gather(-1, bin_idx)[..., 0]
+
+ input_heights = heights.gather(-1, bin_idx)[..., 0]
+
+ if inverse:
+ a = (inputs - input_cumheights) * (
+ input_derivatives + input_derivatives_plus_one - 2 * input_delta
+ ) + input_heights * (input_delta - input_derivatives)
+ b = input_heights * input_derivatives - (inputs - input_cumheights) * (
+ input_derivatives + input_derivatives_plus_one - 2 * input_delta
+ )
+ c = -input_delta * (inputs - input_cumheights)
+
+ discriminant = b.pow(2) - 4 * a * c
+ assert (discriminant >= 0).all()
+
+ root = (2 * c) / (-b - torch.sqrt(discriminant))
+ outputs = root * input_bin_widths + input_cumwidths
+
+ theta_one_minus_theta = root * (1 - root)
+ denominator = input_delta + (
+ (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
+ * theta_one_minus_theta
+ )
+ derivative_numerator = input_delta.pow(2) * (
+ input_derivatives_plus_one * root.pow(2)
+ + 2 * input_delta * theta_one_minus_theta
+ + input_derivatives * (1 - root).pow(2)
+ )
+ logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
+
+ return outputs, -logabsdet
+ else:
+ theta = (inputs - input_cumwidths) / input_bin_widths
+ theta_one_minus_theta = theta * (1 - theta)
+
+ numerator = input_heights * (
+ input_delta * theta.pow(2) + input_derivatives * theta_one_minus_theta
+ )
+ denominator = input_delta + (
+ (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
+ * theta_one_minus_theta
+ )
+ outputs = input_cumheights + numerator / denominator
+
+ derivative_numerator = input_delta.pow(2) * (
+ input_derivatives_plus_one * theta.pow(2)
+ + 2 * input_delta * theta_one_minus_theta
+ + input_derivatives * (1 - theta).pow(2)
+ )
+ logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
+
+ return outputs, logabsdet
diff --git a/infer_uvr5.py b/infer_uvr5.py
new file mode 100644
index 0000000000000000000000000000000000000000..884c841dd6179677bd0a6d5f5f639954a206a77e
--- /dev/null
+++ b/infer_uvr5.py
@@ -0,0 +1,363 @@
+import os, sys, torch, warnings, pdb
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+from json import load as ll
+
+warnings.filterwarnings("ignore")
+import librosa
+import importlib
+import numpy as np
+import hashlib, math
+from tqdm import tqdm
+from uvr5_pack.lib_v5 import spec_utils
+from uvr5_pack.utils import _get_name_params, inference
+from uvr5_pack.lib_v5.model_param_init import ModelParameters
+import soundfile as sf
+from uvr5_pack.lib_v5.nets_new import CascadedNet
+from uvr5_pack.lib_v5 import nets_61968KB as nets
+
+
+class _audio_pre_:
+ def __init__(self, agg, model_path, device, is_half):
+ self.model_path = model_path
+ self.device = device
+ self.data = {
+ # Processing Options
+ "postprocess": False,
+ "tta": False,
+ # Constants
+ "window_size": 512,
+ "agg": agg,
+ "high_end_process": "mirroring",
+ }
+ mp = ModelParameters("uvr5_pack/lib_v5/modelparams/4band_v2.json")
+ model = nets.CascadedASPPNet(mp.param["bins"] * 2)
+ cpk = torch.load(model_path, map_location="cpu")
+ model.load_state_dict(cpk)
+ model.eval()
+ if is_half:
+ model = model.half().to(device)
+ else:
+ model = model.to(device)
+
+ self.mp = mp
+ self.model = model
+
+ def _path_audio_(self, music_file, ins_root=None, vocal_root=None, format="flac"):
+ if ins_root is None and vocal_root is None:
+ return "No save root."
+ name = os.path.basename(music_file)
+ if ins_root is not None:
+ os.makedirs(ins_root, exist_ok=True)
+ if vocal_root is not None:
+ os.makedirs(vocal_root, exist_ok=True)
+ X_wave, y_wave, X_spec_s, y_spec_s = {}, {}, {}, {}
+ bands_n = len(self.mp.param["band"])
+ # print(bands_n)
+ for d in range(bands_n, 0, -1):
+ bp = self.mp.param["band"][d]
+ if d == bands_n: # high-end band
+ (
+ X_wave[d],
+ _,
+ ) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
+ music_file,
+ bp["sr"],
+ False,
+ dtype=np.float32,
+ res_type=bp["res_type"],
+ )
+ if X_wave[d].ndim == 1:
+ X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
+ else: # lower bands
+ X_wave[d] = librosa.core.resample(
+ X_wave[d + 1],
+ self.mp.param["band"][d + 1]["sr"],
+ bp["sr"],
+ res_type=bp["res_type"],
+ )
+ # Stft of wave source
+ X_spec_s[d] = spec_utils.wave_to_spectrogram_mt(
+ X_wave[d],
+ bp["hl"],
+ bp["n_fft"],
+ self.mp.param["mid_side"],
+ self.mp.param["mid_side_b2"],
+ self.mp.param["reverse"],
+ )
+ # pdb.set_trace()
+ if d == bands_n and self.data["high_end_process"] != "none":
+ input_high_end_h = (bp["n_fft"] // 2 - bp["crop_stop"]) + (
+ self.mp.param["pre_filter_stop"] - self.mp.param["pre_filter_start"]
+ )
+ input_high_end = X_spec_s[d][
+ :, bp["n_fft"] // 2 - input_high_end_h : bp["n_fft"] // 2, :
+ ]
+
+ X_spec_m = spec_utils.combine_spectrograms(X_spec_s, self.mp)
+ aggresive_set = float(self.data["agg"] / 100)
+ aggressiveness = {
+ "value": aggresive_set,
+ "split_bin": self.mp.param["band"][1]["crop_stop"],
+ }
+ with torch.no_grad():
+ pred, X_mag, X_phase = inference(
+ X_spec_m, self.device, self.model, aggressiveness, self.data
+ )
+ # Postprocess
+ if self.data["postprocess"]:
+ pred_inv = np.clip(X_mag - pred, 0, np.inf)
+ pred = spec_utils.mask_silence(pred, pred_inv)
+ y_spec_m = pred * X_phase
+ v_spec_m = X_spec_m - y_spec_m
+
+ if ins_root is not None:
+ if self.data["high_end_process"].startswith("mirroring"):
+ input_high_end_ = spec_utils.mirroring(
+ self.data["high_end_process"], y_spec_m, input_high_end, self.mp
+ )
+ wav_instrument = spec_utils.cmb_spectrogram_to_wave(
+ y_spec_m, self.mp, input_high_end_h, input_high_end_
+ )
+ else:
+ wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
+ print("%s instruments done" % name)
+ if format in ["wav", "flac"]:
+ sf.write(
+ os.path.join(
+ ins_root,
+ "instrument_{}_{}.{}".format(name, self.data["agg"], format),
+ ),
+ (np.array(wav_instrument) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ ) #
+ else:
+ path = os.path.join(
+ ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
+ )
+ sf.write(
+ path,
+ (np.array(wav_instrument) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ )
+ if os.path.exists(path):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path, path[:-4] + ".%s" % format)
+ )
+ if vocal_root is not None:
+ if self.data["high_end_process"].startswith("mirroring"):
+ input_high_end_ = spec_utils.mirroring(
+ self.data["high_end_process"], v_spec_m, input_high_end, self.mp
+ )
+ wav_vocals = spec_utils.cmb_spectrogram_to_wave(
+ v_spec_m, self.mp, input_high_end_h, input_high_end_
+ )
+ else:
+ wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
+ print("%s vocals done" % name)
+ if format in ["wav", "flac"]:
+ sf.write(
+ os.path.join(
+ vocal_root,
+ "vocal_{}_{}.{}".format(name, self.data["agg"], format),
+ ),
+ (np.array(wav_vocals) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ )
+ else:
+ path = os.path.join(
+ vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
+ )
+ sf.write(
+ path,
+ (np.array(wav_vocals) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ )
+ if os.path.exists(path):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path, path[:-4] + ".%s" % format)
+ )
+
+
+class _audio_pre_new:
+ def __init__(self, agg, model_path, device, is_half):
+ self.model_path = model_path
+ self.device = device
+ self.data = {
+ # Processing Options
+ "postprocess": False,
+ "tta": False,
+ # Constants
+ "window_size": 512,
+ "agg": agg,
+ "high_end_process": "mirroring",
+ }
+ mp = ModelParameters("uvr5_pack/lib_v5/modelparams/4band_v3.json")
+ nout = 64 if "DeReverb" in model_path else 48
+ model = CascadedNet(mp.param["bins"] * 2, nout)
+ cpk = torch.load(model_path, map_location="cpu")
+ model.load_state_dict(cpk)
+ model.eval()
+ if is_half:
+ model = model.half().to(device)
+ else:
+ model = model.to(device)
+
+ self.mp = mp
+ self.model = model
+
+ def _path_audio_(
+ self, music_file, vocal_root=None, ins_root=None, format="flac"
+ ): # 3个VR模型vocal和ins是反的
+ if ins_root is None and vocal_root is None:
+ return "No save root."
+ name = os.path.basename(music_file)
+ if ins_root is not None:
+ os.makedirs(ins_root, exist_ok=True)
+ if vocal_root is not None:
+ os.makedirs(vocal_root, exist_ok=True)
+ X_wave, y_wave, X_spec_s, y_spec_s = {}, {}, {}, {}
+ bands_n = len(self.mp.param["band"])
+ # print(bands_n)
+ for d in range(bands_n, 0, -1):
+ bp = self.mp.param["band"][d]
+ if d == bands_n: # high-end band
+ (
+ X_wave[d],
+ _,
+ ) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
+ music_file,
+ bp["sr"],
+ False,
+ dtype=np.float32,
+ res_type=bp["res_type"],
+ )
+ if X_wave[d].ndim == 1:
+ X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
+ else: # lower bands
+ X_wave[d] = librosa.core.resample(
+ X_wave[d + 1],
+ self.mp.param["band"][d + 1]["sr"],
+ bp["sr"],
+ res_type=bp["res_type"],
+ )
+ # Stft of wave source
+ X_spec_s[d] = spec_utils.wave_to_spectrogram_mt(
+ X_wave[d],
+ bp["hl"],
+ bp["n_fft"],
+ self.mp.param["mid_side"],
+ self.mp.param["mid_side_b2"],
+ self.mp.param["reverse"],
+ )
+ # pdb.set_trace()
+ if d == bands_n and self.data["high_end_process"] != "none":
+ input_high_end_h = (bp["n_fft"] // 2 - bp["crop_stop"]) + (
+ self.mp.param["pre_filter_stop"] - self.mp.param["pre_filter_start"]
+ )
+ input_high_end = X_spec_s[d][
+ :, bp["n_fft"] // 2 - input_high_end_h : bp["n_fft"] // 2, :
+ ]
+
+ X_spec_m = spec_utils.combine_spectrograms(X_spec_s, self.mp)
+ aggresive_set = float(self.data["agg"] / 100)
+ aggressiveness = {
+ "value": aggresive_set,
+ "split_bin": self.mp.param["band"][1]["crop_stop"],
+ }
+ with torch.no_grad():
+ pred, X_mag, X_phase = inference(
+ X_spec_m, self.device, self.model, aggressiveness, self.data
+ )
+ # Postprocess
+ if self.data["postprocess"]:
+ pred_inv = np.clip(X_mag - pred, 0, np.inf)
+ pred = spec_utils.mask_silence(pred, pred_inv)
+ y_spec_m = pred * X_phase
+ v_spec_m = X_spec_m - y_spec_m
+
+ if ins_root is not None:
+ if self.data["high_end_process"].startswith("mirroring"):
+ input_high_end_ = spec_utils.mirroring(
+ self.data["high_end_process"], y_spec_m, input_high_end, self.mp
+ )
+ wav_instrument = spec_utils.cmb_spectrogram_to_wave(
+ y_spec_m, self.mp, input_high_end_h, input_high_end_
+ )
+ else:
+ wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
+ print("%s instruments done" % name)
+ if format in ["wav", "flac"]:
+ sf.write(
+ os.path.join(
+ ins_root,
+ "instrument_{}_{}.{}".format(name, self.data["agg"], format),
+ ),
+ (np.array(wav_instrument) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ ) #
+ else:
+ path = os.path.join(
+ ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
+ )
+ sf.write(
+ path,
+ (np.array(wav_instrument) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ )
+ if os.path.exists(path):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path, path[:-4] + ".%s" % format)
+ )
+ if vocal_root is not None:
+ if self.data["high_end_process"].startswith("mirroring"):
+ input_high_end_ = spec_utils.mirroring(
+ self.data["high_end_process"], v_spec_m, input_high_end, self.mp
+ )
+ wav_vocals = spec_utils.cmb_spectrogram_to_wave(
+ v_spec_m, self.mp, input_high_end_h, input_high_end_
+ )
+ else:
+ wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
+ print("%s vocals done" % name)
+ if format in ["wav", "flac"]:
+ sf.write(
+ os.path.join(
+ vocal_root,
+ "vocal_{}_{}.{}".format(name, self.data["agg"], format),
+ ),
+ (np.array(wav_vocals) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ )
+ else:
+ path = os.path.join(
+ vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
+ )
+ sf.write(
+ path,
+ (np.array(wav_vocals) * 32768).astype("int16"),
+ self.mp.param["sr"],
+ )
+ if os.path.exists(path):
+ os.system(
+ "ffmpeg -i %s -vn %s -q:a 2 -y"
+ % (path, path[:-4] + ".%s" % format)
+ )
+
+
+if __name__ == "__main__":
+ device = "cuda"
+ is_half = True
+ # model_path = "uvr5_weights/2_HP-UVR.pth"
+ # model_path = "uvr5_weights/VR-DeEchoDeReverb.pth"
+ # model_path = "uvr5_weights/VR-DeEchoNormal.pth"
+ model_path = "uvr5_weights/DeEchoNormal.pth"
+ # pre_fun = _audio_pre_(model_path=model_path, device=device, is_half=True,agg=10)
+ pre_fun = _audio_pre_new(model_path=model_path, device=device, is_half=True, agg=10)
+ audio_path = "雪雪伴奏对消HP5.wav"
+ save_path = "opt"
+ pre_fun._path_audio_(audio_path, save_path, save_path)
diff --git a/logs/added_IVF2225_Flat_nprobe_1_simple-guitar-crepe-guolv_v2.index b/logs/added_IVF2225_Flat_nprobe_1_simple-guitar-crepe-guolv_v2.index
new file mode 100644
index 0000000000000000000000000000000000000000..bb061dfb1f370c40e17944d59deb8ab92b120bb1
--- /dev/null
+++ b/logs/added_IVF2225_Flat_nprobe_1_simple-guitar-crepe-guolv_v2.index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a732056818fd24489a8905c60a004f2b1d78b5a37c2b4dac89bbb23192a96ac4
+size 274200219
diff --git a/logs/mute/0_gt_wavs/mute32k.wav b/logs/mute/0_gt_wavs/mute32k.wav
new file mode 100644
index 0000000000000000000000000000000000000000..b4b5029205bf72dee5856bbe0c65c34337dc8dd4
Binary files /dev/null and b/logs/mute/0_gt_wavs/mute32k.wav differ
diff --git a/logs/mute/0_gt_wavs/mute40k.wav b/logs/mute/0_gt_wavs/mute40k.wav
new file mode 100644
index 0000000000000000000000000000000000000000..fcf1281d4d1b01417a4d6738022f4402594a6802
Binary files /dev/null and b/logs/mute/0_gt_wavs/mute40k.wav differ
diff --git a/logs/mute/0_gt_wavs/mute48k.wav b/logs/mute/0_gt_wavs/mute48k.wav
new file mode 100644
index 0000000000000000000000000000000000000000..72822a01251e77d7d2a4a7da9d94805426829083
Binary files /dev/null and b/logs/mute/0_gt_wavs/mute48k.wav differ
diff --git a/logs/mute/1_16k_wavs/mute.wav b/logs/mute/1_16k_wavs/mute.wav
new file mode 100644
index 0000000000000000000000000000000000000000..27a7d638558539c521aacf8c0f34bd0d4816aa9d
Binary files /dev/null and b/logs/mute/1_16k_wavs/mute.wav differ
diff --git a/logs/mute/2a_f0/mute.wav.npy b/logs/mute/2a_f0/mute.wav.npy
new file mode 100644
index 0000000000000000000000000000000000000000..dd7e9afd2e7f2aefaa30bcd4541a23ce96a9e150
--- /dev/null
+++ b/logs/mute/2a_f0/mute.wav.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9acf9ab7facdb032e1d687fe35182670b0b94566c4b209ae48c239d19956a6
+size 1332
diff --git a/logs/mute/2b-f0nsf/mute.wav.npy b/logs/mute/2b-f0nsf/mute.wav.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7644e325ddd34bd186153ecf7461aa1593a054f3
--- /dev/null
+++ b/logs/mute/2b-f0nsf/mute.wav.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30792849c8e72d67e6691754077f2888b101cb741e9c7f193c91dd9692870c87
+size 2536
diff --git a/logs/mute/3_feature256/mute.npy b/logs/mute/3_feature256/mute.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c57ae95d19d969788ef186a81cdc2f4b462ed6df
--- /dev/null
+++ b/logs/mute/3_feature256/mute.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d5abbac078e19a3f649c0d78a02cb33a71407ded3ddf2db78e6b803d0c0126
+size 152704
diff --git a/logs/mute/3_feature768/mute.npy b/logs/mute/3_feature768/mute.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ea5f9dddca08ff210791b27e3db3fc5676eabc90
--- /dev/null
+++ b/logs/mute/3_feature768/mute.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ef62b957887ac9f0913aa5158f18983afff1ef5a3e4c5fd067ac20fc380d54
+size 457856
diff --git a/my_utils.py b/my_utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..a7223e839bec2a1b3779107fdaa7ef45fb7ae4e2
--- /dev/null
+++ b/my_utils.py
@@ -0,0 +1,21 @@
+import ffmpeg
+import numpy as np
+
+
+def load_audio(file, sr):
+ try:
+ # https://github.com/openai/whisper/blob/main/whisper/audio.py#L26
+ # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
+ # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
+ file = (
+ file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+ ) # 防止小白拷路径头尾带了空格和"和回车
+ out, _ = (
+ ffmpeg.input(file, threads=0)
+ .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
+ .run(cmd=["./ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
+ )
+ except Exception as e:
+ raise RuntimeError(f"Failed to load audio: {e}")
+
+ return np.frombuffer(out, np.float32).flatten()
diff --git a/onnx_inference_demo.py b/onnx_inference_demo.py
new file mode 100644
index 0000000000000000000000000000000000000000..14e75d0eb4a5dc3542ce1ed6d462c70c7f4e5679
--- /dev/null
+++ b/onnx_inference_demo.py
@@ -0,0 +1,20 @@
+import soundfile
+from infer_pack.onnx_inference import OnnxRVC
+
+hop_size = 512
+sampling_rate = 40000 # 采样率
+f0_up_key = 0 # 升降调
+sid = 0 # 角色ID
+f0_method = "dio" # F0提取算法
+model_path = "ShirohaRVC.onnx" # 模型的完整路径
+vec_name = "vec-256-layer-9" # 内部自动补齐为 f"pretrained/{vec_name}.onnx" 需要onnx的vec模型
+wav_path = "123.wav" # 输入路径或ByteIO实例
+out_path = "out.wav" # 输出路径或ByteIO实例
+
+model = OnnxRVC(
+ model_path, vec_path=vec_name, sr=sampling_rate, hop_size=hop_size, device="cuda"
+)
+
+audio = model.inference(wav_path, sid, f0_method=f0_method, f0_up_key=f0_up_key)
+
+soundfile.write(out_path, audio, sampling_rate)
diff --git a/poetry.lock b/poetry.lock
new file mode 100644
index 0000000000000000000000000000000000000000..dd82b153c6f4a59d0ce2b81ddccd4f03deca6e42
--- /dev/null
+++ b/poetry.lock
@@ -0,0 +1,4008 @@
+# This file is automatically @generated by Poetry and should not be changed by hand.
+
+[[package]]
+name = "absl-py"
+version = "1.4.0"
+description = "Abseil Python Common Libraries, see https://github.com/abseil/abseil-py."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "absl-py-1.4.0.tar.gz", hash = "sha256:d2c244d01048ba476e7c080bd2c6df5e141d211de80223460d5b3b8a2a58433d"},
+ {file = "absl_py-1.4.0-py3-none-any.whl", hash = "sha256:0d3fe606adfa4f7db64792dd4c7aee4ee0c38ab75dfd353b7a83ed3e957fcb47"},
+]
+
+[[package]]
+name = "aiofiles"
+version = "23.1.0"
+description = "File support for asyncio."
+category = "main"
+optional = false
+python-versions = ">=3.7,<4.0"
+files = [
+ {file = "aiofiles-23.1.0-py3-none-any.whl", hash = "sha256:9312414ae06472eb6f1d163f555e466a23aed1c8f60c30cccf7121dba2e53eb2"},
+ {file = "aiofiles-23.1.0.tar.gz", hash = "sha256:edd247df9a19e0db16534d4baaf536d6609a43e1de5401d7a4c1c148753a1635"},
+]
+
+[[package]]
+name = "aiohttp"
+version = "3.8.4"
+description = "Async http client/server framework (asyncio)"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "aiohttp-3.8.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:5ce45967538fb747370308d3145aa68a074bdecb4f3a300869590f725ced69c1"},
+ {file = "aiohttp-3.8.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b744c33b6f14ca26b7544e8d8aadff6b765a80ad6164fb1a430bbadd593dfb1a"},
+ {file = "aiohttp-3.8.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1a45865451439eb320784918617ba54b7a377e3501fb70402ab84d38c2cd891b"},
+ {file = "aiohttp-3.8.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a86d42d7cba1cec432d47ab13b6637bee393a10f664c425ea7b305d1301ca1a3"},
+ {file = "aiohttp-3.8.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ee3c36df21b5714d49fc4580247947aa64bcbe2939d1b77b4c8dcb8f6c9faecc"},
+ {file = "aiohttp-3.8.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:176a64b24c0935869d5bbc4c96e82f89f643bcdf08ec947701b9dbb3c956b7dd"},
+ {file = "aiohttp-3.8.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c844fd628851c0bc309f3c801b3a3d58ce430b2ce5b359cd918a5a76d0b20cb5"},
+ {file = "aiohttp-3.8.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5393fb786a9e23e4799fec788e7e735de18052f83682ce2dfcabaf1c00c2c08e"},
+ {file = "aiohttp-3.8.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:e4b09863aae0dc965c3ef36500d891a3ff495a2ea9ae9171e4519963c12ceefd"},
+ {file = "aiohttp-3.8.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:adfbc22e87365a6e564c804c58fc44ff7727deea782d175c33602737b7feadb6"},
+ {file = "aiohttp-3.8.4-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:147ae376f14b55f4f3c2b118b95be50a369b89b38a971e80a17c3fd623f280c9"},
+ {file = "aiohttp-3.8.4-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:eafb3e874816ebe2a92f5e155f17260034c8c341dad1df25672fb710627c6949"},
+ {file = "aiohttp-3.8.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c6cc15d58053c76eacac5fa9152d7d84b8d67b3fde92709195cb984cfb3475ea"},
+ {file = "aiohttp-3.8.4-cp310-cp310-win32.whl", hash = "sha256:59f029a5f6e2d679296db7bee982bb3d20c088e52a2977e3175faf31d6fb75d1"},
+ {file = "aiohttp-3.8.4-cp310-cp310-win_amd64.whl", hash = "sha256:fe7ba4a51f33ab275515f66b0a236bcde4fb5561498fe8f898d4e549b2e4509f"},
+ {file = "aiohttp-3.8.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3d8ef1a630519a26d6760bc695842579cb09e373c5f227a21b67dc3eb16cfea4"},
+ {file = "aiohttp-3.8.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5b3f2e06a512e94722886c0827bee9807c86a9f698fac6b3aee841fab49bbfb4"},
+ {file = "aiohttp-3.8.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3a80464982d41b1fbfe3154e440ba4904b71c1a53e9cd584098cd41efdb188ef"},
+ {file = "aiohttp-3.8.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b631e26df63e52f7cce0cce6507b7a7f1bc9b0c501fcde69742130b32e8782f"},
+ {file = "aiohttp-3.8.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3f43255086fe25e36fd5ed8f2ee47477408a73ef00e804cb2b5cba4bf2ac7f5e"},
+ {file = "aiohttp-3.8.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4d347a172f866cd1d93126d9b239fcbe682acb39b48ee0873c73c933dd23bd0f"},
+ {file = "aiohttp-3.8.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a3fec6a4cb5551721cdd70473eb009d90935b4063acc5f40905d40ecfea23e05"},
+ {file = "aiohttp-3.8.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:80a37fe8f7c1e6ce8f2d9c411676e4bc633a8462844e38f46156d07a7d401654"},
+ {file = "aiohttp-3.8.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:d1e6a862b76f34395a985b3cd39a0d949ca80a70b6ebdea37d3ab39ceea6698a"},
+ {file = "aiohttp-3.8.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:cd468460eefef601ece4428d3cf4562459157c0f6523db89365202c31b6daebb"},
+ {file = "aiohttp-3.8.4-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:618c901dd3aad4ace71dfa0f5e82e88b46ef57e3239fc7027773cb6d4ed53531"},
+ {file = "aiohttp-3.8.4-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:652b1bff4f15f6287550b4670546a2947f2a4575b6c6dff7760eafb22eacbf0b"},
+ {file = "aiohttp-3.8.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:80575ba9377c5171407a06d0196b2310b679dc752d02a1fcaa2bc20b235dbf24"},
+ {file = "aiohttp-3.8.4-cp311-cp311-win32.whl", hash = "sha256:bbcf1a76cf6f6dacf2c7f4d2ebd411438c275faa1dc0c68e46eb84eebd05dd7d"},
+ {file = "aiohttp-3.8.4-cp311-cp311-win_amd64.whl", hash = "sha256:6e74dd54f7239fcffe07913ff8b964e28b712f09846e20de78676ce2a3dc0bfc"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:880e15bb6dad90549b43f796b391cfffd7af373f4646784795e20d92606b7a51"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb96fa6b56bb536c42d6a4a87dfca570ff8e52de2d63cabebfd6fb67049c34b6"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4a6cadebe132e90cefa77e45f2d2f1a4b2ce5c6b1bfc1656c1ddafcfe4ba8131"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f352b62b45dff37b55ddd7b9c0c8672c4dd2eb9c0f9c11d395075a84e2c40f75"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ab43061a0c81198d88f39aaf90dae9a7744620978f7ef3e3708339b8ed2ef01"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c9cb1565a7ad52e096a6988e2ee0397f72fe056dadf75d17fa6b5aebaea05622"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:1b3ea7edd2d24538959c1c1abf97c744d879d4e541d38305f9bd7d9b10c9ec41"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:7c7837fe8037e96b6dd5cfcf47263c1620a9d332a87ec06a6ca4564e56bd0f36"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:3b90467ebc3d9fa5b0f9b6489dfb2c304a1db7b9946fa92aa76a831b9d587e99"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:cab9401de3ea52b4b4c6971db5fb5c999bd4260898af972bf23de1c6b5dd9d71"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:d1f9282c5f2b5e241034a009779e7b2a1aa045f667ff521e7948ea9b56e0c5ff"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-win32.whl", hash = "sha256:5e14f25765a578a0a634d5f0cd1e2c3f53964553a00347998dfdf96b8137f777"},
+ {file = "aiohttp-3.8.4-cp36-cp36m-win_amd64.whl", hash = "sha256:4c745b109057e7e5f1848c689ee4fb3a016c8d4d92da52b312f8a509f83aa05e"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:aede4df4eeb926c8fa70de46c340a1bc2c6079e1c40ccf7b0eae1313ffd33519"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ddaae3f3d32fc2cb4c53fab020b69a05c8ab1f02e0e59665c6f7a0d3a5be54f"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4eb3b82ca349cf6fadcdc7abcc8b3a50ab74a62e9113ab7a8ebc268aad35bb9"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9bcb89336efa095ea21b30f9e686763f2be4478f1b0a616969551982c4ee4c3b"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c08e8ed6fa3d477e501ec9db169bfac8140e830aa372d77e4a43084d8dd91ab"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c6cd05ea06daca6ad6a4ca3ba7fe7dc5b5de063ff4daec6170ec0f9979f6c332"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:b7a00a9ed8d6e725b55ef98b1b35c88013245f35f68b1b12c5cd4100dddac333"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:de04b491d0e5007ee1b63a309956eaed959a49f5bb4e84b26c8f5d49de140fa9"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:40653609b3bf50611356e6b6554e3a331f6879fa7116f3959b20e3528783e699"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:dbf3a08a06b3f433013c143ebd72c15cac33d2914b8ea4bea7ac2c23578815d6"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:854f422ac44af92bfe172d8e73229c270dc09b96535e8a548f99c84f82dde241"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-win32.whl", hash = "sha256:aeb29c84bb53a84b1a81c6c09d24cf33bb8432cc5c39979021cc0f98c1292a1a"},
+ {file = "aiohttp-3.8.4-cp37-cp37m-win_amd64.whl", hash = "sha256:db3fc6120bce9f446d13b1b834ea5b15341ca9ff3f335e4a951a6ead31105480"},
+ {file = "aiohttp-3.8.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:fabb87dd8850ef0f7fe2b366d44b77d7e6fa2ea87861ab3844da99291e81e60f"},
+ {file = "aiohttp-3.8.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:91f6d540163f90bbaef9387e65f18f73ffd7c79f5225ac3d3f61df7b0d01ad15"},
+ {file = "aiohttp-3.8.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:d265f09a75a79a788237d7f9054f929ced2e69eb0bb79de3798c468d8a90f945"},
+ {file = "aiohttp-3.8.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3d89efa095ca7d442a6d0cbc755f9e08190ba40069b235c9886a8763b03785da"},
+ {file = "aiohttp-3.8.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4dac314662f4e2aa5009977b652d9b8db7121b46c38f2073bfeed9f4049732cd"},
+ {file = "aiohttp-3.8.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fe11310ae1e4cd560035598c3f29d86cef39a83d244c7466f95c27ae04850f10"},
+ {file = "aiohttp-3.8.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ddb2a2026c3f6a68c3998a6c47ab6795e4127315d2e35a09997da21865757f8"},
+ {file = "aiohttp-3.8.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e75b89ac3bd27d2d043b234aa7b734c38ba1b0e43f07787130a0ecac1e12228a"},
+ {file = "aiohttp-3.8.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6e601588f2b502c93c30cd5a45bfc665faaf37bbe835b7cfd461753068232074"},
+ {file = "aiohttp-3.8.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a5d794d1ae64e7753e405ba58e08fcfa73e3fad93ef9b7e31112ef3c9a0efb52"},
+ {file = "aiohttp-3.8.4-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:a1f4689c9a1462f3df0a1f7e797791cd6b124ddbee2b570d34e7f38ade0e2c71"},
+ {file = "aiohttp-3.8.4-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:3032dcb1c35bc330134a5b8a5d4f68c1a87252dfc6e1262c65a7e30e62298275"},
+ {file = "aiohttp-3.8.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8189c56eb0ddbb95bfadb8f60ea1b22fcfa659396ea36f6adcc521213cd7b44d"},
+ {file = "aiohttp-3.8.4-cp38-cp38-win32.whl", hash = "sha256:33587f26dcee66efb2fff3c177547bd0449ab7edf1b73a7f5dea1e38609a0c54"},
+ {file = "aiohttp-3.8.4-cp38-cp38-win_amd64.whl", hash = "sha256:e595432ac259af2d4630008bf638873d69346372d38255774c0e286951e8b79f"},
+ {file = "aiohttp-3.8.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5a7bdf9e57126dc345b683c3632e8ba317c31d2a41acd5800c10640387d193ed"},
+ {file = "aiohttp-3.8.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:22f6eab15b6db242499a16de87939a342f5a950ad0abaf1532038e2ce7d31567"},
+ {file = "aiohttp-3.8.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:7235604476a76ef249bd64cb8274ed24ccf6995c4a8b51a237005ee7a57e8643"},
+ {file = "aiohttp-3.8.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ea9eb976ffdd79d0e893869cfe179a8f60f152d42cb64622fca418cd9b18dc2a"},
+ {file = "aiohttp-3.8.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:92c0cea74a2a81c4c76b62ea1cac163ecb20fb3ba3a75c909b9fa71b4ad493cf"},
+ {file = "aiohttp-3.8.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:493f5bc2f8307286b7799c6d899d388bbaa7dfa6c4caf4f97ef7521b9cb13719"},
+ {file = "aiohttp-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0a63f03189a6fa7c900226e3ef5ba4d3bd047e18f445e69adbd65af433add5a2"},
+ {file = "aiohttp-3.8.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:10c8cefcff98fd9168cdd86c4da8b84baaa90bf2da2269c6161984e6737bf23e"},
+ {file = "aiohttp-3.8.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bca5f24726e2919de94f047739d0a4fc01372801a3672708260546aa2601bf57"},
+ {file = "aiohttp-3.8.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:03baa76b730e4e15a45f81dfe29a8d910314143414e528737f8589ec60cf7391"},
+ {file = "aiohttp-3.8.4-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:8c29c77cc57e40f84acef9bfb904373a4e89a4e8b74e71aa8075c021ec9078c2"},
+ {file = "aiohttp-3.8.4-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:03543dcf98a6619254b409be2d22b51f21ec66272be4ebda7b04e6412e4b2e14"},
+ {file = "aiohttp-3.8.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:17b79c2963db82086229012cff93ea55196ed31f6493bb1ccd2c62f1724324e4"},
+ {file = "aiohttp-3.8.4-cp39-cp39-win32.whl", hash = "sha256:34ce9f93a4a68d1272d26030655dd1b58ff727b3ed2a33d80ec433561b03d67a"},
+ {file = "aiohttp-3.8.4-cp39-cp39-win_amd64.whl", hash = "sha256:41a86a69bb63bb2fc3dc9ad5ea9f10f1c9c8e282b471931be0268ddd09430b04"},
+ {file = "aiohttp-3.8.4.tar.gz", hash = "sha256:bf2e1a9162c1e441bf805a1fd166e249d574ca04e03b34f97e2928769e91ab5c"},
+]
+
+[package.dependencies]
+aiosignal = ">=1.1.2"
+async-timeout = ">=4.0.0a3,<5.0"
+attrs = ">=17.3.0"
+charset-normalizer = ">=2.0,<4.0"
+frozenlist = ">=1.1.1"
+multidict = ">=4.5,<7.0"
+yarl = ">=1.0,<2.0"
+
+[package.extras]
+speedups = ["Brotli", "aiodns", "cchardet"]
+
+[[package]]
+name = "aiosignal"
+version = "1.3.1"
+description = "aiosignal: a list of registered asynchronous callbacks"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "aiosignal-1.3.1-py3-none-any.whl", hash = "sha256:f8376fb07dd1e86a584e4fcdec80b36b7f81aac666ebc724e2c090300dd83b17"},
+ {file = "aiosignal-1.3.1.tar.gz", hash = "sha256:54cd96e15e1649b75d6c87526a6ff0b6c1b0dd3459f43d9ca11d48c339b68cfc"},
+]
+
+[package.dependencies]
+frozenlist = ">=1.1.0"
+
+[[package]]
+name = "altair"
+version = "4.2.2"
+description = "Altair: A declarative statistical visualization library for Python."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "altair-4.2.2-py3-none-any.whl", hash = "sha256:8b45ebeaf8557f2d760c5c77b79f02ae12aee7c46c27c06014febab6f849bc87"},
+ {file = "altair-4.2.2.tar.gz", hash = "sha256:39399a267c49b30d102c10411e67ab26374156a84b1aeb9fcd15140429ba49c5"},
+]
+
+[package.dependencies]
+entrypoints = "*"
+jinja2 = "*"
+jsonschema = ">=3.0"
+numpy = "*"
+pandas = ">=0.18"
+toolz = "*"
+
+[package.extras]
+dev = ["black", "docutils", "flake8", "ipython", "m2r", "mistune (<2.0.0)", "pytest", "recommonmark", "sphinx", "vega-datasets"]
+
+[[package]]
+name = "antlr4-python3-runtime"
+version = "4.8"
+description = "ANTLR 4.8 runtime for Python 3.7"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "antlr4-python3-runtime-4.8.tar.gz", hash = "sha256:15793f5d0512a372b4e7d2284058ad32ce7dd27126b105fb0b2245130445db33"},
+]
+
+[[package]]
+name = "anyio"
+version = "3.6.2"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+category = "main"
+optional = false
+python-versions = ">=3.6.2"
+files = [
+ {file = "anyio-3.6.2-py3-none-any.whl", hash = "sha256:fbbe32bd270d2a2ef3ed1c5d45041250284e31fc0a4df4a5a6071842051a51e3"},
+ {file = "anyio-3.6.2.tar.gz", hash = "sha256:25ea0d673ae30af41a0c442f81cf3b38c7e79fdc7b60335a4c14e05eb0947421"},
+]
+
+[package.dependencies]
+idna = ">=2.8"
+sniffio = ">=1.1"
+
+[package.extras]
+doc = ["packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
+test = ["contextlib2", "coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "mock (>=4)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (<0.15)", "uvloop (>=0.15)"]
+trio = ["trio (>=0.16,<0.22)"]
+
+[[package]]
+name = "async-timeout"
+version = "4.0.2"
+description = "Timeout context manager for asyncio programs"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "async-timeout-4.0.2.tar.gz", hash = "sha256:2163e1640ddb52b7a8c80d0a67a08587e5d245cc9c553a74a847056bc2976b15"},
+ {file = "async_timeout-4.0.2-py3-none-any.whl", hash = "sha256:8ca1e4fcf50d07413d66d1a5e416e42cfdf5851c981d679a09851a6853383b3c"},
+]
+
+[[package]]
+name = "attrs"
+version = "22.2.0"
+description = "Classes Without Boilerplate"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "attrs-22.2.0-py3-none-any.whl", hash = "sha256:29e95c7f6778868dbd49170f98f8818f78f3dc5e0e37c0b1f474e3561b240836"},
+ {file = "attrs-22.2.0.tar.gz", hash = "sha256:c9227bfc2f01993c03f68db37d1d15c9690188323c067c641f1a35ca58185f99"},
+]
+
+[package.extras]
+cov = ["attrs[tests]", "coverage-enable-subprocess", "coverage[toml] (>=5.3)"]
+dev = ["attrs[docs,tests]"]
+docs = ["furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier", "zope.interface"]
+tests = ["attrs[tests-no-zope]", "zope.interface"]
+tests-no-zope = ["cloudpickle", "cloudpickle", "hypothesis", "hypothesis", "mypy (>=0.971,<0.990)", "mypy (>=0.971,<0.990)", "pympler", "pympler", "pytest (>=4.3.0)", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-mypy-plugins", "pytest-xdist[psutil]", "pytest-xdist[psutil]"]
+
+[[package]]
+name = "audioread"
+version = "3.0.0"
+description = "multi-library, cross-platform audio decoding"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "audioread-3.0.0.tar.gz", hash = "sha256:121995bd207eb1fda3d566beb851d3534275925bc35a4fb6da0cb11de0f7251a"},
+]
+
+[[package]]
+name = "bitarray"
+version = "2.7.3"
+description = "efficient arrays of booleans -- C extension"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "bitarray-2.7.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:979d42e0b2c3113526f9716a461e08671788a23ce7e3b5cd090ce3e6a6762641"},
+ {file = "bitarray-2.7.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:860edf8533223d82bd6201894bcaf540f828f49075f363390eecf04b12fb94cb"},
+ {file = "bitarray-2.7.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:78378d8dacbe1f4f263347f42ec0a41cc2097cd671c6ac30a65a838284a5e141"},
+ {file = "bitarray-2.7.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:888df211aafe5fad41c0792a686d95c8ba37345d5037f437aa3c09608f9c3b56"},
+ {file = "bitarray-2.7.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fb3f003dee96dbf24a6df71443557f249b17b20083c189995302b14eb01530bf"},
+ {file = "bitarray-2.7.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c531532c21bc1063e65957a1a85a2d13601ec21801f70821c89d9339b16ebc78"},
+ {file = "bitarray-2.7.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b8fd92c8026e4ba6874e94f538890e35bef2a3a18ea54e3663c578b7916ade1"},
+ {file = "bitarray-2.7.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6d19c34a2121eccfeb642d4ad71163bd3342a8f3a99e6724fe824bdfbc0a5b65"},
+ {file = "bitarray-2.7.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:102db74ee82ec5774aba01481e73eedaebd27ba167344a81d3b42e6fbf9ffb77"},
+ {file = "bitarray-2.7.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7f6540b45b2230442f7a0614745131e0a6f28251f5d33ac19d0ed61d80db7153"},
+ {file = "bitarray-2.7.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:99c9345c417a9cff98f9f6e59b0350dcc10c2e0e1ea66acf7946de1cd60541fa"},
+ {file = "bitarray-2.7.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:a1d439c98e65ab8e5fbcc2b242a16e7a3f076974bff78185ff42ba2d4c220032"},
+ {file = "bitarray-2.7.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:87897ec0e4876c9f2c1ae313519de0ed2ad8041a4d2210a083f9b4a239add2e3"},
+ {file = "bitarray-2.7.3-cp310-cp310-win32.whl", hash = "sha256:cb46c3a4002c8322dd0e1b4b53f8a647dcb0f199f5c7a1fc03d3880c3eabbd2c"},
+ {file = "bitarray-2.7.3-cp310-cp310-win_amd64.whl", hash = "sha256:5df10eb9b794932b0cf806f412d1c6d04fb7655ca7ae5caf6354b9edc380a5f7"},
+ {file = "bitarray-2.7.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:27524bc92fdeb464a5057a4677a35f482cf30be2e920bd1d11c46de533cafda6"},
+ {file = "bitarray-2.7.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3cf37431de779b29e5c0d8e36868f77f6df53c3c19c20e8404137e257dc80040"},
+ {file = "bitarray-2.7.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8abd23f94cdcce971d932a5f0a066d40fbc61901fd087aa70d32cccd1793bd20"},
+ {file = "bitarray-2.7.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7659bdfe7716b14a39007e31e957fa64d7f0d9e40a1dbd024bd81b972d76bffb"},
+ {file = "bitarray-2.7.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:da1570f301abdfda68f4fdb40c4d3f09af4bb6e4550b4fa5395db0d142b680bc"},
+ {file = "bitarray-2.7.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8becbb9649fd29ee577f9f0405ce2fba5cf9fa2c290c9b044bc235c04473f213"},
+ {file = "bitarray-2.7.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:72fd7f6f940bc42914c86700591ccfd1daeff0e414cefcbd7843117df2fac4e9"},
+ {file = "bitarray-2.7.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:23b7bada6d6b62cba08f4a1b8a95da2d8592aae1db3c167dcb52abcba0a7bef5"},
+ {file = "bitarray-2.7.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:4b2d150a81a981537801ac7d4f4f5d082c48343612a21f4e2c4cd2e887973bd5"},
+ {file = "bitarray-2.7.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:1502660ab489b1f18c3493c766252cd5d24bc1cbf4bdf3594e0a30de142ed453"},
+ {file = "bitarray-2.7.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:91f43f6b6c9129a56d3e2dccb8b88ffce0e4f4893dd9d69d285676bdf5b9ca14"},
+ {file = "bitarray-2.7.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:a69c99274aee2ffdc7f1cfd34044ccb7155790d6f5217d677ea46a6ddead6dd2"},
+ {file = "bitarray-2.7.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:d63f20299441e32171f08fc62f7ea7e401cc12a96f67a36ab2d76439ecfcb118"},
+ {file = "bitarray-2.7.3-cp311-cp311-win32.whl", hash = "sha256:0b84fd9dbf999cbca1090a7703aa1404cd01af4035c6ba3adf69d41280611fb6"},
+ {file = "bitarray-2.7.3-cp311-cp311-win_amd64.whl", hash = "sha256:76bbbb9ceebb9cbb2b14369b3681fecab226792b339f612e79f6575ca31fed45"},
+ {file = "bitarray-2.7.3-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50d5e2c026b3e3d145f64c457338ea99edcbdd302fdcbd96418251ac51a98a59"},
+ {file = "bitarray-2.7.3-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7d571056115bbdc18f199a9ee4c2a1b5884f5e63a3c05fe43d2fc7fc67320515"},
+ {file = "bitarray-2.7.3-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e2a0313657e6656efca2148cfc91c50fdafca6f811b6c7d0906e6ba57134e560"},
+ {file = "bitarray-2.7.3-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d3b5abb73c45d40d27f9795dac9d6eb1515729c13f93dd67df2be07be6549990"},
+ {file = "bitarray-2.7.3-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7776c070943f45cd8303543a6625cf82f2e000ef9c885d52d7828be099e52f42"},
+ {file = "bitarray-2.7.3-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:057f9c53a34e42deed6e8813a82b9c85924f4728be28e3b9b65144569ac5a387"},
+ {file = "bitarray-2.7.3-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:8591ad5768860ad186dc94fd58b2932604a7639b57eefbbff2b4865af3407691"},
+ {file = "bitarray-2.7.3-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:bd7f4b2df89bf4e298756c0be0be67fb84d6aa49bda60d46805d43f0e643abd5"},
+ {file = "bitarray-2.7.3-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:433f91c8ab8338662aaa86b0677e6c15c35f8f7b65d4c43d7d1647a8198bc0b0"},
+ {file = "bitarray-2.7.3-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:31e60d8341c3189aa156ca8cb2f6370b29d79cf132e3d091714b0a5a9097eb69"},
+ {file = "bitarray-2.7.3-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:ea33ed09157e032f0a7a2627ef87f156e9927697f59b55961439d34bf45af23a"},
+ {file = "bitarray-2.7.3-cp36-cp36m-win32.whl", hash = "sha256:302149aaff75939beb8af7f32ac9bf922480033a24fb54f4ebc0c9dc175247c4"},
+ {file = "bitarray-2.7.3-cp36-cp36m-win_amd64.whl", hash = "sha256:7a8995737fae8de03b31ed83acf4f4326a55b217022009d18be19ff87fc9010e"},
+ {file = "bitarray-2.7.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8b2f31a4cc28aef27355ab896e4b4cc2da2204b2b7adb674d8be7fefa0c93868"},
+ {file = "bitarray-2.7.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5df624ee8a4098c3b1149f4817f2a4a0121c4920e1c114af324bc52d6659e2b"},
+ {file = "bitarray-2.7.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cb1d60ed709989e34e7158d97fdb077a2f2dfc505998a84161a70f81a6101172"},
+ {file = "bitarray-2.7.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:748847e58c45a37f23db1f53a6dc16ae32aa80ee504653d79336830de1a79ed7"},
+ {file = "bitarray-2.7.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e4b7fdb9772e087174f446655bbc497a1600b5758f279c6d44fcf344c13d5c8a"},
+ {file = "bitarray-2.7.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:86e9c48ffeddb0f943e87ab65e1e95dccc9b44ef3761af3bf9642973ab7646d2"},
+ {file = "bitarray-2.7.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:0d1f49cc51919d6fa0f7eebd073d2c620b80079aa537d084a7fafb46a35c7a4d"},
+ {file = "bitarray-2.7.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:b43d56c7c96f5a055f4051be426496db2a616840645d0ab3733d5ceacb2f701b"},
+ {file = "bitarray-2.7.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:01f8d02c3eae82c98d4259777cb2f042a0b3989d7dceeb37c643cb94b91d5a42"},
+ {file = "bitarray-2.7.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:d089b1d0b157c9a484f8f7475eecea813d0dc3818adc5bf352903da14fe88fc3"},
+ {file = "bitarray-2.7.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:1362e9fb78ca72aa52ec1f1fbd62872801302001b0156ed2a1e707850cd30ffd"},
+ {file = "bitarray-2.7.3-cp37-cp37m-win32.whl", hash = "sha256:2cdf5700537e5aa4ec9f4a0b498b8d5b03b9859d503e01ea17a6a134a838aa30"},
+ {file = "bitarray-2.7.3-cp37-cp37m-win_amd64.whl", hash = "sha256:1e1553933f4533040491f4e4499bcbbfcee42c4056f56d7e18010e779daab33d"},
+ {file = "bitarray-2.7.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:1048a29b3d72b1821a3ae9e8d64e71ed96c53a1a36b1da6db02091a424a8f795"},
+ {file = "bitarray-2.7.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:10dc358fe29d7a4c5be78ab2fb5aa50cb8066babd23e0b5589eb68e26afe58d8"},
+ {file = "bitarray-2.7.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:8ab6770833976448a9a973bc0df63adedc4c30de4774cec5a9928fc496423ebb"},
+ {file = "bitarray-2.7.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4abe2f829f6f2d330bccf1bcde2192264ab9a15d6d00e507265f46dc66557014"},
+ {file = "bitarray-2.7.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:87851a82bdf849e3c40ff6d8af5f734634e17f52a8f7f7e74486c2f8ce717578"},
+ {file = "bitarray-2.7.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a5fc2512bdf5289a1412c936c65d17881d2b46edb0036c63a8d5605dc8d398a3"},
+ {file = "bitarray-2.7.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1289f408a8b5c87cdb4fd7975d4021c6e61209ccb956d0411e72bf43c7f78463"},
+ {file = "bitarray-2.7.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9ee181cc00aaba38d9812f4df4e7d828105b6dde3b068cd2c43f1d8f395e0046"},
+ {file = "bitarray-2.7.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:00e93f70cbcbeabd1e79accf1b6f5b2424cd40556e7877f618549523d0031c98"},
+ {file = "bitarray-2.7.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:3fb6a952796d16c3a309d866eef56a8f4e5591d112c22446e67d33ecb096b44b"},
+ {file = "bitarray-2.7.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:0fe747a134f7f5bc0877eee58090ae7e7f23628eeb459f681ade65719c3f246a"},
+ {file = "bitarray-2.7.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:2c1b2c91bf991b5c641faee78dd5a751dff6155ec51c7a6c7f922dc85431898e"},
+ {file = "bitarray-2.7.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c3956ae54285ab30d802756144887e30e013f81c9f03e5ffff9daa46d8ca0154"},
+ {file = "bitarray-2.7.3-cp38-cp38-win32.whl", hash = "sha256:00a6fc4355bd4e6ead54d05187dc4ea39f0af439b336ae113f0194673ed730ae"},
+ {file = "bitarray-2.7.3-cp38-cp38-win_amd64.whl", hash = "sha256:305e6f7441c007f296644ba3899c0306ce9fd7a482dbbc06b6e7b7bd6e0ddabc"},
+ {file = "bitarray-2.7.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:fe80c23409efb41b86efb5e45f334420a9b5b7828f5b3d08b5ff28f03a024d9e"},
+ {file = "bitarray-2.7.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:16345146b61e93ca20679c83537ccf7245f78b17035f5b1a436fd2b75da04c5e"},
+ {file = "bitarray-2.7.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1af9b720a048c69e999094e2310138b7cfca5471a9d2c1dbe4b53dd10e516720"},
+ {file = "bitarray-2.7.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:088e6e9ea7f0eaf8b672679a68096dbc0a7a7b7a4ed567860f7362e1588370a6"},
+ {file = "bitarray-2.7.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:122cd70ee0de2cc9d94da8b8ebcb7dca12b9f4d3beefb94c11e110e1d87503bb"},
+ {file = "bitarray-2.7.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cb9a8ee23416bd0cfd457118978bc2f6f02c20b95336db486887f670bf92c2b7"},
+ {file = "bitarray-2.7.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9a544f99c24b6f658907eb9edf290a9c54f4106738b2ab84cd19dc6013cc3abf"},
+ {file = "bitarray-2.7.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:980f6564218f853a9341fb045446539d4153338926ed2fb222e86dc9b2ae9b8f"},
+ {file = "bitarray-2.7.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f64abe9301b918d2c352e42198cea0196f3639bc1ad23a4a9d8ae97f66068901"},
+ {file = "bitarray-2.7.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:029c724bf38c6616b90b1c423b846b63f8d607ed5a23d270e3862696d88a5392"},
+ {file = "bitarray-2.7.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:16cb00911584a6e9ca0f42c305714898120dc6bfbbec90dacedeed4690331a47"},
+ {file = "bitarray-2.7.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:699b0134e87c0c4e3b224d879d218c4385a06e6b72df73b4c9c9d549155fb837"},
+ {file = "bitarray-2.7.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b508e1bba4ec68fd0ef28505e2dad2f56de7df710c8334c97036705a562cb908"},
+ {file = "bitarray-2.7.3-cp39-cp39-win32.whl", hash = "sha256:4b84230624d15868e407ba8b66df54fc69ee6a9e9cb6d51eb264b8f2614596f1"},
+ {file = "bitarray-2.7.3-cp39-cp39-win_amd64.whl", hash = "sha256:757a08bf0aed5a650a399f8c66bcba00c210bce34408b6d7b09b4837bee8f4da"},
+ {file = "bitarray-2.7.3.tar.gz", hash = "sha256:f71256a32609b036adad932e1228b66a6b4e2cae6be397e588ddc0babd9a78b9"},
+]
+
+[[package]]
+name = "cachetools"
+version = "5.3.0"
+description = "Extensible memoizing collections and decorators"
+category = "main"
+optional = false
+python-versions = "~=3.7"
+files = [
+ {file = "cachetools-5.3.0-py3-none-any.whl", hash = "sha256:429e1a1e845c008ea6c85aa35d4b98b65d6a9763eeef3e37e92728a12d1de9d4"},
+ {file = "cachetools-5.3.0.tar.gz", hash = "sha256:13dfddc7b8df938c21a940dfa6557ce6e94a2f1cdfa58eb90c805721d58f2c14"},
+]
+
+[[package]]
+name = "certifi"
+version = "2022.12.7"
+description = "Python package for providing Mozilla's CA Bundle."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"},
+ {file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
+]
+
+[[package]]
+name = "cffi"
+version = "1.15.1"
+description = "Foreign Function Interface for Python calling C code."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "cffi-1.15.1-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:a66d3508133af6e8548451b25058d5812812ec3798c886bf38ed24a98216fab2"},
+ {file = "cffi-1.15.1-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:470c103ae716238bbe698d67ad020e1db9d9dba34fa5a899b5e21577e6d52ed2"},
+ {file = "cffi-1.15.1-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:9ad5db27f9cabae298d151c85cf2bad1d359a1b9c686a275df03385758e2f914"},
+ {file = "cffi-1.15.1-cp27-cp27m-win32.whl", hash = "sha256:b3bbeb01c2b273cca1e1e0c5df57f12dce9a4dd331b4fa1635b8bec26350bde3"},
+ {file = "cffi-1.15.1-cp27-cp27m-win_amd64.whl", hash = "sha256:e00b098126fd45523dd056d2efba6c5a63b71ffe9f2bbe1a4fe1716e1d0c331e"},
+ {file = "cffi-1.15.1-cp27-cp27mu-manylinux1_i686.whl", hash = "sha256:d61f4695e6c866a23a21acab0509af1cdfd2c013cf256bbf5b6b5e2695827162"},
+ {file = "cffi-1.15.1-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:ed9cb427ba5504c1dc15ede7d516b84757c3e3d7868ccc85121d9310d27eed0b"},
+ {file = "cffi-1.15.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:39d39875251ca8f612b6f33e6b1195af86d1b3e60086068be9cc053aa4376e21"},
+ {file = "cffi-1.15.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:285d29981935eb726a4399badae8f0ffdff4f5050eaa6d0cfc3f64b857b77185"},
+ {file = "cffi-1.15.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3eb6971dcff08619f8d91607cfc726518b6fa2a9eba42856be181c6d0d9515fd"},
+ {file = "cffi-1.15.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:21157295583fe8943475029ed5abdcf71eb3911894724e360acff1d61c1d54bc"},
+ {file = "cffi-1.15.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5635bd9cb9731e6d4a1132a498dd34f764034a8ce60cef4f5319c0541159392f"},
+ {file = "cffi-1.15.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2012c72d854c2d03e45d06ae57f40d78e5770d252f195b93f581acf3ba44496e"},
+ {file = "cffi-1.15.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd86c085fae2efd48ac91dd7ccffcfc0571387fe1193d33b6394db7ef31fe2a4"},
+ {file = "cffi-1.15.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:fa6693661a4c91757f4412306191b6dc88c1703f780c8234035eac011922bc01"},
+ {file = "cffi-1.15.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:59c0b02d0a6c384d453fece7566d1c7e6b7bae4fc5874ef2ef46d56776d61c9e"},
+ {file = "cffi-1.15.1-cp310-cp310-win32.whl", hash = "sha256:cba9d6b9a7d64d4bd46167096fc9d2f835e25d7e4c121fb2ddfc6528fb0413b2"},
+ {file = "cffi-1.15.1-cp310-cp310-win_amd64.whl", hash = "sha256:ce4bcc037df4fc5e3d184794f27bdaab018943698f4ca31630bc7f84a7b69c6d"},
+ {file = "cffi-1.15.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3d08afd128ddaa624a48cf2b859afef385b720bb4b43df214f85616922e6a5ac"},
+ {file = "cffi-1.15.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3799aecf2e17cf585d977b780ce79ff0dc9b78d799fc694221ce814c2c19db83"},
+ {file = "cffi-1.15.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a591fe9e525846e4d154205572a029f653ada1a78b93697f3b5a8f1f2bc055b9"},
+ {file = "cffi-1.15.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3548db281cd7d2561c9ad9984681c95f7b0e38881201e157833a2342c30d5e8c"},
+ {file = "cffi-1.15.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:91fc98adde3d7881af9b59ed0294046f3806221863722ba7d8d120c575314325"},
+ {file = "cffi-1.15.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:94411f22c3985acaec6f83c6df553f2dbe17b698cc7f8ae751ff2237d96b9e3c"},
+ {file = "cffi-1.15.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:03425bdae262c76aad70202debd780501fabeaca237cdfddc008987c0e0f59ef"},
+ {file = "cffi-1.15.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:cc4d65aeeaa04136a12677d3dd0b1c0c94dc43abac5860ab33cceb42b801c1e8"},
+ {file = "cffi-1.15.1-cp311-cp311-win32.whl", hash = "sha256:a0f100c8912c114ff53e1202d0078b425bee3649ae34d7b070e9697f93c5d52d"},
+ {file = "cffi-1.15.1-cp311-cp311-win_amd64.whl", hash = "sha256:04ed324bda3cda42b9b695d51bb7d54b680b9719cfab04227cdd1e04e5de3104"},
+ {file = "cffi-1.15.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50a74364d85fd319352182ef59c5c790484a336f6db772c1a9231f1c3ed0cbd7"},
+ {file = "cffi-1.15.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e263d77ee3dd201c3a142934a086a4450861778baaeeb45db4591ef65550b0a6"},
+ {file = "cffi-1.15.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cec7d9412a9102bdc577382c3929b337320c4c4c4849f2c5cdd14d7368c5562d"},
+ {file = "cffi-1.15.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4289fc34b2f5316fbb762d75362931e351941fa95fa18789191b33fc4cf9504a"},
+ {file = "cffi-1.15.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:173379135477dc8cac4bc58f45db08ab45d228b3363adb7af79436135d028405"},
+ {file = "cffi-1.15.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:6975a3fac6bc83c4a65c9f9fcab9e47019a11d3d2cf7f3c0d03431bf145a941e"},
+ {file = "cffi-1.15.1-cp36-cp36m-win32.whl", hash = "sha256:2470043b93ff09bf8fb1d46d1cb756ce6132c54826661a32d4e4d132e1977adf"},
+ {file = "cffi-1.15.1-cp36-cp36m-win_amd64.whl", hash = "sha256:30d78fbc8ebf9c92c9b7823ee18eb92f2e6ef79b45ac84db507f52fbe3ec4497"},
+ {file = "cffi-1.15.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:198caafb44239b60e252492445da556afafc7d1e3ab7a1fb3f0584ef6d742375"},
+ {file = "cffi-1.15.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5ef34d190326c3b1f822a5b7a45f6c4535e2f47ed06fec77d3d799c450b2651e"},
+ {file = "cffi-1.15.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8102eaf27e1e448db915d08afa8b41d6c7ca7a04b7d73af6514df10a3e74bd82"},
+ {file = "cffi-1.15.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5df2768244d19ab7f60546d0c7c63ce1581f7af8b5de3eb3004b9b6fc8a9f84b"},
+ {file = "cffi-1.15.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a8c4917bd7ad33e8eb21e9a5bbba979b49d9a97acb3a803092cbc1133e20343c"},
+ {file = "cffi-1.15.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e2642fe3142e4cc4af0799748233ad6da94c62a8bec3a6648bf8ee68b1c7426"},
+ {file = "cffi-1.15.1-cp37-cp37m-win32.whl", hash = "sha256:e229a521186c75c8ad9490854fd8bbdd9a0c9aa3a524326b55be83b54d4e0ad9"},
+ {file = "cffi-1.15.1-cp37-cp37m-win_amd64.whl", hash = "sha256:a0b71b1b8fbf2b96e41c4d990244165e2c9be83d54962a9a1d118fd8657d2045"},
+ {file = "cffi-1.15.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:320dab6e7cb2eacdf0e658569d2575c4dad258c0fcc794f46215e1e39f90f2c3"},
+ {file = "cffi-1.15.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1e74c6b51a9ed6589199c787bf5f9875612ca4a8a0785fb2d4a84429badaf22a"},
+ {file = "cffi-1.15.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5c84c68147988265e60416b57fc83425a78058853509c1b0629c180094904a5"},
+ {file = "cffi-1.15.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3b926aa83d1edb5aa5b427b4053dc420ec295a08e40911296b9eb1b6170f6cca"},
+ {file = "cffi-1.15.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:87c450779d0914f2861b8526e035c5e6da0a3199d8f1add1a665e1cbc6fc6d02"},
+ {file = "cffi-1.15.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f2c9f67e9821cad2e5f480bc8d83b8742896f1242dba247911072d4fa94c192"},
+ {file = "cffi-1.15.1-cp38-cp38-win32.whl", hash = "sha256:8b7ee99e510d7b66cdb6c593f21c043c248537a32e0bedf02e01e9553a172314"},
+ {file = "cffi-1.15.1-cp38-cp38-win_amd64.whl", hash = "sha256:00a9ed42e88df81ffae7a8ab6d9356b371399b91dbdf0c3cb1e84c03a13aceb5"},
+ {file = "cffi-1.15.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:54a2db7b78338edd780e7ef7f9f6c442500fb0d41a5a4ea24fff1c929d5af585"},
+ {file = "cffi-1.15.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fcd131dd944808b5bdb38e6f5b53013c5aa4f334c5cad0c72742f6eba4b73db0"},
+ {file = "cffi-1.15.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7473e861101c9e72452f9bf8acb984947aa1661a7704553a9f6e4baa5ba64415"},
+ {file = "cffi-1.15.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6c9a799e985904922a4d207a94eae35c78ebae90e128f0c4e521ce339396be9d"},
+ {file = "cffi-1.15.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3bcde07039e586f91b45c88f8583ea7cf7a0770df3a1649627bf598332cb6984"},
+ {file = "cffi-1.15.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:33ab79603146aace82c2427da5ca6e58f2b3f2fb5da893ceac0c42218a40be35"},
+ {file = "cffi-1.15.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d598b938678ebf3c67377cdd45e09d431369c3b1a5b331058c338e201f12b27"},
+ {file = "cffi-1.15.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:db0fbb9c62743ce59a9ff687eb5f4afbe77e5e8403d6697f7446e5f609976f76"},
+ {file = "cffi-1.15.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:98d85c6a2bef81588d9227dde12db8a7f47f639f4a17c9ae08e773aa9c697bf3"},
+ {file = "cffi-1.15.1-cp39-cp39-win32.whl", hash = "sha256:40f4774f5a9d4f5e344f31a32b5096977b5d48560c5592e2f3d2c4374bd543ee"},
+ {file = "cffi-1.15.1-cp39-cp39-win_amd64.whl", hash = "sha256:70df4e3b545a17496c9b3f41f5115e69a4f2e77e94e1d2a8e1070bc0c38c8a3c"},
+ {file = "cffi-1.15.1.tar.gz", hash = "sha256:d400bfb9a37b1351253cb402671cea7e89bdecc294e8016a707f6d1d8ac934f9"},
+]
+
+[package.dependencies]
+pycparser = "*"
+
+[[package]]
+name = "charset-normalizer"
+version = "3.1.0"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+files = [
+ {file = "charset-normalizer-3.1.0.tar.gz", hash = "sha256:34e0a2f9c370eb95597aae63bf85eb5e96826d81e3dcf88b8886012906f509b5"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e0ac8959c929593fee38da1c2b64ee9778733cdf03c482c9ff1d508b6b593b2b"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d7fc3fca01da18fbabe4625d64bb612b533533ed10045a2ac3dd194bfa656b60"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:04eefcee095f58eaabe6dc3cc2262f3bcd776d2c67005880894f447b3f2cb9c1"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20064ead0717cf9a73a6d1e779b23d149b53daf971169289ed2ed43a71e8d3b0"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1435ae15108b1cb6fffbcea2af3d468683b7afed0169ad718451f8db5d1aff6f"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c84132a54c750fda57729d1e2599bb598f5fa0344085dbde5003ba429a4798c0"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75f2568b4189dda1c567339b48cba4ac7384accb9c2a7ed655cd86b04055c795"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:11d3bcb7be35e7b1bba2c23beedac81ee893ac9871d0ba79effc7fc01167db6c"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:891cf9b48776b5c61c700b55a598621fdb7b1e301a550365571e9624f270c203"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:5f008525e02908b20e04707a4f704cd286d94718f48bb33edddc7d7b584dddc1"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:b06f0d3bf045158d2fb8837c5785fe9ff9b8c93358be64461a1089f5da983137"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:49919f8400b5e49e961f320c735388ee686a62327e773fa5b3ce6721f7e785ce"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:22908891a380d50738e1f978667536f6c6b526a2064156203d418f4856d6e86a"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-win32.whl", hash = "sha256:12d1a39aa6b8c6f6248bb54550efcc1c38ce0d8096a146638fd4738e42284448"},
+ {file = "charset_normalizer-3.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:65ed923f84a6844de5fd29726b888e58c62820e0769b76565480e1fdc3d062f8"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9a3267620866c9d17b959a84dd0bd2d45719b817245e49371ead79ed4f710d19"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6734e606355834f13445b6adc38b53c0fd45f1a56a9ba06c2058f86893ae8017"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f8303414c7b03f794347ad062c0516cee0e15f7a612abd0ce1e25caf6ceb47df"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aaf53a6cebad0eae578f062c7d462155eada9c172bd8c4d250b8c1d8eb7f916a"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3dc5b6a8ecfdc5748a7e429782598e4f17ef378e3e272eeb1340ea57c9109f41"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e1b25e3ad6c909f398df8921780d6a3d120d8c09466720226fc621605b6f92b1"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ca564606d2caafb0abe6d1b5311c2649e8071eb241b2d64e75a0d0065107e62"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b82fab78e0b1329e183a65260581de4375f619167478dddab510c6c6fb04d9b6"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bd7163182133c0c7701b25e604cf1611c0d87712e56e88e7ee5d72deab3e76b5"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:11d117e6c63e8f495412d37e7dc2e2fff09c34b2d09dbe2bee3c6229577818be"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:cf6511efa4801b9b38dc5546d7547d5b5c6ef4b081c60b23e4d941d0eba9cbeb"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:abc1185d79f47c0a7aaf7e2412a0eb2c03b724581139193d2d82b3ad8cbb00ac"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:cb7b2ab0188829593b9de646545175547a70d9a6e2b63bf2cd87a0a391599324"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-win32.whl", hash = "sha256:c36bcbc0d5174a80d6cccf43a0ecaca44e81d25be4b7f90f0ed7bcfbb5a00909"},
+ {file = "charset_normalizer-3.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:cca4def576f47a09a943666b8f829606bcb17e2bc2d5911a46c8f8da45f56755"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:0c95f12b74681e9ae127728f7e5409cbbef9cd914d5896ef238cc779b8152373"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fca62a8301b605b954ad2e9c3666f9d97f63872aa4efcae5492baca2056b74ab"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ac0aa6cd53ab9a31d397f8303f92c42f534693528fafbdb997c82bae6e477ad9"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c3af8e0f07399d3176b179f2e2634c3ce9c1301379a6b8c9c9aeecd481da494f"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a5fc78f9e3f501a1614a98f7c54d3969f3ad9bba8ba3d9b438c3bc5d047dd28"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:628c985afb2c7d27a4800bfb609e03985aaecb42f955049957814e0491d4006d"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:74db0052d985cf37fa111828d0dd230776ac99c740e1a758ad99094be4f1803d"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:1e8fcdd8f672a1c4fc8d0bd3a2b576b152d2a349782d1eb0f6b8e52e9954731d"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:04afa6387e2b282cf78ff3dbce20f0cc071c12dc8f685bd40960cc68644cfea6"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:dd5653e67b149503c68c4018bf07e42eeed6b4e956b24c00ccdf93ac79cdff84"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d2686f91611f9e17f4548dbf050e75b079bbc2a82be565832bc8ea9047b61c8c"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-win32.whl", hash = "sha256:4155b51ae05ed47199dc5b2a4e62abccb274cee6b01da5b895099b61b1982974"},
+ {file = "charset_normalizer-3.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:322102cdf1ab682ecc7d9b1c5eed4ec59657a65e1c146a0da342b78f4112db23"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:e633940f28c1e913615fd624fcdd72fdba807bf53ea6925d6a588e84e1151531"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:3a06f32c9634a8705f4ca9946d667609f52cf130d5548881401f1eb2c39b1e2c"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7381c66e0561c5757ffe616af869b916c8b4e42b367ab29fedc98481d1e74e14"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3573d376454d956553c356df45bb824262c397c6e26ce43e8203c4c540ee0acb"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e89df2958e5159b811af9ff0f92614dabf4ff617c03a4c1c6ff53bf1c399e0e1"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:78cacd03e79d009d95635e7d6ff12c21eb89b894c354bd2b2ed0b4763373693b"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de5695a6f1d8340b12a5d6d4484290ee74d61e467c39ff03b39e30df62cf83a0"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1c60b9c202d00052183c9be85e5eaf18a4ada0a47d188a83c8f5c5b23252f649"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:f645caaf0008bacf349875a974220f1f1da349c5dbe7c4ec93048cdc785a3326"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:ea9f9c6034ea2d93d9147818f17c2a0860d41b71c38b9ce4d55f21b6f9165a11"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:80d1543d58bd3d6c271b66abf454d437a438dff01c3e62fdbcd68f2a11310d4b"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:73dc03a6a7e30b7edc5b01b601e53e7fc924b04e1835e8e407c12c037e81adbd"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6f5c2e7bc8a4bf7c426599765b1bd33217ec84023033672c1e9a8b35eaeaaaf8"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-win32.whl", hash = "sha256:12a2b561af122e3d94cdb97fe6fb2bb2b82cef0cdca131646fdb940a1eda04f0"},
+ {file = "charset_normalizer-3.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:3160a0fd9754aab7d47f95a6b63ab355388d890163eb03b2d2b87ab0a30cfa59"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:38e812a197bf8e71a59fe55b757a84c1f946d0ac114acafaafaf21667a7e169e"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6baf0baf0d5d265fa7944feb9f7451cc316bfe30e8df1a61b1bb08577c554f31"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8f25e17ab3039b05f762b0a55ae0b3632b2e073d9c8fc88e89aca31a6198e88f"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3747443b6a904001473370d7810aa19c3a180ccd52a7157aacc264a5ac79265e"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b116502087ce8a6b7a5f1814568ccbd0e9f6cfd99948aa59b0e241dc57cf739f"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d16fd5252f883eb074ca55cb622bc0bee49b979ae4e8639fff6ca3ff44f9f854"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21fa558996782fc226b529fdd2ed7866c2c6ec91cee82735c98a197fae39f706"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6f6c7a8a57e9405cad7485f4c9d3172ae486cfef1344b5ddd8e5239582d7355e"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ac3775e3311661d4adace3697a52ac0bab17edd166087d493b52d4f4f553f9f0"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:10c93628d7497c81686e8e5e557aafa78f230cd9e77dd0c40032ef90c18f2230"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:6f4f4668e1831850ebcc2fd0b1cd11721947b6dc7c00bf1c6bd3c929ae14f2c7"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0be65ccf618c1e7ac9b849c315cc2e8a8751d9cfdaa43027d4f6624bd587ab7e"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:53d0a3fa5f8af98a1e261de6a3943ca631c526635eb5817a87a59d9a57ebf48f"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-win32.whl", hash = "sha256:a04f86f41a8916fe45ac5024ec477f41f886b3c435da2d4e3d2709b22ab02af1"},
+ {file = "charset_normalizer-3.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:830d2948a5ec37c386d3170c483063798d7879037492540f10a475e3fd6f244b"},
+ {file = "charset_normalizer-3.1.0-py3-none-any.whl", hash = "sha256:3d9098b479e78c85080c98e1e35ff40b4a31d8953102bb0fd7d1b6f8a2111a3d"},
+]
+
+[[package]]
+name = "click"
+version = "8.1.3"
+description = "Composable command line interface toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
+ {file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "cmake"
+version = "3.26.1"
+description = "CMake is an open-source, cross-platform family of tools designed to build, test and package software"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "cmake-3.26.1-py2.py3-none-macosx_10_10_universal2.macosx_10_10_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:d8a7e0cc8677677a732aff3e3fd0ad64eeff43cac772614b03c436912247d0d8"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2010_i686.manylinux_2_12_i686.whl", hash = "sha256:f2f721f5aebe304c281ee4b1d2dfbf7f4a52fca003834b2b4a3ba838aeded63c"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:63a012b72836702eadfe4fba9642aeb17337f26861f4768e837053f40e98cb46"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2b72be88b7bfaa6ae59566cbb9d6a5553f19b2a8d14efa6ac0cf019a29860a1b"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:1278354f7210e22458aa9137d46a56da1f115a7b76ad2733f0bf6041fb40f1dc"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:de96a5522917fba0ab0da2d01d9dd9462fa80f365218bf27162d539c2335758f"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:449928ad7dfcd41e4dcff64c7d44f86557883c70577666a19e79e22d783bbbd0"},
+ {file = "cmake-3.26.1-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:19fa3e457afecf2803265f71652ef17c3f1d317173c330ba46767a0853d38fa0"},
+ {file = "cmake-3.26.1-py2.py3-none-musllinux_1_1_aarch64.whl", hash = "sha256:43360650d60d177d979e4ad0a5f31afa286e6d88f5350f7a38c29d94514900eb"},
+ {file = "cmake-3.26.1-py2.py3-none-musllinux_1_1_i686.whl", hash = "sha256:16aac10363bc926da5109a59ef8fe46ddcd7e3d421de61f871b35524eef2f1ae"},
+ {file = "cmake-3.26.1-py2.py3-none-musllinux_1_1_ppc64le.whl", hash = "sha256:e460ba5070be4dcac9613cb526a46db4e5fa19d8b909a8d8d5244c6cc3c777e1"},
+ {file = "cmake-3.26.1-py2.py3-none-musllinux_1_1_s390x.whl", hash = "sha256:fd2ecc0899f7939a014bd906df85e8681bd63ce457de3ab0b5d9e369fa3bdf79"},
+ {file = "cmake-3.26.1-py2.py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:22781a23e274ba9bf380b970649654851c1b4b9d83b65fec12ee2e2e03b6ffc4"},
+ {file = "cmake-3.26.1-py2.py3-none-win32.whl", hash = "sha256:7b4e81de30ac1fb2f1eb5287063e140b53f376fd9ed7e2060c1c7b5917bd5f83"},
+ {file = "cmake-3.26.1-py2.py3-none-win_amd64.whl", hash = "sha256:90845b6c87a25be07e9220f67dd7f6c891c6ec14d764d37335218d97f9ea4520"},
+ {file = "cmake-3.26.1-py2.py3-none-win_arm64.whl", hash = "sha256:43bd96327e2631183bb4829ba20cb810e20b4b0c68f852fcd7082fbb5359d57c"},
+ {file = "cmake-3.26.1.tar.gz", hash = "sha256:4e0eb3c03dcf2d459f78d96cc85f7482476aeb1ae5ada65150b1db35c0f70cc7"},
+]
+
+[package.extras]
+test = ["codecov (>=2.0.5)", "coverage (>=4.2)", "flake8 (>=3.0.4)", "path.py (>=11.5.0)", "pytest (>=3.0.3)", "pytest-cov (>=2.4.0)", "pytest-runner (>=2.9)", "pytest-virtualenv (>=1.7.0)", "scikit-build (>=0.10.0)", "setuptools (>=28.0.0)", "virtualenv (>=15.0.3)", "wheel"]
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+ {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
+ {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
+]
+
+[[package]]
+name = "contourpy"
+version = "1.0.7"
+description = "Python library for calculating contours of 2D quadrilateral grids"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "contourpy-1.0.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:95c3acddf921944f241b6773b767f1cbce71d03307270e2d769fd584d5d1092d"},
+ {file = "contourpy-1.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:fc1464c97579da9f3ab16763c32e5c5d5bb5fa1ec7ce509a4ca6108b61b84fab"},
+ {file = "contourpy-1.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8acf74b5d383414401926c1598ed77825cd530ac7b463ebc2e4f46638f56cce6"},
+ {file = "contourpy-1.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1c71fdd8f1c0f84ffd58fca37d00ca4ebaa9e502fb49825484da075ac0b0b803"},
+ {file = "contourpy-1.0.7-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f99e9486bf1bb979d95d5cffed40689cb595abb2b841f2991fc894b3452290e8"},
+ {file = "contourpy-1.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87f4d8941a9564cda3f7fa6a6cd9b32ec575830780677932abdec7bcb61717b0"},
+ {file = "contourpy-1.0.7-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9e20e5a1908e18aaa60d9077a6d8753090e3f85ca25da6e25d30dc0a9e84c2c6"},
+ {file = "contourpy-1.0.7-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a877ada905f7d69b2a31796c4b66e31a8068b37aa9b78832d41c82fc3e056ddd"},
+ {file = "contourpy-1.0.7-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:6381fa66866b0ea35e15d197fc06ac3840a9b2643a6475c8fff267db8b9f1e69"},
+ {file = "contourpy-1.0.7-cp310-cp310-win32.whl", hash = "sha256:3c184ad2433635f216645fdf0493011a4667e8d46b34082f5a3de702b6ec42e3"},
+ {file = "contourpy-1.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:3caea6365b13119626ee996711ab63e0c9d7496f65641f4459c60a009a1f3e80"},
+ {file = "contourpy-1.0.7-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ed33433fc3820263a6368e532f19ddb4c5990855e4886088ad84fd7c4e561c71"},
+ {file = "contourpy-1.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:38e2e577f0f092b8e6774459317c05a69935a1755ecfb621c0a98f0e3c09c9a5"},
+ {file = "contourpy-1.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ae90d5a8590e5310c32a7630b4b8618cef7563cebf649011da80874d0aa8f414"},
+ {file = "contourpy-1.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:130230b7e49825c98edf0b428b7aa1125503d91732735ef897786fe5452b1ec2"},
+ {file = "contourpy-1.0.7-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:58569c491e7f7e874f11519ef46737cea1d6eda1b514e4eb5ac7dab6aa864d02"},
+ {file = "contourpy-1.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:54d43960d809c4c12508a60b66cb936e7ed57d51fb5e30b513934a4a23874fae"},
+ {file = "contourpy-1.0.7-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:152fd8f730c31fd67fe0ffebe1df38ab6a669403da93df218801a893645c6ccc"},
+ {file = "contourpy-1.0.7-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:9056c5310eb1daa33fc234ef39ebfb8c8e2533f088bbf0bc7350f70a29bde1ac"},
+ {file = "contourpy-1.0.7-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a9d7587d2fdc820cc9177139b56795c39fb8560f540bba9ceea215f1f66e1566"},
+ {file = "contourpy-1.0.7-cp311-cp311-win32.whl", hash = "sha256:4ee3ee247f795a69e53cd91d927146fb16c4e803c7ac86c84104940c7d2cabf0"},
+ {file = "contourpy-1.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:5caeacc68642e5f19d707471890f037a13007feba8427eb7f2a60811a1fc1350"},
+ {file = "contourpy-1.0.7-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:fd7dc0e6812b799a34f6d12fcb1000539098c249c8da54f3566c6a6461d0dbad"},
+ {file = "contourpy-1.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0f9d350b639db6c2c233d92c7f213d94d2e444d8e8fc5ca44c9706cf72193772"},
+ {file = "contourpy-1.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e96a08b62bb8de960d3a6afbc5ed8421bf1a2d9c85cc4ea73f4bc81b4910500f"},
+ {file = "contourpy-1.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:031154ed61f7328ad7f97662e48660a150ef84ee1bc8876b6472af88bf5a9b98"},
+ {file = "contourpy-1.0.7-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2e9ebb4425fc1b658e13bace354c48a933b842d53c458f02c86f371cecbedecc"},
+ {file = "contourpy-1.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:efb8f6d08ca7998cf59eaf50c9d60717f29a1a0a09caa46460d33b2924839dbd"},
+ {file = "contourpy-1.0.7-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6c180d89a28787e4b73b07e9b0e2dac7741261dbdca95f2b489c4f8f887dd810"},
+ {file = "contourpy-1.0.7-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:b8d587cc39057d0afd4166083d289bdeff221ac6d3ee5046aef2d480dc4b503c"},
+ {file = "contourpy-1.0.7-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:769eef00437edf115e24d87f8926955f00f7704bede656ce605097584f9966dc"},
+ {file = "contourpy-1.0.7-cp38-cp38-win32.whl", hash = "sha256:62398c80ef57589bdbe1eb8537127321c1abcfdf8c5f14f479dbbe27d0322e66"},
+ {file = "contourpy-1.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:57119b0116e3f408acbdccf9eb6ef19d7fe7baf0d1e9aaa5381489bc1aa56556"},
+ {file = "contourpy-1.0.7-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:30676ca45084ee61e9c3da589042c24a57592e375d4b138bd84d8709893a1ba4"},
+ {file = "contourpy-1.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3e927b3868bd1e12acee7cc8f3747d815b4ab3e445a28d2e5373a7f4a6e76ba1"},
+ {file = "contourpy-1.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:366a0cf0fc079af5204801786ad7a1c007714ee3909e364dbac1729f5b0849e5"},
+ {file = "contourpy-1.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89ba9bb365446a22411f0673abf6ee1fea3b2cf47b37533b970904880ceb72f3"},
+ {file = "contourpy-1.0.7-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:71b0bf0c30d432278793d2141362ac853859e87de0a7dee24a1cea35231f0d50"},
+ {file = "contourpy-1.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e7281244c99fd7c6f27c1c6bfafba878517b0b62925a09b586d88ce750a016d2"},
+ {file = "contourpy-1.0.7-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b6d0f9e1d39dbfb3977f9dd79f156c86eb03e57a7face96f199e02b18e58d32a"},
+ {file = "contourpy-1.0.7-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7f6979d20ee5693a1057ab53e043adffa1e7418d734c1532e2d9e915b08d8ec2"},
+ {file = "contourpy-1.0.7-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5dd34c1ae752515318224cba7fc62b53130c45ac6a1040c8b7c1a223c46e8967"},
+ {file = "contourpy-1.0.7-cp39-cp39-win32.whl", hash = "sha256:c5210e5d5117e9aec8c47d9156d1d3835570dd909a899171b9535cb4a3f32693"},
+ {file = "contourpy-1.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:60835badb5ed5f4e194a6f21c09283dd6e007664a86101431bf870d9e86266c4"},
+ {file = "contourpy-1.0.7-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ce41676b3d0dd16dbcfabcc1dc46090aaf4688fd6e819ef343dbda5a57ef0161"},
+ {file = "contourpy-1.0.7-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5a011cf354107b47c58ea932d13b04d93c6d1d69b8b6dce885e642531f847566"},
+ {file = "contourpy-1.0.7-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:31a55dccc8426e71817e3fe09b37d6d48ae40aae4ecbc8c7ad59d6893569c436"},
+ {file = "contourpy-1.0.7-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:69f8ff4db108815addd900a74df665e135dbbd6547a8a69333a68e1f6e368ac2"},
+ {file = "contourpy-1.0.7-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:efe99298ba37e37787f6a2ea868265465410822f7bea163edcc1bd3903354ea9"},
+ {file = "contourpy-1.0.7-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a1e97b86f73715e8670ef45292d7cc033548266f07d54e2183ecb3c87598888f"},
+ {file = "contourpy-1.0.7-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc331c13902d0f50845099434cd936d49d7a2ca76cb654b39691974cb1e4812d"},
+ {file = "contourpy-1.0.7-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:24847601071f740837aefb730e01bd169fbcaa610209779a78db7ebb6e6a7051"},
+ {file = "contourpy-1.0.7-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:abf298af1e7ad44eeb93501e40eb5a67abbf93b5d90e468d01fc0c4451971afa"},
+ {file = "contourpy-1.0.7-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:64757f6460fc55d7e16ed4f1de193f362104285c667c112b50a804d482777edd"},
+ {file = "contourpy-1.0.7.tar.gz", hash = "sha256:d8165a088d31798b59e91117d1f5fc3df8168d8b48c4acc10fc0df0d0bdbcc5e"},
+]
+
+[package.dependencies]
+numpy = ">=1.16"
+
+[package.extras]
+bokeh = ["bokeh", "chromedriver", "selenium"]
+docs = ["furo", "sphinx-copybutton"]
+mypy = ["contourpy[bokeh]", "docutils-stubs", "mypy (==0.991)", "types-Pillow"]
+test = ["Pillow", "matplotlib", "pytest"]
+test-no-images = ["pytest"]
+
+[[package]]
+name = "cycler"
+version = "0.11.0"
+description = "Composable style cycles"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "cycler-0.11.0-py3-none-any.whl", hash = "sha256:3a27e95f763a428a739d2add979fa7494c912a32c17c4c38c4d5f082cad165a3"},
+ {file = "cycler-0.11.0.tar.gz", hash = "sha256:9c87405839a19696e837b3b818fed3f5f69f16f1eec1a1ad77e043dcea9c772f"},
+]
+
+[[package]]
+name = "cython"
+version = "0.29.34"
+description = "The Cython compiler for writing C extensions for the Python language."
+category = "main"
+optional = false
+python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
+files = [
+ {file = "Cython-0.29.34-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:742544024ddb74314e2d597accdb747ed76bd126e61fcf49940a5b5be0a8f381"},
+ {file = "Cython-0.29.34-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:03daae07f8cbf797506446adae512c3dd86e7f27a62a541fa1ee254baf43e32c"},
+ {file = "Cython-0.29.34-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5a8de3e793a576e40ca9b4f5518610cd416273c7dc5e254115656b6e4ec70663"},
+ {file = "Cython-0.29.34-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:60969d38e6a456a67e7ef8ae20668eff54e32ba439d4068ccf2854a44275a30f"},
+ {file = "Cython-0.29.34-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:21b88200620d80cfe193d199b259cdad2b9af56f916f0f7f474b5a3631ca0caa"},
+ {file = "Cython-0.29.34-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:308c8f1e58bf5e6e8a1c4dcf8abbd2d13d0f9b1e582f4d9ae8b89857342d8bb5"},
+ {file = "Cython-0.29.34-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_24_i686.whl", hash = "sha256:d8f822fb6ecd5d88c42136561f82960612421154fc5bf23c57103a367bb91356"},
+ {file = "Cython-0.29.34-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:56866323f1660cecb4d5ff3a1fba92a56b91b7cfae0a8253777aa4bdb3bdf9a8"},
+ {file = "Cython-0.29.34-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:e971db8aeb12e7c0697cefafe65eefcc33ff1224ae3d8c7f83346cbc42c6c270"},
+ {file = "Cython-0.29.34-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:e4401270b0dc464c23671e2e9d52a60985f988318febaf51b047190e855bbe7d"},
+ {file = "Cython-0.29.34-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_24_i686.whl", hash = "sha256:dce0a36d163c05ae8b21200059511217d79b47baf2b7b0f926e8367bd7a3cc24"},
+ {file = "Cython-0.29.34-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:dbd79221869ee9a6ccc4953b2c8838bb6ae08ab4d50ea4b60d7894f03739417b"},
+ {file = "Cython-0.29.34-cp35-cp35m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a0f4229df10bc4545ebbeaaf96ebb706011d8b333e54ed202beb03f2bee0a50e"},
+ {file = "Cython-0.29.34-cp35-cp35m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:fd1ea21f1cebf33ae288caa0f3e9b5563a709f4df8925d53bad99be693fc0d9b"},
+ {file = "Cython-0.29.34-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:d7ef5f68f4c5baa93349ea54a352f8716d18bee9a37f3e93eff38a5d4e9b7262"},
+ {file = "Cython-0.29.34-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:459994d1de0f99bb18fad9f2325f760c4b392b1324aef37bcc1cd94922dfce41"},
+ {file = "Cython-0.29.34-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_24_i686.whl", hash = "sha256:1d6c809e2f9ce5950bbc52a1d2352ef3d4fc56186b64cb0d50c8c5a3c1d17661"},
+ {file = "Cython-0.29.34-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f674ceb5f722d364395f180fbac273072fc1a266aab924acc9cfd5afc645aae1"},
+ {file = "Cython-0.29.34-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:9489de5b2044dcdfd9d6ca8242a02d560137b3c41b1f5ae1c4f6707d66d6e44d"},
+ {file = "Cython-0.29.34-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:5c121dc185040f4333bfded68963b4529698e1b6d994da56be32c97a90c896b6"},
+ {file = "Cython-0.29.34-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:b6149f7cc5b31bccb158c5b968e5a8d374fdc629792e7b928a9b66e08b03fca5"},
+ {file = "Cython-0.29.34-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:0ab3cbf3d62b0354631a45dc93cfcdf79098663b1c65a6033af4a452b52217a7"},
+ {file = "Cython-0.29.34-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_24_i686.whl", hash = "sha256:4a2723447d1334484681d5aede34184f2da66317891f94b80e693a2f96a8f1a7"},
+ {file = "Cython-0.29.34-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e40cf86aadc29ecd1cb6de67b0d9488705865deea4fc185c7ad56d7a6fc78703"},
+ {file = "Cython-0.29.34-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:8c3cd8bb8e880a3346f5685601004d96e0a2221e73edcaeea57ea848618b4ac6"},
+ {file = "Cython-0.29.34-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:0e9032cd650b0cb1d2c2ef2623f5714c14d14c28d7647d589c3eeed0baf7428e"},
+ {file = "Cython-0.29.34-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:bdb3285660e3068438791ace7dd7b1efd6b442a10b5c8d7a4f0c9d184d08c8ed"},
+ {file = "Cython-0.29.34-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:a8ad755f9364e720f10a36734a1c7a5ced5c679446718b589259261438a517c9"},
+ {file = "Cython-0.29.34-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_24_i686.whl", hash = "sha256:7595d29eaee95633dd8060f50f0e54b27472d01587659557ebcfe39da3ea946b"},
+ {file = "Cython-0.29.34-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e6ef7879668214d80ea3914c17e7d4e1ebf4242e0dd4dabe95ca5ccbe75589a5"},
+ {file = "Cython-0.29.34-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:ccb223b5f0fd95d8d27561efc0c14502c0945f1a32274835831efa5d5baddfc1"},
+ {file = "Cython-0.29.34-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:11b1b278b8edef215caaa5250ad65a10023bfa0b5a93c776552248fc6f60098d"},
+ {file = "Cython-0.29.34-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:5718319a01489688fdd22ddebb8e2fcbbd60be5f30de4336ea7063c3ae29fbe5"},
+ {file = "Cython-0.29.34-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:cfb2302ef617d647ee590a4c0a00ba3c2da05f301dcefe7721125565d2e51351"},
+ {file = "Cython-0.29.34-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_24_i686.whl", hash = "sha256:67b850cf46b861bc27226d31e1d87c0e69869a02f8d3cc5d5bef549764029879"},
+ {file = "Cython-0.29.34-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0963266dad685812c1dbb758fcd4de78290e3adc7db271c8664dcde27380b13e"},
+ {file = "Cython-0.29.34-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:7879992487d9060a61393eeefe00d299210256928dce44d887b6be313d342bac"},
+ {file = "Cython-0.29.34-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:44733366f1604b0c327613b6918469284878d2f5084297d10d26072fc6948d51"},
+ {file = "Cython-0.29.34-py2.py3-none-any.whl", hash = "sha256:be4f6b7be75a201c290c8611c0978549c60353890204573078e865423dbe3c83"},
+ {file = "Cython-0.29.34.tar.gz", hash = "sha256:1909688f5d7b521a60c396d20bba9e47a1b2d2784bfb085401e1e1e7d29a29a8"},
+]
+
+[[package]]
+name = "decorator"
+version = "5.1.1"
+description = "Decorators for Humans"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+files = [
+ {file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
+ {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
+]
+
+[[package]]
+name = "entrypoints"
+version = "0.4"
+description = "Discover and load entry points from installed packages."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "entrypoints-0.4-py3-none-any.whl", hash = "sha256:f174b5ff827504fd3cd97cc3f8649f3693f51538c7e4bdf3ef002c8429d42f9f"},
+ {file = "entrypoints-0.4.tar.gz", hash = "sha256:b706eddaa9218a19ebcd67b56818f05bb27589b1ca9e8d797b74affad4ccacd4"},
+]
+
+[[package]]
+name = "fairseq"
+version = "0.12.2"
+description = "Facebook AI Research Sequence-to-Sequence Toolkit"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "fairseq-0.12.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:fe65b07c5121b7cda0c7a17166994a6b0059259ce37881b6daa117b8c209b662"},
+ {file = "fairseq-0.12.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:0543905012e39f00bd8c3f3781d9f49e76ab309801eb2eb7de250f5984df0de3"},
+ {file = "fairseq-0.12.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c4877d65346797fc580a3a7e6e2364d2331a0026ef099c22eb8311441e49c2c6"},
+ {file = "fairseq-0.12.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:26454f334ca705c67f898846dff34e14c148fcdaf53b4f52d64209773b509347"},
+ {file = "fairseq-0.12.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:3b8c8b6dc368d2fd23a06ff613a2af05959eee275fe90846d7cffef4a43c522a"},
+ {file = "fairseq-0.12.2-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:08fa308c760f995cdc13d9c385e2b9d923a78b48275d8b4d78f3a854c71a8f29"},
+ {file = "fairseq-0.12.2.tar.gz", hash = "sha256:34f1b18426bf3844714534162f065ab733e049597476daa35fffb4d06a92b524"},
+]
+
+[package.dependencies]
+bitarray = "*"
+cffi = "*"
+cython = "*"
+hydra-core = ">=1.0.7,<1.1"
+numpy = {version = "*", markers = "python_version >= \"3.7\""}
+omegaconf = "<2.1"
+regex = "*"
+sacrebleu = ">=1.4.12"
+torch = "*"
+torchaudio = ">=0.8.0"
+tqdm = "*"
+
+[[package]]
+name = "faiss-cpu"
+version = "1.7.3"
+description = "A library for efficient similarity search and clustering of dense vectors."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "faiss-cpu-1.7.3.tar.gz", hash = "sha256:cb71fe3f2934732d157d9d8cfb6ed2dd4020a0065571c84842ff6a3f0beab310"},
+ {file = "faiss_cpu-1.7.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:343f025e0846239d987d0c719772387ad685b74e5ef62b2e5616cabef9062729"},
+ {file = "faiss_cpu-1.7.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8b7b1cf693d7c24b5a633ff024717bd715fec501af4854357da0805b4899bcec"},
+ {file = "faiss_cpu-1.7.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1c37e5fc0a266839844798a53dd42dd6afbee0c5905611f3f278297053fccbd7"},
+ {file = "faiss_cpu-1.7.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0628f7b0c6263ef4431995bb4f5f39833f999e96e6663935cbf0a1f2243dc4ac"},
+ {file = "faiss_cpu-1.7.3-cp310-cp310-win_amd64.whl", hash = "sha256:e22d1887c617156a673665c913ee82a30bfc1a3bc939ba8500b61328bce5a625"},
+ {file = "faiss_cpu-1.7.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6d411449a5f3c3abfcafadaac3190ab1ab206023fc9110da86649506dcbe8a27"},
+ {file = "faiss_cpu-1.7.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a10ea8622908f9f9ca4003e66da809dfad4af5c7d9fb7f582722d703bbc6c8bd"},
+ {file = "faiss_cpu-1.7.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c5ced43ae058a62f63b12194ec9aa4c34066b0ea813ecbd936c65b7d52848c8"},
+ {file = "faiss_cpu-1.7.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3df6371012248dea8e9509949e2d2c6d73dea7c1bdaa4ba4563eb1c3cd8021a6"},
+ {file = "faiss_cpu-1.7.3-cp311-cp311-win_amd64.whl", hash = "sha256:8b6ff7854c3f46104718c6b34e81cd48c156d970dd87703c5122ca90217bb8dc"},
+ {file = "faiss_cpu-1.7.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:ab6314a8fbcce11dc3ecb6f48dda8c4ec274ed11c1f336f599f480bf0561442c"},
+ {file = "faiss_cpu-1.7.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:877c0bbf4c4a1806d88e091aba4c91ff3fa35c3ede5663b7fafc5b39247a369e"},
+ {file = "faiss_cpu-1.7.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6f199be10d30ecc6ed65350931006eca01b7bb8faa27d63069318eea0f6a0c1"},
+ {file = "faiss_cpu-1.7.3-cp37-cp37m-win_amd64.whl", hash = "sha256:1ca2b7cdbfdcc6a2e8fa75a09594916b50ec8260913ca48334dc3ce797179b5f"},
+ {file = "faiss_cpu-1.7.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7b3f91856c19cfb8464178bab7e8ea94a391f6947b556be6754f9fc10b3c25fb"},
+ {file = "faiss_cpu-1.7.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7a238a0ef4d36c614d6f60e1ea308288b3920091638a3687f708de6071d007c1"},
+ {file = "faiss_cpu-1.7.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:af53bee502c629eaaaf8b5ec648484a726be0fd2768ad4ef2bd4b829384b2682"},
+ {file = "faiss_cpu-1.7.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:441d1c305595d925138f2cde63dabe8c10ee05fc8ad66bf750e278a7e8c409bd"},
+ {file = "faiss_cpu-1.7.3-cp38-cp38-win_amd64.whl", hash = "sha256:2766cc14b9004c1aae3b3943e693c3a9566eb1a25168b681981f9048276fe1e7"},
+ {file = "faiss_cpu-1.7.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:20ef191bb6164c8e794b11d20427568a75d15980b6d66732071e9aa57ea06e2d"},
+ {file = "faiss_cpu-1.7.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c57c293c4682066955626c2a2956be9a3b92594f69ed1a33abd72260a6911b69"},
+ {file = "faiss_cpu-1.7.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bd128170446ff3c3e28d89e813d32cd04f17fa3025794778a01a0d81524275dc"},
+ {file = "faiss_cpu-1.7.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a14d832b5361ce9af21977eb1dcdebe23b9edcc12aad40316df7ca1bd86bc6b5"},
+ {file = "faiss_cpu-1.7.3-cp39-cp39-win_amd64.whl", hash = "sha256:52df8895c5e59d1c9eda368a63790381a6f7fceddb22bed08f9c90a706d8a148"},
+]
+
+[[package]]
+name = "fastapi"
+version = "0.95.2"
+description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "fastapi-0.95.2-py3-none-any.whl", hash = "sha256:d374dbc4ef2ad9b803899bd3360d34c534adc574546e25314ab72c0c4411749f"},
+ {file = "fastapi-0.95.2.tar.gz", hash = "sha256:4d9d3e8c71c73f11874bcf5e33626258d143252e329a01002f767306c64fb982"},
+]
+
+[package.dependencies]
+pydantic = ">=1.6.2,<1.7 || >1.7,<1.7.1 || >1.7.1,<1.7.2 || >1.7.2,<1.7.3 || >1.7.3,<1.8 || >1.8,<1.8.1 || >1.8.1,<2.0.0"
+starlette = ">=0.27.0,<0.28.0"
+
+[package.extras]
+all = ["email-validator (>=1.1.1)", "httpx (>=0.23.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=2.11.2)", "orjson (>=3.2.1)", "python-multipart (>=0.0.5)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"]
+dev = ["pre-commit (>=2.17.0,<3.0.0)", "ruff (==0.0.138)", "uvicorn[standard] (>=0.12.0,<0.21.0)"]
+doc = ["mdx-include (>=1.4.1,<2.0.0)", "mkdocs (>=1.1.2,<2.0.0)", "mkdocs-markdownextradata-plugin (>=0.1.7,<0.3.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "pyyaml (>=5.3.1,<7.0.0)", "typer-cli (>=0.0.13,<0.0.14)", "typer[all] (>=0.6.1,<0.8.0)"]
+test = ["anyio[trio] (>=3.2.1,<4.0.0)", "black (==23.1.0)", "coverage[toml] (>=6.5.0,<8.0)", "databases[sqlite] (>=0.3.2,<0.7.0)", "email-validator (>=1.1.1,<2.0.0)", "flask (>=1.1.2,<3.0.0)", "httpx (>=0.23.0,<0.24.0)", "isort (>=5.0.6,<6.0.0)", "mypy (==0.982)", "orjson (>=3.2.1,<4.0.0)", "passlib[bcrypt] (>=1.7.2,<2.0.0)", "peewee (>=3.13.3,<4.0.0)", "pytest (>=7.1.3,<8.0.0)", "python-jose[cryptography] (>=3.3.0,<4.0.0)", "python-multipart (>=0.0.5,<0.0.7)", "pyyaml (>=5.3.1,<7.0.0)", "ruff (==0.0.138)", "sqlalchemy (>=1.3.18,<1.4.43)", "types-orjson (==3.6.2)", "types-ujson (==5.7.0.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)"]
+
+[[package]]
+name = "ffmpeg-python"
+version = "0.2.0"
+description = "Python bindings for FFmpeg - with complex filtering support"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "ffmpeg-python-0.2.0.tar.gz", hash = "sha256:65225db34627c578ef0e11c8b1eb528bb35e024752f6f10b78c011f6f64c4127"},
+ {file = "ffmpeg_python-0.2.0-py3-none-any.whl", hash = "sha256:ac441a0404e053f8b6a1113a77c0f452f1cfc62f6344a769475ffdc0f56c23c5"},
+]
+
+[package.dependencies]
+future = "*"
+
+[package.extras]
+dev = ["Sphinx (==2.1.0)", "future (==0.17.1)", "numpy (==1.16.4)", "pytest (==4.6.1)", "pytest-mock (==1.10.4)", "tox (==3.12.1)"]
+
+[[package]]
+name = "ffmpy"
+version = "0.3.0"
+description = "A simple Python wrapper for ffmpeg"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "ffmpy-0.3.0.tar.gz", hash = "sha256:757591581eee25b4a50ac9ffb9b58035a2794533db47e0512f53fb2d7b6f9adc"},
+]
+
+[[package]]
+name = "filelock"
+version = "3.10.7"
+description = "A platform independent file lock."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "filelock-3.10.7-py3-none-any.whl", hash = "sha256:bde48477b15fde2c7e5a0713cbe72721cb5a5ad32ee0b8f419907960b9d75536"},
+ {file = "filelock-3.10.7.tar.gz", hash = "sha256:892be14aa8efc01673b5ed6589dbccb95f9a8596f0507e232626155495c18105"},
+]
+
+[package.extras]
+docs = ["furo (>=2022.12.7)", "sphinx (>=6.1.3)", "sphinx-autodoc-typehints (>=1.22,!=1.23.4)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.2.2)", "diff-cover (>=7.5)", "pytest (>=7.2.2)", "pytest-cov (>=4)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"]
+
+[[package]]
+name = "fonttools"
+version = "4.39.3"
+description = "Tools to manipulate font files"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "fonttools-4.39.3-py3-none-any.whl", hash = "sha256:64c0c05c337f826183637570ac5ab49ee220eec66cf50248e8df527edfa95aeb"},
+ {file = "fonttools-4.39.3.zip", hash = "sha256:9234b9f57b74e31b192c3fc32ef1a40750a8fbc1cd9837a7b7bfc4ca4a5c51d7"},
+]
+
+[package.extras]
+all = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "fs (>=2.2.0,<3)", "lxml (>=4.0,<5)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres", "scipy", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.0.0)", "xattr", "zopfli (>=0.1.4)"]
+graphite = ["lz4 (>=1.7.4.2)"]
+interpolatable = ["munkres", "scipy"]
+lxml = ["lxml (>=4.0,<5)"]
+pathops = ["skia-pathops (>=0.5.0)"]
+plot = ["matplotlib"]
+repacker = ["uharfbuzz (>=0.23.0)"]
+symfont = ["sympy"]
+type1 = ["xattr"]
+ufo = ["fs (>=2.2.0,<3)"]
+unicode = ["unicodedata2 (>=15.0.0)"]
+woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
+
+[[package]]
+name = "frozenlist"
+version = "1.3.3"
+description = "A list-like structure which implements collections.abc.MutableSequence"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "frozenlist-1.3.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ff8bf625fe85e119553b5383ba0fb6aa3d0ec2ae980295aaefa552374926b3f4"},
+ {file = "frozenlist-1.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dfbac4c2dfcc082fcf8d942d1e49b6aa0766c19d3358bd86e2000bf0fa4a9cf0"},
+ {file = "frozenlist-1.3.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b1c63e8d377d039ac769cd0926558bb7068a1f7abb0f003e3717ee003ad85530"},
+ {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7fdfc24dcfce5b48109867c13b4cb15e4660e7bd7661741a391f821f23dfdca7"},
+ {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2c926450857408e42f0bbc295e84395722ce74bae69a3b2aa2a65fe22cb14b99"},
+ {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1841e200fdafc3d51f974d9d377c079a0694a8f06de2e67b48150328d66d5483"},
+ {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f470c92737afa7d4c3aacc001e335062d582053d4dbe73cda126f2d7031068dd"},
+ {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:783263a4eaad7c49983fe4b2e7b53fa9770c136c270d2d4bbb6d2192bf4d9caf"},
+ {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:924620eef691990dfb56dc4709f280f40baee568c794b5c1885800c3ecc69816"},
+ {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ae4dc05c465a08a866b7a1baf360747078b362e6a6dbeb0c57f234db0ef88ae0"},
+ {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:bed331fe18f58d844d39ceb398b77d6ac0b010d571cba8267c2e7165806b00ce"},
+ {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:02c9ac843e3390826a265e331105efeab489ffaf4dd86384595ee8ce6d35ae7f"},
+ {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9545a33965d0d377b0bc823dcabf26980e77f1b6a7caa368a365a9497fb09420"},
+ {file = "frozenlist-1.3.3-cp310-cp310-win32.whl", hash = "sha256:d5cd3ab21acbdb414bb6c31958d7b06b85eeb40f66463c264a9b343a4e238642"},
+ {file = "frozenlist-1.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:b756072364347cb6aa5b60f9bc18e94b2f79632de3b0190253ad770c5df17db1"},
+ {file = "frozenlist-1.3.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b4395e2f8d83fbe0c627b2b696acce67868793d7d9750e90e39592b3626691b7"},
+ {file = "frozenlist-1.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:14143ae966a6229350021384870458e4777d1eae4c28d1a7aa47f24d030e6678"},
+ {file = "frozenlist-1.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5d8860749e813a6f65bad8285a0520607c9500caa23fea6ee407e63debcdbef6"},
+ {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23d16d9f477bb55b6154654e0e74557040575d9d19fe78a161bd33d7d76808e8"},
+ {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:eb82dbba47a8318e75f679690190c10a5e1f447fbf9df41cbc4c3afd726d88cb"},
+ {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9309869032abb23d196cb4e4db574232abe8b8be1339026f489eeb34a4acfd91"},
+ {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a97b4fe50b5890d36300820abd305694cb865ddb7885049587a5678215782a6b"},
+ {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c188512b43542b1e91cadc3c6c915a82a5eb95929134faf7fd109f14f9892ce4"},
+ {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:303e04d422e9b911a09ad499b0368dc551e8c3cd15293c99160c7f1f07b59a48"},
+ {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:0771aed7f596c7d73444c847a1c16288937ef988dc04fb9f7be4b2aa91db609d"},
+ {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:66080ec69883597e4d026f2f71a231a1ee9887835902dbe6b6467d5a89216cf6"},
+ {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:41fe21dc74ad3a779c3d73a2786bdf622ea81234bdd4faf90b8b03cad0c2c0b4"},
+ {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f20380df709d91525e4bee04746ba612a4df0972c1b8f8e1e8af997e678c7b81"},
+ {file = "frozenlist-1.3.3-cp311-cp311-win32.whl", hash = "sha256:f30f1928162e189091cf4d9da2eac617bfe78ef907a761614ff577ef4edfb3c8"},
+ {file = "frozenlist-1.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:a6394d7dadd3cfe3f4b3b186e54d5d8504d44f2d58dcc89d693698e8b7132b32"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8df3de3a9ab8325f94f646609a66cbeeede263910c5c0de0101079ad541af332"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0693c609e9742c66ba4870bcee1ad5ff35462d5ffec18710b4ac89337ff16e27"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cd4210baef299717db0a600d7a3cac81d46ef0e007f88c9335db79f8979c0d3d"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:394c9c242113bfb4b9aa36e2b80a05ffa163a30691c7b5a29eba82e937895d5e"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6327eb8e419f7d9c38f333cde41b9ae348bec26d840927332f17e887a8dcb70d"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e24900aa13212e75e5b366cb9065e78bbf3893d4baab6052d1aca10d46d944c"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:3843f84a6c465a36559161e6c59dce2f2ac10943040c2fd021cfb70d58c4ad56"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:84610c1502b2461255b4c9b7d5e9c48052601a8957cd0aea6ec7a7a1e1fb9420"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:c21b9aa40e08e4f63a2f92ff3748e6b6c84d717d033c7b3438dd3123ee18f70e"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:efce6ae830831ab6a22b9b4091d411698145cb9b8fc869e1397ccf4b4b6455cb"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:40de71985e9042ca00b7953c4f41eabc3dc514a2d1ff534027f091bc74416401"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-win32.whl", hash = "sha256:180c00c66bde6146a860cbb81b54ee0df350d2daf13ca85b275123bbf85de18a"},
+ {file = "frozenlist-1.3.3-cp37-cp37m-win_amd64.whl", hash = "sha256:9bbbcedd75acdfecf2159663b87f1bb5cfc80e7cd99f7ddd9d66eb98b14a8411"},
+ {file = "frozenlist-1.3.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:034a5c08d36649591be1cbb10e09da9f531034acfe29275fc5454a3b101ce41a"},
+ {file = "frozenlist-1.3.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ba64dc2b3b7b158c6660d49cdb1d872d1d0bf4e42043ad8d5006099479a194e5"},
+ {file = "frozenlist-1.3.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:47df36a9fe24054b950bbc2db630d508cca3aa27ed0566c0baf661225e52c18e"},
+ {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:008a054b75d77c995ea26629ab3a0c0d7281341f2fa7e1e85fa6153ae29ae99c"},
+ {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:841ea19b43d438a80b4de62ac6ab21cfe6827bb8a9dc62b896acc88eaf9cecba"},
+ {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e235688f42b36be2b6b06fc37ac2126a73b75fb8d6bc66dd632aa35286238703"},
+ {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca713d4af15bae6e5d79b15c10c8522859a9a89d3b361a50b817c98c2fb402a2"},
+ {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ac5995f2b408017b0be26d4a1d7c61bce106ff3d9e3324374d66b5964325448"},
+ {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:a4ae8135b11652b08a8baf07631d3ebfe65a4c87909dbef5fa0cdde440444ee4"},
+ {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4ea42116ceb6bb16dbb7d526e242cb6747b08b7710d9782aa3d6732bd8d27649"},
+ {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:810860bb4bdce7557bc0febb84bbd88198b9dbc2022d8eebe5b3590b2ad6c842"},
+ {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:ee78feb9d293c323b59a6f2dd441b63339a30edf35abcb51187d2fc26e696d13"},
+ {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:0af2e7c87d35b38732e810befb9d797a99279cbb85374d42ea61c1e9d23094b3"},
+ {file = "frozenlist-1.3.3-cp38-cp38-win32.whl", hash = "sha256:899c5e1928eec13fd6f6d8dc51be23f0d09c5281e40d9cf4273d188d9feeaf9b"},
+ {file = "frozenlist-1.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:7f44e24fa70f6fbc74aeec3e971f60a14dde85da364aa87f15d1be94ae75aeef"},
+ {file = "frozenlist-1.3.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:2b07ae0c1edaa0a36339ec6cce700f51b14a3fc6545fdd32930d2c83917332cf"},
+ {file = "frozenlist-1.3.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ebb86518203e12e96af765ee89034a1dbb0c3c65052d1b0c19bbbd6af8a145e1"},
+ {file = "frozenlist-1.3.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5cf820485f1b4c91e0417ea0afd41ce5cf5965011b3c22c400f6d144296ccbc0"},
+ {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c11e43016b9024240212d2a65043b70ed8dfd3b52678a1271972702d990ac6d"},
+ {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8fa3c6e3305aa1146b59a09b32b2e04074945ffcfb2f0931836d103a2c38f936"},
+ {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:352bd4c8c72d508778cf05ab491f6ef36149f4d0cb3c56b1b4302852255d05d5"},
+ {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:65a5e4d3aa679610ac6e3569e865425b23b372277f89b5ef06cf2cdaf1ebf22b"},
+ {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1e2c1185858d7e10ff045c496bbf90ae752c28b365fef2c09cf0fa309291669"},
+ {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f163d2fd041c630fed01bc48d28c3ed4a3b003c00acd396900e11ee5316b56bb"},
+ {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:05cdb16d09a0832eedf770cb7bd1fe57d8cf4eaf5aced29c4e41e3f20b30a784"},
+ {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:8bae29d60768bfa8fb92244b74502b18fae55a80eac13c88eb0b496d4268fd2d"},
+ {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:eedab4c310c0299961ac285591acd53dc6723a1ebd90a57207c71f6e0c2153ab"},
+ {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:3bbdf44855ed8f0fbcd102ef05ec3012d6a4fd7c7562403f76ce6a52aeffb2b1"},
+ {file = "frozenlist-1.3.3-cp39-cp39-win32.whl", hash = "sha256:efa568b885bca461f7c7b9e032655c0c143d305bf01c30caf6db2854a4532b38"},
+ {file = "frozenlist-1.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:cfe33efc9cb900a4c46f91a5ceba26d6df370ffddd9ca386eb1d4f0ad97b9ea9"},
+ {file = "frozenlist-1.3.3.tar.gz", hash = "sha256:58bcc55721e8a90b88332d6cd441261ebb22342e238296bb330968952fbb3a6a"},
+]
+
+[[package]]
+name = "fsspec"
+version = "2023.3.0"
+description = "File-system specification"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "fsspec-2023.3.0-py3-none-any.whl", hash = "sha256:bf57215e19dbfa4fe7edae53040cc1deef825e3b1605cca9a8d2c2fadd2328a0"},
+ {file = "fsspec-2023.3.0.tar.gz", hash = "sha256:24e635549a590d74c6c18274ddd3ffab4753341753e923408b1904eaabafe04d"},
+]
+
+[package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+dropbox = ["dropbox", "dropboxdrivefs", "requests"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
+git = ["pygit2"]
+github = ["requests"]
+gs = ["gcsfs"]
+gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
+http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "requests"]
+libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
+smb = ["smbprotocol"]
+ssh = ["paramiko"]
+tqdm = ["tqdm"]
+
+[[package]]
+name = "functorch"
+version = "2.0.0"
+description = "JAX-like composable function transforms for PyTorch"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "functorch-2.0.0-py2.py3-none-any.whl", hash = "sha256:ca21ace6b9048e2ec6d132fa0fd18c776eb165ca1c91ef7e3584fdc668eaa4ea"},
+]
+
+[package.dependencies]
+torch = ">=2.0,<2.1"
+
+[package.extras]
+aot = ["networkx"]
+
+[[package]]
+name = "future"
+version = "0.18.3"
+description = "Clean single-source support for Python 3 and 2"
+category = "main"
+optional = false
+python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
+files = [
+ {file = "future-0.18.3.tar.gz", hash = "sha256:34a17436ed1e96697a86f9de3d15a3b0be01d8bc8de9c1dffd59fb8234ed5307"},
+]
+
+[[package]]
+name = "google-auth"
+version = "2.17.1"
+description = "Google Authentication Library"
+category = "main"
+optional = false
+python-versions = ">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*"
+files = [
+ {file = "google-auth-2.17.1.tar.gz", hash = "sha256:8f379b46bad381ad2a0b989dfb0c13ad28d3c2a79f27348213f8946a1d15d55a"},
+ {file = "google_auth-2.17.1-py2.py3-none-any.whl", hash = "sha256:357ff22a75b4c0f6093470f21816a825d2adee398177569824e37b6c10069e19"},
+]
+
+[package.dependencies]
+cachetools = ">=2.0.0,<6.0"
+pyasn1-modules = ">=0.2.1"
+rsa = {version = ">=3.1.4,<5", markers = "python_version >= \"3.6\""}
+six = ">=1.9.0"
+
+[package.extras]
+aiohttp = ["aiohttp (>=3.6.2,<4.0.0dev)", "requests (>=2.20.0,<3.0.0dev)"]
+enterprise-cert = ["cryptography (==36.0.2)", "pyopenssl (==22.0.0)"]
+pyopenssl = ["cryptography (>=38.0.3)", "pyopenssl (>=20.0.0)"]
+reauth = ["pyu2f (>=0.1.5)"]
+requests = ["requests (>=2.20.0,<3.0.0dev)"]
+
+[[package]]
+name = "google-auth-oauthlib"
+version = "1.0.0"
+description = "Google Authentication Library"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "google-auth-oauthlib-1.0.0.tar.gz", hash = "sha256:e375064964820b47221a7e1b7ee1fd77051b6323c3f9e3e19785f78ab67ecfc5"},
+ {file = "google_auth_oauthlib-1.0.0-py2.py3-none-any.whl", hash = "sha256:95880ca704928c300f48194d1770cf5b1462835b6e49db61445a520f793fd5fb"},
+]
+
+[package.dependencies]
+google-auth = ">=2.15.0"
+requests-oauthlib = ">=0.7.0"
+
+[package.extras]
+tool = ["click (>=6.0.0)"]
+
+[[package]]
+name = "gradio"
+version = "3.24.1"
+description = "Python library for easily interacting with trained machine learning models"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "gradio-3.24.1-py3-none-any.whl", hash = "sha256:a9b2fb94007b370ba5442159775a0987b27810451582525fe10711517082b1d2"},
+ {file = "gradio-3.24.1.tar.gz", hash = "sha256:19f11c8b5d9b23a22a7e0e3a32332146474d215588674afdfdbe2f86fe0a7811"},
+]
+
+[package.dependencies]
+aiofiles = "*"
+aiohttp = "*"
+altair = ">=4.2.0"
+fastapi = "*"
+ffmpy = "*"
+gradio-client = ">=0.0.5"
+httpx = "*"
+huggingface-hub = ">=0.13.0"
+jinja2 = "*"
+markdown-it-py = {version = ">=2.0.0", extras = ["linkify"]}
+markupsafe = "*"
+matplotlib = "*"
+mdit-py-plugins = "<=0.3.3"
+numpy = "*"
+orjson = "*"
+pandas = "*"
+pillow = "*"
+pydantic = "*"
+pydub = "*"
+python-multipart = "*"
+pyyaml = "*"
+requests = "*"
+semantic-version = "*"
+typing-extensions = "*"
+uvicorn = "*"
+websockets = ">=10.0"
+
+[[package]]
+name = "gradio-client"
+version = "0.0.7"
+description = "Python library for easily interacting with trained machine learning models"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "gradio_client-0.0.7-py3-none-any.whl", hash = "sha256:71887ff8ce9ce85b12dd1342eeed4ecdbe82c3b3d5a66f05f6dfcb17c9874631"},
+ {file = "gradio_client-0.0.7.tar.gz", hash = "sha256:c7cababd6213fc3541b4cd68a69305dee496125d0d18bc9a1326484c49275858"},
+]
+
+[package.dependencies]
+fsspec = "*"
+huggingface-hub = ">=0.13.0"
+packaging = "*"
+requests = "*"
+typing-extensions = "*"
+websockets = "*"
+
+[[package]]
+name = "grpcio"
+version = "1.53.0"
+description = "HTTP/2-based RPC framework"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "grpcio-1.53.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:752d2949b40e12e6ad3ed8cc552a65b54d226504f6b1fb67cab2ccee502cc06f"},
+ {file = "grpcio-1.53.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:8a48fd3a7222be226bb86b7b413ad248f17f3101a524018cdc4562eeae1eb2a3"},
+ {file = "grpcio-1.53.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:f3e837d29f0e1b9d6e7b29d569e2e9b0da61889e41879832ea15569c251c303a"},
+ {file = "grpcio-1.53.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aef7d30242409c3aa5839b501e877e453a2c8d3759ca8230dd5a21cda029f046"},
+ {file = "grpcio-1.53.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e6f90698b5d1c5dd7b3236cd1fa959d7b80e17923f918d5be020b65f1c78b173"},
+ {file = "grpcio-1.53.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a96c3c7f564b263c5d7c0e49a337166c8611e89c4c919f66dba7b9a84abad137"},
+ {file = "grpcio-1.53.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ee81349411648d1abc94095c68cd25e3c2812e4e0367f9a9355be1e804a5135c"},
+ {file = "grpcio-1.53.0-cp310-cp310-win32.whl", hash = "sha256:fdc6191587de410a184550d4143e2b24a14df495c86ca15e59508710681690ac"},
+ {file = "grpcio-1.53.0-cp310-cp310-win_amd64.whl", hash = "sha256:658ffe1e39171be00490db5bd3b966f79634ac4215a1eb9a85c6cd6783bf7f6e"},
+ {file = "grpcio-1.53.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:1b172e6d497191940c4b8d75b53de82dc252e15b61de2951d577ec5b43316b29"},
+ {file = "grpcio-1.53.0-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:82434ba3a5935e47908bc861ce1ebc43c2edfc1001d235d6e31e5d3ed55815f7"},
+ {file = "grpcio-1.53.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:1c734a2d4843e4e14ececf5600c3c4750990ec319e1299db7e4f0d02c25c1467"},
+ {file = "grpcio-1.53.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b6a2ead3de3b2d53119d473aa2f224030257ef33af1e4ddabd4afee1dea5f04c"},
+ {file = "grpcio-1.53.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a34d6e905f071f9b945cabbcc776e2055de1fdb59cd13683d9aa0a8f265b5bf9"},
+ {file = "grpcio-1.53.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:eaf8e3b97caaf9415227a3c6ca5aa8d800fecadd526538d2bf8f11af783f1550"},
+ {file = "grpcio-1.53.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:da95778d37be8e4e9afca771a83424f892296f5dfb2a100eda2571a1d8bbc0dc"},
+ {file = "grpcio-1.53.0-cp311-cp311-win32.whl", hash = "sha256:e4f513d63df6336fd84b74b701f17d1bb3b64e9d78a6ed5b5e8a198bbbe8bbfa"},
+ {file = "grpcio-1.53.0-cp311-cp311-win_amd64.whl", hash = "sha256:ddb2511fbbb440ed9e5c9a4b9b870f2ed649b7715859fd6f2ebc585ee85c0364"},
+ {file = "grpcio-1.53.0-cp37-cp37m-linux_armv7l.whl", hash = "sha256:2a912397eb8d23c177d6d64e3c8bc46b8a1c7680b090d9f13a640b104aaec77c"},
+ {file = "grpcio-1.53.0-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:55930c56b8f5b347d6c8c609cc341949a97e176c90f5cbb01d148d778f3bbd23"},
+ {file = "grpcio-1.53.0-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:6601d812105583948ab9c6e403a7e2dba6e387cc678c010e74f2d6d589d1d1b3"},
+ {file = "grpcio-1.53.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c705e0c21acb0e8478a00e7e773ad0ecdb34bd0e4adc282d3d2f51ba3961aac7"},
+ {file = "grpcio-1.53.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba074af9ca268ad7b05d3fc2b920b5fb3c083da94ab63637aaf67f4f71ecb755"},
+ {file = "grpcio-1.53.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:14817de09317dd7d3fbc8272864288320739973ef0f4b56bf2c0032349da8cdf"},
+ {file = "grpcio-1.53.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c7ad9fbedb93f331c2e9054e202e95cf825b885811f1bcbbdfdc301e451442db"},
+ {file = "grpcio-1.53.0-cp37-cp37m-win_amd64.whl", hash = "sha256:dad5b302a4c21c604d88a5d441973f320134e6ff6a84ecef9c1139e5ffd466f6"},
+ {file = "grpcio-1.53.0-cp38-cp38-linux_armv7l.whl", hash = "sha256:fa8eaac75d3107e3f5465f2c9e3bbd13db21790c6e45b7de1756eba16b050aca"},
+ {file = "grpcio-1.53.0-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:104a2210edd3776c38448b4f76c2f16e527adafbde171fc72a8a32976c20abc7"},
+ {file = "grpcio-1.53.0-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:dbc1ba968639c1d23476f75c356e549e7bbf2d8d6688717dcab5290e88e8482b"},
+ {file = "grpcio-1.53.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:95952d3fe795b06af29bb8ec7bbf3342cdd867fc17b77cc25e6733d23fa6c519"},
+ {file = "grpcio-1.53.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f144a790f14c51b8a8e591eb5af40507ffee45ea6b818c2482f0457fec2e1a2e"},
+ {file = "grpcio-1.53.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:0698c094688a2dd4c7c2f2c0e3e142cac439a64d1cef6904c97f6cde38ba422f"},
+ {file = "grpcio-1.53.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6b6d60b0958be711bab047e9f4df5dbbc40367955f8651232bfdcdd21450b9ab"},
+ {file = "grpcio-1.53.0-cp38-cp38-win32.whl", hash = "sha256:1948539ce78805d4e6256ab0e048ec793956d54787dc9d6777df71c1d19c7f81"},
+ {file = "grpcio-1.53.0-cp38-cp38-win_amd64.whl", hash = "sha256:df9ba1183b3f649210788cf80c239041dddcb375d6142d8bccafcfdf549522cd"},
+ {file = "grpcio-1.53.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:19caa5b7282a89b799e63776ff602bb39604f7ca98db6df27e2de06756ae86c3"},
+ {file = "grpcio-1.53.0-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:b5bd026ac928c96cc23149e6ef79183125542062eb6d1ccec34c0a37e02255e7"},
+ {file = "grpcio-1.53.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:7dc8584ca6c015ad82e186e82f4c0fe977394588f66b8ecfc4ec873285314619"},
+ {file = "grpcio-1.53.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2eddaae8af625e45b5c8500dcca1043264d751a6872cde2eda5022df8a336959"},
+ {file = "grpcio-1.53.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c5fb6f3d7824696c1c9f2ad36ddb080ba5a86f2d929ef712d511b4d9972d3d27"},
+ {file = "grpcio-1.53.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:8270d1dc2c98ab57e6dbf36fa187db8df4c036f04a398e5d5e25b4e01a766d70"},
+ {file = "grpcio-1.53.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:976a7f24eb213e8429cab78d5e120500dfcdeb01041f1f5a77b17b9101902615"},
+ {file = "grpcio-1.53.0-cp39-cp39-win32.whl", hash = "sha256:9c84a481451e7174f3a764a44150f93b041ab51045aa33d7b5b68b6979114e48"},
+ {file = "grpcio-1.53.0-cp39-cp39-win_amd64.whl", hash = "sha256:6beb84f83360ff29a3654f43f251ec11b809dcb5524b698d711550243debd289"},
+ {file = "grpcio-1.53.0.tar.gz", hash = "sha256:a4952899b4931a6ba12951f9a141ef3e74ff8a6ec9aa2dc602afa40f63595e33"},
+]
+
+[package.extras]
+protobuf = ["grpcio-tools (>=1.53.0)"]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
+ {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
+]
+
+[[package]]
+name = "httpcore"
+version = "0.16.3"
+description = "A minimal low-level HTTP client."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "httpcore-0.16.3-py3-none-any.whl", hash = "sha256:da1fb708784a938aa084bde4feb8317056c55037247c787bd7e19eb2c2949dc0"},
+ {file = "httpcore-0.16.3.tar.gz", hash = "sha256:c5d6f04e2fc530f39e0c077e6a30caa53f1451096120f1f38b954afd0b17c0cb"},
+]
+
+[package.dependencies]
+anyio = ">=3.0,<5.0"
+certifi = "*"
+h11 = ">=0.13,<0.15"
+sniffio = ">=1.0.0,<2.0.0"
+
+[package.extras]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (>=1.0.0,<2.0.0)"]
+
+[[package]]
+name = "httpx"
+version = "0.23.3"
+description = "The next generation HTTP client."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "httpx-0.23.3-py3-none-any.whl", hash = "sha256:a211fcce9b1254ea24f0cd6af9869b3d29aba40154e947d2a07bb499b3e310d6"},
+ {file = "httpx-0.23.3.tar.gz", hash = "sha256:9818458eb565bb54898ccb9b8b251a28785dd4a55afbc23d0eb410754fe7d0f9"},
+]
+
+[package.dependencies]
+certifi = "*"
+httpcore = ">=0.15.0,<0.17.0"
+rfc3986 = {version = ">=1.3,<2", extras = ["idna2008"]}
+sniffio = "*"
+
+[package.extras]
+brotli = ["brotli", "brotlicffi"]
+cli = ["click (>=8.0.0,<9.0.0)", "pygments (>=2.0.0,<3.0.0)", "rich (>=10,<13)"]
+http2 = ["h2 (>=3,<5)"]
+socks = ["socksio (>=1.0.0,<2.0.0)"]
+
+[[package]]
+name = "huggingface-hub"
+version = "0.13.3"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+files = [
+ {file = "huggingface_hub-0.13.3-py3-none-any.whl", hash = "sha256:f73a298a55028575334f9670d86b8171a4dd890b320315f3ad28a20b9eb3b5bc"},
+ {file = "huggingface_hub-0.13.3.tar.gz", hash = "sha256:1f95f65c5e7aa76728701402f55b697ee8a8b50234adda91fbdbb81038fbcd21"},
+]
+
+[package.dependencies]
+filelock = "*"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = ">=4.42.1"
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+cli = ["InquirerPy (==0.3.4)"]
+dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
+quality = ["black (>=23.1,<24.0)", "mypy (==0.982)", "ruff (>=0.0.241)"]
+tensorflow = ["graphviz", "pydot", "tensorflow"]
+testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "jedi", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "soundfile"]
+torch = ["torch"]
+typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+
+[[package]]
+name = "hydra-core"
+version = "1.0.7"
+description = "A framework for elegantly configuring complex applications"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "hydra-core-1.0.7.tar.gz", hash = "sha256:58cc3f7531995b6d8de162ca21f936e17bdaebd4d1e8614d63c32e17c2e41e45"},
+ {file = "hydra_core-1.0.7-py3-none-any.whl", hash = "sha256:e800c6deb8309395508094851fa93bc13408f2285261eb97e626d37193b58a9f"},
+]
+
+[package.dependencies]
+antlr4-python3-runtime = "4.8"
+importlib-resources = {version = "*", markers = "python_version < \"3.9\""}
+omegaconf = ">=2.0.5,<2.1"
+
+[[package]]
+name = "idna"
+version = "3.4"
+description = "Internationalized Domain Names in Applications (IDNA)"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+files = [
+ {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
+ {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
+]
+
+[[package]]
+name = "importlib-metadata"
+version = "6.1.0"
+description = "Read metadata from Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "importlib_metadata-6.1.0-py3-none-any.whl", hash = "sha256:ff80f3b5394912eb1b108fcfd444dc78b7f1f3e16b16188054bd01cb9cb86f09"},
+ {file = "importlib_metadata-6.1.0.tar.gz", hash = "sha256:43ce9281e097583d758c2c708c4376371261a02c34682491a8e98352365aad20"},
+]
+
+[package.dependencies]
+zipp = ">=0.5"
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+perf = ["ipython"]
+testing = ["flake8 (<5)", "flufl.flake8", "importlib-resources (>=1.3)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)", "pytest-perf (>=0.9.2)"]
+
+[[package]]
+name = "importlib-resources"
+version = "5.12.0"
+description = "Read resources from Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "importlib_resources-5.12.0-py3-none-any.whl", hash = "sha256:7b1deeebbf351c7578e09bf2f63fa2ce8b5ffec296e0d349139d43cca061a81a"},
+ {file = "importlib_resources-5.12.0.tar.gz", hash = "sha256:4be82589bf5c1d7999aedf2a45159d10cb3ca4f19b2271f8792bc8e6da7b22f6"},
+]
+
+[package.dependencies]
+zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+testing = ["flake8 (<5)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
+
+[[package]]
+name = "jinja2"
+version = "3.1.2"
+description = "A very fast and expressive template engine."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "Jinja2-3.1.2-py3-none-any.whl", hash = "sha256:6088930bfe239f0e6710546ab9c19c9ef35e29792895fed6e6e31a023a182a61"},
+ {file = "Jinja2-3.1.2.tar.gz", hash = "sha256:31351a702a408a9e7595a8fc6150fc3f43bb6bf7e319770cbc0db9df9437e852"},
+]
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "joblib"
+version = "1.2.0"
+description = "Lightweight pipelining with Python functions"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "joblib-1.2.0-py3-none-any.whl", hash = "sha256:091138ed78f800342968c523bdde947e7a305b8594b910a0fea2ab83c3c6d385"},
+ {file = "joblib-1.2.0.tar.gz", hash = "sha256:e1cee4a79e4af22881164f218d4311f60074197fb707e082e803b61f6d137018"},
+]
+
+[[package]]
+name = "json5"
+version = "0.9.11"
+description = "A Python implementation of the JSON5 data format."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "json5-0.9.11-py2.py3-none-any.whl", hash = "sha256:1aa54b80b5e507dfe31d12b7743a642e2ffa6f70bf73b8e3d7d1d5fba83d99bd"},
+ {file = "json5-0.9.11.tar.gz", hash = "sha256:4f1e196acc55b83985a51318489f345963c7ba84aa37607e49073066c562e99b"},
+]
+
+[package.extras]
+dev = ["hypothesis"]
+
+[[package]]
+name = "jsonschema"
+version = "4.17.3"
+description = "An implementation of JSON Schema validation for Python"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "jsonschema-4.17.3-py3-none-any.whl", hash = "sha256:a870ad254da1a8ca84b6a2905cac29d265f805acc57af304784962a2aa6508f6"},
+ {file = "jsonschema-4.17.3.tar.gz", hash = "sha256:0f864437ab8b6076ba6707453ef8f98a6a0d512a80e93f8abdb676f737ecb60d"},
+]
+
+[package.dependencies]
+attrs = ">=17.4.0"
+importlib-resources = {version = ">=1.4.0", markers = "python_version < \"3.9\""}
+pkgutil-resolve-name = {version = ">=1.3.10", markers = "python_version < \"3.9\""}
+pyrsistent = ">=0.14.0,<0.17.0 || >0.17.0,<0.17.1 || >0.17.1,<0.17.2 || >0.17.2"
+
+[package.extras]
+format = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3987", "uri-template", "webcolors (>=1.11)"]
+format-nongpl = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3986-validator (>0.1.0)", "uri-template", "webcolors (>=1.11)"]
+
+[[package]]
+name = "kiwisolver"
+version = "1.4.4"
+description = "A fast implementation of the Cassowary constraint solver"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "kiwisolver-1.4.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:2f5e60fabb7343a836360c4f0919b8cd0d6dbf08ad2ca6b9cf90bf0c76a3c4f6"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:10ee06759482c78bdb864f4109886dff7b8a56529bc1609d4f1112b93fe6423c"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c79ebe8f3676a4c6630fd3f777f3cfecf9289666c84e775a67d1d358578dc2e3"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:abbe9fa13da955feb8202e215c4018f4bb57469b1b78c7a4c5c7b93001699938"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7577c1987baa3adc4b3c62c33bd1118c3ef5c8ddef36f0f2c950ae0b199e100d"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f8ad8285b01b0d4695102546b342b493b3ccc6781fc28c8c6a1bb63e95d22f09"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8ed58b8acf29798b036d347791141767ccf65eee7f26bde03a71c944449e53de"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a68b62a02953b9841730db7797422f983935aeefceb1679f0fc85cbfbd311c32"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-win32.whl", hash = "sha256:e92a513161077b53447160b9bd8f522edfbed4bd9759e4c18ab05d7ef7e49408"},
+ {file = "kiwisolver-1.4.4-cp310-cp310-win_amd64.whl", hash = "sha256:3fe20f63c9ecee44560d0e7f116b3a747a5d7203376abeea292ab3152334d004"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e0ea21f66820452a3f5d1655f8704a60d66ba1191359b96541eaf457710a5fc6"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:bc9db8a3efb3e403e4ecc6cd9489ea2bac94244f80c78e27c31dcc00d2790ac2"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d5b61785a9ce44e5a4b880272baa7cf6c8f48a5180c3e81c59553ba0cb0821ca"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c2dbb44c3f7e6c4d3487b31037b1bdbf424d97687c1747ce4ff2895795c9bf69"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6295ecd49304dcf3bfbfa45d9a081c96509e95f4b9d0eb7ee4ec0530c4a96514"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4bd472dbe5e136f96a4b18f295d159d7f26fd399136f5b17b08c4e5f498cd494"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bf7d9fce9bcc4752ca4a1b80aabd38f6d19009ea5cbda0e0856983cf6d0023f5"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78d6601aed50c74e0ef02f4204da1816147a6d3fbdc8b3872d263338a9052c51"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:877272cf6b4b7e94c9614f9b10140e198d2186363728ed0f701c6eee1baec1da"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:db608a6757adabb32f1cfe6066e39b3706d8c3aa69bbc353a5b61edad36a5cb4"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:5853eb494c71e267912275e5586fe281444eb5e722de4e131cddf9d442615626"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:f0a1dbdb5ecbef0d34eb77e56fcb3e95bbd7e50835d9782a45df81cc46949750"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:283dffbf061a4ec60391d51e6155e372a1f7a4f5b15d59c8505339454f8989e4"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-win32.whl", hash = "sha256:d06adcfa62a4431d404c31216f0f8ac97397d799cd53800e9d3efc2fbb3cf14e"},
+ {file = "kiwisolver-1.4.4-cp311-cp311-win_amd64.whl", hash = "sha256:e7da3fec7408813a7cebc9e4ec55afed2d0fd65c4754bc376bf03498d4e92686"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:62ac9cc684da4cf1778d07a89bf5f81b35834cb96ca523d3a7fb32509380cbf6"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41dae968a94b1ef1897cb322b39360a0812661dba7c682aa45098eb8e193dbdf"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:02f79693ec433cb4b5f51694e8477ae83b3205768a6fb48ffba60549080e295b"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0611a0a2a518464c05ddd5a3a1a0e856ccc10e67079bb17f265ad19ab3c7597"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:db5283d90da4174865d520e7366801a93777201e91e79bacbac6e6927cbceede"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:1041feb4cda8708ce73bb4dcb9ce1ccf49d553bf87c3954bdfa46f0c3f77252c"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-win32.whl", hash = "sha256:a553dadda40fef6bfa1456dc4be49b113aa92c2a9a9e8711e955618cd69622e3"},
+ {file = "kiwisolver-1.4.4-cp37-cp37m-win_amd64.whl", hash = "sha256:03baab2d6b4a54ddbb43bba1a3a2d1627e82d205c5cf8f4c924dc49284b87166"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:841293b17ad704d70c578f1f0013c890e219952169ce8a24ebc063eecf775454"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f4f270de01dd3e129a72efad823da90cc4d6aafb64c410c9033aba70db9f1ff0"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:f9f39e2f049db33a908319cf46624a569b36983c7c78318e9726a4cb8923b26c"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c97528e64cb9ebeff9701e7938653a9951922f2a38bd847787d4a8e498cc83ae"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d1573129aa0fd901076e2bfb4275a35f5b7aa60fbfb984499d661ec950320b0"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ad881edc7ccb9d65b0224f4e4d05a1e85cf62d73aab798943df6d48ab0cd79a1"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b428ef021242344340460fa4c9185d0b1f66fbdbfecc6c63eff4b7c29fad429d"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:2e407cb4bd5a13984a6c2c0fe1845e4e41e96f183e5e5cd4d77a857d9693494c"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-win32.whl", hash = "sha256:75facbe9606748f43428fc91a43edb46c7ff68889b91fa31f53b58894503a191"},
+ {file = "kiwisolver-1.4.4-cp38-cp38-win_amd64.whl", hash = "sha256:5bce61af018b0cb2055e0e72e7d65290d822d3feee430b7b8203d8a855e78766"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8c808594c88a025d4e322d5bb549282c93c8e1ba71b790f539567932722d7bd8"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f0a71d85ecdd570ded8ac3d1c0f480842f49a40beb423bb8014539a9f32a5897"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b533558eae785e33e8c148a8d9921692a9fe5aa516efbdff8606e7d87b9d5824"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:efda5fc8cc1c61e4f639b8067d118e742b812c930f708e6667a5ce0d13499e29"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7c43e1e1206cd421cd92e6b3280d4385d41d7166b3ed577ac20444b6995a445f"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bc8d3bd6c72b2dd9decf16ce70e20abcb3274ba01b4e1c96031e0c4067d1e7cd"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4ea39b0ccc4f5d803e3337dd46bcce60b702be4d86fd0b3d7531ef10fd99a1ac"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:968f44fdbf6dd757d12920d63b566eeb4d5b395fd2d00d29d7ef00a00582aac9"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-win32.whl", hash = "sha256:da7e547706e69e45d95e116e6939488d62174e033b763ab1496b4c29b76fabea"},
+ {file = "kiwisolver-1.4.4-cp39-cp39-win_amd64.whl", hash = "sha256:ba59c92039ec0a66103b1d5fe588fa546373587a7d68f5c96f743c3396afc04b"},
+ {file = "kiwisolver-1.4.4-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:91672bacaa030f92fc2f43b620d7b337fd9a5af28b0d6ed3f77afc43c4a64b5a"},
+ {file = "kiwisolver-1.4.4-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:787518a6789009c159453da4d6b683f468ef7a65bbde796bcea803ccf191058d"},
+ {file = "kiwisolver-1.4.4-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:da152d8cdcab0e56e4f45eb08b9aea6455845ec83172092f09b0e077ece2cf7a"},
+ {file = "kiwisolver-1.4.4-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:ecb1fa0db7bf4cff9dac752abb19505a233c7f16684c5826d1f11ebd9472b871"},
+ {file = "kiwisolver-1.4.4-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:28bc5b299f48150b5f822ce68624e445040595a4ac3d59251703779836eceff9"},
+ {file = "kiwisolver-1.4.4-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:81e38381b782cc7e1e46c4e14cd997ee6040768101aefc8fa3c24a4cc58e98f8"},
+ {file = "kiwisolver-1.4.4-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:2a66fdfb34e05b705620dd567f5a03f239a088d5a3f321e7b6ac3239d22aa286"},
+ {file = "kiwisolver-1.4.4-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:872b8ca05c40d309ed13eb2e582cab0c5a05e81e987ab9c521bf05ad1d5cf5cb"},
+ {file = "kiwisolver-1.4.4-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:70e7c2e7b750585569564e2e5ca9845acfaa5da56ac46df68414f29fea97be9f"},
+ {file = "kiwisolver-1.4.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9f85003f5dfa867e86d53fac6f7e6f30c045673fa27b603c397753bebadc3008"},
+ {file = "kiwisolver-1.4.4-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2e307eb9bd99801f82789b44bb45e9f541961831c7311521b13a6c85afc09767"},
+ {file = "kiwisolver-1.4.4-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b1792d939ec70abe76f5054d3f36ed5656021dcad1322d1cc996d4e54165cef9"},
+ {file = "kiwisolver-1.4.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6cb459eea32a4e2cf18ba5fcece2dbdf496384413bc1bae15583f19e567f3b2"},
+ {file = "kiwisolver-1.4.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:36dafec3d6d6088d34e2de6b85f9d8e2324eb734162fba59d2ba9ed7a2043d5b"},
+ {file = "kiwisolver-1.4.4.tar.gz", hash = "sha256:d41997519fcba4a1e46eb4a2fe31bc12f0ff957b2b81bac28db24744f333e955"},
+]
+
+[[package]]
+name = "librosa"
+version = "0.9.2"
+description = "Python module for audio and music processing"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "librosa-0.9.2-py3-none-any.whl", hash = "sha256:322a813e6d37af9fbc369e6a637dcf5fdc5c6925ce806a0d27c68de61a81350f"},
+ {file = "librosa-0.9.2.tar.gz", hash = "sha256:5b576b5efdce428e90bc988bdd5a953d12a727e5f931f30d74c53b63abbe3c89"},
+]
+
+[package.dependencies]
+audioread = ">=2.1.9"
+decorator = ">=4.0.10"
+joblib = ">=0.14"
+numba = ">=0.45.1"
+numpy = ">=1.17.0"
+packaging = ">=20.0"
+pooch = ">=1.0"
+resampy = ">=0.2.2"
+scikit-learn = ">=0.19.1"
+scipy = ">=1.2.0"
+soundfile = ">=0.10.2"
+
+[package.extras]
+display = ["matplotlib (>=3.3.0)"]
+docs = ["ipython (>=7.0)", "matplotlib (>=3.3.0)", "mir-eval (>=0.5)", "numba (<0.50)", "numpydoc", "presets", "sphinx (!=1.3.1)", "sphinx-gallery (>=0.7)", "sphinx-multiversion (>=0.2.3)", "sphinx-rtd-theme (>=1.0.0,<2.0.0)", "sphinxcontrib-svg2pdfconverter"]
+tests = ["contextlib2", "matplotlib (>=3.3.0)", "pytest", "pytest-cov", "pytest-mpl", "samplerate", "soxr"]
+
+[[package]]
+name = "linkify-it-py"
+version = "2.0.0"
+description = "Links recognition library with FULL unicode support."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "linkify-it-py-2.0.0.tar.gz", hash = "sha256:476464480906bed8b2fa3813bf55566282e55214ad7e41b7d1c2b564666caf2f"},
+ {file = "linkify_it_py-2.0.0-py3-none-any.whl", hash = "sha256:1bff43823e24e507a099e328fc54696124423dd6320c75a9da45b4b754b748ad"},
+]
+
+[package.dependencies]
+uc-micro-py = "*"
+
+[package.extras]
+benchmark = ["pytest", "pytest-benchmark"]
+dev = ["black", "flake8", "isort", "pre-commit"]
+doc = ["myst-parser", "sphinx", "sphinx-book-theme"]
+test = ["coverage", "pytest", "pytest-cov"]
+
+[[package]]
+name = "lit"
+version = "16.0.0"
+description = "A Software Testing Tool"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "lit-16.0.0.tar.gz", hash = "sha256:3c4ac372122a1de4a88deb277b956f91b7209420a0bef683b1ab2d2b16dabe11"},
+]
+
+[[package]]
+name = "llvmlite"
+version = "0.39.0"
+description = "lightweight wrapper around basic LLVM functionality"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "llvmlite-0.39.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:589f08a1b1920e6004735819ce9aafdd85d030d4a231c1e7adaca9360724b1ed"},
+ {file = "llvmlite-0.39.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:44a9a5cbe76db8ba01a5f6fa21649d91aa8a2634cc6f3a60291797e42e67d79e"},
+ {file = "llvmlite-0.39.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74d89f2ec4734d3e200fb90ea0b3ca5e9be40f3b3e50eb368ca9002ed5b3e4f8"},
+ {file = "llvmlite-0.39.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8b4cb4f433b48792f02ec4ab619b86b145689302a3088a3f3853f50df6c2559d"},
+ {file = "llvmlite-0.39.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:35db4122182cc5112912a3ec94a3c18eab9a990bd588bfda8445087c1b748563"},
+ {file = "llvmlite-0.39.0-cp310-cp310-win32.whl", hash = "sha256:c00bf7a8dc56b4b3618c65b67e75046410f751512871d9e23919cf1feb1007b2"},
+ {file = "llvmlite-0.39.0-cp310-cp310-win_amd64.whl", hash = "sha256:72bd2e5db9790344ec39cef77098486635853829ecb0e66e6fa516488ff6dd9e"},
+ {file = "llvmlite-0.39.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:53c7c608baffdcdc2213926f4e3600036d4048aed08d6209b9f76a5439e529d6"},
+ {file = "llvmlite-0.39.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c3bbd23e42593f85a842614d8ddb2b2943630e4c4c8418ea0d8cf1dce9f2fa7a"},
+ {file = "llvmlite-0.39.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d733eb9c02bb8b01373228a1339901b1e50be4581105239c6052b9573ddb9298"},
+ {file = "llvmlite-0.39.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f575fcb9bebe5bcbe20373c56ad3ebf63bae0e27d3c22c1a4dc27fa4666d0324"},
+ {file = "llvmlite-0.39.0-cp37-cp37m-win32.whl", hash = "sha256:5ca4ea962da6ec3b007bedab17065781803d71159b03435f24ce6845cf3d1c66"},
+ {file = "llvmlite-0.39.0-cp37-cp37m-win_amd64.whl", hash = "sha256:8e461608135859ac40e39211d9c63a1ce35176513f6b8be87efb554d4af3a388"},
+ {file = "llvmlite-0.39.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:62a11b8e9e5fc4783d94da45d94c5a047ce6ccc4c112ae5f764109e9405fcc2c"},
+ {file = "llvmlite-0.39.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:9272b7e344d12b36dafeb6911054eff32d2a9be7256a2866f0c09d08f945e17f"},
+ {file = "llvmlite-0.39.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3df59a7c2b60764fb9eeaf9c442d757eca1f3e87298d4f88849203667528581e"},
+ {file = "llvmlite-0.39.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4cfd6688efd0f551168dd8626f386464aef25663268a2400c0f6a089b97a73dc"},
+ {file = "llvmlite-0.39.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c7292b394956749e51ae3d51a2085932a0e3261108b35eda61d702c1b977102c"},
+ {file = "llvmlite-0.39.0-cp38-cp38-win32.whl", hash = "sha256:f8e9463a7d0152994b6f7d630012297bb160db237ad9ca8e75c8dceef7a747cf"},
+ {file = "llvmlite-0.39.0-cp38-cp38-win_amd64.whl", hash = "sha256:8d8149fdaab40ae48ea4ec816ae2ae5d36d664795e1b1dfb911fc2c62bc73184"},
+ {file = "llvmlite-0.39.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:0929e3c26bcafb53545c77bcf7020b943dcefcf8d7d3010f414384458f805cc1"},
+ {file = "llvmlite-0.39.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:56ea23c6bbcd25a7c050a26b6effe836a575a33183744cbc28fb21358b3801f8"},
+ {file = "llvmlite-0.39.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2f82d605c5d6c8df96fe19bc3a61c934580e24cafa694cbf79cb227cdc0e426a"},
+ {file = "llvmlite-0.39.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e7f7a7278ba6d75533be46abc3d9e242030ab017f0016dd081b55f821cc03be9"},
+ {file = "llvmlite-0.39.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56ccfe736a12aef2e39450a22e4c027eee4f488c5786c81d0b18ff8a6cf52531"},
+ {file = "llvmlite-0.39.0-cp39-cp39-win32.whl", hash = "sha256:0706abf522dc510ddc818f5c9e1cdae521a1416d3c399bbfc4827813379f0164"},
+ {file = "llvmlite-0.39.0-cp39-cp39-win_amd64.whl", hash = "sha256:d4a8199263859b97f174035e39297e770617d3497fac44fe738f74ce9c51d22b"},
+ {file = "llvmlite-0.39.0.tar.gz", hash = "sha256:01098be54f1aa25e391cebba8ea71cd1533f8cd1f50e34c7dd7540c2560a93af"},
+]
+
+[[package]]
+name = "lxml"
+version = "4.9.2"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
+files = [
+ {file = "lxml-4.9.2-cp27-cp27m-macosx_10_15_x86_64.whl", hash = "sha256:76cf573e5a365e790396a5cc2b909812633409306c6531a6877c59061e42c4f2"},
+ {file = "lxml-4.9.2-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b1f42b6921d0e81b1bcb5e395bc091a70f41c4d4e55ba99c6da2b31626c44892"},
+ {file = "lxml-4.9.2-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:9f102706d0ca011de571de32c3247c6476b55bb6bc65a20f682f000b07a4852a"},
+ {file = "lxml-4.9.2-cp27-cp27m-win32.whl", hash = "sha256:8d0b4612b66ff5d62d03bcaa043bb018f74dfea51184e53f067e6fdcba4bd8de"},
+ {file = "lxml-4.9.2-cp27-cp27m-win_amd64.whl", hash = "sha256:4c8f293f14abc8fd3e8e01c5bd86e6ed0b6ef71936ded5bf10fe7a5efefbaca3"},
+ {file = "lxml-4.9.2-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2899456259589aa38bfb018c364d6ae7b53c5c22d8e27d0ec7609c2a1ff78b50"},
+ {file = "lxml-4.9.2-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:6749649eecd6a9871cae297bffa4ee76f90b4504a2a2ab528d9ebe912b101975"},
+ {file = "lxml-4.9.2-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:a08cff61517ee26cb56f1e949cca38caabe9ea9fbb4b1e10a805dc39844b7d5c"},
+ {file = "lxml-4.9.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:85cabf64adec449132e55616e7ca3e1000ab449d1d0f9d7f83146ed5bdcb6d8a"},
+ {file = "lxml-4.9.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:8340225bd5e7a701c0fa98284c849c9b9fc9238abf53a0ebd90900f25d39a4e4"},
+ {file = "lxml-4.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:1ab8f1f932e8f82355e75dda5413a57612c6ea448069d4fb2e217e9a4bed13d4"},
+ {file = "lxml-4.9.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:699a9af7dffaf67deeae27b2112aa06b41c370d5e7633e0ee0aea2e0b6c211f7"},
+ {file = "lxml-4.9.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b9cc34af337a97d470040f99ba4282f6e6bac88407d021688a5d585e44a23184"},
+ {file = "lxml-4.9.2-cp310-cp310-win32.whl", hash = "sha256:d02a5399126a53492415d4906ab0ad0375a5456cc05c3fc0fc4ca11771745cda"},
+ {file = "lxml-4.9.2-cp310-cp310-win_amd64.whl", hash = "sha256:a38486985ca49cfa574a507e7a2215c0c780fd1778bb6290c21193b7211702ab"},
+ {file = "lxml-4.9.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:c83203addf554215463b59f6399835201999b5e48019dc17f182ed5ad87205c9"},
+ {file = "lxml-4.9.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:2a87fa548561d2f4643c99cd13131acb607ddabb70682dcf1dff5f71f781a4bf"},
+ {file = "lxml-4.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:d6b430a9938a5a5d85fc107d852262ddcd48602c120e3dbb02137c83d212b380"},
+ {file = "lxml-4.9.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:3efea981d956a6f7173b4659849f55081867cf897e719f57383698af6f618a92"},
+ {file = "lxml-4.9.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:df0623dcf9668ad0445e0558a21211d4e9a149ea8f5666917c8eeec515f0a6d1"},
+ {file = "lxml-4.9.2-cp311-cp311-win32.whl", hash = "sha256:da248f93f0418a9e9d94b0080d7ebc407a9a5e6d0b57bb30db9b5cc28de1ad33"},
+ {file = "lxml-4.9.2-cp311-cp311-win_amd64.whl", hash = "sha256:3818b8e2c4b5148567e1b09ce739006acfaa44ce3156f8cbbc11062994b8e8dd"},
+ {file = "lxml-4.9.2-cp35-cp35m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ca989b91cf3a3ba28930a9fc1e9aeafc2a395448641df1f387a2d394638943b0"},
+ {file = "lxml-4.9.2-cp35-cp35m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:822068f85e12a6e292803e112ab876bc03ed1f03dddb80154c395f891ca6b31e"},
+ {file = "lxml-4.9.2-cp35-cp35m-win32.whl", hash = "sha256:be7292c55101e22f2a3d4d8913944cbea71eea90792bf914add27454a13905df"},
+ {file = "lxml-4.9.2-cp35-cp35m-win_amd64.whl", hash = "sha256:998c7c41910666d2976928c38ea96a70d1aa43be6fe502f21a651e17483a43c5"},
+ {file = "lxml-4.9.2-cp36-cp36m-macosx_10_15_x86_64.whl", hash = "sha256:b26a29f0b7fc6f0897f043ca366142d2b609dc60756ee6e4e90b5f762c6adc53"},
+ {file = "lxml-4.9.2-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:ab323679b8b3030000f2be63e22cdeea5b47ee0abd2d6a1dc0c8103ddaa56cd7"},
+ {file = "lxml-4.9.2-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:689bb688a1db722485e4610a503e3e9210dcc20c520b45ac8f7533c837be76fe"},
+ {file = "lxml-4.9.2-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:f49e52d174375a7def9915c9f06ec4e569d235ad428f70751765f48d5926678c"},
+ {file = "lxml-4.9.2-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:36c3c175d34652a35475a73762b545f4527aec044910a651d2bf50de9c3352b1"},
+ {file = "lxml-4.9.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:a35f8b7fa99f90dd2f5dc5a9fa12332642f087a7641289ca6c40d6e1a2637d8e"},
+ {file = "lxml-4.9.2-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:58bfa3aa19ca4c0f28c5dde0ff56c520fbac6f0daf4fac66ed4c8d2fb7f22e74"},
+ {file = "lxml-4.9.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:bc718cd47b765e790eecb74d044cc8d37d58562f6c314ee9484df26276d36a38"},
+ {file = "lxml-4.9.2-cp36-cp36m-win32.whl", hash = "sha256:d5bf6545cd27aaa8a13033ce56354ed9e25ab0e4ac3b5392b763d8d04b08e0c5"},
+ {file = "lxml-4.9.2-cp36-cp36m-win_amd64.whl", hash = "sha256:3ab9fa9d6dc2a7f29d7affdf3edebf6ece6fb28a6d80b14c3b2fb9d39b9322c3"},
+ {file = "lxml-4.9.2-cp37-cp37m-macosx_10_15_x86_64.whl", hash = "sha256:05ca3f6abf5cf78fe053da9b1166e062ade3fa5d4f92b4ed688127ea7d7b1d03"},
+ {file = "lxml-4.9.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:a5da296eb617d18e497bcf0a5c528f5d3b18dadb3619fbdadf4ed2356ef8d941"},
+ {file = "lxml-4.9.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:04876580c050a8c5341d706dd464ff04fd597095cc8c023252566a8826505726"},
+ {file = "lxml-4.9.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:c9ec3eaf616d67db0764b3bb983962b4f385a1f08304fd30c7283954e6a7869b"},
+ {file = "lxml-4.9.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2a29ba94d065945944016b6b74e538bdb1751a1db6ffb80c9d3c2e40d6fa9894"},
+ {file = "lxml-4.9.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:a82d05da00a58b8e4c0008edbc8a4b6ec5a4bc1e2ee0fb6ed157cf634ed7fa45"},
+ {file = "lxml-4.9.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:223f4232855ade399bd409331e6ca70fb5578efef22cf4069a6090acc0f53c0e"},
+ {file = "lxml-4.9.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d17bc7c2ccf49c478c5bdd447594e82692c74222698cfc9b5daae7ae7e90743b"},
+ {file = "lxml-4.9.2-cp37-cp37m-win32.whl", hash = "sha256:b64d891da92e232c36976c80ed7ebb383e3f148489796d8d31a5b6a677825efe"},
+ {file = "lxml-4.9.2-cp37-cp37m-win_amd64.whl", hash = "sha256:a0a336d6d3e8b234a3aae3c674873d8f0e720b76bc1d9416866c41cd9500ffb9"},
+ {file = "lxml-4.9.2-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:da4dd7c9c50c059aba52b3524f84d7de956f7fef88f0bafcf4ad7dde94a064e8"},
+ {file = "lxml-4.9.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:821b7f59b99551c69c85a6039c65b75f5683bdc63270fec660f75da67469ca24"},
+ {file = "lxml-4.9.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:e5168986b90a8d1f2f9dc1b841467c74221bd752537b99761a93d2d981e04889"},
+ {file = "lxml-4.9.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:8e20cb5a47247e383cf4ff523205060991021233ebd6f924bca927fcf25cf86f"},
+ {file = "lxml-4.9.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:13598ecfbd2e86ea7ae45ec28a2a54fb87ee9b9fdb0f6d343297d8e548392c03"},
+ {file = "lxml-4.9.2-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:880bbbcbe2fca64e2f4d8e04db47bcdf504936fa2b33933efd945e1b429bea8c"},
+ {file = "lxml-4.9.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:7d2278d59425777cfcb19735018d897ca8303abe67cc735f9f97177ceff8027f"},
+ {file = "lxml-4.9.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:5344a43228767f53a9df6e5b253f8cdca7dfc7b7aeae52551958192f56d98457"},
+ {file = "lxml-4.9.2-cp38-cp38-win32.whl", hash = "sha256:925073b2fe14ab9b87e73f9a5fde6ce6392da430f3004d8b72cc86f746f5163b"},
+ {file = "lxml-4.9.2-cp38-cp38-win_amd64.whl", hash = "sha256:9b22c5c66f67ae00c0199f6055705bc3eb3fcb08d03d2ec4059a2b1b25ed48d7"},
+ {file = "lxml-4.9.2-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:5f50a1c177e2fa3ee0667a5ab79fdc6b23086bc8b589d90b93b4bd17eb0e64d1"},
+ {file = "lxml-4.9.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:090c6543d3696cbe15b4ac6e175e576bcc3f1ccfbba970061b7300b0c15a2140"},
+ {file = "lxml-4.9.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:63da2ccc0857c311d764e7d3d90f429c252e83b52d1f8f1d1fe55be26827d1f4"},
+ {file = "lxml-4.9.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:5b4545b8a40478183ac06c073e81a5ce4cf01bf1734962577cf2bb569a5b3bbf"},
+ {file = "lxml-4.9.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2e430cd2824f05f2d4f687701144556646bae8f249fd60aa1e4c768ba7018947"},
+ {file = "lxml-4.9.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:6804daeb7ef69e7b36f76caddb85cccd63d0c56dedb47555d2fc969e2af6a1a5"},
+ {file = "lxml-4.9.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a6e441a86553c310258aca15d1c05903aaf4965b23f3bc2d55f200804e005ee5"},
+ {file = "lxml-4.9.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ca34efc80a29351897e18888c71c6aca4a359247c87e0b1c7ada14f0ab0c0fb2"},
+ {file = "lxml-4.9.2-cp39-cp39-win32.whl", hash = "sha256:6b418afe5df18233fc6b6093deb82a32895b6bb0b1155c2cdb05203f583053f1"},
+ {file = "lxml-4.9.2-cp39-cp39-win_amd64.whl", hash = "sha256:f1496ea22ca2c830cbcbd473de8f114a320da308438ae65abad6bab7867fe38f"},
+ {file = "lxml-4.9.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:b264171e3143d842ded311b7dccd46ff9ef34247129ff5bf5066123c55c2431c"},
+ {file = "lxml-4.9.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:0dc313ef231edf866912e9d8f5a042ddab56c752619e92dfd3a2c277e6a7299a"},
+ {file = "lxml-4.9.2-pp38-pypy38_pp73-macosx_10_15_x86_64.whl", hash = "sha256:16efd54337136e8cd72fb9485c368d91d77a47ee2d42b057564aae201257d419"},
+ {file = "lxml-4.9.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:0f2b1e0d79180f344ff9f321327b005ca043a50ece8713de61d1cb383fb8ac05"},
+ {file = "lxml-4.9.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:7b770ed79542ed52c519119473898198761d78beb24b107acf3ad65deae61f1f"},
+ {file = "lxml-4.9.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:efa29c2fe6b4fdd32e8ef81c1528506895eca86e1d8c4657fda04c9b3786ddf9"},
+ {file = "lxml-4.9.2-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7e91ee82f4199af8c43d8158024cbdff3d931df350252288f0d4ce656df7f3b5"},
+ {file = "lxml-4.9.2-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:b23e19989c355ca854276178a0463951a653309fb8e57ce674497f2d9f208746"},
+ {file = "lxml-4.9.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:01d36c05f4afb8f7c20fd9ed5badca32a2029b93b1750f571ccc0b142531caf7"},
+ {file = "lxml-4.9.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7b515674acfdcadb0eb5d00d8a709868173acece5cb0be3dd165950cbfdf5409"},
+ {file = "lxml-4.9.2.tar.gz", hash = "sha256:2455cfaeb7ac70338b3257f41e21f0724f4b5b0c0e7702da67ee6c3640835b67"},
+]
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html5 = ["html5lib"]
+htmlsoup = ["BeautifulSoup4"]
+source = ["Cython (>=0.29.7)"]
+
+[[package]]
+name = "markdown"
+version = "3.4.3"
+description = "Python implementation of John Gruber's Markdown."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "Markdown-3.4.3-py3-none-any.whl", hash = "sha256:065fd4df22da73a625f14890dd77eb8040edcbd68794bcd35943be14490608b2"},
+ {file = "Markdown-3.4.3.tar.gz", hash = "sha256:8bf101198e004dc93e84a12a7395e31aac6a9c9942848ae1d99b9d72cf9b3520"},
+]
+
+[package.dependencies]
+importlib-metadata = {version = ">=4.4", markers = "python_version < \"3.10\""}
+
+[package.extras]
+testing = ["coverage", "pyyaml"]
+
+[[package]]
+name = "markdown-it-py"
+version = "2.2.0"
+description = "Python port of markdown-it. Markdown parsing, done right!"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "markdown-it-py-2.2.0.tar.gz", hash = "sha256:7c9a5e412688bc771c67432cbfebcdd686c93ce6484913dccf06cb5a0bea35a1"},
+ {file = "markdown_it_py-2.2.0-py3-none-any.whl", hash = "sha256:5a35f8d1870171d9acc47b99612dc146129b631baf04970128b568f190d0cc30"},
+]
+
+[package.dependencies]
+linkify-it-py = {version = ">=1,<3", optional = true, markers = "extra == \"linkify\""}
+mdurl = ">=0.1,<1.0"
+
+[package.extras]
+benchmarking = ["psutil", "pytest", "pytest-benchmark"]
+code-style = ["pre-commit (>=3.0,<4.0)"]
+compare = ["commonmark (>=0.9,<1.0)", "markdown (>=3.4,<4.0)", "mistletoe (>=1.0,<2.0)", "mistune (>=2.0,<3.0)", "panflute (>=2.3,<3.0)"]
+linkify = ["linkify-it-py (>=1,<3)"]
+plugins = ["mdit-py-plugins"]
+profiling = ["gprof2dot"]
+rtd = ["attrs", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx_book_theme"]
+testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
+
+[[package]]
+name = "markupsafe"
+version = "2.1.2"
+description = "Safely add untrusted strings to HTML/XML markup."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "MarkupSafe-2.1.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:665a36ae6f8f20a4676b53224e33d456a6f5a72657d9c83c2aa00765072f31f7"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:340bea174e9761308703ae988e982005aedf427de816d1afe98147668cc03036"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22152d00bf4a9c7c83960521fc558f55a1adbc0631fbb00a9471e097b19d72e1"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28057e985dace2f478e042eaa15606c7efccb700797660629da387eb289b9323"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca244fa73f50a800cf8c3ebf7fd93149ec37f5cb9596aa8873ae2c1d23498601"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d9d971ec1e79906046aa3ca266de79eac42f1dbf3612a05dc9368125952bd1a1"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7e007132af78ea9df29495dbf7b5824cb71648d7133cf7848a2a5dd00d36f9ff"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:7313ce6a199651c4ed9d7e4cfb4aa56fe923b1adf9af3b420ee14e6d9a73df65"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-win32.whl", hash = "sha256:c4a549890a45f57f1ebf99c067a4ad0cb423a05544accaf2b065246827ed9603"},
+ {file = "MarkupSafe-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:835fb5e38fd89328e9c81067fd642b3593c33e1e17e2fdbf77f5676abb14a156"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2ec4f2d48ae59bbb9d1f9d7efb9236ab81429a764dedca114f5fdabbc3788013"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:608e7073dfa9e38a85d38474c082d4281f4ce276ac0010224eaba11e929dd53a"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65608c35bfb8a76763f37036547f7adfd09270fbdbf96608be2bead319728fcd"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2bfb563d0211ce16b63c7cb9395d2c682a23187f54c3d79bfec33e6705473c6"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:da25303d91526aac3672ee6d49a2f3db2d9502a4a60b55519feb1a4c7714e07d"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:9cad97ab29dfc3f0249b483412c85c8ef4766d96cdf9dcf5a1e3caa3f3661cf1"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:085fd3201e7b12809f9e6e9bc1e5c96a368c8523fad5afb02afe3c051ae4afcc"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1bea30e9bf331f3fef67e0a3877b2288593c98a21ccb2cf29b74c581a4eb3af0"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-win32.whl", hash = "sha256:7df70907e00c970c60b9ef2938d894a9381f38e6b9db73c5be35e59d92e06625"},
+ {file = "MarkupSafe-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:e55e40ff0cc8cc5c07996915ad367fa47da6b3fc091fdadca7f5403239c5fec3"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:a6e40afa7f45939ca356f348c8e23048e02cb109ced1eb8420961b2f40fb373a"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf877ab4ed6e302ec1d04952ca358b381a882fbd9d1b07cccbfd61783561f98a"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:63ba06c9941e46fa389d389644e2d8225e0e3e5ebcc4ff1ea8506dce646f8c8a"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f1cd098434e83e656abf198f103a8207a8187c0fc110306691a2e94a78d0abb2"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:55f44b440d491028addb3b88f72207d71eeebfb7b5dbf0643f7c023ae1fba619"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:a6f2fcca746e8d5910e18782f976489939d54a91f9411c32051b4aab2bd7c513"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:0b462104ba25f1ac006fdab8b6a01ebbfbce9ed37fd37fd4acd70c67c973e460"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-win32.whl", hash = "sha256:7668b52e102d0ed87cb082380a7e2e1e78737ddecdde129acadb0eccc5423859"},
+ {file = "MarkupSafe-2.1.2-cp37-cp37m-win_amd64.whl", hash = "sha256:6d6607f98fcf17e534162f0709aaad3ab7a96032723d8ac8750ffe17ae5a0666"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:a806db027852538d2ad7555b203300173dd1b77ba116de92da9afbc3a3be3eed"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a4abaec6ca3ad8660690236d11bfe28dfd707778e2442b45addd2f086d6ef094"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f03a532d7dee1bed20bc4884194a16160a2de9ffc6354b3878ec9682bb623c54"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4cf06cdc1dda95223e9d2d3c58d3b178aa5dacb35ee7e3bbac10e4e1faacb419"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22731d79ed2eb25059ae3df1dfc9cb1546691cc41f4e3130fe6bfbc3ecbbecfa"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:f8ffb705ffcf5ddd0e80b65ddf7bed7ee4f5a441ea7d3419e861a12eaf41af58"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:8db032bf0ce9022a8e41a22598eefc802314e81b879ae093f36ce9ddf39ab1ba"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2298c859cfc5463f1b64bd55cb3e602528db6fa0f3cfd568d3605c50678f8f03"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-win32.whl", hash = "sha256:50c42830a633fa0cf9e7d27664637532791bfc31c731a87b202d2d8ac40c3ea2"},
+ {file = "MarkupSafe-2.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:bb06feb762bade6bf3c8b844462274db0c76acc95c52abe8dbed28ae3d44a147"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:99625a92da8229df6d44335e6fcc558a5037dd0a760e11d84be2260e6f37002f"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8bca7e26c1dd751236cfb0c6c72d4ad61d986e9a41bbf76cb445f69488b2a2bd"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40627dcf047dadb22cd25ea7ecfe9cbf3bbbad0482ee5920b582f3809c97654f"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40dfd3fefbef579ee058f139733ac336312663c6706d1163b82b3003fb1925c4"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:090376d812fb6ac5f171e5938e82e7f2d7adc2b629101cec0db8b267815c85e2"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2e7821bffe00aa6bd07a23913b7f4e01328c3d5cc0b40b36c0bd81d362faeb65"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:c0a33bc9f02c2b17c3ea382f91b4db0e6cde90b63b296422a939886a7a80de1c"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b8526c6d437855442cdd3d87eede9c425c4445ea011ca38d937db299382e6fa3"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-win32.whl", hash = "sha256:137678c63c977754abe9086a3ec011e8fd985ab90631145dfb9294ad09c102a7"},
+ {file = "MarkupSafe-2.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:0576fe974b40a400449768941d5d0858cc624e3249dfd1e0c33674e5c7ca7aed"},
+ {file = "MarkupSafe-2.1.2.tar.gz", hash = "sha256:abcabc8c2b26036d62d4c746381a6f7cf60aafcc653198ad678306986b09450d"},
+]
+
+[[package]]
+name = "matplotlib"
+version = "3.7.1"
+description = "Python plotting package"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "matplotlib-3.7.1-cp310-cp310-macosx_10_12_universal2.whl", hash = "sha256:95cbc13c1fc6844ab8812a525bbc237fa1470863ff3dace7352e910519e194b1"},
+ {file = "matplotlib-3.7.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:08308bae9e91aca1ec6fd6dda66237eef9f6294ddb17f0d0b3c863169bf82353"},
+ {file = "matplotlib-3.7.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:544764ba51900da4639c0f983b323d288f94f65f4024dc40ecb1542d74dc0500"},
+ {file = "matplotlib-3.7.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:56d94989191de3fcc4e002f93f7f1be5da476385dde410ddafbb70686acf00ea"},
+ {file = "matplotlib-3.7.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e99bc9e65901bb9a7ce5e7bb24af03675cbd7c70b30ac670aa263240635999a4"},
+ {file = "matplotlib-3.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eb7d248c34a341cd4c31a06fd34d64306624c8cd8d0def7abb08792a5abfd556"},
+ {file = "matplotlib-3.7.1-cp310-cp310-win32.whl", hash = "sha256:ce463ce590f3825b52e9fe5c19a3c6a69fd7675a39d589e8b5fbe772272b3a24"},
+ {file = "matplotlib-3.7.1-cp310-cp310-win_amd64.whl", hash = "sha256:3d7bc90727351fb841e4d8ae620d2d86d8ed92b50473cd2b42ce9186104ecbba"},
+ {file = "matplotlib-3.7.1-cp311-cp311-macosx_10_12_universal2.whl", hash = "sha256:770a205966d641627fd5cf9d3cb4b6280a716522cd36b8b284a8eb1581310f61"},
+ {file = "matplotlib-3.7.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:f67bfdb83a8232cb7a92b869f9355d677bce24485c460b19d01970b64b2ed476"},
+ {file = "matplotlib-3.7.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2bf092f9210e105f414a043b92af583c98f50050559616930d884387d0772aba"},
+ {file = "matplotlib-3.7.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89768d84187f31717349c6bfadc0e0d8c321e8eb34522acec8a67b1236a66332"},
+ {file = "matplotlib-3.7.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:83111e6388dec67822e2534e13b243cc644c7494a4bb60584edbff91585a83c6"},
+ {file = "matplotlib-3.7.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a867bf73a7eb808ef2afbca03bcdb785dae09595fbe550e1bab0cd023eba3de0"},
+ {file = "matplotlib-3.7.1-cp311-cp311-win32.whl", hash = "sha256:fbdeeb58c0cf0595efe89c05c224e0a502d1aa6a8696e68a73c3efc6bc354304"},
+ {file = "matplotlib-3.7.1-cp311-cp311-win_amd64.whl", hash = "sha256:c0bd19c72ae53e6ab979f0ac6a3fafceb02d2ecafa023c5cca47acd934d10be7"},
+ {file = "matplotlib-3.7.1-cp38-cp38-macosx_10_12_universal2.whl", hash = "sha256:6eb88d87cb2c49af00d3bbc33a003f89fd9f78d318848da029383bfc08ecfbfb"},
+ {file = "matplotlib-3.7.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:cf0e4f727534b7b1457898c4f4ae838af1ef87c359b76dcd5330fa31893a3ac7"},
+ {file = "matplotlib-3.7.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:46a561d23b91f30bccfd25429c3c706afe7d73a5cc64ef2dfaf2b2ac47c1a5dc"},
+ {file = "matplotlib-3.7.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:8704726d33e9aa8a6d5215044b8d00804561971163563e6e6591f9dcf64340cc"},
+ {file = "matplotlib-3.7.1-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:4cf327e98ecf08fcbb82685acaf1939d3338548620ab8dfa02828706402c34de"},
+ {file = "matplotlib-3.7.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:617f14ae9d53292ece33f45cba8503494ee199a75b44de7717964f70637a36aa"},
+ {file = "matplotlib-3.7.1-cp38-cp38-win32.whl", hash = "sha256:7c9a4b2da6fac77bcc41b1ea95fadb314e92508bf5493ceff058e727e7ecf5b0"},
+ {file = "matplotlib-3.7.1-cp38-cp38-win_amd64.whl", hash = "sha256:14645aad967684e92fc349493fa10c08a6da514b3d03a5931a1bac26e6792bd1"},
+ {file = "matplotlib-3.7.1-cp39-cp39-macosx_10_12_universal2.whl", hash = "sha256:81a6b377ea444336538638d31fdb39af6be1a043ca5e343fe18d0f17e098770b"},
+ {file = "matplotlib-3.7.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:28506a03bd7f3fe59cd3cd4ceb2a8d8a2b1db41afede01f66c42561b9be7b4b7"},
+ {file = "matplotlib-3.7.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8c587963b85ce41e0a8af53b9b2de8dddbf5ece4c34553f7bd9d066148dc719c"},
+ {file = "matplotlib-3.7.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8bf26ade3ff0f27668989d98c8435ce9327d24cffb7f07d24ef609e33d582439"},
+ {file = "matplotlib-3.7.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:def58098f96a05f90af7e92fd127d21a287068202aa43b2a93476170ebd99e87"},
+ {file = "matplotlib-3.7.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f883a22a56a84dba3b588696a2b8a1ab0d2c3d41be53264115c71b0a942d8fdb"},
+ {file = "matplotlib-3.7.1-cp39-cp39-win32.whl", hash = "sha256:4f99e1b234c30c1e9714610eb0c6d2f11809c9c78c984a613ae539ea2ad2eb4b"},
+ {file = "matplotlib-3.7.1-cp39-cp39-win_amd64.whl", hash = "sha256:3ba2af245e36990facf67fde840a760128ddd71210b2ab6406e640188d69d136"},
+ {file = "matplotlib-3.7.1-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3032884084f541163f295db8a6536e0abb0db464008fadca6c98aaf84ccf4717"},
+ {file = "matplotlib-3.7.1-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3a2cb34336110e0ed8bb4f650e817eed61fa064acbefeb3591f1b33e3a84fd96"},
+ {file = "matplotlib-3.7.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b867e2f952ed592237a1828f027d332d8ee219ad722345b79a001f49df0936eb"},
+ {file = "matplotlib-3.7.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:57bfb8c8ea253be947ccb2bc2d1bb3862c2bccc662ad1b4626e1f5e004557042"},
+ {file = "matplotlib-3.7.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:438196cdf5dc8d39b50a45cb6e3f6274edbcf2254f85fa9b895bf85851c3a613"},
+ {file = "matplotlib-3.7.1-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:21e9cff1a58d42e74d01153360de92b326708fb205250150018a52c70f43c290"},
+ {file = "matplotlib-3.7.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75d4725d70b7c03e082bbb8a34639ede17f333d7247f56caceb3801cb6ff703d"},
+ {file = "matplotlib-3.7.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:97cc368a7268141afb5690760921765ed34867ffb9655dd325ed207af85c7529"},
+ {file = "matplotlib-3.7.1.tar.gz", hash = "sha256:7b73305f25eab4541bd7ee0b96d87e53ae9c9f1823be5659b806cd85786fe882"},
+]
+
+[package.dependencies]
+contourpy = ">=1.0.1"
+cycler = ">=0.10"
+fonttools = ">=4.22.0"
+importlib-resources = {version = ">=3.2.0", markers = "python_version < \"3.10\""}
+kiwisolver = ">=1.0.1"
+numpy = ">=1.20"
+packaging = ">=20.0"
+pillow = ">=6.2.0"
+pyparsing = ">=2.3.1"
+python-dateutil = ">=2.7"
+
+[[package]]
+name = "matplotlib-inline"
+version = "0.1.6"
+description = "Inline Matplotlib backend for Jupyter"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+files = [
+ {file = "matplotlib-inline-0.1.6.tar.gz", hash = "sha256:f887e5f10ba98e8d2b150ddcf4702c1e5f8b3a20005eb0f74bfdbd360ee6f304"},
+ {file = "matplotlib_inline-0.1.6-py3-none-any.whl", hash = "sha256:f1f41aab5328aa5aaea9b16d083b128102f8712542f819fe7e6a420ff581b311"},
+]
+
+[package.dependencies]
+traitlets = "*"
+
+[[package]]
+name = "mdit-py-plugins"
+version = "0.3.3"
+description = "Collection of plugins for markdown-it-py"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "mdit-py-plugins-0.3.3.tar.gz", hash = "sha256:5cfd7e7ac582a594e23ba6546a2f406e94e42eb33ae596d0734781261c251260"},
+ {file = "mdit_py_plugins-0.3.3-py3-none-any.whl", hash = "sha256:36d08a29def19ec43acdcd8ba471d3ebab132e7879d442760d963f19913e04b9"},
+]
+
+[package.dependencies]
+markdown-it-py = ">=1.0.0,<3.0.0"
+
+[package.extras]
+code-style = ["pre-commit"]
+rtd = ["attrs", "myst-parser (>=0.16.1,<0.17.0)", "sphinx-book-theme (>=0.1.0,<0.2.0)"]
+testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
+
+[[package]]
+name = "mdurl"
+version = "0.1.2"
+description = "Markdown URL utilities"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8"},
+ {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
+]
+
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
+ {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
+]
+
+[package.extras]
+develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
+[[package]]
+name = "multidict"
+version = "6.0.4"
+description = "multidict implementation"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b1a97283e0c85772d613878028fec909f003993e1007eafa715b24b377cb9b8"},
+ {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb6dcc05e911516ae3d1f207d4b0520d07f54484c49dfc294d6e7d63b734171"},
+ {file = "multidict-6.0.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d6d635d5209b82a3492508cf5b365f3446afb65ae7ebd755e70e18f287b0adf7"},
+ {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c048099e4c9e9d615545e2001d3d8a4380bd403e1a0578734e0d31703d1b0c0b"},
+ {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ea20853c6dbbb53ed34cb4d080382169b6f4554d394015f1bef35e881bf83547"},
+ {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:16d232d4e5396c2efbbf4f6d4df89bfa905eb0d4dc5b3549d872ab898451f569"},
+ {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36c63aaa167f6c6b04ef2c85704e93af16c11d20de1d133e39de6a0e84582a93"},
+ {file = "multidict-6.0.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:64bdf1086b6043bf519869678f5f2757f473dee970d7abf6da91ec00acb9cb98"},
+ {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:43644e38f42e3af682690876cff722d301ac585c5b9e1eacc013b7a3f7b696a0"},
+ {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7582a1d1030e15422262de9f58711774e02fa80df0d1578995c76214f6954988"},
+ {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:ddff9c4e225a63a5afab9dd15590432c22e8057e1a9a13d28ed128ecf047bbdc"},
+ {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:ee2a1ece51b9b9e7752e742cfb661d2a29e7bcdba2d27e66e28a99f1890e4fa0"},
+ {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a2e4369eb3d47d2034032a26c7a80fcb21a2cb22e1173d761a162f11e562caa5"},
+ {file = "multidict-6.0.4-cp310-cp310-win32.whl", hash = "sha256:574b7eae1ab267e5f8285f0fe881f17efe4b98c39a40858247720935b893bba8"},
+ {file = "multidict-6.0.4-cp310-cp310-win_amd64.whl", hash = "sha256:4dcbb0906e38440fa3e325df2359ac6cb043df8e58c965bb45f4e406ecb162cc"},
+ {file = "multidict-6.0.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0dfad7a5a1e39c53ed00d2dd0c2e36aed4650936dc18fd9a1826a5ae1cad6f03"},
+ {file = "multidict-6.0.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:64da238a09d6039e3bd39bb3aee9c21a5e34f28bfa5aa22518581f910ff94af3"},
+ {file = "multidict-6.0.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ff959bee35038c4624250473988b24f846cbeb2c6639de3602c073f10410ceba"},
+ {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:01a3a55bd90018c9c080fbb0b9f4891db37d148a0a18722b42f94694f8b6d4c9"},
+ {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5cb09abb18c1ea940fb99360ea0396f34d46566f157122c92dfa069d3e0e982"},
+ {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:666daae833559deb2d609afa4490b85830ab0dfca811a98b70a205621a6109fe"},
+ {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11bdf3f5e1518b24530b8241529d2050014c884cf18b6fc69c0c2b30ca248710"},
+ {file = "multidict-6.0.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d18748f2d30f94f498e852c67d61261c643b349b9d2a581131725595c45ec6c"},
+ {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:458f37be2d9e4c95e2d8866a851663cbc76e865b78395090786f6cd9b3bbf4f4"},
+ {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:b1a2eeedcead3a41694130495593a559a668f382eee0727352b9a41e1c45759a"},
+ {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7d6ae9d593ef8641544d6263c7fa6408cc90370c8cb2bbb65f8d43e5b0351d9c"},
+ {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:5979b5632c3e3534e42ca6ff856bb24b2e3071b37861c2c727ce220d80eee9ed"},
+ {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:dcfe792765fab89c365123c81046ad4103fcabbc4f56d1c1997e6715e8015461"},
+ {file = "multidict-6.0.4-cp311-cp311-win32.whl", hash = "sha256:3601a3cece3819534b11d4efc1eb76047488fddd0c85a3948099d5da4d504636"},
+ {file = "multidict-6.0.4-cp311-cp311-win_amd64.whl", hash = "sha256:81a4f0b34bd92df3da93315c6a59034df95866014ac08535fc819f043bfd51f0"},
+ {file = "multidict-6.0.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:67040058f37a2a51ed8ea8f6b0e6ee5bd78ca67f169ce6122f3e2ec80dfe9b78"},
+ {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:853888594621e6604c978ce2a0444a1e6e70c8d253ab65ba11657659dcc9100f"},
+ {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:39ff62e7d0f26c248b15e364517a72932a611a9b75f35b45be078d81bdb86603"},
+ {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:af048912e045a2dc732847d33821a9d84ba553f5c5f028adbd364dd4765092ac"},
+ {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1e8b901e607795ec06c9e42530788c45ac21ef3aaa11dbd0c69de543bfb79a9"},
+ {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62501642008a8b9871ddfccbf83e4222cf8ac0d5aeedf73da36153ef2ec222d2"},
+ {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:99b76c052e9f1bc0721f7541e5e8c05db3941eb9ebe7b8553c625ef88d6eefde"},
+ {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:509eac6cf09c794aa27bcacfd4d62c885cce62bef7b2c3e8b2e49d365b5003fe"},
+ {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:21a12c4eb6ddc9952c415f24eef97e3e55ba3af61f67c7bc388dcdec1404a067"},
+ {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:5cad9430ab3e2e4fa4a2ef4450f548768400a2ac635841bc2a56a2052cdbeb87"},
+ {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ab55edc2e84460694295f401215f4a58597f8f7c9466faec545093045476327d"},
+ {file = "multidict-6.0.4-cp37-cp37m-win32.whl", hash = "sha256:5a4dcf02b908c3b8b17a45fb0f15b695bf117a67b76b7ad18b73cf8e92608775"},
+ {file = "multidict-6.0.4-cp37-cp37m-win_amd64.whl", hash = "sha256:6ed5f161328b7df384d71b07317f4d8656434e34591f20552c7bcef27b0ab88e"},
+ {file = "multidict-6.0.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5fc1b16f586f049820c5c5b17bb4ee7583092fa0d1c4e28b5239181ff9532e0c"},
+ {file = "multidict-6.0.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1502e24330eb681bdaa3eb70d6358e818e8e8f908a22a1851dfd4e15bc2f8161"},
+ {file = "multidict-6.0.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b692f419760c0e65d060959df05f2a531945af31fda0c8a3b3195d4efd06de11"},
+ {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45e1ecb0379bfaab5eef059f50115b54571acfbe422a14f668fc8c27ba410e7e"},
+ {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ddd3915998d93fbcd2566ddf9cf62cdb35c9e093075f862935573d265cf8f65d"},
+ {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:59d43b61c59d82f2effb39a93c48b845efe23a3852d201ed2d24ba830d0b4cf2"},
+ {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc8e1d0c705233c5dd0c5e6460fbad7827d5d36f310a0fadfd45cc3029762258"},
+ {file = "multidict-6.0.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d6aa0418fcc838522256761b3415822626f866758ee0bc6632c9486b179d0b52"},
+ {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6748717bb10339c4760c1e63da040f5f29f5ed6e59d76daee30305894069a660"},
+ {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4d1a3d7ef5e96b1c9e92f973e43aa5e5b96c659c9bc3124acbbd81b0b9c8a951"},
+ {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4372381634485bec7e46718edc71528024fcdc6f835baefe517b34a33c731d60"},
+ {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:fc35cb4676846ef752816d5be2193a1e8367b4c1397b74a565a9d0389c433a1d"},
+ {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:4b9d9e4e2b37daddb5c23ea33a3417901fa7c7b3dee2d855f63ee67a0b21e5b1"},
+ {file = "multidict-6.0.4-cp38-cp38-win32.whl", hash = "sha256:e41b7e2b59679edfa309e8db64fdf22399eec4b0b24694e1b2104fb789207779"},
+ {file = "multidict-6.0.4-cp38-cp38-win_amd64.whl", hash = "sha256:d6c254ba6e45d8e72739281ebc46ea5eb5f101234f3ce171f0e9f5cc86991480"},
+ {file = "multidict-6.0.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:16ab77bbeb596e14212e7bab8429f24c1579234a3a462105cda4a66904998664"},
+ {file = "multidict-6.0.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc779e9e6f7fda81b3f9aa58e3a6091d49ad528b11ed19f6621408806204ad35"},
+ {file = "multidict-6.0.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4ceef517eca3e03c1cceb22030a3e39cb399ac86bff4e426d4fc6ae49052cc60"},
+ {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:281af09f488903fde97923c7744bb001a9b23b039a909460d0f14edc7bf59706"},
+ {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:52f2dffc8acaba9a2f27174c41c9e57f60b907bb9f096b36b1a1f3be71c6284d"},
+ {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b41156839806aecb3641f3208c0dafd3ac7775b9c4c422d82ee2a45c34ba81ca"},
+ {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5e3fc56f88cc98ef8139255cf8cd63eb2c586531e43310ff859d6bb3a6b51f1"},
+ {file = "multidict-6.0.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8316a77808c501004802f9beebde51c9f857054a0c871bd6da8280e718444449"},
+ {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f70b98cd94886b49d91170ef23ec5c0e8ebb6f242d734ed7ed677b24d50c82cf"},
+ {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bf6774e60d67a9efe02b3616fee22441d86fab4c6d335f9d2051d19d90a40063"},
+ {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:e69924bfcdda39b722ef4d9aa762b2dd38e4632b3641b1d9a57ca9cd18f2f83a"},
+ {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:6b181d8c23da913d4ff585afd1155a0e1194c0b50c54fcfe286f70cdaf2b7176"},
+ {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:52509b5be062d9eafc8170e53026fbc54cf3b32759a23d07fd935fb04fc22d95"},
+ {file = "multidict-6.0.4-cp39-cp39-win32.whl", hash = "sha256:27c523fbfbdfd19c6867af7346332b62b586eed663887392cff78d614f9ec313"},
+ {file = "multidict-6.0.4-cp39-cp39-win_amd64.whl", hash = "sha256:33029f5734336aa0d4c0384525da0387ef89148dc7191aae00ca5fb23d7aafc2"},
+ {file = "multidict-6.0.4.tar.gz", hash = "sha256:3666906492efb76453c0e7b97f2cf459b0682e7402c0489a95484965dbc1da49"},
+]
+
+[[package]]
+name = "networkx"
+version = "3.1"
+description = "Python package for creating and manipulating graphs and networks"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "networkx-3.1-py3-none-any.whl", hash = "sha256:4f33f68cb2afcf86f28a45f43efc27a9386b535d567d2127f8f61d51dec58d36"},
+ {file = "networkx-3.1.tar.gz", hash = "sha256:de346335408f84de0eada6ff9fafafff9bcda11f0a0dfaa931133debb146ab61"},
+]
+
+[package.extras]
+default = ["matplotlib (>=3.4)", "numpy (>=1.20)", "pandas (>=1.3)", "scipy (>=1.8)"]
+developer = ["mypy (>=1.1)", "pre-commit (>=3.2)"]
+doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.13)", "sphinx (>=6.1)", "sphinx-gallery (>=0.12)", "texext (>=0.6.7)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
+test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
+[[package]]
+name = "numba"
+version = "0.56.4"
+description = "compiling Python code using LLVM"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "numba-0.56.4-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:9f62672145f8669ec08762895fe85f4cf0ead08ce3164667f2b94b2f62ab23c3"},
+ {file = "numba-0.56.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c602d015478b7958408d788ba00a50272649c5186ea8baa6cf71d4a1c761bba1"},
+ {file = "numba-0.56.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:85dbaed7a05ff96492b69a8900c5ba605551afb9b27774f7f10511095451137c"},
+ {file = "numba-0.56.4-cp310-cp310-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:f4cfc3a19d1e26448032049c79fc60331b104f694cf570a9e94f4e2c9d0932bb"},
+ {file = "numba-0.56.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4e08e203b163ace08bad500b0c16f6092b1eb34fd1fce4feaf31a67a3a5ecf3b"},
+ {file = "numba-0.56.4-cp310-cp310-win32.whl", hash = "sha256:0611e6d3eebe4cb903f1a836ffdb2bda8d18482bcd0a0dcc56e79e2aa3fefef5"},
+ {file = "numba-0.56.4-cp310-cp310-win_amd64.whl", hash = "sha256:fbfb45e7b297749029cb28694abf437a78695a100e7c2033983d69f0ba2698d4"},
+ {file = "numba-0.56.4-cp37-cp37m-macosx_10_14_x86_64.whl", hash = "sha256:3cb1a07a082a61df80a468f232e452d818f5ae254b40c26390054e4e868556e0"},
+ {file = "numba-0.56.4-cp37-cp37m-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d69ad934e13c15684e7887100a8f5f0f61d7a8e57e0fd29d9993210089a5b531"},
+ {file = "numba-0.56.4-cp37-cp37m-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:dbcc847bac2d225265d054993a7f910fda66e73d6662fe7156452cac0325b073"},
+ {file = "numba-0.56.4-cp37-cp37m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8a95ca9cc77ea4571081f6594e08bd272b66060634b8324e99cd1843020364f9"},
+ {file = "numba-0.56.4-cp37-cp37m-win32.whl", hash = "sha256:fcdf84ba3ed8124eb7234adfbb8792f311991cbf8aed1cad4b1b1a7ee08380c1"},
+ {file = "numba-0.56.4-cp37-cp37m-win_amd64.whl", hash = "sha256:42f9e1be942b215df7e6cc9948cf9c15bb8170acc8286c063a9e57994ef82fd1"},
+ {file = "numba-0.56.4-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:553da2ce74e8862e18a72a209ed3b6d2924403bdd0fb341fa891c6455545ba7c"},
+ {file = "numba-0.56.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4373da9757049db7c90591e9ec55a2e97b2b36ba7ae3bf9c956a513374077470"},
+ {file = "numba-0.56.4-cp38-cp38-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3a993349b90569518739009d8f4b523dfedd7e0049e6838c0e17435c3e70dcc4"},
+ {file = "numba-0.56.4-cp38-cp38-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:720886b852a2d62619ae3900fe71f1852c62db4f287d0c275a60219e1643fc04"},
+ {file = "numba-0.56.4-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e64d338b504c9394a4a34942df4627e1e6cb07396ee3b49fe7b8d6420aa5104f"},
+ {file = "numba-0.56.4-cp38-cp38-win32.whl", hash = "sha256:03fe94cd31e96185cce2fae005334a8cc712fc2ba7756e52dff8c9400718173f"},
+ {file = "numba-0.56.4-cp38-cp38-win_amd64.whl", hash = "sha256:91f021145a8081f881996818474ef737800bcc613ffb1e618a655725a0f9e246"},
+ {file = "numba-0.56.4-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:d0ae9270a7a5cc0ede63cd234b4ff1ce166c7a749b91dbbf45e0000c56d3eade"},
+ {file = "numba-0.56.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c75e8a5f810ce80a0cfad6e74ee94f9fde9b40c81312949bf356b7304ef20740"},
+ {file = "numba-0.56.4-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:a12ef323c0f2101529d455cfde7f4135eaa147bad17afe10b48634f796d96abd"},
+ {file = "numba-0.56.4-cp39-cp39-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:03634579d10a6129181129de293dd6b5eaabee86881369d24d63f8fe352dd6cb"},
+ {file = "numba-0.56.4-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:0240f9026b015e336069329839208ebd70ec34ae5bfbf402e4fcc8e06197528e"},
+ {file = "numba-0.56.4-cp39-cp39-win32.whl", hash = "sha256:14dbbabf6ffcd96ee2ac827389afa59a70ffa9f089576500434c34abf9b054a4"},
+ {file = "numba-0.56.4-cp39-cp39-win_amd64.whl", hash = "sha256:0da583c532cd72feefd8e551435747e0e0fbb3c0530357e6845fcc11e38d6aea"},
+ {file = "numba-0.56.4.tar.gz", hash = "sha256:32d9fef412c81483d7efe0ceb6cf4d3310fde8b624a9cecca00f790573ac96ee"},
+]
+
+[package.dependencies]
+importlib-metadata = {version = "*", markers = "python_version < \"3.9\""}
+llvmlite = ">=0.39.0dev0,<0.40"
+numpy = ">=1.18,<1.24"
+setuptools = "*"
+
+[[package]]
+name = "numpy"
+version = "1.23.5"
+description = "NumPy is the fundamental package for array computing with Python."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "numpy-1.23.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9c88793f78fca17da0145455f0d7826bcb9f37da4764af27ac945488116efe63"},
+ {file = "numpy-1.23.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e9f4c4e51567b616be64e05d517c79a8a22f3606499941d97bb76f2ca59f982d"},
+ {file = "numpy-1.23.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7903ba8ab592b82014713c491f6c5d3a1cde5b4a3bf116404e08f5b52f6daf43"},
+ {file = "numpy-1.23.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e05b1c973a9f858c74367553e236f287e749465f773328c8ef31abe18f691e1"},
+ {file = "numpy-1.23.5-cp310-cp310-win32.whl", hash = "sha256:522e26bbf6377e4d76403826ed689c295b0b238f46c28a7251ab94716da0b280"},
+ {file = "numpy-1.23.5-cp310-cp310-win_amd64.whl", hash = "sha256:dbee87b469018961d1ad79b1a5d50c0ae850000b639bcb1b694e9981083243b6"},
+ {file = "numpy-1.23.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ce571367b6dfe60af04e04a1834ca2dc5f46004ac1cc756fb95319f64c095a96"},
+ {file = "numpy-1.23.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:56e454c7833e94ec9769fa0f86e6ff8e42ee38ce0ce1fa4cbb747ea7e06d56aa"},
+ {file = "numpy-1.23.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5039f55555e1eab31124a5768898c9e22c25a65c1e0037f4d7c495a45778c9f2"},
+ {file = "numpy-1.23.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58f545efd1108e647604a1b5aa809591ccd2540f468a880bedb97247e72db387"},
+ {file = "numpy-1.23.5-cp311-cp311-win32.whl", hash = "sha256:b2a9ab7c279c91974f756c84c365a669a887efa287365a8e2c418f8b3ba73fb0"},
+ {file = "numpy-1.23.5-cp311-cp311-win_amd64.whl", hash = "sha256:0cbe9848fad08baf71de1a39e12d1b6310f1d5b2d0ea4de051058e6e1076852d"},
+ {file = "numpy-1.23.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f063b69b090c9d918f9df0a12116029e274daf0181df392839661c4c7ec9018a"},
+ {file = "numpy-1.23.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0aaee12d8883552fadfc41e96b4c82ee7d794949e2a7c3b3a7201e968c7ecab9"},
+ {file = "numpy-1.23.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:92c8c1e89a1f5028a4c6d9e3ccbe311b6ba53694811269b992c0b224269e2398"},
+ {file = "numpy-1.23.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d208a0f8729f3fb790ed18a003f3a57895b989b40ea4dce4717e9cf4af62c6bb"},
+ {file = "numpy-1.23.5-cp38-cp38-win32.whl", hash = "sha256:06005a2ef6014e9956c09ba07654f9837d9e26696a0470e42beedadb78c11b07"},
+ {file = "numpy-1.23.5-cp38-cp38-win_amd64.whl", hash = "sha256:ca51fcfcc5f9354c45f400059e88bc09215fb71a48d3768fb80e357f3b457e1e"},
+ {file = "numpy-1.23.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8969bfd28e85c81f3f94eb4a66bc2cf1dbdc5c18efc320af34bffc54d6b1e38f"},
+ {file = "numpy-1.23.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a7ac231a08bb37f852849bbb387a20a57574a97cfc7b6cabb488a4fc8be176de"},
+ {file = "numpy-1.23.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bf837dc63ba5c06dc8797c398db1e223a466c7ece27a1f7b5232ba3466aafe3d"},
+ {file = "numpy-1.23.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33161613d2269025873025b33e879825ec7b1d831317e68f4f2f0f84ed14c719"},
+ {file = "numpy-1.23.5-cp39-cp39-win32.whl", hash = "sha256:af1da88f6bc3d2338ebbf0e22fe487821ea4d8e89053e25fa59d1d79786e7481"},
+ {file = "numpy-1.23.5-cp39-cp39-win_amd64.whl", hash = "sha256:09b7847f7e83ca37c6e627682f145856de331049013853f344f37b0c9690e3df"},
+ {file = "numpy-1.23.5-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:abdde9f795cf292fb9651ed48185503a2ff29be87770c3b8e2a14b0cd7aa16f8"},
+ {file = "numpy-1.23.5-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9a909a8bae284d46bbfdefbdd4a262ba19d3bc9921b1e76126b1d21c3c34135"},
+ {file = "numpy-1.23.5-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:01dd17cbb340bf0fc23981e52e1d18a9d4050792e8fb8363cecbf066a84b827d"},
+ {file = "numpy-1.23.5.tar.gz", hash = "sha256:1b1766d6f397c18153d40015ddfc79ddb715cabadc04d2d228d4e5a8bc4ded1a"},
+]
+
+[[package]]
+name = "nvidia-cublas-cu11"
+version = "11.10.3.66"
+description = "CUBLAS native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl", hash = "sha256:d32e4d75f94ddfb93ea0a5dda08389bcc65d8916a25cb9f37ac89edaeed3bded"},
+ {file = "nvidia_cublas_cu11-11.10.3.66-py3-none-win_amd64.whl", hash = "sha256:8ac17ba6ade3ed56ab898a036f9ae0756f1e81052a317bf98f8c6d18dc3ae49e"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cuda-cupti-cu11"
+version = "11.7.101"
+description = "CUDA profiling tools runtime libs."
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cuda_cupti_cu11-11.7.101-py3-none-manylinux1_x86_64.whl", hash = "sha256:e0cfd9854e1f2edaa36ca20d21cd0bdd5dcfca4e3b9e130a082e05b33b6c5895"},
+ {file = "nvidia_cuda_cupti_cu11-11.7.101-py3-none-win_amd64.whl", hash = "sha256:7cc5b8f91ae5e1389c3c0ad8866b3b016a175e827ea8f162a672990a402ab2b0"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu11"
+version = "11.7.99"
+description = "NVRTC native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:9f1562822ea264b7e34ed5930567e89242d266448e936b85bc97a3370feabb03"},
+ {file = "nvidia_cuda_nvrtc_cu11-11.7.99-py3-none-manylinux1_x86_64.whl", hash = "sha256:f7d9610d9b7c331fa0da2d1b2858a4a8315e6d49765091d28711c8946e7425e7"},
+ {file = "nvidia_cuda_nvrtc_cu11-11.7.99-py3-none-win_amd64.whl", hash = "sha256:f2effeb1309bdd1b3854fc9b17eaf997808f8b25968ce0c7070945c4265d64a3"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cuda-runtime-cu11"
+version = "11.7.99"
+description = "CUDA Runtime native Libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl", hash = "sha256:cc768314ae58d2641f07eac350f40f99dcb35719c4faff4bc458a7cd2b119e31"},
+ {file = "nvidia_cuda_runtime_cu11-11.7.99-py3-none-win_amd64.whl", hash = "sha256:bc77fa59a7679310df9d5c70ab13c4e34c64ae2124dd1efd7e5474b71be125c7"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cudnn-cu11"
+version = "8.5.0.96"
+description = "cuDNN runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:402f40adfc6f418f9dae9ab402e773cfed9beae52333f6d86ae3107a1b9527e7"},
+ {file = "nvidia_cudnn_cu11-8.5.0.96-py3-none-manylinux1_x86_64.whl", hash = "sha256:71f8111eb830879ff2836db3cccf03bbd735df9b0d17cd93761732ac50a8a108"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cufft-cu11"
+version = "10.9.0.58"
+description = "CUFFT native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cufft_cu11-10.9.0.58-py3-none-manylinux1_x86_64.whl", hash = "sha256:222f9da70c80384632fd6035e4c3f16762d64ea7a843829cb278f98b3cb7dd81"},
+ {file = "nvidia_cufft_cu11-10.9.0.58-py3-none-win_amd64.whl", hash = "sha256:c4d316f17c745ec9c728e30409612eaf77a8404c3733cdf6c9c1569634d1ca03"},
+]
+
+[[package]]
+name = "nvidia-curand-cu11"
+version = "10.2.10.91"
+description = "CURAND native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_curand_cu11-10.2.10.91-py3-none-manylinux1_x86_64.whl", hash = "sha256:eecb269c970fa599a2660c9232fa46aaccbf90d9170b96c462e13bcb4d129e2c"},
+ {file = "nvidia_curand_cu11-10.2.10.91-py3-none-win_amd64.whl", hash = "sha256:f742052af0e1e75523bde18895a9ed016ecf1e5aa0ecddfcc3658fd11a1ff417"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cusolver-cu11"
+version = "11.4.0.1"
+description = "CUDA solver native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cusolver_cu11-11.4.0.1-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:72fa7261d755ed55c0074960df5904b65e2326f7adce364cbe4945063c1be412"},
+ {file = "nvidia_cusolver_cu11-11.4.0.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:700b781bfefd57d161443aff9ace1878584b93e0b2cfef3d6e9296d96febbf99"},
+ {file = "nvidia_cusolver_cu11-11.4.0.1-py3-none-win_amd64.whl", hash = "sha256:00f70b256add65f8c1eb3b6a65308795a93e7740f6df9e273eccbba770d370c4"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-cusparse-cu11"
+version = "11.7.4.91"
+description = "CUSPARSE native runtime libraries"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_cusparse_cu11-11.7.4.91-py3-none-manylinux1_x86_64.whl", hash = "sha256:a3389de714db63321aa11fbec3919271f415ef19fda58aed7f2ede488c32733d"},
+ {file = "nvidia_cusparse_cu11-11.7.4.91-py3-none-win_amd64.whl", hash = "sha256:304a01599534f5186a8ed1c3756879282c72c118bc77dd890dc1ff868cad25b9"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "nvidia-nccl-cu11"
+version = "2.14.3"
+description = "NVIDIA Collective Communication Library (NCCL) Runtime"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_nccl_cu11-2.14.3-py3-none-manylinux1_x86_64.whl", hash = "sha256:5e5534257d1284b8e825bc3a182c6f06acd6eb405e9f89d49340e98cd8f136eb"},
+]
+
+[[package]]
+name = "nvidia-nvtx-cu11"
+version = "11.7.91"
+description = "NVIDIA Tools Extension"
+category = "main"
+optional = false
+python-versions = ">=3"
+files = [
+ {file = "nvidia_nvtx_cu11-11.7.91-py3-none-manylinux1_x86_64.whl", hash = "sha256:b22c64eee426a62fc00952b507d6d29cf62b4c9df7a480fcc417e540e05fd5ac"},
+ {file = "nvidia_nvtx_cu11-11.7.91-py3-none-win_amd64.whl", hash = "sha256:dfd7fcb2a91742513027d63a26b757f38dd8b07fecac282c4d132a9d373ff064"},
+]
+
+[package.dependencies]
+setuptools = "*"
+wheel = "*"
+
+[[package]]
+name = "oauthlib"
+version = "3.2.2"
+description = "A generic, spec-compliant, thorough implementation of the OAuth request-signing logic"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "oauthlib-3.2.2-py3-none-any.whl", hash = "sha256:8139f29aac13e25d502680e9e19963e83f16838d48a0d71c287fe40e7067fbca"},
+ {file = "oauthlib-3.2.2.tar.gz", hash = "sha256:9859c40929662bec5d64f34d01c99e093149682a3f38915dc0655d5a633dd918"},
+]
+
+[package.extras]
+rsa = ["cryptography (>=3.0.0)"]
+signals = ["blinker (>=1.4.0)"]
+signedtoken = ["cryptography (>=3.0.0)", "pyjwt (>=2.0.0,<3)"]
+
+[[package]]
+name = "omegaconf"
+version = "2.0.6"
+description = "A flexible configuration library"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "omegaconf-2.0.6-py3-none-any.whl", hash = "sha256:9e349fd76819b95b47aa628edea1ff83fed5b25108608abdd6c7fdca188e302a"},
+ {file = "omegaconf-2.0.6.tar.gz", hash = "sha256:92ca535a788d21651bf4c2eaf5c1ca4c7a8003b2dab4a87cbb09109784268806"},
+]
+
+[package.dependencies]
+PyYAML = ">=5.1"
+typing-extensions = "*"
+
+[[package]]
+name = "orjson"
+version = "3.8.9"
+description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "orjson-3.8.9-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:5d029843eae7b6cbd6468b63517b8b61471afed6572162171d8b6471b6dbf41f"},
+ {file = "orjson-3.8.9-cp310-cp310-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:405933c05490efb209d0f940d8ef1403d2932a97e47010a26d2694e9dd49f84d"},
+ {file = "orjson-3.8.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:183de66eff4d41c330a3006f210ab0bce7affe398da6f6eda9579b67245a34ff"},
+ {file = "orjson-3.8.9-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:bb4081fe340ed1df42dddfd055e1d50479cb0ccb976d13e6b5e8667a07fec6f4"},
+ {file = "orjson-3.8.9-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d11593a2e736055dd7b9587dbf89cd1cbe4a42a70e70f186e51aee7e1b38902e"},
+ {file = "orjson-3.8.9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e20649359e28f34d01b2570e4650a076f439a959bae3a8bbe7f5923ad80f54e8"},
+ {file = "orjson-3.8.9-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:c02ece4f36a160c83efe74adfba5f189c7c7702361f02b809ab73744923ee139"},
+ {file = "orjson-3.8.9-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f0e19801836cf1b30f333d475b05d79051b8ae8639a8e2422fb5f64e82676ae7"},
+ {file = "orjson-3.8.9-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d4850fe5650cead3c0f8822192e381cee9d4c3b8162eb082c86c927124572dc6"},
+ {file = "orjson-3.8.9-cp310-none-win_amd64.whl", hash = "sha256:5fd4193f260d9d30112b5e379d0870b54dc88040807c93cbe8d67bfea148ba5a"},
+ {file = "orjson-3.8.9-cp311-cp311-macosx_10_7_x86_64.whl", hash = "sha256:70eae063ad8d7405dc63873760567b600fc10728ba0da24a69d49c1a5d318d6d"},
+ {file = "orjson-3.8.9-cp311-cp311-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:251653437632583d02203e6b118b72b99c04425175853f35340f4bac7034a36e"},
+ {file = "orjson-3.8.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ea833751f017ba321c277e7425b51c0b1a18a2c60f8c9c0f4c6c4d7e16cbd6c"},
+ {file = "orjson-3.8.9-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8563c2cdeb923b82a5cc5bfc76c28c786777428263ee39292d928e9687165fb4"},
+ {file = "orjson-3.8.9-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6f33e9ea45b4c9457eedca0c40f38cf5732c91b0fb68f091ac59e6ea68e03eb2"},
+ {file = "orjson-3.8.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:855dee152daecb7de7b4cd7069d7854e11aa291687bffe8433156af0a224417e"},
+ {file = "orjson-3.8.9-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:74fa9e02589339defc9d3662de9e7eef51d8f9f3a7f6304b43b18b39d7bbf10f"},
+ {file = "orjson-3.8.9-cp311-none-win_amd64.whl", hash = "sha256:6c5b10ba1e62df8f96cbc37f6d5ae9acb3f6475926dea8b1b6a1a60f201a64f7"},
+ {file = "orjson-3.8.9-cp37-cp37m-macosx_10_7_x86_64.whl", hash = "sha256:a651123d01bc399fcd866e56acc2d76512e62aae3673652b13b470ea69faf1f4"},
+ {file = "orjson-3.8.9-cp37-cp37m-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:73019b6d2cc998c99556020c6bd8f8bc28420c69583186ca290c66a27916a3b7"},
+ {file = "orjson-3.8.9-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f5c3daa8b02786ad5f0e14ae16a59bbb4e02cbae3a41989a25188e5a6c962ff"},
+ {file = "orjson-3.8.9-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:598598b7f81f8fda7c3e09c88165f844152b7be223bc4ea929ec8ad59b00ea17"},
+ {file = "orjson-3.8.9-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:090b10bdb06baae6d5cd3550d772ecbabd833bfceed7592ff167c0a82f5b4c20"},
+ {file = "orjson-3.8.9-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bd46f688ddf9c2ea10367446fe9bf3ceba0f7490c15b4f96420491c7f00bb283"},
+ {file = "orjson-3.8.9-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:b8ed8d780e9fab01bc404a70d755a8b2b34ea6c0b6604b65de135daaaadaf9a9"},
+ {file = "orjson-3.8.9-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:8a32c9fb742868a34346f3c52e12d893a9d27f8e0c0bf3c480db7e6903d8be28"},
+ {file = "orjson-3.8.9-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:2ba366009b98ac8899e935eff6fef7672d3ea43d3ce9deb3ee33452134b6cc3a"},
+ {file = "orjson-3.8.9-cp37-none-win_amd64.whl", hash = "sha256:236b9313425cb2570626c64dd5cb6caff13882d1717d491da542cff228b96e97"},
+ {file = "orjson-3.8.9-cp38-cp38-macosx_10_7_x86_64.whl", hash = "sha256:e8efc7e9ec35336f7cc98b6692536b1262046ff1d2a545295a4d89b8a2495903"},
+ {file = "orjson-3.8.9-cp38-cp38-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:8c7eba3610ae69f4aba4032ecb61b0a6fbd1e4537283d1553eb8c1cb136e9118"},
+ {file = "orjson-3.8.9-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7742649e4c357d4e7ad483a35ff5f55d519e895de56772cc486913614ee7d23b"},
+ {file = "orjson-3.8.9-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b6566fb8daa538c7848fd6822e2409a7e1c41dae8e65e6536598d505f641a318"},
+ {file = "orjson-3.8.9-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0ce8a2a667221e2e5160021e26b09e9c13eeedafb5cda1981340c8c0c0bc8f9d"},
+ {file = "orjson-3.8.9-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c0399631b88fa4868956badef2561fba07dffcaf050bf53959ee50d26edf6f6"},
+ {file = "orjson-3.8.9-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:189ccb16ed140a824d133fa1c55175cf0d2207edaade54f1db0456a526cb5fd8"},
+ {file = "orjson-3.8.9-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:b707fa4481e1af19b3052ec9352c688bad3f539d7bdd8aa4a451f6dd7e4bae73"},
+ {file = "orjson-3.8.9-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c3d988eb562da1dda7d49e9abd8a64b3cabc632b4299d177fb9e0c0ca9f06b8c"},
+ {file = "orjson-3.8.9-cp38-none-win_amd64.whl", hash = "sha256:b30240eb6b22daab604f1595f6aacf92bcdac0d29e2d7ad507dfac68d2b39182"},
+ {file = "orjson-3.8.9-cp39-cp39-macosx_10_7_x86_64.whl", hash = "sha256:81869a6de00bc676d10056fa8bb28cbe805b1cf498a45c14cb7b1765eee33fcb"},
+ {file = "orjson-3.8.9-cp39-cp39-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:a25a5a215b19d414de8d416a3c5414f29165843a06f704cc0345ded9eac34ac1"},
+ {file = "orjson-3.8.9-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dec0f2bea52e30ea98ce095f1f42da04535791f9a31b2aab2499caa88307bc49"},
+ {file = "orjson-3.8.9-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7b91d88fe96b698b28bb1b95b1fce226f72757ab3ab7d8d97551e23bc629c84f"},
+ {file = "orjson-3.8.9-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7629841ccdcccd3c43ebc6a4165abe9844909fcedb2041994c0153470f610801"},
+ {file = "orjson-3.8.9-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d875b304e19f4b2758d233bbf2b9d627c66fac50b3150b8d31a35ba6cda3db67"},
+ {file = "orjson-3.8.9-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:723ec880c5290fe4de330febb8030e57c1978fbd624fc5b9399969e7d7d74984"},
+ {file = "orjson-3.8.9-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b11f8a71c82d19fce11ce487efeec2ca0dc3bcf5b4564445fecfc68d9c268744"},
+ {file = "orjson-3.8.9-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b2079bf86dec62731c1b90fdfea3211f993f0c894d9261e0ce9b68ed9c9dfbec"},
+ {file = "orjson-3.8.9-cp39-none-win_amd64.whl", hash = "sha256:97d94322a2eaab767ba8d52f6bf9d0ec0f35313fe36287be6e6085dd65d55d37"},
+ {file = "orjson-3.8.9.tar.gz", hash = "sha256:c40bece58c11cb09aff17424d21b41f6f767d2b1252b2f745ec3ff29cce6a240"},
+]
+
+[[package]]
+name = "packaging"
+version = "23.0"
+description = "Core utilities for Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "packaging-23.0-py3-none-any.whl", hash = "sha256:714ac14496c3e68c99c29b00845f7a2b85f3bb6f1078fd9f72fd20f0570002b2"},
+ {file = "packaging-23.0.tar.gz", hash = "sha256:b6ad297f8907de0fa2fe1ccbd26fdaf387f5f47c7275fedf8cce89f99446cf97"},
+]
+
+[[package]]
+name = "pandas"
+version = "2.0.0"
+description = "Powerful data structures for data analysis, time series, and statistics"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "pandas-2.0.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bbb2c5e94d6aa4e632646a3bacd05c2a871c3aa3e85c9bec9be99cb1267279f2"},
+ {file = "pandas-2.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b5337c87c4e963f97becb1217965b6b75c6fe5f54c4cf09b9a5ac52fc0bd03d3"},
+ {file = "pandas-2.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ded51f7e3dd9b4f8b87f2ceb7bd1a8df2491f7ee72f7074c6927a512607199e"},
+ {file = "pandas-2.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52c858de9e9fc422d25e67e1592a6e6135d7bcf9a19fcaf4d0831a0be496bf21"},
+ {file = "pandas-2.0.0-cp310-cp310-win32.whl", hash = "sha256:2d1d138848dd71b37e3cbe7cd952ff84e2ab04d8988972166e18567dcc811245"},
+ {file = "pandas-2.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:d08e41d96bc4de6f500afe80936c68fce6099d5a434e2af7c7fd8e7c72a3265d"},
+ {file = "pandas-2.0.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:24472cfc7ced511ac90608728b88312be56edc8f19b9ed885a7d2e47ffaf69c0"},
+ {file = "pandas-2.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4ffb14f50c74ee541610668137830bb93e9dfa319b1bef2cedf2814cd5ac9c70"},
+ {file = "pandas-2.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c24c7d12d033a372a9daf9ff2c80f8b0af6f98d14664dbb0a4f6a029094928a7"},
+ {file = "pandas-2.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8318de0f886e4dcb8f9f36e45a3d6a6c3d1cfdc508354da85e739090f0222991"},
+ {file = "pandas-2.0.0-cp311-cp311-win32.whl", hash = "sha256:57c34b79c13249505e850d0377b722961b99140f81dafbe6f19ef10239f6284a"},
+ {file = "pandas-2.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:8f987ec26e96a8490909bc5d98c514147236e49830cba7df8690f6087c12bbae"},
+ {file = "pandas-2.0.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b3ba8f5dd470d8bfbc4259829589f4a32881151c49e36384d9eb982b35a12020"},
+ {file = "pandas-2.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:fcd471c9d9f60926ab2f15c6c29164112f458acb42280365fbefa542d0c2fc74"},
+ {file = "pandas-2.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9253edfd015520ce77a9343eb7097429479c039cd3ebe81d7810ea11b4b24695"},
+ {file = "pandas-2.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:977326039bd1ded620001a1889e2ed4798460a6bc5a24fbaebb5f07a41c32a55"},
+ {file = "pandas-2.0.0-cp38-cp38-win32.whl", hash = "sha256:78425ca12314b23356c28b16765639db10ebb7d8983f705d6759ff7fe41357fa"},
+ {file = "pandas-2.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:d93b7fcfd9f3328072b250d6d001dcfeec5d3bb66c1b9c8941e109a46c0c01a8"},
+ {file = "pandas-2.0.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:425705cee8be54db2504e8dd2a730684790b15e5904b750c367611ede49098ab"},
+ {file = "pandas-2.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a4f789b7c012a608c08cda4ff0872fd979cb18907a37982abe884e6f529b8793"},
+ {file = "pandas-2.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3bb9d840bf15656805f6a3d87eea9dcb7efdf1314a82adcf7f00b820427c5570"},
+ {file = "pandas-2.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0778ab54c8f399d83d98ffb674d11ec716449956bc6f6821891ab835848687f2"},
+ {file = "pandas-2.0.0-cp39-cp39-win32.whl", hash = "sha256:70db5c278bbec0306d32bf78751ff56b9594c05a5098386f6c8a563659124f91"},
+ {file = "pandas-2.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:4f3320bb55f34af4193020158ef8118ee0fb9aec7cc47d2084dbfdd868a0a24f"},
+ {file = "pandas-2.0.0.tar.gz", hash = "sha256:cda9789e61b44463c1c4fe17ef755de77bcd13b09ba31c940d20f193d63a5dc8"},
+]
+
+[package.dependencies]
+numpy = [
+ {version = ">=1.20.3", markers = "python_version < \"3.10\""},
+ {version = ">=1.21.0", markers = "python_version >= \"3.10\""},
+]
+python-dateutil = ">=2.8.2"
+pytz = ">=2020.1"
+tzdata = ">=2022.1"
+
+[package.extras]
+all = ["PyQt5 (>=5.15.1)", "SQLAlchemy (>=1.4.16)", "beautifulsoup4 (>=4.9.3)", "bottleneck (>=1.3.2)", "brotlipy (>=0.7.0)", "fastparquet (>=0.6.3)", "fsspec (>=2021.07.0)", "gcsfs (>=2021.07.0)", "html5lib (>=1.1)", "hypothesis (>=6.34.2)", "jinja2 (>=3.0.0)", "lxml (>=4.6.3)", "matplotlib (>=3.6.1)", "numba (>=0.53.1)", "numexpr (>=2.7.3)", "odfpy (>=1.4.1)", "openpyxl (>=3.0.7)", "pandas-gbq (>=0.15.0)", "psycopg2 (>=2.8.6)", "pyarrow (>=7.0.0)", "pymysql (>=1.0.2)", "pyreadstat (>=1.1.2)", "pytest (>=7.0.0)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)", "python-snappy (>=0.6.0)", "pyxlsb (>=1.0.8)", "qtpy (>=2.2.0)", "s3fs (>=2021.08.0)", "scipy (>=1.7.1)", "tables (>=3.6.1)", "tabulate (>=0.8.9)", "xarray (>=0.21.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=1.4.3)", "zstandard (>=0.15.2)"]
+aws = ["s3fs (>=2021.08.0)"]
+clipboard = ["PyQt5 (>=5.15.1)", "qtpy (>=2.2.0)"]
+compression = ["brotlipy (>=0.7.0)", "python-snappy (>=0.6.0)", "zstandard (>=0.15.2)"]
+computation = ["scipy (>=1.7.1)", "xarray (>=0.21.0)"]
+excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.0.7)", "pyxlsb (>=1.0.8)", "xlrd (>=2.0.1)", "xlsxwriter (>=1.4.3)"]
+feather = ["pyarrow (>=7.0.0)"]
+fss = ["fsspec (>=2021.07.0)"]
+gcp = ["gcsfs (>=2021.07.0)", "pandas-gbq (>=0.15.0)"]
+hdf5 = ["tables (>=3.6.1)"]
+html = ["beautifulsoup4 (>=4.9.3)", "html5lib (>=1.1)", "lxml (>=4.6.3)"]
+mysql = ["SQLAlchemy (>=1.4.16)", "pymysql (>=1.0.2)"]
+output-formatting = ["jinja2 (>=3.0.0)", "tabulate (>=0.8.9)"]
+parquet = ["pyarrow (>=7.0.0)"]
+performance = ["bottleneck (>=1.3.2)", "numba (>=0.53.1)", "numexpr (>=2.7.1)"]
+plot = ["matplotlib (>=3.6.1)"]
+postgresql = ["SQLAlchemy (>=1.4.16)", "psycopg2 (>=2.8.6)"]
+spss = ["pyreadstat (>=1.1.2)"]
+sql-other = ["SQLAlchemy (>=1.4.16)"]
+test = ["hypothesis (>=6.34.2)", "pytest (>=7.0.0)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"]
+xml = ["lxml (>=4.6.3)"]
+
+[[package]]
+name = "pillow"
+version = "9.3.0"
+description = "Python Imaging Library (Fork)"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "Pillow-9.3.0-1-cp37-cp37m-win32.whl", hash = "sha256:e6ea6b856a74d560d9326c0f5895ef8050126acfdc7ca08ad703eb0081e82b74"},
+ {file = "Pillow-9.3.0-1-cp37-cp37m-win_amd64.whl", hash = "sha256:32a44128c4bdca7f31de5be641187367fe2a450ad83b833ef78910397db491aa"},
+ {file = "Pillow-9.3.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:0b7257127d646ff8676ec8a15520013a698d1fdc48bc2a79ba4e53df792526f2"},
+ {file = "Pillow-9.3.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b90f7616ea170e92820775ed47e136208e04c967271c9ef615b6fbd08d9af0e3"},
+ {file = "Pillow-9.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68943d632f1f9e3dce98908e873b3a090f6cba1cbb1b892a9e8d97c938871fbe"},
+ {file = "Pillow-9.3.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:be55f8457cd1eac957af0c3f5ece7bc3f033f89b114ef30f710882717670b2a8"},
+ {file = "Pillow-9.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d77adcd56a42d00cc1be30843d3426aa4e660cab4a61021dc84467123f7a00c"},
+ {file = "Pillow-9.3.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:829f97c8e258593b9daa80638aee3789b7df9da5cf1336035016d76f03b8860c"},
+ {file = "Pillow-9.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:801ec82e4188e935c7f5e22e006d01611d6b41661bba9fe45b60e7ac1a8f84de"},
+ {file = "Pillow-9.3.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:871b72c3643e516db4ecf20efe735deb27fe30ca17800e661d769faab45a18d7"},
+ {file = "Pillow-9.3.0-cp310-cp310-win32.whl", hash = "sha256:655a83b0058ba47c7c52e4e2df5ecf484c1b0b0349805896dd350cbc416bdd91"},
+ {file = "Pillow-9.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:9f47eabcd2ded7698106b05c2c338672d16a6f2a485e74481f524e2a23c2794b"},
+ {file = "Pillow-9.3.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:57751894f6618fd4308ed8e0c36c333e2f5469744c34729a27532b3db106ee20"},
+ {file = "Pillow-9.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7db8b751ad307d7cf238f02101e8e36a128a6cb199326e867d1398067381bff4"},
+ {file = "Pillow-9.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3033fbe1feb1b59394615a1cafaee85e49d01b51d54de0cbf6aa8e64182518a1"},
+ {file = "Pillow-9.3.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22b012ea2d065fd163ca096f4e37e47cd8b59cf4b0fd47bfca6abb93df70b34c"},
+ {file = "Pillow-9.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b9a65733d103311331875c1dca05cb4606997fd33d6acfed695b1232ba1df193"},
+ {file = "Pillow-9.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:502526a2cbfa431d9fc2a079bdd9061a2397b842bb6bc4239bb176da00993812"},
+ {file = "Pillow-9.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:90fb88843d3902fe7c9586d439d1e8c05258f41da473952aa8b328d8b907498c"},
+ {file = "Pillow-9.3.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:89dca0ce00a2b49024df6325925555d406b14aa3efc2f752dbb5940c52c56b11"},
+ {file = "Pillow-9.3.0-cp311-cp311-win32.whl", hash = "sha256:3168434d303babf495d4ba58fc22d6604f6e2afb97adc6a423e917dab828939c"},
+ {file = "Pillow-9.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:18498994b29e1cf86d505edcb7edbe814d133d2232d256db8c7a8ceb34d18cef"},
+ {file = "Pillow-9.3.0-cp37-cp37m-macosx_10_10_x86_64.whl", hash = "sha256:772a91fc0e03eaf922c63badeca75e91baa80fe2f5f87bdaed4280662aad25c9"},
+ {file = "Pillow-9.3.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afa4107d1b306cdf8953edde0534562607fe8811b6c4d9a486298ad31de733b2"},
+ {file = "Pillow-9.3.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b4012d06c846dc2b80651b120e2cdd787b013deb39c09f407727ba90015c684f"},
+ {file = "Pillow-9.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:77ec3e7be99629898c9a6d24a09de089fa5356ee408cdffffe62d67bb75fdd72"},
+ {file = "Pillow-9.3.0-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:6c738585d7a9961d8c2821a1eb3dcb978d14e238be3d70f0a706f7fa9316946b"},
+ {file = "Pillow-9.3.0-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:828989c45c245518065a110434246c44a56a8b2b2f6347d1409c787e6e4651ee"},
+ {file = "Pillow-9.3.0-cp37-cp37m-win32.whl", hash = "sha256:82409ffe29d70fd733ff3c1025a602abb3e67405d41b9403b00b01debc4c9a29"},
+ {file = "Pillow-9.3.0-cp37-cp37m-win_amd64.whl", hash = "sha256:41e0051336807468be450d52b8edd12ac60bebaa97fe10c8b660f116e50b30e4"},
+ {file = "Pillow-9.3.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:b03ae6f1a1878233ac620c98f3459f79fd77c7e3c2b20d460284e1fb370557d4"},
+ {file = "Pillow-9.3.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4390e9ce199fc1951fcfa65795f239a8a4944117b5935a9317fb320e7767b40f"},
+ {file = "Pillow-9.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40e1ce476a7804b0fb74bcfa80b0a2206ea6a882938eaba917f7a0f004b42502"},
+ {file = "Pillow-9.3.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a0a06a052c5f37b4ed81c613a455a81f9a3a69429b4fd7bb913c3fa98abefc20"},
+ {file = "Pillow-9.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:03150abd92771742d4a8cd6f2fa6246d847dcd2e332a18d0c15cc75bf6703040"},
+ {file = "Pillow-9.3.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:15c42fb9dea42465dfd902fb0ecf584b8848ceb28b41ee2b58f866411be33f07"},
+ {file = "Pillow-9.3.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:51e0e543a33ed92db9f5ef69a0356e0b1a7a6b6a71b80df99f1d181ae5875636"},
+ {file = "Pillow-9.3.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:3dd6caf940756101205dffc5367babf288a30043d35f80936f9bfb37f8355b32"},
+ {file = "Pillow-9.3.0-cp38-cp38-win32.whl", hash = "sha256:f1ff2ee69f10f13a9596480335f406dd1f70c3650349e2be67ca3139280cade0"},
+ {file = "Pillow-9.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:276a5ca930c913f714e372b2591a22c4bd3b81a418c0f6635ba832daec1cbcfc"},
+ {file = "Pillow-9.3.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:73bd195e43f3fadecfc50c682f5055ec32ee2c933243cafbfdec69ab1aa87cad"},
+ {file = "Pillow-9.3.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1c7c8ae3864846fc95f4611c78129301e203aaa2af813b703c55d10cc1628535"},
+ {file = "Pillow-9.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e0918e03aa0c72ea56edbb00d4d664294815aa11291a11504a377ea018330d3"},
+ {file = "Pillow-9.3.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b0915e734b33a474d76c28e07292f196cdf2a590a0d25bcc06e64e545f2d146c"},
+ {file = "Pillow-9.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:af0372acb5d3598f36ec0914deed2a63f6bcdb7b606da04dc19a88d31bf0c05b"},
+ {file = "Pillow-9.3.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:ad58d27a5b0262c0c19b47d54c5802db9b34d38bbf886665b626aff83c74bacd"},
+ {file = "Pillow-9.3.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:97aabc5c50312afa5e0a2b07c17d4ac5e865b250986f8afe2b02d772567a380c"},
+ {file = "Pillow-9.3.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9aaa107275d8527e9d6e7670b64aabaaa36e5b6bd71a1015ddd21da0d4e06448"},
+ {file = "Pillow-9.3.0-cp39-cp39-win32.whl", hash = "sha256:bac18ab8d2d1e6b4ce25e3424f709aceef668347db8637c2296bcf41acb7cf48"},
+ {file = "Pillow-9.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:b472b5ea442148d1c3e2209f20f1e0bb0eb556538690fa70b5e1f79fa0ba8dc2"},
+ {file = "Pillow-9.3.0-pp37-pypy37_pp73-macosx_10_10_x86_64.whl", hash = "sha256:ab388aaa3f6ce52ac1cb8e122c4bd46657c15905904b3120a6248b5b8b0bc228"},
+ {file = "Pillow-9.3.0-pp37-pypy37_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dbb8e7f2abee51cef77673be97760abff1674ed32847ce04b4af90f610144c7b"},
+ {file = "Pillow-9.3.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bca31dd6014cb8b0b2db1e46081b0ca7d936f856da3b39744aef499db5d84d02"},
+ {file = "Pillow-9.3.0-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c7025dce65566eb6e89f56c9509d4f628fddcedb131d9465cacd3d8bac337e7e"},
+ {file = "Pillow-9.3.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:ebf2029c1f464c59b8bdbe5143c79fa2045a581ac53679733d3a91d400ff9efb"},
+ {file = "Pillow-9.3.0-pp38-pypy38_pp73-macosx_10_10_x86_64.whl", hash = "sha256:b59430236b8e58840a0dfb4099a0e8717ffb779c952426a69ae435ca1f57210c"},
+ {file = "Pillow-9.3.0-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:12ce4932caf2ddf3e41d17fc9c02d67126935a44b86df6a206cf0d7161548627"},
+ {file = "Pillow-9.3.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ae5331c23ce118c53b172fa64a4c037eb83c9165aba3a7ba9ddd3ec9fa64a699"},
+ {file = "Pillow-9.3.0-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:0b07fffc13f474264c336298d1b4ce01d9c5a011415b79d4ee5527bb69ae6f65"},
+ {file = "Pillow-9.3.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:073adb2ae23431d3b9bcbcff3fe698b62ed47211d0716b067385538a1b0f28b8"},
+ {file = "Pillow-9.3.0.tar.gz", hash = "sha256:c935a22a557a560108d780f9a0fc426dd7459940dc54faa49d83249c8d3e760f"},
+]
+
+[package.extras]
+docs = ["furo", "olefile", "sphinx (>=2.4)", "sphinx-copybutton", "sphinx-issues (>=3.0.1)", "sphinx-removed-in", "sphinxext-opengraph"]
+tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
+
+[[package]]
+name = "pkgutil-resolve-name"
+version = "1.3.10"
+description = "Resolve a name to an object."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "pkgutil_resolve_name-1.3.10-py3-none-any.whl", hash = "sha256:ca27cc078d25c5ad71a9de0a7a330146c4e014c2462d9af19c6b828280649c5e"},
+ {file = "pkgutil_resolve_name-1.3.10.tar.gz", hash = "sha256:357d6c9e6a755653cfd78893817c0853af365dd51ec97f3d358a819373bbd174"},
+]
+
+[[package]]
+name = "platformdirs"
+version = "3.2.0"
+description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "platformdirs-3.2.0-py3-none-any.whl", hash = "sha256:ebe11c0d7a805086e99506aa331612429a72ca7cd52a1f0d277dc4adc20cb10e"},
+ {file = "platformdirs-3.2.0.tar.gz", hash = "sha256:d5b638ca397f25f979350ff789db335903d7ea010ab28903f57b27e1b16c2b08"},
+]
+
+[package.extras]
+docs = ["furo (>=2022.12.7)", "proselint (>=0.13)", "sphinx (>=6.1.3)", "sphinx-autodoc-typehints (>=1.22,!=1.23.4)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.2.2)", "pytest-cov (>=4)", "pytest-mock (>=3.10)"]
+
+[[package]]
+name = "pooch"
+version = "1.7.0"
+description = "\"Pooch manages your Python library's sample data files: it automatically downloads and stores them in a local directory, with support for versioning and corruption checks.\""
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "pooch-1.7.0-py3-none-any.whl", hash = "sha256:74258224fc33d58f53113cf955e8d51bf01386b91492927d0d1b6b341a765ad7"},
+ {file = "pooch-1.7.0.tar.gz", hash = "sha256:f174a1041b6447f0eef8860f76d17f60ed2f857dc0efa387a7f08228af05d998"},
+]
+
+[package.dependencies]
+packaging = ">=20.0"
+platformdirs = ">=2.5.0"
+requests = ">=2.19.0"
+
+[package.extras]
+progress = ["tqdm (>=4.41.0,<5.0.0)"]
+sftp = ["paramiko (>=2.7.0)"]
+xxhash = ["xxhash (>=1.4.3)"]
+
+[[package]]
+name = "portalocker"
+version = "2.7.0"
+description = "Wraps the portalocker recipe for easy usage"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+files = [
+ {file = "portalocker-2.7.0-py2.py3-none-any.whl", hash = "sha256:a07c5b4f3985c3cf4798369631fb7011adb498e2a46d8440efc75a8f29a0f983"},
+ {file = "portalocker-2.7.0.tar.gz", hash = "sha256:032e81d534a88ec1736d03f780ba073f047a06c478b06e2937486f334e955c51"},
+]
+
+[package.dependencies]
+pywin32 = {version = ">=226", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+docs = ["sphinx (>=1.7.1)"]
+redis = ["redis"]
+tests = ["pytest (>=5.4.1)", "pytest-cov (>=2.8.1)", "pytest-mypy (>=0.8.0)", "pytest-timeout (>=2.1.0)", "redis", "sphinx (>=6.0.0)"]
+
+[[package]]
+name = "praat-parselmouth"
+version = "0.4.3"
+description = "Praat in Python, the Pythonic way"
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
+files = [
+ {file = "praat-parselmouth-0.4.3.tar.gz", hash = "sha256:93538d0ba06444b68d18b793efb436b0d645c62c0397c4977c1d27b679aee168"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:124925f3e40a6d626d65789d449bdabe43078528efbee6f3a1df6e67db60c971"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:0d3023d9b625c6b0a3cbe8a4f09cc23f666f9b9df40c59e33c4c9ca5b8ea1dac"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:6841b9d9d2a614382cf186311610d663f0170ba20824296878eb98905b04899a"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27m-win32.whl", hash = "sha256:4fee56603cb57326457c6af779b89f96e7b2745114baa996659e1d52e5f245a3"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27m-win_amd64.whl", hash = "sha256:dc688749a0db4144936d3ed5180996500eb927bbf321192019ddee535fb97f3d"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:c0ccf73de16c0f69162952b0d1865d4dbc929de0f9b88a9d7aea57f454de3cb8"},
+ {file = "praat_parselmouth-0.4.3-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:87fa2dd7f8b5dd5e3127af82e97b229ae2db8e1656525329224df4c0bffa024c"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:2bc111055efccf2bb25039a7891ec9ef106b13ddc5680293659ff0b4c5f4353f"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cd38542210b1f381086b4a9424832b2330c42712e0fb7ea6c28c9200119c294b"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a536b37411c52171500984c97bfd66dc000701a7dc0807e11061b85a653a600a"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6ea1ab0632eff129516f147041aaf7874e50770561a2e9b9c81913b6de243f2a"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:543ba3deb32502e93074b76b1cfb3f09e598e5d9f74a0345fa5b3928fedb5a51"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-win32.whl", hash = "sha256:e0addf774a57d57a54df2b06de04ad0de34e81a3abfda03f744c732776c779ec"},
+ {file = "praat_parselmouth-0.4.3-cp310-cp310-win_amd64.whl", hash = "sha256:fc497357aeea2e3cbca2fb308d66b9de9739dc6b320ca2661ca6250f7a7489bd"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:afac52cb7a72cda7fe2ec1d9573d8f402786abcb06bd7a22f2ca240f95e33263"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b2261a79c2dc5387a7a678ec304ef8dd00ed93d9e028148bbb064fd0ac222a3a"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:de31b458d3c1ca7ee45506871a38fdc3aec44526c065552adf8bec2876e816bd"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:63ff24e045bed7c44f140fb7bab910d89fd3a45b7e8afe5b5e936aa2eea62904"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a40c51c628235c54c8956306fc58fd14cd04127d85359134ef73ef35ff19d651"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-win32.whl", hash = "sha256:f8ad9ee3be60d33f1ad593ec5f99466b1c266e00d29a5ec5787f969c618a7a9a"},
+ {file = "praat_parselmouth-0.4.3-cp311-cp311-win_amd64.whl", hash = "sha256:c32b1f3632e69ed67f501c635fff37ad72e1eae4ddd1c2c0827c4690c06ee990"},
+ {file = "praat_parselmouth-0.4.3-cp35-cp35m-macosx_10_9_x86_64.whl", hash = "sha256:1dcb6f55376f193c83d123953a55de471bcadd756af3b157c13d455b0c052999"},
+ {file = "praat_parselmouth-0.4.3-cp35-cp35m-manylinux2010_i686.whl", hash = "sha256:0970facd26b771f5799a396a0e54d12a69fbf8904a4f6ae0442f3831175e4508"},
+ {file = "praat_parselmouth-0.4.3-cp35-cp35m-manylinux2010_x86_64.whl", hash = "sha256:5c1104f41d9fef48cd44247738b9c8735e10a12ba0a1860e478e0bd69201813e"},
+ {file = "praat_parselmouth-0.4.3-cp35-cp35m-win32.whl", hash = "sha256:3d12469e301d9a25f29f6cb5427aa9a1276e7f2f1edf1a3caede69a84c46170f"},
+ {file = "praat_parselmouth-0.4.3-cp35-cp35m-win_amd64.whl", hash = "sha256:c4142faf664dd6c7f1773d04331b278d92e17064eaaef09132954f72a9041ea0"},
+ {file = "praat_parselmouth-0.4.3-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:5ea2079d519e8d42ed8d2de3c4f68803110060a8ae5d1c56df795c600aa1c3be"},
+ {file = "praat_parselmouth-0.4.3-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:2e88f00b740548cf3de5768b2d06e296e525164ea71ccc991920f41f2e277ad2"},
+ {file = "praat_parselmouth-0.4.3-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:2da226bccd52fd81223eb94a7ea43a1a7588e4384ea65ce0818329b73ef8df6d"},
+ {file = "praat_parselmouth-0.4.3-cp36-cp36m-win32.whl", hash = "sha256:0f3af0413992398ac613b0eefdfbcb8cad064c36a28b972300a2bb760523c109"},
+ {file = "praat_parselmouth-0.4.3-cp36-cp36m-win_amd64.whl", hash = "sha256:e0ed79941b6e37a440860511767eedd85ec003060870d10ff1f98773b2a268ae"},
+ {file = "praat_parselmouth-0.4.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:10f3113ad4f5f6df5fe81d4080ca3ad46de2fe0fdb8ebbcad1ba884b1cae3b9d"},
+ {file = "praat_parselmouth-0.4.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6e9338f7a1b304390014bb2eec619e5a306527a4df438e68439c92aa968627dc"},
+ {file = "praat_parselmouth-0.4.3-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cb3798b2ca8163444662b6ae84a74b1add38b2c04e5af8d07bde55cf0335300a"},
+ {file = "praat_parselmouth-0.4.3-cp37-cp37m-win32.whl", hash = "sha256:d947f9d1fb092b91acca1259ce4dd62ff4f456338958fd1fd41ee65efc53ca2c"},
+ {file = "praat_parselmouth-0.4.3-cp37-cp37m-win_amd64.whl", hash = "sha256:2f3e026f590aeec8f68921359f56a42efa43076942f271244bee57fd22db8eef"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:28844229dab2a9335629b4526188b9540d02208856f48b1a46776279c022f937"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:410748af84eb8c2eb69e408e300694a45090ed7c4f31375c4ec75a8c18f87169"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:30ff6f17babad25b9d6ab086465a54494eef9d1b4368b0722230c5282be2bf94"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ff7096bc3e87a8f719e66f5e16a90e2f6de445612abd234f86837d390b947421"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f41d121c4d2322ff12808bb2c4490609f750f89064170e327dfd74fca13cc212"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-win32.whl", hash = "sha256:9af9945db11fab0e1ed29ad20f7c97a3e7a8d016328ad6d7237a0d7819db075e"},
+ {file = "praat_parselmouth-0.4.3-cp38-cp38-win_amd64.whl", hash = "sha256:ae0c63c432e8216d7c70da44131f51c845fb81d48ac04eb5f39ebcfae34624be"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8e25658af5a87ed502753de6924c51bf3400d4078e67a611b5874ab08b478fdb"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7aa2ffd0c6e47feda35343a9d6722b2558f3677a4a51bf5ec864f27ab80e2f42"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3b245d9457ab39f12142da160cda12c4c2a58d9b916e5bb33e6b3ac267882d46"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:da9779a694941074bc5b199dd3cb41ad4af3306552f06af8dbfdea6ab0a87dec"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cfa141c04fd8a0477f91c168878112098a25cbac7ac4a20de627bc9293ee4667"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-win32.whl", hash = "sha256:6941fe602802fd57ecbedecd612b41493b7d1c6bf722ac0cbf3f47f805fbbd43"},
+ {file = "praat_parselmouth-0.4.3-cp39-cp39-win_amd64.whl", hash = "sha256:5252496e0391754a642973837670c56ecd39c8e0a1f7ec6e6b60b0cd2cc9f51d"},
+ {file = "praat_parselmouth-0.4.3-pp27-pypy_73-macosx_10_9_x86_64.whl", hash = "sha256:fd7c143c6511807b67c92b3ab94733746c0ae3a7b4ba52d6763585c4d459061d"},
+ {file = "praat_parselmouth-0.4.3-pp27-pypy_73-manylinux2010_x86_64.whl", hash = "sha256:7ad0739ad6c102817c7d43b67b7270f78cb431eb72b6ecd9a17e354d1b379deb"},
+ {file = "praat_parselmouth-0.4.3-pp27-pypy_73-win32.whl", hash = "sha256:f5e98ec1f41efba90bedab358cff8e6a3c6473978e1f42b55d0977e580efe673"},
+ {file = "praat_parselmouth-0.4.3-pp36-pypy36_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7b58c1c8fd967446f6d74775b5d9bceadfe35a928fa5f192d4d03d80cb005d92"},
+ {file = "praat_parselmouth-0.4.3-pp36-pypy36_pp73-manylinux2010_x86_64.whl", hash = "sha256:d217df07c770156fa284aff3e7a5c11eb43e37f0226730d729d6b45be8a7c4d7"},
+ {file = "praat_parselmouth-0.4.3-pp36-pypy36_pp73-win32.whl", hash = "sha256:29cb47438989f8155c3b3dca987afd48999dec71e4b79564aa7e922c3c5c1f9a"},
+ {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5f772b4a097654883f4bba41efae419f9ebdd5e83ef7a857e547100d26663e2c"},
+ {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:bf9634a6986732dc43a88b3a16a0000cff903da1db6556b7959a6a4897f25570"},
+ {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:fab1bbb6a88f47cb5d0db07a4fd6d88b9294d2775a7556aeb459e96ac372e29f"},
+ {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-win32.whl", hash = "sha256:261f03f95f25943da2cf746599e47acfcf79b7fc823c871571901d6c97bad948"},
+ {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:199b8df2659a1e6f30e9ae3064b0a28a661d834d2bccb56d22051c40cc348817"},
+ {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ef1f3f6bd08cc410d0d595f6a9c7dd72558e30ad3bd7949c94ea4e07a2de2605"},
+ {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:28a61b7a3cf95a53554dd3ebb4f48e991d4b913ae2d2fbc3868a4e864d69794f"},
+ {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:488833ee33690fa1a57a3c429d286e42e6882748f5c3d28dc50889abec12b8c2"},
+ {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:10f181e199c47fa90fe7cad065275f7f3ccda2de6febf86394cf96aa48531079"},
+ {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:52702bc5cdf59b2b4db87448fe9042307e5ebce6b67ee5ea55c2b8627ce803e0"},
+ {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a7d4f5d7c701517986654365f0a41b8b4a610a2ddc0365da60e48c098774259b"},
+ {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4dc013608a536ad74efdc3242421cabfcb8cb2e9cd1259ec9de9aeaa141c2d14"},
+ {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:d593065ed1500d305d9cf3d20f5ac7e3671061c3c073ef6e94e97817a664d399"},
+]
+
+[package.dependencies]
+numpy = ">=1.7.0"
+
+[[package]]
+name = "protobuf"
+version = "3.20.3"
+description = "Protocol Buffers"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "protobuf-3.20.3-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:f4bd856d702e5b0d96a00ec6b307b0f51c1982c2bf9c0052cf9019e9a544ba99"},
+ {file = "protobuf-3.20.3-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:9aae4406ea63d825636cc11ffb34ad3379335803216ee3a856787bcf5ccc751e"},
+ {file = "protobuf-3.20.3-cp310-cp310-win32.whl", hash = "sha256:28545383d61f55b57cf4df63eebd9827754fd2dc25f80c5253f9184235db242c"},
+ {file = "protobuf-3.20.3-cp310-cp310-win_amd64.whl", hash = "sha256:67a3598f0a2dcbc58d02dd1928544e7d88f764b47d4a286202913f0b2801c2e7"},
+ {file = "protobuf-3.20.3-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:899dc660cd599d7352d6f10d83c95df430a38b410c1b66b407a6b29265d66469"},
+ {file = "protobuf-3.20.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e64857f395505ebf3d2569935506ae0dfc4a15cb80dc25261176c784662cdcc4"},
+ {file = "protobuf-3.20.3-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:d9e4432ff660d67d775c66ac42a67cf2453c27cb4d738fc22cb53b5d84c135d4"},
+ {file = "protobuf-3.20.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:74480f79a023f90dc6e18febbf7b8bac7508420f2006fabd512013c0c238f454"},
+ {file = "protobuf-3.20.3-cp37-cp37m-win32.whl", hash = "sha256:b6cc7ba72a8850621bfec987cb72623e703b7fe2b9127a161ce61e61558ad905"},
+ {file = "protobuf-3.20.3-cp37-cp37m-win_amd64.whl", hash = "sha256:8c0c984a1b8fef4086329ff8dd19ac77576b384079247c770f29cc8ce3afa06c"},
+ {file = "protobuf-3.20.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:de78575669dddf6099a8a0f46a27e82a1783c557ccc38ee620ed8cc96d3be7d7"},
+ {file = "protobuf-3.20.3-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:f4c42102bc82a51108e449cbb32b19b180022941c727bac0cfd50170341f16ee"},
+ {file = "protobuf-3.20.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:44246bab5dd4b7fbd3c0c80b6f16686808fab0e4aca819ade6e8d294a29c7050"},
+ {file = "protobuf-3.20.3-cp38-cp38-win32.whl", hash = "sha256:c02ce36ec760252242a33967d51c289fd0e1c0e6e5cc9397e2279177716add86"},
+ {file = "protobuf-3.20.3-cp38-cp38-win_amd64.whl", hash = "sha256:447d43819997825d4e71bf5769d869b968ce96848b6479397e29fc24c4a5dfe9"},
+ {file = "protobuf-3.20.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:398a9e0c3eaceb34ec1aee71894ca3299605fa8e761544934378bbc6c97de23b"},
+ {file = "protobuf-3.20.3-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:bf01b5720be110540be4286e791db73f84a2b721072a3711efff6c324cdf074b"},
+ {file = "protobuf-3.20.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:daa564862dd0d39c00f8086f88700fdbe8bc717e993a21e90711acfed02f2402"},
+ {file = "protobuf-3.20.3-cp39-cp39-win32.whl", hash = "sha256:819559cafa1a373b7096a482b504ae8a857c89593cf3a25af743ac9ecbd23480"},
+ {file = "protobuf-3.20.3-cp39-cp39-win_amd64.whl", hash = "sha256:03038ac1cfbc41aa21f6afcbcd357281d7521b4157926f30ebecc8d4ea59dcb7"},
+ {file = "protobuf-3.20.3-py2.py3-none-any.whl", hash = "sha256:a7ca6d488aa8ff7f329d4c545b2dbad8ac31464f1d8b1c87ad1346717731e4db"},
+ {file = "protobuf-3.20.3.tar.gz", hash = "sha256:2e3427429c9cffebf259491be0af70189607f365c2f41c7c3764af6f337105f2"},
+]
+
+[[package]]
+name = "pyasn1"
+version = "0.4.8"
+description = "ASN.1 types and codecs"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "pyasn1-0.4.8-py2.py3-none-any.whl", hash = "sha256:39c7e2ec30515947ff4e87fb6f456dfc6e84857d34be479c9d4a4ba4bf46aa5d"},
+ {file = "pyasn1-0.4.8.tar.gz", hash = "sha256:aef77c9fb94a3ac588e87841208bdec464471d9871bd5050a287cc9a475cd0ba"},
+]
+
+[[package]]
+name = "pyasn1-modules"
+version = "0.2.8"
+description = "A collection of ASN.1-based protocols modules."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "pyasn1-modules-0.2.8.tar.gz", hash = "sha256:905f84c712230b2c592c19470d3ca8d552de726050d1d1716282a1f6146be65e"},
+ {file = "pyasn1_modules-0.2.8-py2.py3-none-any.whl", hash = "sha256:a50b808ffeb97cb3601dd25981f6b016cbb3d31fbf57a8b8a87428e6158d0c74"},
+]
+
+[package.dependencies]
+pyasn1 = ">=0.4.6,<0.5.0"
+
+[[package]]
+name = "pycparser"
+version = "2.21"
+description = "C parser in Python"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+ {file = "pycparser-2.21-py2.py3-none-any.whl", hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9"},
+ {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"},
+]
+
+[[package]]
+name = "pydantic"
+version = "1.10.7"
+description = "Data validation and settings management using python type hints"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "pydantic-1.10.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e79e999e539872e903767c417c897e729e015872040e56b96e67968c3b918b2d"},
+ {file = "pydantic-1.10.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:01aea3a42c13f2602b7ecbbea484a98169fb568ebd9e247593ea05f01b884b2e"},
+ {file = "pydantic-1.10.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:516f1ed9bc2406a0467dd777afc636c7091d71f214d5e413d64fef45174cfc7a"},
+ {file = "pydantic-1.10.7-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae150a63564929c675d7f2303008d88426a0add46efd76c3fc797cd71cb1b46f"},
+ {file = "pydantic-1.10.7-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ecbbc51391248116c0a055899e6c3e7ffbb11fb5e2a4cd6f2d0b93272118a209"},
+ {file = "pydantic-1.10.7-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f4a2b50e2b03d5776e7f21af73e2070e1b5c0d0df255a827e7c632962f8315af"},
+ {file = "pydantic-1.10.7-cp310-cp310-win_amd64.whl", hash = "sha256:a7cd2251439988b413cb0a985c4ed82b6c6aac382dbaff53ae03c4b23a70e80a"},
+ {file = "pydantic-1.10.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:68792151e174a4aa9e9fc1b4e653e65a354a2fa0fed169f7b3d09902ad2cb6f1"},
+ {file = "pydantic-1.10.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dfe2507b8ef209da71b6fb5f4e597b50c5a34b78d7e857c4f8f3115effaef5fe"},
+ {file = "pydantic-1.10.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10a86d8c8db68086f1e30a530f7d5f83eb0685e632e411dbbcf2d5c0150e8dcd"},
+ {file = "pydantic-1.10.7-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d75ae19d2a3dbb146b6f324031c24f8a3f52ff5d6a9f22f0683694b3afcb16fb"},
+ {file = "pydantic-1.10.7-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:464855a7ff7f2cc2cf537ecc421291b9132aa9c79aef44e917ad711b4a93163b"},
+ {file = "pydantic-1.10.7-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:193924c563fae6ddcb71d3f06fa153866423ac1b793a47936656e806b64e24ca"},
+ {file = "pydantic-1.10.7-cp311-cp311-win_amd64.whl", hash = "sha256:b4a849d10f211389502059c33332e91327bc154acc1845f375a99eca3afa802d"},
+ {file = "pydantic-1.10.7-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:cc1dde4e50a5fc1336ee0581c1612215bc64ed6d28d2c7c6f25d2fe3e7c3e918"},
+ {file = "pydantic-1.10.7-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e0cfe895a504c060e5d36b287ee696e2fdad02d89e0d895f83037245218a87fe"},
+ {file = "pydantic-1.10.7-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:670bb4683ad1e48b0ecb06f0cfe2178dcf74ff27921cdf1606e527d2617a81ee"},
+ {file = "pydantic-1.10.7-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:950ce33857841f9a337ce07ddf46bc84e1c4946d2a3bba18f8280297157a3fd1"},
+ {file = "pydantic-1.10.7-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c15582f9055fbc1bfe50266a19771bbbef33dd28c45e78afbe1996fd70966c2a"},
+ {file = "pydantic-1.10.7-cp37-cp37m-win_amd64.whl", hash = "sha256:82dffb306dd20bd5268fd6379bc4bfe75242a9c2b79fec58e1041fbbdb1f7914"},
+ {file = "pydantic-1.10.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:8c7f51861d73e8b9ddcb9916ae7ac39fb52761d9ea0df41128e81e2ba42886cd"},
+ {file = "pydantic-1.10.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6434b49c0b03a51021ade5c4daa7d70c98f7a79e95b551201fff682fc1661245"},
+ {file = "pydantic-1.10.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64d34ab766fa056df49013bb6e79921a0265204c071984e75a09cbceacbbdd5d"},
+ {file = "pydantic-1.10.7-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:701daea9ffe9d26f97b52f1d157e0d4121644f0fcf80b443248434958fd03dc3"},
+ {file = "pydantic-1.10.7-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:cf135c46099ff3f919d2150a948ce94b9ce545598ef2c6c7bf55dca98a304b52"},
+ {file = "pydantic-1.10.7-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b0f85904f73161817b80781cc150f8b906d521fa11e3cdabae19a581c3606209"},
+ {file = "pydantic-1.10.7-cp38-cp38-win_amd64.whl", hash = "sha256:9f6f0fd68d73257ad6685419478c5aece46432f4bdd8d32c7345f1986496171e"},
+ {file = "pydantic-1.10.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c230c0d8a322276d6e7b88c3f7ce885f9ed16e0910354510e0bae84d54991143"},
+ {file = "pydantic-1.10.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:976cae77ba6a49d80f461fd8bba183ff7ba79f44aa5cfa82f1346b5626542f8e"},
+ {file = "pydantic-1.10.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7d45fc99d64af9aaf7e308054a0067fdcd87ffe974f2442312372dfa66e1001d"},
+ {file = "pydantic-1.10.7-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d2a5ebb48958754d386195fe9e9c5106f11275867051bf017a8059410e9abf1f"},
+ {file = "pydantic-1.10.7-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:abfb7d4a7cd5cc4e1d1887c43503a7c5dd608eadf8bc615413fc498d3e4645cd"},
+ {file = "pydantic-1.10.7-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:80b1fab4deb08a8292d15e43a6edccdffa5377a36a4597bb545b93e79c5ff0a5"},
+ {file = "pydantic-1.10.7-cp39-cp39-win_amd64.whl", hash = "sha256:d71e69699498b020ea198468e2480a2f1e7433e32a3a99760058c6520e2bea7e"},
+ {file = "pydantic-1.10.7-py3-none-any.whl", hash = "sha256:0cd181f1d0b1d00e2b705f1bf1ac7799a2d938cce3376b8007df62b29be3c2c6"},
+ {file = "pydantic-1.10.7.tar.gz", hash = "sha256:cfc83c0678b6ba51b0532bea66860617c4cd4251ecf76e9846fa5a9f3454e97e"},
+]
+
+[package.dependencies]
+typing-extensions = ">=4.2.0"
+
+[package.extras]
+dotenv = ["python-dotenv (>=0.10.4)"]
+email = ["email-validator (>=1.0.3)"]
+
+[[package]]
+name = "pydub"
+version = "0.25.1"
+description = "Manipulate audio with an simple and easy high level interface"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "pydub-0.25.1-py2.py3-none-any.whl", hash = "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6"},
+ {file = "pydub-0.25.1.tar.gz", hash = "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f"},
+]
+
+[[package]]
+name = "pyparsing"
+version = "3.0.9"
+description = "pyparsing module - Classes and methods to define and execute parsing grammars"
+category = "main"
+optional = false
+python-versions = ">=3.6.8"
+files = [
+ {file = "pyparsing-3.0.9-py3-none-any.whl", hash = "sha256:5026bae9a10eeaefb61dab2f09052b9f4307d44aee4eda64b309723d8d206bbc"},
+ {file = "pyparsing-3.0.9.tar.gz", hash = "sha256:2b020ecf7d21b687f219b71ecad3631f644a47f01403fa1d1036b0c6416d70fb"},
+]
+
+[package.extras]
+diagrams = ["jinja2", "railroad-diagrams"]
+
+[[package]]
+name = "pyrsistent"
+version = "0.19.3"
+description = "Persistent/Functional/Immutable data structures"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "pyrsistent-0.19.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:20460ac0ea439a3e79caa1dbd560344b64ed75e85d8703943e0b66c2a6150e4a"},
+ {file = "pyrsistent-0.19.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4c18264cb84b5e68e7085a43723f9e4c1fd1d935ab240ce02c0324a8e01ccb64"},
+ {file = "pyrsistent-0.19.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4b774f9288dda8d425adb6544e5903f1fb6c273ab3128a355c6b972b7df39dcf"},
+ {file = "pyrsistent-0.19.3-cp310-cp310-win32.whl", hash = "sha256:5a474fb80f5e0d6c9394d8db0fc19e90fa540b82ee52dba7d246a7791712f74a"},
+ {file = "pyrsistent-0.19.3-cp310-cp310-win_amd64.whl", hash = "sha256:49c32f216c17148695ca0e02a5c521e28a4ee6c5089f97e34fe24163113722da"},
+ {file = "pyrsistent-0.19.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:f0774bf48631f3a20471dd7c5989657b639fd2d285b861237ea9e82c36a415a9"},
+ {file = "pyrsistent-0.19.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ab2204234c0ecd8b9368dbd6a53e83c3d4f3cab10ecaf6d0e772f456c442393"},
+ {file = "pyrsistent-0.19.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e42296a09e83028b3476f7073fcb69ffebac0e66dbbfd1bd847d61f74db30f19"},
+ {file = "pyrsistent-0.19.3-cp311-cp311-win32.whl", hash = "sha256:64220c429e42a7150f4bfd280f6f4bb2850f95956bde93c6fda1b70507af6ef3"},
+ {file = "pyrsistent-0.19.3-cp311-cp311-win_amd64.whl", hash = "sha256:016ad1afadf318eb7911baa24b049909f7f3bb2c5b1ed7b6a8f21db21ea3faa8"},
+ {file = "pyrsistent-0.19.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c4db1bd596fefd66b296a3d5d943c94f4fac5bcd13e99bffe2ba6a759d959a28"},
+ {file = "pyrsistent-0.19.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aeda827381f5e5d65cced3024126529ddc4289d944f75e090572c77ceb19adbf"},
+ {file = "pyrsistent-0.19.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:42ac0b2f44607eb92ae88609eda931a4f0dfa03038c44c772e07f43e738bcac9"},
+ {file = "pyrsistent-0.19.3-cp37-cp37m-win32.whl", hash = "sha256:e8f2b814a3dc6225964fa03d8582c6e0b6650d68a232df41e3cc1b66a5d2f8d1"},
+ {file = "pyrsistent-0.19.3-cp37-cp37m-win_amd64.whl", hash = "sha256:c9bb60a40a0ab9aba40a59f68214eed5a29c6274c83b2cc206a359c4a89fa41b"},
+ {file = "pyrsistent-0.19.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:a2471f3f8693101975b1ff85ffd19bb7ca7dd7c38f8a81701f67d6b4f97b87d8"},
+ {file = "pyrsistent-0.19.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc5d149f31706762c1f8bda2e8c4f8fead6e80312e3692619a75301d3dbb819a"},
+ {file = "pyrsistent-0.19.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3311cb4237a341aa52ab8448c27e3a9931e2ee09561ad150ba94e4cfd3fc888c"},
+ {file = "pyrsistent-0.19.3-cp38-cp38-win32.whl", hash = "sha256:f0e7c4b2f77593871e918be000b96c8107da48444d57005b6a6bc61fb4331b2c"},
+ {file = "pyrsistent-0.19.3-cp38-cp38-win_amd64.whl", hash = "sha256:c147257a92374fde8498491f53ffa8f4822cd70c0d85037e09028e478cababb7"},
+ {file = "pyrsistent-0.19.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:b735e538f74ec31378f5a1e3886a26d2ca6351106b4dfde376a26fc32a044edc"},
+ {file = "pyrsistent-0.19.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99abb85579e2165bd8522f0c0138864da97847875ecbd45f3e7e2af569bfc6f2"},
+ {file = "pyrsistent-0.19.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3a8cb235fa6d3fd7aae6a4f1429bbb1fec1577d978098da1252f0489937786f3"},
+ {file = "pyrsistent-0.19.3-cp39-cp39-win32.whl", hash = "sha256:c74bed51f9b41c48366a286395c67f4e894374306b197e62810e0fdaf2364da2"},
+ {file = "pyrsistent-0.19.3-cp39-cp39-win_amd64.whl", hash = "sha256:878433581fc23e906d947a6814336eee031a00e6defba224234169ae3d3d6a98"},
+ {file = "pyrsistent-0.19.3-py3-none-any.whl", hash = "sha256:ccf0d6bd208f8111179f0c26fdf84ed7c3891982f2edaeae7422575f47e66b64"},
+ {file = "pyrsistent-0.19.3.tar.gz", hash = "sha256:1a2994773706bbb4995c31a97bc94f1418314923bd1048c6d964837040376440"},
+]
+
+[[package]]
+name = "python-dateutil"
+version = "2.8.2"
+description = "Extensions to the standard Python datetime module"
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+files = [
+ {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
+ {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
+]
+
+[package.dependencies]
+six = ">=1.5"
+
+[[package]]
+name = "python-multipart"
+version = "0.0.6"
+description = "A streaming multipart parser for Python"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "python_multipart-0.0.6-py3-none-any.whl", hash = "sha256:ee698bab5ef148b0a760751c261902cd096e57e10558e11aca17646b74ee1c18"},
+ {file = "python_multipart-0.0.6.tar.gz", hash = "sha256:e9925a80bb668529f1b67c7fdb0a5dacdd7cbfc6fb0bff3ea443fe22bdd62132"},
+]
+
+[package.extras]
+dev = ["atomicwrites (==1.2.1)", "attrs (==19.2.0)", "coverage (==6.5.0)", "hatch", "invoke (==1.7.3)", "more-itertools (==4.3.0)", "pbr (==4.3.0)", "pluggy (==1.0.0)", "py (==1.11.0)", "pytest (==7.2.0)", "pytest-cov (==4.0.0)", "pytest-timeout (==2.1.0)", "pyyaml (==5.1)"]
+
+[[package]]
+name = "pytz"
+version = "2023.3"
+description = "World timezone definitions, modern and historical"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "pytz-2023.3-py2.py3-none-any.whl", hash = "sha256:a151b3abb88eda1d4e34a9814df37de2a80e301e68ba0fd856fb9b46bfbbbffb"},
+ {file = "pytz-2023.3.tar.gz", hash = "sha256:1d8ce29db189191fb55338ee6d0387d82ab59f3d00eac103412d64e0ebd0c588"},
+]
+
+[[package]]
+name = "pywin32"
+version = "306"
+description = "Python for Window Extensions"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "pywin32-306-cp310-cp310-win32.whl", hash = "sha256:06d3420a5155ba65f0b72f2699b5bacf3109f36acbe8923765c22938a69dfc8d"},
+ {file = "pywin32-306-cp310-cp310-win_amd64.whl", hash = "sha256:84f4471dbca1887ea3803d8848a1616429ac94a4a8d05f4bc9c5dcfd42ca99c8"},
+ {file = "pywin32-306-cp311-cp311-win32.whl", hash = "sha256:e65028133d15b64d2ed8f06dd9fbc268352478d4f9289e69c190ecd6818b6407"},
+ {file = "pywin32-306-cp311-cp311-win_amd64.whl", hash = "sha256:a7639f51c184c0272e93f244eb24dafca9b1855707d94c192d4a0b4c01e1100e"},
+ {file = "pywin32-306-cp311-cp311-win_arm64.whl", hash = "sha256:70dba0c913d19f942a2db25217d9a1b726c278f483a919f1abfed79c9cf64d3a"},
+ {file = "pywin32-306-cp312-cp312-win32.whl", hash = "sha256:383229d515657f4e3ed1343da8be101000562bf514591ff383ae940cad65458b"},
+ {file = "pywin32-306-cp312-cp312-win_amd64.whl", hash = "sha256:37257794c1ad39ee9be652da0462dc2e394c8159dfd913a8a4e8eb6fd346da0e"},
+ {file = "pywin32-306-cp312-cp312-win_arm64.whl", hash = "sha256:5821ec52f6d321aa59e2db7e0a35b997de60c201943557d108af9d4ae1ec7040"},
+ {file = "pywin32-306-cp37-cp37m-win32.whl", hash = "sha256:1c73ea9a0d2283d889001998059f5eaaba3b6238f767c9cf2833b13e6a685f65"},
+ {file = "pywin32-306-cp37-cp37m-win_amd64.whl", hash = "sha256:72c5f621542d7bdd4fdb716227be0dd3f8565c11b280be6315b06ace35487d36"},
+ {file = "pywin32-306-cp38-cp38-win32.whl", hash = "sha256:e4c092e2589b5cf0d365849e73e02c391c1349958c5ac3e9d5ccb9a28e017b3a"},
+ {file = "pywin32-306-cp38-cp38-win_amd64.whl", hash = "sha256:e8ac1ae3601bee6ca9f7cb4b5363bf1c0badb935ef243c4733ff9a393b1690c0"},
+ {file = "pywin32-306-cp39-cp39-win32.whl", hash = "sha256:e25fd5b485b55ac9c057f67d94bc203f3f6595078d1fb3b458c9c28b7153a802"},
+ {file = "pywin32-306-cp39-cp39-win_amd64.whl", hash = "sha256:39b61c15272833b5c329a2989999dcae836b1eed650252ab1b7bfbe1d59f30f4"},
+]
+
+[[package]]
+name = "pyworld"
+version = "0.3.2"
+description = "PyWorld is a Python wrapper for WORLD vocoder."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "pyworld-0.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:688730fa5394709a185061e5a58e7a614b4548d814eeecc1dc825f73af53a9aa"},
+ {file = "pyworld-0.3.2-cp36-cp36m-win32.whl", hash = "sha256:1e110e2f95d45b0765f4ba4e49b389f9b931c9c438cd69774dce20699cc6dc7d"},
+ {file = "pyworld-0.3.2-cp36-cp36m-win_amd64.whl", hash = "sha256:e858668185a177e9e30c0ff12de3e166b39124c14b424ba3be31418694dcb2b7"},
+ {file = "pyworld-0.3.2-cp37-cp37m-win32.whl", hash = "sha256:b5325e7a08f104a9bf533d54423546bd3ef05953b80b79a8ced34efbb892862b"},
+ {file = "pyworld-0.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:fddd503ac264810221d9460bfdc1454c5c1313214e1c58a4ddd9417699f99bc8"},
+ {file = "pyworld-0.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:502fbf577f4e56a497b3ad8c29434ec423eabc4674b93fa11046837d297c97be"},
+ {file = "pyworld-0.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:a8ea62219b9bce0e514ff05ee80cfbc1248b165d8d802f00b9b8754510701f3e"},
+ {file = "pyworld-0.3.2.tar.gz", hash = "sha256:668d09842c3cfa74b1f6edabdb0058a64c04f9cf17b93883e6da811e1204ad4d"},
+]
+
+[package.dependencies]
+cython = "*"
+numpy = "*"
+
+[package.extras]
+sdist = ["cython", "numpy"]
+test = ["nose"]
+
+[[package]]
+name = "pyyaml"
+version = "6.0"
+description = "YAML parser and emitter for Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"},
+ {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"},
+ {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"},
+ {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a80a78046a72361de73f8f395f1f1e49f956c6be882eed58505a15f3e430962b"},
+ {file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"},
+ {file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"},
+ {file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"},
+ {file = "PyYAML-6.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d4b0ba9512519522b118090257be113b9468d804b19d63c71dbcf4a48fa32358"},
+ {file = "PyYAML-6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:81957921f441d50af23654aa6c5e5eaf9b06aba7f0a19c18a538dc7ef291c5a1"},
+ {file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afa17f5bc4d1b10afd4466fd3a44dc0e245382deca5b3c353d8b757f9e3ecb8d"},
+ {file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dbad0e9d368bb989f4515da330b88a057617d16b6a8245084f1b05400f24609f"},
+ {file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:432557aa2c09802be39460360ddffd48156e30721f5e8d917f01d31694216782"},
+ {file = "PyYAML-6.0-cp311-cp311-win32.whl", hash = "sha256:bfaef573a63ba8923503d27530362590ff4f576c626d86a9fed95822a8255fd7"},
+ {file = "PyYAML-6.0-cp311-cp311-win_amd64.whl", hash = "sha256:01b45c0191e6d66c470b6cf1b9531a771a83c1c4208272ead47a3ae4f2f603bf"},
+ {file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"},
+ {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"},
+ {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"},
+ {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98c4d36e99714e55cfbaaee6dd5badbc9a1ec339ebfc3b1f52e293aee6bb71a4"},
+ {file = "PyYAML-6.0-cp36-cp36m-win32.whl", hash = "sha256:0283c35a6a9fbf047493e3a0ce8d79ef5030852c51e9d911a27badfde0605293"},
+ {file = "PyYAML-6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:07751360502caac1c067a8132d150cf3d61339af5691fe9e87803040dbc5db57"},
+ {file = "PyYAML-6.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:819b3830a1543db06c4d4b865e70ded25be52a2e0631ccd2f6a47a2822f2fd7c"},
+ {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:473f9edb243cb1935ab5a084eb238d842fb8f404ed2193a915d1784b5a6b5fc0"},
+ {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ce82d761c532fe4ec3f87fc45688bdd3a4c1dc5e0b4a19814b9009a29baefd4"},
+ {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:231710d57adfd809ef5d34183b8ed1eeae3f76459c18fb4a0b373ad56bedcdd9"},
+ {file = "PyYAML-6.0-cp37-cp37m-win32.whl", hash = "sha256:c5687b8d43cf58545ade1fe3e055f70eac7a5a1a0bf42824308d868289a95737"},
+ {file = "PyYAML-6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d15a181d1ecd0d4270dc32edb46f7cb7733c7c508857278d3d378d14d606db2d"},
+ {file = "PyYAML-6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0b4624f379dab24d3725ffde76559cff63d9ec94e1736b556dacdfebe5ab6d4b"},
+ {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:213c60cd50106436cc818accf5baa1aba61c0189ff610f64f4a3e8c6726218ba"},
+ {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fa600030013c4de8165339db93d182b9431076eb98eb40ee068700c9c813e34"},
+ {file = "PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:277a0ef2981ca40581a47093e9e2d13b3f1fbbeffae064c1d21bfceba2030287"},
+ {file = "PyYAML-6.0-cp38-cp38-win32.whl", hash = "sha256:d4eccecf9adf6fbcc6861a38015c2a64f38b9d94838ac1810a9023a0609e1b78"},
+ {file = "PyYAML-6.0-cp38-cp38-win_amd64.whl", hash = "sha256:1e4747bc279b4f613a09eb64bba2ba602d8a6664c6ce6396a4d0cd413a50ce07"},
+ {file = "PyYAML-6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:055d937d65826939cb044fc8c9b08889e8c743fdc6a32b33e2390f66013e449b"},
+ {file = "PyYAML-6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e61ceaab6f49fb8bdfaa0f92c4b57bcfbea54c09277b1b4f7ac376bfb7a7c174"},
+ {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d839ede4ed1b28a4e8909735fc992a923cdb84e618544973d7dfc71540803"},
+ {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cba8c411ef271aa037d7357a2bc8f9ee8b58b9965831d9e51baf703280dc73d3"},
+ {file = "PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40527857252b61eacd1d9af500c3337ba8deb8fc298940291486c465c8b46ec0"},
+ {file = "PyYAML-6.0-cp39-cp39-win32.whl", hash = "sha256:b5b9eccad747aabaaffbc6064800670f0c297e52c12754eb1d976c57e4f74dcb"},
+ {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"},
+ {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"},
+]
+
+[[package]]
+name = "regex"
+version = "2023.3.23"
+description = "Alternative regular expression module, to replace re."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "regex-2023.3.23-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:845a5e2d84389c4ddada1a9b95c055320070f18bb76512608374aca00d22eca8"},
+ {file = "regex-2023.3.23-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:87d9951f5a538dd1d016bdc0dcae59241d15fa94860964833a54d18197fcd134"},
+ {file = "regex-2023.3.23-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:37ae17d3be44c0b3f782c28ae9edd8b47c1f1776d4cabe87edc0b98e1f12b021"},
+ {file = "regex-2023.3.23-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0b8eb1e3bca6b48dc721818a60ae83b8264d4089a4a41d62be6d05316ec38e15"},
+ {file = "regex-2023.3.23-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:df45fac182ebc3c494460c644e853515cc24f5ad9da05f8ffb91da891bfee879"},
+ {file = "regex-2023.3.23-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b7006105b10b59971d3b248ad75acc3651c7e4cf54d81694df5a5130a3c3f7ea"},
+ {file = "regex-2023.3.23-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93f3f1aa608380fe294aa4cb82e2afda07a7598e828d0341e124b8fd9327c715"},
+ {file = "regex-2023.3.23-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:787954f541ab95d8195d97b0b8cf1dc304424adb1e07365967e656b92b38a699"},
+ {file = "regex-2023.3.23-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:20abe0bdf03630fe92ccafc45a599bca8b3501f48d1de4f7d121153350a2f77d"},
+ {file = "regex-2023.3.23-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:11d00c31aeab9a6e0503bc77e73ed9f4527b3984279d997eb145d7c7be6268fd"},
+ {file = "regex-2023.3.23-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:d5bbe0e1511b844794a3be43d6c145001626ba9a6c1db8f84bdc724e91131d9d"},
+ {file = "regex-2023.3.23-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:ea3c0cb56eadbf4ab2277e7a095676370b3e46dbfc74d5c383bd87b0d6317910"},
+ {file = "regex-2023.3.23-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d895b4c863059a4934d3e874b90998df774644a41b349ebb330f85f11b4ef2c0"},
+ {file = "regex-2023.3.23-cp310-cp310-win32.whl", hash = "sha256:9d764514d19b4edcc75fd8cb1423448ef393e8b6cbd94f38cab983ab1b75855d"},
+ {file = "regex-2023.3.23-cp310-cp310-win_amd64.whl", hash = "sha256:11d1f2b7a0696dc0310de0efb51b1f4d813ad4401fe368e83c0c62f344429f98"},
+ {file = "regex-2023.3.23-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8a9c63cde0eaa345795c0fdeb19dc62d22e378c50b0bc67bf4667cd5b482d98b"},
+ {file = "regex-2023.3.23-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dd7200b4c27b68cf9c9646da01647141c6db09f48cc5b51bc588deaf8e98a797"},
+ {file = "regex-2023.3.23-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22720024b90a6ba673a725dcc62e10fb1111b889305d7c6b887ac7466b74bedb"},
+ {file = "regex-2023.3.23-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6b190a339090e6af25f4a5fd9e77591f6d911cc7b96ecbb2114890b061be0ac1"},
+ {file = "regex-2023.3.23-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e76b6fc0d8e9efa39100369a9b3379ce35e20f6c75365653cf58d282ad290f6f"},
+ {file = "regex-2023.3.23-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7868b8f218bf69a2a15402fde08b08712213a1f4b85a156d90473a6fb6b12b09"},
+ {file = "regex-2023.3.23-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2472428efc4127374f494e570e36b30bb5e6b37d9a754f7667f7073e43b0abdd"},
+ {file = "regex-2023.3.23-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c37df2a060cb476d94c047b18572ee2b37c31f831df126c0da3cd9227b39253d"},
+ {file = "regex-2023.3.23-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:4479f9e2abc03362df4045b1332d4a2b7885b245a30d4f4b051c4083b97d95d8"},
+ {file = "regex-2023.3.23-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e2396e0678167f2d0c197da942b0b3fb48fee2f0b5915a0feb84d11b6686afe6"},
+ {file = "regex-2023.3.23-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:75f288c60232a5339e0ff2fa05779a5e9c74e9fc085c81e931d4a264501e745b"},
+ {file = "regex-2023.3.23-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c869260aa62cee21c5eb171a466c0572b5e809213612ef8d495268cd2e34f20d"},
+ {file = "regex-2023.3.23-cp311-cp311-win32.whl", hash = "sha256:25f0532fd0c53e96bad84664171969de9673b4131f2297f1db850d3918d58858"},
+ {file = "regex-2023.3.23-cp311-cp311-win_amd64.whl", hash = "sha256:5ccfafd98473e007cebf7da10c1411035b7844f0f204015efd050601906dbb53"},
+ {file = "regex-2023.3.23-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6572ff287176c0fb96568adb292674b421fa762153ed074d94b1d939ed92c253"},
+ {file = "regex-2023.3.23-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a610e0adfcb0fc84ea25f6ea685e39e74cbcd9245a72a9a7aab85ff755a5ed27"},
+ {file = "regex-2023.3.23-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:086afe222d58b88b62847bdbd92079b4699350b4acab892f88a935db5707c790"},
+ {file = "regex-2023.3.23-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:79e29fd62fa2f597a6754b247356bda14b866131a22444d67f907d6d341e10f3"},
+ {file = "regex-2023.3.23-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c07ce8e9eee878a48ebeb32ee661b49504b85e164b05bebf25420705709fdd31"},
+ {file = "regex-2023.3.23-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86b036f401895e854de9fefe061518e78d506d8a919cc250dc3416bca03f6f9a"},
+ {file = "regex-2023.3.23-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:78ac8dd8e18800bb1f97aad0d73f68916592dddf233b99d2b5cabc562088503a"},
+ {file = "regex-2023.3.23-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:539dd010dc35af935b32f248099e38447bbffc10b59c2b542bceead2bed5c325"},
+ {file = "regex-2023.3.23-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:9bf4a5626f2a0ea006bf81e8963f498a57a47d58907eaa58f4b3e13be68759d8"},
+ {file = "regex-2023.3.23-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:cf86b4328c204c3f315074a61bc1c06f8a75a8e102359f18ce99fbcbbf1951f0"},
+ {file = "regex-2023.3.23-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:2848bf76673c83314068241c8d5b7fa9ad9bed866c979875a0e84039349e8fa7"},
+ {file = "regex-2023.3.23-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:c125a02d22c555e68f7433bac8449992fa1cead525399f14e47c2d98f2f0e467"},
+ {file = "regex-2023.3.23-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:cd1671e9d5ac05ce6aa86874dd8dfa048824d1dbe73060851b310c6c1a201a96"},
+ {file = "regex-2023.3.23-cp38-cp38-win32.whl", hash = "sha256:fffe57312a358be6ec6baeb43d253c36e5790e436b7bf5b7a38df360363e88e9"},
+ {file = "regex-2023.3.23-cp38-cp38-win_amd64.whl", hash = "sha256:dbb3f87e15d3dd76996d604af8678316ad2d7d20faa394e92d9394dfd621fd0c"},
+ {file = "regex-2023.3.23-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c88e8c226473b5549fe9616980ea7ca09289246cfbdf469241edf4741a620004"},
+ {file = "regex-2023.3.23-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6560776ec19c83f3645bbc5db64a7a5816c9d8fb7ed7201c5bcd269323d88072"},
+ {file = "regex-2023.3.23-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b1fc2632c01f42e06173d8dd9bb2e74ab9b0afa1d698058c867288d2c7a31f3"},
+ {file = "regex-2023.3.23-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fdf7ad455f1916b8ea5cdbc482d379f6daf93f3867b4232d14699867a5a13af7"},
+ {file = "regex-2023.3.23-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5fc33b27b1d800fc5b78d7f7d0f287e35079ecabe68e83d46930cf45690e1c8c"},
+ {file = "regex-2023.3.23-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c49552dc938e3588f63f8a78c86f3c9c75301e813bca0bef13bdb4b87ccf364"},
+ {file = "regex-2023.3.23-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e152461e9a0aedec7d37fc66ec0fa635eca984777d3d3c3e36f53bf3d3ceb16e"},
+ {file = "regex-2023.3.23-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:db034255e72d2995cf581b14bb3fc9c00bdbe6822b49fcd4eef79e1d5f232618"},
+ {file = "regex-2023.3.23-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:55ae114da21b7a790b90255ea52d2aa3a0d121a646deb2d3c6a3194e722fc762"},
+ {file = "regex-2023.3.23-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:ef3f528fe1cc3d139508fe1b22523745aa77b9d6cb5b0bf277f48788ee0b993f"},
+ {file = "regex-2023.3.23-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:a81c9ec59ca2303acd1ccd7b9ac409f1e478e40e96f8f79b943be476c5fdb8bb"},
+ {file = "regex-2023.3.23-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:cde09c4fdd070772aa2596d97e942eb775a478b32459e042e1be71b739d08b77"},
+ {file = "regex-2023.3.23-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:3cd9f5dd7b821f141d3a6ca0d5d9359b9221e4f051ca3139320adea9f1679691"},
+ {file = "regex-2023.3.23-cp39-cp39-win32.whl", hash = "sha256:7304863f3a652dab5e68e6fb1725d05ebab36ec0390676d1736e0571ebb713ef"},
+ {file = "regex-2023.3.23-cp39-cp39-win_amd64.whl", hash = "sha256:54c3fa855a3f7438149de3211738dd9b5f0c733f48b54ae05aa7fce83d48d858"},
+ {file = "regex-2023.3.23.tar.gz", hash = "sha256:dc80df325b43ffea5cdea2e3eaa97a44f3dd298262b1c7fe9dbb2a9522b956a7"},
+]
+
+[[package]]
+name = "requests"
+version = "2.31.0"
+description = "Python HTTP for Humans."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
+ {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
+]
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "requests-oauthlib"
+version = "1.3.1"
+description = "OAuthlib authentication support for Requests."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+ {file = "requests-oauthlib-1.3.1.tar.gz", hash = "sha256:75beac4a47881eeb94d5ea5d6ad31ef88856affe2332b9aafb52c6452ccf0d7a"},
+ {file = "requests_oauthlib-1.3.1-py2.py3-none-any.whl", hash = "sha256:2577c501a2fb8d05a304c09d090d6e47c306fef15809d102b327cf8364bddab5"},
+]
+
+[package.dependencies]
+oauthlib = ">=3.0.0"
+requests = ">=2.0.0"
+
+[package.extras]
+rsa = ["oauthlib[signedtoken] (>=3.0.0)"]
+
+[[package]]
+name = "resampy"
+version = "0.4.2"
+description = "Efficient signal resampling"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "resampy-0.4.2-py3-none-any.whl", hash = "sha256:4340b6c4e685a865621dfcf016e2a3dd49d865446b6025e30fe88567f22e052e"},
+ {file = "resampy-0.4.2.tar.gz", hash = "sha256:0a469e6ddb89956f4fd6c88728300e4bbd186fae569dd4fd17dae51a91cbaa15"},
+]
+
+[package.dependencies]
+numba = ">=0.53"
+numpy = ">=1.17"
+
+[package.extras]
+design = ["optuna (>=2.10.0)"]
+docs = ["numpydoc", "sphinx (!=1.3.1)"]
+tests = ["pytest (<8)", "pytest-cov", "scipy (>=1.0)"]
+
+[[package]]
+name = "rfc3986"
+version = "1.5.0"
+description = "Validating URI References per RFC 3986"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "rfc3986-1.5.0-py2.py3-none-any.whl", hash = "sha256:a86d6e1f5b1dc238b218b012df0aa79409667bb209e58da56d0b94704e712a97"},
+ {file = "rfc3986-1.5.0.tar.gz", hash = "sha256:270aaf10d87d0d4e095063c65bf3ddbc6ee3d0b226328ce21e036f946e421835"},
+]
+
+[package.dependencies]
+idna = {version = "*", optional = true, markers = "extra == \"idna2008\""}
+
+[package.extras]
+idna2008 = ["idna"]
+
+[[package]]
+name = "rsa"
+version = "4.9"
+description = "Pure-Python RSA implementation"
+category = "main"
+optional = false
+python-versions = ">=3.6,<4"
+files = [
+ {file = "rsa-4.9-py3-none-any.whl", hash = "sha256:90260d9058e514786967344d0ef75fa8727eed8a7d2e43ce9f4bcf1b536174f7"},
+ {file = "rsa-4.9.tar.gz", hash = "sha256:e38464a49c6c85d7f1351b0126661487a7e0a14a50f1675ec50eb34d4f20ef21"},
+]
+
+[package.dependencies]
+pyasn1 = ">=0.1.3"
+
+[[package]]
+name = "sacrebleu"
+version = "2.3.1"
+description = "Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "sacrebleu-2.3.1-py3-none-any.whl", hash = "sha256:352227b8ca9e04ed509266d1fee6c8cff0ea1417c429f8c684645ad2db8b02e7"},
+ {file = "sacrebleu-2.3.1.tar.gz", hash = "sha256:7969b294f15dae84d80fb2b76d30c83b245f49f4ecb1cac79acb553eb93cb537"},
+]
+
+[package.dependencies]
+colorama = "*"
+lxml = "*"
+numpy = ">=1.17"
+portalocker = "*"
+regex = "*"
+tabulate = ">=0.8.9"
+
+[package.extras]
+ja = ["ipadic (>=1.0,<2.0)", "mecab-python3 (==1.0.5)"]
+ko = ["mecab-ko (==1.0.0)", "mecab-ko-dic (>=1.0,<2.0)"]
+
+[[package]]
+name = "scikit-learn"
+version = "1.2.2"
+description = "A set of python modules for machine learning and data mining"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "scikit-learn-1.2.2.tar.gz", hash = "sha256:8429aea30ec24e7a8c7ed8a3fa6213adf3814a6efbea09e16e0a0c71e1a1a3d7"},
+ {file = "scikit_learn-1.2.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:99cc01184e347de485bf253d19fcb3b1a3fb0ee4cea5ee3c43ec0cc429b6d29f"},
+ {file = "scikit_learn-1.2.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:e6e574db9914afcb4e11ade84fab084536a895ca60aadea3041e85b8ac963edb"},
+ {file = "scikit_learn-1.2.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6fe83b676f407f00afa388dd1fdd49e5c6612e551ed84f3b1b182858f09e987d"},
+ {file = "scikit_learn-1.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e2642baa0ad1e8f8188917423dd73994bf25429f8893ddbe115be3ca3183584"},
+ {file = "scikit_learn-1.2.2-cp310-cp310-win_amd64.whl", hash = "sha256:ad66c3848c0a1ec13464b2a95d0a484fd5b02ce74268eaa7e0c697b904f31d6c"},
+ {file = "scikit_learn-1.2.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:dfeaf8be72117eb61a164ea6fc8afb6dfe08c6f90365bde2dc16456e4bc8e45f"},
+ {file = "scikit_learn-1.2.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:fe0aa1a7029ed3e1dcbf4a5bc675aa3b1bc468d9012ecf6c6f081251ca47f590"},
+ {file = "scikit_learn-1.2.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:065e9673e24e0dc5113e2dd2b4ca30c9d8aa2fa90f4c0597241c93b63130d233"},
+ {file = "scikit_learn-1.2.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bf036ea7ef66115e0d49655f16febfa547886deba20149555a41d28f56fd6d3c"},
+ {file = "scikit_learn-1.2.2-cp311-cp311-win_amd64.whl", hash = "sha256:8b0670d4224a3c2d596fd572fb4fa673b2a0ccfb07152688ebd2ea0b8c61025c"},
+ {file = "scikit_learn-1.2.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9c710ff9f9936ba8a3b74a455ccf0dcf59b230caa1e9ba0223773c490cab1e51"},
+ {file = "scikit_learn-1.2.2-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:2dd3ffd3950e3d6c0c0ef9033a9b9b32d910c61bd06cb8206303fb4514b88a49"},
+ {file = "scikit_learn-1.2.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:44b47a305190c28dd8dd73fc9445f802b6ea716669cfc22ab1eb97b335d238b1"},
+ {file = "scikit_learn-1.2.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:953236889928d104c2ef14027539f5f2609a47ebf716b8cbe4437e85dce42744"},
+ {file = "scikit_learn-1.2.2-cp38-cp38-win_amd64.whl", hash = "sha256:7f69313884e8eb311460cc2f28676d5e400bd929841a2c8eb8742ae78ebf7c20"},
+ {file = "scikit_learn-1.2.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8156db41e1c39c69aa2d8599ab7577af53e9e5e7a57b0504e116cc73c39138dd"},
+ {file = "scikit_learn-1.2.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:fe175ee1dab589d2e1033657c5b6bec92a8a3b69103e3dd361b58014729975c3"},
+ {file = "scikit_learn-1.2.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7d5312d9674bed14f73773d2acf15a3272639b981e60b72c9b190a0cffed5bad"},
+ {file = "scikit_learn-1.2.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea061bf0283bf9a9f36ea3c5d3231ba2176221bbd430abd2603b1c3b2ed85c89"},
+ {file = "scikit_learn-1.2.2-cp39-cp39-win_amd64.whl", hash = "sha256:6477eed40dbce190f9f9e9d0d37e020815825b300121307942ec2110302b66a3"},
+]
+
+[package.dependencies]
+joblib = ">=1.1.1"
+numpy = ">=1.17.3"
+scipy = ">=1.3.2"
+threadpoolctl = ">=2.0.0"
+
+[package.extras]
+benchmark = ["matplotlib (>=3.1.3)", "memory-profiler (>=0.57.0)", "pandas (>=1.0.5)"]
+docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.1.3)", "memory-profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.0.5)", "plotly (>=5.10.0)", "pooch (>=1.6.0)", "scikit-image (>=0.16.2)", "seaborn (>=0.9.0)", "sphinx (>=4.0.1)", "sphinx-gallery (>=0.7.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
+examples = ["matplotlib (>=3.1.3)", "pandas (>=1.0.5)", "plotly (>=5.10.0)", "pooch (>=1.6.0)", "scikit-image (>=0.16.2)", "seaborn (>=0.9.0)"]
+tests = ["black (>=22.3.0)", "flake8 (>=3.8.2)", "matplotlib (>=3.1.3)", "mypy (>=0.961)", "numpydoc (>=1.2.0)", "pandas (>=1.0.5)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pytest (>=5.3.1)", "pytest-cov (>=2.9.0)", "scikit-image (>=0.16.2)"]
+
+[[package]]
+name = "scipy"
+version = "1.9.3"
+description = "Fundamental algorithms for scientific computing in Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "scipy-1.9.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1884b66a54887e21addf9c16fb588720a8309a57b2e258ae1c7986d4444d3bc0"},
+ {file = "scipy-1.9.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:83b89e9586c62e787f5012e8475fbb12185bafb996a03257e9675cd73d3736dd"},
+ {file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a72d885fa44247f92743fc20732ae55564ff2a519e8302fb7e18717c5355a8b"},
+ {file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d01e1dd7b15bd2449c8bfc6b7cc67d630700ed655654f0dfcf121600bad205c9"},
+ {file = "scipy-1.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:68239b6aa6f9c593da8be1509a05cb7f9efe98b80f43a5861cd24c7557e98523"},
+ {file = "scipy-1.9.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b41bc822679ad1c9a5f023bc93f6d0543129ca0f37c1ce294dd9d386f0a21096"},
+ {file = "scipy-1.9.3-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:90453d2b93ea82a9f434e4e1cba043e779ff67b92f7a0e85d05d286a3625df3c"},
+ {file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c06e62a390a9167da60bedd4575a14c1f58ca9dfde59830fc42e5197283dab"},
+ {file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:abaf921531b5aeaafced90157db505e10345e45038c39e5d9b6c7922d68085cb"},
+ {file = "scipy-1.9.3-cp311-cp311-win_amd64.whl", hash = "sha256:06d2e1b4c491dc7d8eacea139a1b0b295f74e1a1a0f704c375028f8320d16e31"},
+ {file = "scipy-1.9.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:5a04cd7d0d3eff6ea4719371cbc44df31411862b9646db617c99718ff68d4840"},
+ {file = "scipy-1.9.3-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:545c83ffb518094d8c9d83cce216c0c32f8c04aaf28b92cc8283eda0685162d5"},
+ {file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d54222d7a3ba6022fdf5773931b5d7c56efe41ede7f7128c7b1637700409108"},
+ {file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cff3a5295234037e39500d35316a4c5794739433528310e117b8a9a0c76d20fc"},
+ {file = "scipy-1.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:2318bef588acc7a574f5bfdff9c172d0b1bf2c8143d9582e05f878e580a3781e"},
+ {file = "scipy-1.9.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d644a64e174c16cb4b2e41dfea6af722053e83d066da7343f333a54dae9bc31c"},
+ {file = "scipy-1.9.3-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:da8245491d73ed0a994ed9c2e380fd058ce2fa8a18da204681f2fe1f57f98f95"},
+ {file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4db5b30849606a95dcf519763dd3ab6fe9bd91df49eba517359e450a7d80ce2e"},
+ {file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c68db6b290cbd4049012990d7fe71a2abd9ffbe82c0056ebe0f01df8be5436b0"},
+ {file = "scipy-1.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:5b88e6d91ad9d59478fafe92a7c757d00c59e3bdc3331be8ada76a4f8d683f58"},
+ {file = "scipy-1.9.3.tar.gz", hash = "sha256:fbc5c05c85c1a02be77b1ff591087c83bc44579c6d2bd9fb798bb64ea5e1a027"},
+]
+
+[package.dependencies]
+numpy = ">=1.18.5,<1.26.0"
+
+[package.extras]
+dev = ["flake8", "mypy", "pycodestyle", "typing_extensions"]
+doc = ["matplotlib (>2)", "numpydoc", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-panels (>=0.5.2)", "sphinx-tabs"]
+test = ["asv", "gmpy2", "mpmath", "pytest", "pytest-cov", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
+
+[[package]]
+name = "semantic-version"
+version = "2.10.0"
+description = "A library implementing the 'SemVer' scheme."
+category = "main"
+optional = false
+python-versions = ">=2.7"
+files = [
+ {file = "semantic_version-2.10.0-py2.py3-none-any.whl", hash = "sha256:de78a3b8e0feda74cabc54aab2da702113e33ac9d9eb9d2389bcf1f58b7d9177"},
+ {file = "semantic_version-2.10.0.tar.gz", hash = "sha256:bdabb6d336998cbb378d4b9db3a4b56a1e3235701dc05ea2690d9a997ed5041c"},
+]
+
+[package.extras]
+dev = ["Django (>=1.11)", "check-manifest", "colorama (<=0.4.1)", "coverage", "flake8", "nose2", "readme-renderer (<25.0)", "tox", "wheel", "zest.releaser[recommended]"]
+doc = ["Sphinx", "sphinx-rtd-theme"]
+
+[[package]]
+name = "setuptools"
+version = "67.7.2"
+description = "Easily download, build, install, upgrade, and uninstall Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "setuptools-67.7.2-py3-none-any.whl", hash = "sha256:23aaf86b85ca52ceb801d32703f12d77517b2556af839621c641fca11287952b"},
+ {file = "setuptools-67.7.2.tar.gz", hash = "sha256:f104fa03692a2602fa0fec6c6a9e63b6c8a968de13e17c026957dd1f53d80990"},
+]
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-hoverxref (<2)", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (==0.8.3)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
+testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8 (<5)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pip-run (>=8.8)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+testing-integration = ["build[virtualenv]", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
+
+[[package]]
+name = "six"
+version = "1.16.0"
+description = "Python 2 and 3 compatibility utilities"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+files = [
+ {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
+ {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
+]
+
+[[package]]
+name = "sniffio"
+version = "1.3.0"
+description = "Sniff out which async library your code is running under"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "sniffio-1.3.0-py3-none-any.whl", hash = "sha256:eecefdce1e5bbfb7ad2eeaabf7c1eeb404d7757c379bd1f7e5cce9d8bf425384"},
+ {file = "sniffio-1.3.0.tar.gz", hash = "sha256:e60305c5e5d314f5389259b7f22aaa33d8f7dee49763119234af3755c55b9101"},
+]
+
+[[package]]
+name = "soundfile"
+version = "0.12.1"
+description = "An audio library based on libsndfile, CFFI and NumPy"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "soundfile-0.12.1-py2.py3-none-any.whl", hash = "sha256:828a79c2e75abab5359f780c81dccd4953c45a2c4cd4f05ba3e233ddf984b882"},
+ {file = "soundfile-0.12.1-py2.py3-none-macosx_10_9_x86_64.whl", hash = "sha256:d922be1563ce17a69582a352a86f28ed8c9f6a8bc951df63476ffc310c064bfa"},
+ {file = "soundfile-0.12.1-py2.py3-none-macosx_11_0_arm64.whl", hash = "sha256:bceaab5c4febb11ea0554566784bcf4bc2e3977b53946dda2b12804b4fe524a8"},
+ {file = "soundfile-0.12.1-py2.py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:2dc3685bed7187c072a46ab4ffddd38cef7de9ae5eb05c03df2ad569cf4dacbc"},
+ {file = "soundfile-0.12.1-py2.py3-none-manylinux_2_31_x86_64.whl", hash = "sha256:074247b771a181859d2bc1f98b5ebf6d5153d2c397b86ee9e29ba602a8dfe2a6"},
+ {file = "soundfile-0.12.1-py2.py3-none-win32.whl", hash = "sha256:59dfd88c79b48f441bbf6994142a19ab1de3b9bb7c12863402c2bc621e49091a"},
+ {file = "soundfile-0.12.1-py2.py3-none-win_amd64.whl", hash = "sha256:0d86924c00b62552b650ddd28af426e3ff2d4dc2e9047dae5b3d8452e0a49a77"},
+ {file = "soundfile-0.12.1.tar.gz", hash = "sha256:e8e1017b2cf1dda767aef19d2fd9ee5ebe07e050d430f77a0a7c66ba08b8cdae"},
+]
+
+[package.dependencies]
+cffi = ">=1.0"
+
+[package.extras]
+numpy = ["numpy"]
+
+[[package]]
+name = "starlette"
+version = "0.27.0"
+description = "The little ASGI library that shines."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "starlette-0.27.0-py3-none-any.whl", hash = "sha256:918416370e846586541235ccd38a474c08b80443ed31c578a418e2209b3eef91"},
+ {file = "starlette-0.27.0.tar.gz", hash = "sha256:6a6b0d042acb8d469a01eba54e9cda6cbd24ac602c4cd016723117d6a7e73b75"},
+]
+
+[package.dependencies]
+anyio = ">=3.4.0,<5"
+typing-extensions = {version = ">=3.10.0", markers = "python_version < \"3.10\""}
+
+[package.extras]
+full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart", "pyyaml"]
+
+[[package]]
+name = "sympy"
+version = "1.11.1"
+description = "Computer algebra system (CAS) in Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "sympy-1.11.1-py3-none-any.whl", hash = "sha256:938f984ee2b1e8eae8a07b884c8b7a1146010040fccddc6539c54f401c8f6fcf"},
+ {file = "sympy-1.11.1.tar.gz", hash = "sha256:e32380dce63cb7c0108ed525570092fd45168bdae2faa17e528221ef72e88658"},
+]
+
+[package.dependencies]
+mpmath = ">=0.19"
+
+[[package]]
+name = "tabulate"
+version = "0.9.0"
+description = "Pretty-print tabular data"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"},
+ {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"},
+]
+
+[package.extras]
+widechars = ["wcwidth"]
+
+[[package]]
+name = "tensorboard"
+version = "2.12.1"
+description = "TensorBoard lets you watch Tensors Flow"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+ {file = "tensorboard-2.12.1-py3-none-any.whl", hash = "sha256:58f1c2a25b4829b9c48d2b1ec951dedc9325dcd1ea4b0f601d241d2887d0ed65"},
+]
+
+[package.dependencies]
+absl-py = ">=0.4"
+google-auth = ">=1.6.3,<3"
+google-auth-oauthlib = ">=0.5,<1.1"
+grpcio = ">=1.48.2"
+markdown = ">=2.6.8"
+numpy = ">=1.12.0"
+protobuf = ">=3.19.6"
+requests = ">=2.21.0,<3"
+setuptools = ">=41.0.0"
+tensorboard-data-server = ">=0.7.0,<0.8.0"
+tensorboard-plugin-wit = ">=1.6.0"
+werkzeug = ">=1.0.1"
+wheel = ">=0.26"
+
+[[package]]
+name = "tensorboard-data-server"
+version = "0.7.0"
+description = "Fast data loading for TensorBoard"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "tensorboard_data_server-0.7.0-py3-none-any.whl", hash = "sha256:753d4214799b31da7b6d93837959abebbc6afa86e69eacf1e9a317a48daa31eb"},
+ {file = "tensorboard_data_server-0.7.0-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:eb7fa518737944dbf4f0cf83c2e40a7ac346bf91be2e6a0215de98be74e85454"},
+ {file = "tensorboard_data_server-0.7.0-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64aa1be7c23e80b1a42c13b686eb0875bb70f5e755f4d2b8de5c1d880cf2267f"},
+]
+
+[[package]]
+name = "tensorboard-plugin-wit"
+version = "1.8.1"
+description = "What-If Tool TensorBoard plugin."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "tensorboard_plugin_wit-1.8.1-py3-none-any.whl", hash = "sha256:ff26bdd583d155aa951ee3b152b3d0cffae8005dc697f72b44a8e8c2a77a8cbe"},
+]
+
+[[package]]
+name = "tensorboardx"
+version = "2.6"
+description = "TensorBoardX lets you watch Tensors Flow without Tensorflow"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "tensorboardX-2.6-py2.py3-none-any.whl", hash = "sha256:24a7cd076488de1e9d15ef25371b8ebf90c4f8f622af2477c611198f03f4a606"},
+ {file = "tensorboardX-2.6.tar.gz", hash = "sha256:d4c036964dd2deb075a1909832b276daa383eab3f9db519ad90b99f5aea06b0c"},
+]
+
+[package.dependencies]
+numpy = "*"
+packaging = "*"
+protobuf = ">=3.8.0,<4"
+
+[[package]]
+name = "threadpoolctl"
+version = "3.1.0"
+description = "threadpoolctl"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "threadpoolctl-3.1.0-py3-none-any.whl", hash = "sha256:8b99adda265feb6773280df41eece7b2e6561b772d21ffd52e372f999024907b"},
+ {file = "threadpoolctl-3.1.0.tar.gz", hash = "sha256:a335baacfaa4400ae1f0d8e3a58d6674d2f8828e3716bb2802c44955ad391380"},
+]
+
+[[package]]
+name = "toolz"
+version = "0.12.0"
+description = "List processing tools and functional utilities"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+files = [
+ {file = "toolz-0.12.0-py3-none-any.whl", hash = "sha256:2059bd4148deb1884bb0eb770a3cde70e7f954cfbbdc2285f1f2de01fd21eb6f"},
+ {file = "toolz-0.12.0.tar.gz", hash = "sha256:88c570861c440ee3f2f6037c4654613228ff40c93a6c25e0eba70d17282c6194"},
+]
+
+[[package]]
+name = "torch"
+version = "2.0.0"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+category = "main"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+ {file = "torch-2.0.0-1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:c9090bda7d2eeeecd74f51b721420dbeb44f838d4536cc1b284e879417e3064a"},
+ {file = "torch-2.0.0-1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:bd42db2a48a20574d2c33489e120e9f32789c4dc13c514b0c44272972d14a2d7"},
+ {file = "torch-2.0.0-1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:8969aa8375bcbc0c2993e7ede0a7f889df9515f18b9b548433f412affed478d9"},
+ {file = "torch-2.0.0-1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:ab2da16567cb55b67ae39e32d520d68ec736191d88ac79526ca5874754c32203"},
+ {file = "torch-2.0.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:7a9319a67294ef02459a19738bbfa8727bb5307b822dadd708bc2ccf6c901aca"},
+ {file = "torch-2.0.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:9f01fe1f6263f31bd04e1757946fd63ad531ae37f28bb2dbf66f5c826ee089f4"},
+ {file = "torch-2.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:527f4ae68df7b8301ee6b1158ca56350282ea633686537b30dbb5d7b4a52622a"},
+ {file = "torch-2.0.0-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:ce9b5a49bd513dff7950a5a07d6e26594dd51989cee05ba388b03e8e366fd5d5"},
+ {file = "torch-2.0.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:53e1c33c6896583cdb9a583693e22e99266444c4a43392dddc562640d39e542b"},
+ {file = "torch-2.0.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:09651bff72e439d004c991f15add0c397c66f98ab36fe60d5514b44e4da722e8"},
+ {file = "torch-2.0.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:d439aec349c98f12819e8564b8c54008e4613dd4428582af0e6e14c24ca85870"},
+ {file = "torch-2.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:2802f84f021907deee7e9470ed10c0e78af7457ac9a08a6cd7d55adef835fede"},
+ {file = "torch-2.0.0-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:01858620f25f25e7a9ec4b547ff38e5e27c92d38ec4ccba9cfbfb31d7071ed9c"},
+ {file = "torch-2.0.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:9a2e53b5783ef5896a6af338b36d782f28e83c8ddfc2ac44b67b066d9d76f498"},
+ {file = "torch-2.0.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:ec5fff2447663e369682838ff0f82187b4d846057ef4d119a8dea7772a0b17dd"},
+ {file = "torch-2.0.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:11b0384fe3c18c01b8fc5992e70fc519cde65e44c51cc87be1838c1803daf42f"},
+ {file = "torch-2.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:e54846aa63855298cfb1195487f032e413e7ac9cbfa978fda32354cc39551475"},
+ {file = "torch-2.0.0-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:cc788cbbbbc6eb4c90e52c550efd067586c2693092cf367c135b34893a64ae78"},
+ {file = "torch-2.0.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:d292640f0fd72b7a31b2a6e3b635eb5065fcbedd4478f9cad1a1e7a9ec861d35"},
+ {file = "torch-2.0.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:6befaad784004b7af357e3d87fa0863c1f642866291f12a4c2af2de435e8ac5c"},
+ {file = "torch-2.0.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:a83b26bd6ae36fbf5fee3d56973d9816e2002e8a3b7d9205531167c28aaa38a7"},
+ {file = "torch-2.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:c7e67195e1c3e33da53954b026e89a8e1ff3bc1aeb9eb32b677172d4a9b5dcbf"},
+ {file = "torch-2.0.0-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:6e0b97beb037a165669c312591f242382e9109a240e20054d5a5782d9236cad0"},
+ {file = "torch-2.0.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:297a4919aff1c0f98a58ebe969200f71350a1d4d4f986dbfd60c02ffce780e99"},
+]
+
+[package.dependencies]
+filelock = "*"
+jinja2 = "*"
+networkx = "*"
+nvidia-cublas-cu11 = {version = "11.10.3.66", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu11 = {version = "11.7.101", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu11 = {version = "11.7.99", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu11 = {version = "11.7.99", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cudnn-cu11 = {version = "8.5.0.96", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cufft-cu11 = {version = "10.9.0.58", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu11 = {version = "10.2.10.91", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu11 = {version = "11.4.0.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu11 = {version = "11.7.4.91", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu11 = {version = "2.14.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu11 = {version = "11.7.91", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+sympy = "*"
+triton = {version = "2.0.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+typing-extensions = "*"
+
+[package.extras]
+opt-einsum = ["opt-einsum (>=3.3)"]
+
+[[package]]
+name = "torchaudio"
+version = "2.0.1"
+description = "An audio package for PyTorch"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "torchaudio-2.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b5d21ebbb55e7040d418d5062b0e882f9660d68b477b38fd436fa6c92ccbb52a"},
+ {file = "torchaudio-2.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6dbcd93b29d71a2f500f36a34ea5e467f510f773da85322098e6bdd8c9dc9948"},
+ {file = "torchaudio-2.0.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:5fdaba10ff06d098d603d9eb8d2ff541c3f3fe28ba178a78787190cec0d5187f"},
+ {file = "torchaudio-2.0.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:6419199c773c5045c594ff950d5e5dbbfa6c830892ec09721d4ed8704b702bfd"},
+ {file = "torchaudio-2.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:a5c81e480e5dcdcba065af1e3e31678ac29518991f00260094d37a39e63d76e5"},
+ {file = "torchaudio-2.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e2a047675493c0aa258fec621ef40e8b01abe3d8dbc872152e4b5998418aa3c5"},
+ {file = "torchaudio-2.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:91a28e587f708a03320eddbcc4a7dd1ad7150b3d4846b6c1557d85cc89a8d06c"},
+ {file = "torchaudio-2.0.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:ba7740d98f601218ff667598ab3d9dab5f326878374fcb52d656f4ff033b9e96"},
+ {file = "torchaudio-2.0.1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:f401b192921c8b77cc5e478ede589b256dba463f1cee91172ecb376fea45a288"},
+ {file = "torchaudio-2.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:0ef6754cf75ca5fd5117cb6243a6cf33552d67e9af0075aa6954b2c34bbf1036"},
+ {file = "torchaudio-2.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:022ca1baa4bb819b78343bd47b57ff6dc6f9fc19fa4ef269946aadf7e62db3c0"},
+ {file = "torchaudio-2.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a153ad5cdb62de8ec9fd1360a0d080bbaf39d578ae04e788db211571e675b7e0"},
+ {file = "torchaudio-2.0.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:aa7897774ab4156d0b72f7078b823ebc1371ee24c50df965447782889552367a"},
+ {file = "torchaudio-2.0.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:48d133593cddfe0424a350b566d54065bf6fe7469654de7add2f11b3ef03c5d9"},
+ {file = "torchaudio-2.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:ac65eb067feee435debba81adfe8337fa007a06de6508c0d80261c5562b6d098"},
+ {file = "torchaudio-2.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e3c6c8f9ea9f0e2df7a0b9375b0dcf955906e38fc12fab542b72a861564af8e7"},
+ {file = "torchaudio-2.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1d0cf0779a334ec1861e9fa28bceb66a633c42e8f6b3322e2e37ff9f20d0ae81"},
+ {file = "torchaudio-2.0.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:ab7acd2b5d351a2c65e4d935bb90b9256382bed93df57ee177bdbbe31c3cc984"},
+ {file = "torchaudio-2.0.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:77b953fd7278773269a9477315b8998ae7e5011cc4b2907e0df18162327482f1"},
+ {file = "torchaudio-2.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:c01bcea9d4c4a6616452e6cbd44d55913d8e6dee58191b925f35d46a2bf6e71b"},
+]
+
+[package.dependencies]
+torch = "2.0.0"
+
+[[package]]
+name = "torchgen"
+version = "0.0.1"
+description = "Ready to use implementations of state-of-the-art generative models in PyTorch"
+category = "main"
+optional = false
+python-versions = ">=3.7, <4"
+files = [
+ {file = "torchgen-0.0.1-py3-none-any.whl", hash = "sha256:78d02b5e4ea0231ce46b4262564a05a9cb2047fcfcdcf4a4ab56230a0f21be66"},
+]
+
+[[package]]
+name = "tornado"
+version = "6.3.2"
+description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed."
+category = "main"
+optional = false
+python-versions = ">= 3.8"
+files = [
+ {file = "tornado-6.3.2-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:c367ab6c0393d71171123ca5515c61ff62fe09024fa6bf299cd1339dc9456829"},
+ {file = "tornado-6.3.2-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:b46a6ab20f5c7c1cb949c72c1994a4585d2eaa0be4853f50a03b5031e964fc7c"},
+ {file = "tornado-6.3.2-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c2de14066c4a38b4ecbbcd55c5cc4b5340eb04f1c5e81da7451ef555859c833f"},
+ {file = "tornado-6.3.2-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:05615096845cf50a895026f749195bf0b10b8909f9be672f50b0fe69cba368e4"},
+ {file = "tornado-6.3.2-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5b17b1cf5f8354efa3d37c6e28fdfd9c1c1e5122f2cb56dac121ac61baa47cbe"},
+ {file = "tornado-6.3.2-cp38-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:29e71c847a35f6e10ca3b5c2990a52ce38b233019d8e858b755ea6ce4dcdd19d"},
+ {file = "tornado-6.3.2-cp38-abi3-musllinux_1_1_i686.whl", hash = "sha256:834ae7540ad3a83199a8da8f9f2d383e3c3d5130a328889e4cc991acc81e87a0"},
+ {file = "tornado-6.3.2-cp38-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:6a0848f1aea0d196a7c4f6772197cbe2abc4266f836b0aac76947872cd29b411"},
+ {file = "tornado-6.3.2-cp38-abi3-win32.whl", hash = "sha256:7efcbcc30b7c654eb6a8c9c9da787a851c18f8ccd4a5a3a95b05c7accfa068d2"},
+ {file = "tornado-6.3.2-cp38-abi3-win_amd64.whl", hash = "sha256:0c325e66c8123c606eea33084976c832aa4e766b7dff8aedd7587ea44a604cdf"},
+ {file = "tornado-6.3.2.tar.gz", hash = "sha256:4b927c4f19b71e627b13f3db2324e4ae660527143f9e1f2e2fb404f3a187e2ba"},
+]
+
+[[package]]
+name = "tqdm"
+version = "4.65.0"
+description = "Fast, Extensible Progress Meter"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "tqdm-4.65.0-py3-none-any.whl", hash = "sha256:c4f53a17fe37e132815abceec022631be8ffe1b9381c2e6e30aa70edc99e9671"},
+ {file = "tqdm-4.65.0.tar.gz", hash = "sha256:1871fb68a86b8fb3b59ca4cdd3dcccbc7e6d613eeed31f4c332531977b89beb5"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["py-make (>=0.1.0)", "twine", "wheel"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[[package]]
+name = "traitlets"
+version = "5.9.0"
+description = "Traitlets Python configuration system"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "traitlets-5.9.0-py3-none-any.whl", hash = "sha256:9e6ec080259b9a5940c797d58b613b5e31441c2257b87c2e795c5228ae80d2d8"},
+ {file = "traitlets-5.9.0.tar.gz", hash = "sha256:f6cde21a9c68cf756af02035f72d5a723bf607e862e7be33ece505abf4a3bad9"},
+]
+
+[package.extras]
+docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"]
+test = ["argcomplete (>=2.0)", "pre-commit", "pytest", "pytest-mock"]
+
+[[package]]
+name = "triton"
+version = "2.0.0"
+description = "A language and compiler for custom Deep Learning operations"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+ {file = "triton-2.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:38806ee9663f4b0f7cd64790e96c579374089e58f49aac4a6608121aa55e2505"},
+ {file = "triton-2.0.0-1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:226941c7b8595219ddef59a1fdb821e8c744289a132415ddd584facedeb475b1"},
+ {file = "triton-2.0.0-1-cp36-cp36m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4c9fc8c89874bc48eb7e7b2107a9b8d2c0bf139778637be5bfccb09191685cfd"},
+ {file = "triton-2.0.0-1-cp37-cp37m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d2684b6a60b9f174f447f36f933e9a45f31db96cb723723ecd2dcfd1c57b778b"},
+ {file = "triton-2.0.0-1-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9d4978298b74fcf59a75fe71e535c092b023088933b2f1df933ec32615e4beef"},
+ {file = "triton-2.0.0-1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:74f118c12b437fb2ca25e1a04759173b517582fcf4c7be11913316c764213656"},
+ {file = "triton-2.0.0-1-pp37-pypy37_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9618815a8da1d9157514f08f855d9e9ff92e329cd81c0305003eb9ec25cc5add"},
+ {file = "triton-2.0.0-1-pp38-pypy38_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1aca3303629cd3136375b82cb9921727f804e47ebee27b2677fef23005c3851a"},
+ {file = "triton-2.0.0-1-pp39-pypy39_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e3e13aa8b527c9b642e3a9defcc0fbd8ffbe1c80d8ac8c15a01692478dc64d8a"},
+ {file = "triton-2.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f05a7e64e4ca0565535e3d5d3405d7e49f9d308505bb7773d21fb26a4c008c2"},
+ {file = "triton-2.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb4b99ca3c6844066e516658541d876c28a5f6e3a852286bbc97ad57134827fd"},
+ {file = "triton-2.0.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47b4d70dc92fb40af553b4460492c31dc7d3a114a979ffb7a5cdedb7eb546c08"},
+ {file = "triton-2.0.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fedce6a381901b1547e0e7e1f2546e4f65dca6d91e2d8a7305a2d1f5551895be"},
+ {file = "triton-2.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75834f27926eab6c7f00ce73aaf1ab5bfb9bec6eb57ab7c0bfc0a23fac803b4c"},
+ {file = "triton-2.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0117722f8c2b579cd429e0bee80f7731ae05f63fe8e9414acd9a679885fcbf42"},
+ {file = "triton-2.0.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcd9be5d0c2e45d2b7e6ddc6da20112b6862d69741576f9c3dbaf941d745ecae"},
+ {file = "triton-2.0.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42a0d2c3fc2eab4ba71384f2e785fbfd47aa41ae05fa58bf12cb31dcbd0aeceb"},
+ {file = "triton-2.0.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52c47b72c72693198163ece9d90a721299e4fb3b8e24fd13141e384ad952724f"},
+]
+
+[package.dependencies]
+cmake = "*"
+filelock = "*"
+lit = "*"
+torch = "*"
+
+[package.extras]
+tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)"]
+tutorials = ["matplotlib", "pandas", "tabulate"]
+
+[[package]]
+name = "typing-extensions"
+version = "4.5.0"
+description = "Backported and Experimental Type Hints for Python 3.7+"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "typing_extensions-4.5.0-py3-none-any.whl", hash = "sha256:fb33085c39dd998ac16d1431ebc293a8b3eedd00fd4a32de0ff79002c19511b4"},
+ {file = "typing_extensions-4.5.0.tar.gz", hash = "sha256:5cb5f4a79139d699607b3ef622a1dedafa84e115ab0024e0d9c044a9479ca7cb"},
+]
+
+[[package]]
+name = "tzdata"
+version = "2023.3"
+description = "Provider of IANA time zone data"
+category = "main"
+optional = false
+python-versions = ">=2"
+files = [
+ {file = "tzdata-2023.3-py2.py3-none-any.whl", hash = "sha256:7e65763eef3120314099b6939b5546db7adce1e7d6f2e179e3df563c70511eda"},
+ {file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"},
+]
+
+[[package]]
+name = "uc-micro-py"
+version = "1.0.1"
+description = "Micro subset of unicode data files for linkify-it-py projects."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "uc-micro-py-1.0.1.tar.gz", hash = "sha256:b7cdf4ea79433043ddfe2c82210208f26f7962c0cfbe3bacb05ee879a7fdb596"},
+ {file = "uc_micro_py-1.0.1-py3-none-any.whl", hash = "sha256:316cfb8b6862a0f1d03540f0ae6e7b033ff1fa0ddbe60c12cbe0d4cec846a69f"},
+]
+
+[package.extras]
+test = ["coverage", "pytest", "pytest-cov"]
+
+[[package]]
+name = "urllib3"
+version = "1.26.15"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+files = [
+ {file = "urllib3-1.26.15-py2.py3-none-any.whl", hash = "sha256:aa751d169e23c7479ce47a0cb0da579e3ede798f994f5816a74e4f4500dcea42"},
+ {file = "urllib3-1.26.15.tar.gz", hash = "sha256:8a388717b9476f934a21484e8c8e61875ab60644d29b9b39e11e4b9dc1c6b305"},
+]
+
+[package.extras]
+brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[[package]]
+name = "uvicorn"
+version = "0.21.1"
+description = "The lightning-fast ASGI server."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "uvicorn-0.21.1-py3-none-any.whl", hash = "sha256:e47cac98a6da10cd41e6fd036d472c6f58ede6c5dbee3dbee3ef7a100ed97742"},
+ {file = "uvicorn-0.21.1.tar.gz", hash = "sha256:0fac9cb342ba099e0d582966005f3fdba5b0290579fed4a6266dc702ca7bb032"},
+]
+
+[package.dependencies]
+click = ">=7.0"
+h11 = ">=0.8"
+
+[package.extras]
+standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+
+[[package]]
+name = "websockets"
+version = "11.0"
+description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "websockets-11.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:269e3547877a6ca55f62acdf291b256b01bc3469535e892af36afd3e17de284a"},
+ {file = "websockets-11.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:70a4e03d2416c1dad16ccfab97c975192337c6481b07167c90221f1926893e1e"},
+ {file = "websockets-11.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4100dc8566ea3b9c0528dee73284be524ab053aebd77e3fc7439a90e0d57745b"},
+ {file = "websockets-11.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a8e0505c556b2b48078291b300d930f2fb8ba81d1e36379b637c060cfa561ae4"},
+ {file = "websockets-11.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1d5bc68cec8269b4b52ab6d1d8690f56dba35f7bcb83a5487518406300f81cf1"},
+ {file = "websockets-11.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:067ac1f6153fc5218afc4563491dcbdb7384895cfc588a0afee962ca77fe0b58"},
+ {file = "websockets-11.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:910c84c0cfe4f872905b6ebe1866c579582070331abcb7a58621935eca95c18a"},
+ {file = "websockets-11.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:df0f7769450ca67a53182f917910e2b0b6dd3f8268f88cbfe54ee6be96812889"},
+ {file = "websockets-11.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fe23605f5c351773b6fb82fcf680549980d63e126fab5213ed875686c0cec25d"},
+ {file = "websockets-11.0-cp310-cp310-win32.whl", hash = "sha256:eb2e7cd654a05c36fccf726385c64a0e1027997d05ba0859f4d84c3d87db1623"},
+ {file = "websockets-11.0-cp310-cp310-win_amd64.whl", hash = "sha256:fb26c333751a1e3805ecc416a85dcfa3657676b185acd515fd6992f0cea898ef"},
+ {file = "websockets-11.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b4a939963bae1055f14976ef2cf53e797c1997f8835ca9cf23060afc3e7d6718"},
+ {file = "websockets-11.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d7fc189fb632f8b31af8a5b32105919662a1bbaac20912320482415b7fed9c96"},
+ {file = "websockets-11.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6e3cfc890f1326c95fd7d4cc50f2bd496d3f014fb2da36b4525a10f226be565d"},
+ {file = "websockets-11.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9093f4c72c23ed5e475970c6a37e77c4f3a8856223421b9eb405b9fb2170629f"},
+ {file = "websockets-11.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5c56547f97bc76293522ccfcfbdde12442420f1a2c0218ff45d733a0030046df"},
+ {file = "websockets-11.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffb406b4449d4fa41ebc47faa3b9153a082f6fe0e4a0891f596a5ddb69fdeccd"},
+ {file = "websockets-11.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:8fad76be2c5e36fb3620ad507ac8004e9f358f5c4a9a1b756dbe7918d58884a0"},
+ {file = "websockets-11.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:17eb1988d320e2f1f20e4a3523f1068a0bb08318ab123962fc99fd90c90ab0d6"},
+ {file = "websockets-11.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9873288db9c673a2ba9c0f7b59a130576c50fc75f3336a706fff686009c41631"},
+ {file = "websockets-11.0-cp311-cp311-win32.whl", hash = "sha256:cf4ef6343478bf63098d3060fe06baf54d9c011b4b1b05e65e7957091cc87ef4"},
+ {file = "websockets-11.0-cp311-cp311-win_amd64.whl", hash = "sha256:713cd5fc1fd40436495c90a259274e1a4a39416c65447a256434941ddaf2f424"},
+ {file = "websockets-11.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:649ddddcbafd318d427b843425c92b1c035660c32507645c472c77356226cf07"},
+ {file = "websockets-11.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:564c53d84b95da527e96778f2cc873ef186038924abee601f9e8f12ebda9ad46"},
+ {file = "websockets-11.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66d8df2db9801063e4093efe01458b1705c9f76382ad32617c005eeeb201a730"},
+ {file = "websockets-11.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bbcd876ed166a82d250fcf012b729315489e9d653cb659c2e013c19daba2eb8f"},
+ {file = "websockets-11.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:cb00963b49d343210ebbdbe69a35004fbecad73da2158e83d481cd2a6716cf19"},
+ {file = "websockets-11.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:3d6f7c2f822e439f47f3492ee3e48c87c7d134d619a42c6dba1a318504501bfb"},
+ {file = "websockets-11.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c4b2ae9c0f1acec5d2f8000eb496eebb9db19055a63716ee166cf0694b945982"},
+ {file = "websockets-11.0-cp37-cp37m-win32.whl", hash = "sha256:2b363e0f9b4247a0c7482e22c70ef39fb3259a14f7c0791c9200b93145f60b4b"},
+ {file = "websockets-11.0-cp37-cp37m-win_amd64.whl", hash = "sha256:3d372c3426f165a0a22be9250526b1cd12e3556e80b4b2afaa6fd6649c99b086"},
+ {file = "websockets-11.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:7eb914d37e0574246c63b995f9ca8d7bb7c2f2d53a8d4e9b00200ea856aa43c4"},
+ {file = "websockets-11.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a8717a5f3a00cde308e2971064bd5fcb14e0cc08f8234b97f4eb92b505ea95d4"},
+ {file = "websockets-11.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a17151722349c4af221616cca2f28e79237738bfbc53e7155240e2a8a7cc02f4"},
+ {file = "websockets-11.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a4b60686d9b2ba500847c045595eb5887f4cca7102b4615773b6f490aa611107"},
+ {file = "websockets-11.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eededf25ef6b838e650eeeb1511804b82e9ece566fe6cdc11aa909d2992dcdaf"},
+ {file = "websockets-11.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7587f339f016f0e1b0b6f013e98c83e382c5929774f2b8234c1b2d3f01dd1339"},
+ {file = "websockets-11.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:26369646078e16e7364729ed3e3b1a4315ab1a22ca3c48b4e25dea48fcc1a881"},
+ {file = "websockets-11.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:92f51fbe87381ff76c1791dd44d599152b400f1adfa8453613f1ff6857200ee7"},
+ {file = "websockets-11.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b5bb04a77c326d727c0b986c37a76147916d79db95629267307d1be47788a020"},
+ {file = "websockets-11.0-cp38-cp38-win32.whl", hash = "sha256:50ac95111009178e58b9a25aa51702cdaad4ed843b98eb9b58d69b323ccb224e"},
+ {file = "websockets-11.0-cp38-cp38-win_amd64.whl", hash = "sha256:7a4076cd6a3678def988668fc4b1779da598e1e5c9fa26319af5499f00c23e1c"},
+ {file = "websockets-11.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:26559e8a385f71ce2a58f3bb1d005ddd3db7d3328ddbfbff1034f4039d46c4ec"},
+ {file = "websockets-11.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f10d283697dec8d91fa983eb8e217c9cac27bc1032057768129b89780009318e"},
+ {file = "websockets-11.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f74efe229e078bf5595e207e9a7b135ff37a10858263ed86be66003c4c98d47b"},
+ {file = "websockets-11.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f048c88bfcc5bf0e038630cfb970b2c479f913819fd9653db920eef3b105a2b1"},
+ {file = "websockets-11.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ceab6c1827fa14ad10c6b0806941d577b21d17012a3648787ac2b946182285b4"},
+ {file = "websockets-11.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:817227e23897808c4bb621da7f57b1f83ee18345bdc44f5c9c1bbd3a094a73f6"},
+ {file = "websockets-11.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6fdcc17348d8697c1f88bba38680cca94131f2a9db727a61fe067284e1e59e8d"},
+ {file = "websockets-11.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:8b21ad915b747075f29fe2fa5590111d98988d6730d2cd212acfe52bbe6a2545"},
+ {file = "websockets-11.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9ae401ad881d5329062b9b2d8160f0b2a147430974f2a3f32e6cedadddc2d634"},
+ {file = "websockets-11.0-cp39-cp39-win32.whl", hash = "sha256:ee84660927293f449760badfe010e06409edb99d72e1910e2e404d2eeff6990f"},
+ {file = "websockets-11.0-cp39-cp39-win_amd64.whl", hash = "sha256:2b4e704a9dac1faf4994e63dceae9e2f504913ff0f865bd3e5a097cbd5874a8f"},
+ {file = "websockets-11.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:c2d6429c9bcd70ed8126a1f9ca6069e4ab95c96a3cc141fc84ce02917f7b45ec"},
+ {file = "websockets-11.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ff3f67567862a853af2c0db362ede8249be50c576cd9eaf380736c6fce840414"},
+ {file = "websockets-11.0-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b86ce3d17bcc4b6556b2a2e1277beed74ff6b1de23f002f9763e9875e8ba361d"},
+ {file = "websockets-11.0-pp37-pypy37_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59c4b458cc09ea6470a5eee98b06ccaa84f2a193b92e337a879612614df0f8eb"},
+ {file = "websockets-11.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:e5e21aeb350906dfcff321bfa6c60541a1d05cadb6d431ecf9d6376365be60d4"},
+ {file = "websockets-11.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:8731189f6985b239a6c34a353c36b45cb3c9fed1c287fbcf7f61df9e4a7ac392"},
+ {file = "websockets-11.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ee3aa7660ae0d3a4e47517bb5a545b9a02ff7b9632a640f617e755990ef65f66"},
+ {file = "websockets-11.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:027aabfd053715ce0f5f6fc5107e5093e05b3c94fa555fb65375aa09cb845a66"},
+ {file = "websockets-11.0-pp38-pypy38_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e8c729aa179ef105f096cad12070aef230be9e2ae509eb47c3cdd9257213c14"},
+ {file = "websockets-11.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:ff607c6e16409ac83f1ae59cc96167fead577bc652e8dff48f7458ce082372ff"},
+ {file = "websockets-11.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ca3d7c08f472c40f28bb9fb99610d28dc97137612ab5308f80dac7ce79f87fe1"},
+ {file = "websockets-11.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f179deef8288dd8ec227d644ba5b711609093b634008643561f6d9c74938c3c"},
+ {file = "websockets-11.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:269d33f1573a31130da9afd63a2558f60131522d3fe86d0aa2d1612ad065d27c"},
+ {file = "websockets-11.0-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eb0b306c1180d0268341447982b415aca7c072c84b4a59688dbc1d7d2ec25df9"},
+ {file = "websockets-11.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:6ae209f11e433575e17d5d6e61a2f77ceda53b4bce07df55af614aa1d618e2e7"},
+ {file = "websockets-11.0-py3-none-any.whl", hash = "sha256:6ebd971b9b2c0aaa2188c472016e4dad93108b3db425a33ad584bdc41b22026d"},
+ {file = "websockets-11.0.tar.gz", hash = "sha256:19d638549c470f5fd3b67b52b2a08f2edba5a04e05323a706937e35f5f19d056"},
+]
+
+[[package]]
+name = "werkzeug"
+version = "2.2.3"
+description = "The comprehensive WSGI web application library."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "Werkzeug-2.2.3-py3-none-any.whl", hash = "sha256:56433961bc1f12533306c624f3be5e744389ac61d722175d543e1751285da612"},
+ {file = "Werkzeug-2.2.3.tar.gz", hash = "sha256:2e1ccc9417d4da358b9de6f174e3ac094391ea1d4fbef2d667865d819dfd0afe"},
+]
+
+[package.dependencies]
+MarkupSafe = ">=2.1.1"
+
+[package.extras]
+watchdog = ["watchdog"]
+
+[[package]]
+name = "wheel"
+version = "0.40.0"
+description = "A built-package format for Python"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "wheel-0.40.0-py3-none-any.whl", hash = "sha256:d236b20e7cb522daf2390fa84c55eea81c5c30190f90f29ae2ca1ad8355bf247"},
+ {file = "wheel-0.40.0.tar.gz", hash = "sha256:cd1196f3faee2b31968d626e1731c94f99cbdb67cf5a46e4f5656cbee7738873"},
+]
+
+[package.extras]
+test = ["pytest (>=6.0.0)"]
+
+[[package]]
+name = "yarl"
+version = "1.8.2"
+description = "Yet another URL library"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "yarl-1.8.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:bb81f753c815f6b8e2ddd2eef3c855cf7da193b82396ac013c661aaa6cc6b0a5"},
+ {file = "yarl-1.8.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:47d49ac96156f0928f002e2424299b2c91d9db73e08c4cd6742923a086f1c863"},
+ {file = "yarl-1.8.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3fc056e35fa6fba63248d93ff6e672c096f95f7836938241ebc8260e062832fe"},
+ {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:58a3c13d1c3005dbbac5c9f0d3210b60220a65a999b1833aa46bd6677c69b08e"},
+ {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:10b08293cda921157f1e7c2790999d903b3fd28cd5c208cf8826b3b508026996"},
+ {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:de986979bbd87272fe557e0a8fcb66fd40ae2ddfe28a8b1ce4eae22681728fef"},
+ {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c4fcfa71e2c6a3cb568cf81aadc12768b9995323186a10827beccf5fa23d4f8"},
+ {file = "yarl-1.8.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae4d7ff1049f36accde9e1ef7301912a751e5bae0a9d142459646114c70ecba6"},
+ {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:bf071f797aec5b96abfc735ab97da9fd8f8768b43ce2abd85356a3127909d146"},
+ {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:74dece2bfc60f0f70907c34b857ee98f2c6dd0f75185db133770cd67300d505f"},
+ {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:df60a94d332158b444301c7f569659c926168e4d4aad2cfbf4bce0e8fb8be826"},
+ {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:63243b21c6e28ec2375f932a10ce7eda65139b5b854c0f6b82ed945ba526bff3"},
+ {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:cfa2bbca929aa742b5084fd4663dd4b87c191c844326fcb21c3afd2d11497f80"},
+ {file = "yarl-1.8.2-cp310-cp310-win32.whl", hash = "sha256:b05df9ea7496df11b710081bd90ecc3a3db6adb4fee36f6a411e7bc91a18aa42"},
+ {file = "yarl-1.8.2-cp310-cp310-win_amd64.whl", hash = "sha256:24ad1d10c9db1953291f56b5fe76203977f1ed05f82d09ec97acb623a7976574"},
+ {file = "yarl-1.8.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2a1fca9588f360036242f379bfea2b8b44cae2721859b1c56d033adfd5893634"},
+ {file = "yarl-1.8.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f37db05c6051eff17bc832914fe46869f8849de5b92dc4a3466cd63095d23dfd"},
+ {file = "yarl-1.8.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:77e913b846a6b9c5f767b14dc1e759e5aff05502fe73079f6f4176359d832581"},
+ {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0978f29222e649c351b173da2b9b4665ad1feb8d1daa9d971eb90df08702668a"},
+ {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:388a45dc77198b2460eac0aca1efd6a7c09e976ee768b0d5109173e521a19daf"},
+ {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2305517e332a862ef75be8fad3606ea10108662bc6fe08509d5ca99503ac2aee"},
+ {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42430ff511571940d51e75cf42f1e4dbdded477e71c1b7a17f4da76c1da8ea76"},
+ {file = "yarl-1.8.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3150078118f62371375e1e69b13b48288e44f6691c1069340081c3fd12c94d5b"},
+ {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c15163b6125db87c8f53c98baa5e785782078fbd2dbeaa04c6141935eb6dab7a"},
+ {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:4d04acba75c72e6eb90745447d69f84e6c9056390f7a9724605ca9c56b4afcc6"},
+ {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e7fd20d6576c10306dea2d6a5765f46f0ac5d6f53436217913e952d19237efc4"},
+ {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:75c16b2a900b3536dfc7014905a128a2bea8fb01f9ee26d2d7d8db0a08e7cb2c"},
+ {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:6d88056a04860a98341a0cf53e950e3ac9f4e51d1b6f61a53b0609df342cc8b2"},
+ {file = "yarl-1.8.2-cp311-cp311-win32.whl", hash = "sha256:fb742dcdd5eec9f26b61224c23baea46c9055cf16f62475e11b9b15dfd5c117b"},
+ {file = "yarl-1.8.2-cp311-cp311-win_amd64.whl", hash = "sha256:8c46d3d89902c393a1d1e243ac847e0442d0196bbd81aecc94fcebbc2fd5857c"},
+ {file = "yarl-1.8.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:ceff9722e0df2e0a9e8a79c610842004fa54e5b309fe6d218e47cd52f791d7ef"},
+ {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f6b4aca43b602ba0f1459de647af954769919c4714706be36af670a5f44c9c1"},
+ {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1684a9bd9077e922300ecd48003ddae7a7474e0412bea38d4631443a91d61077"},
+ {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ebb78745273e51b9832ef90c0898501006670d6e059f2cdb0e999494eb1450c2"},
+ {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3adeef150d528ded2a8e734ebf9ae2e658f4c49bf413f5f157a470e17a4a2e89"},
+ {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:57a7c87927a468e5a1dc60c17caf9597161d66457a34273ab1760219953f7f4c"},
+ {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:efff27bd8cbe1f9bd127e7894942ccc20c857aa8b5a0327874f30201e5ce83d0"},
+ {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:a783cd344113cb88c5ff7ca32f1f16532a6f2142185147822187913eb989f739"},
+ {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:705227dccbe96ab02c7cb2c43e1228e2826e7ead880bb19ec94ef279e9555b5b"},
+ {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:34c09b43bd538bf6c4b891ecce94b6fa4f1f10663a8d4ca589a079a5018f6ed7"},
+ {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a48f4f7fea9a51098b02209d90297ac324241bf37ff6be6d2b0149ab2bd51b37"},
+ {file = "yarl-1.8.2-cp37-cp37m-win32.whl", hash = "sha256:0414fd91ce0b763d4eadb4456795b307a71524dbacd015c657bb2a39db2eab89"},
+ {file = "yarl-1.8.2-cp37-cp37m-win_amd64.whl", hash = "sha256:d881d152ae0007809c2c02e22aa534e702f12071e6b285e90945aa3c376463c5"},
+ {file = "yarl-1.8.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5df5e3d04101c1e5c3b1d69710b0574171cc02fddc4b23d1b2813e75f35a30b1"},
+ {file = "yarl-1.8.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7a66c506ec67eb3159eea5096acd05f5e788ceec7b96087d30c7d2865a243918"},
+ {file = "yarl-1.8.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2b4fa2606adf392051d990c3b3877d768771adc3faf2e117b9de7eb977741229"},
+ {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e21fb44e1eff06dd6ef971d4bdc611807d6bd3691223d9c01a18cec3677939e"},
+ {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:93202666046d9edadfe9f2e7bf5e0782ea0d497b6d63da322e541665d65a044e"},
+ {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fc77086ce244453e074e445104f0ecb27530d6fd3a46698e33f6c38951d5a0f1"},
+ {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64dd68a92cab699a233641f5929a40f02a4ede8c009068ca8aa1fe87b8c20ae3"},
+ {file = "yarl-1.8.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1b372aad2b5f81db66ee7ec085cbad72c4da660d994e8e590c997e9b01e44901"},
+ {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:e6f3515aafe0209dd17fb9bdd3b4e892963370b3de781f53e1746a521fb39fc0"},
+ {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:dfef7350ee369197106805e193d420b75467b6cceac646ea5ed3049fcc950a05"},
+ {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:728be34f70a190566d20aa13dc1f01dc44b6aa74580e10a3fb159691bc76909d"},
+ {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:ff205b58dc2929191f68162633d5e10e8044398d7a45265f90a0f1d51f85f72c"},
+ {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:baf211dcad448a87a0d9047dc8282d7de59473ade7d7fdf22150b1d23859f946"},
+ {file = "yarl-1.8.2-cp38-cp38-win32.whl", hash = "sha256:272b4f1599f1b621bf2aabe4e5b54f39a933971f4e7c9aa311d6d7dc06965165"},
+ {file = "yarl-1.8.2-cp38-cp38-win_amd64.whl", hash = "sha256:326dd1d3caf910cd26a26ccbfb84c03b608ba32499b5d6eeb09252c920bcbe4f"},
+ {file = "yarl-1.8.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f8ca8ad414c85bbc50f49c0a106f951613dfa5f948ab69c10ce9b128d368baf8"},
+ {file = "yarl-1.8.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:418857f837347e8aaef682679f41e36c24250097f9e2f315d39bae3a99a34cbf"},
+ {file = "yarl-1.8.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ae0eec05ab49e91a78700761777f284c2df119376e391db42c38ab46fd662b77"},
+ {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:009a028127e0a1755c38b03244c0bea9d5565630db9c4cf9572496e947137a87"},
+ {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3edac5d74bb3209c418805bda77f973117836e1de7c000e9755e572c1f7850d0"},
+ {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:da65c3f263729e47351261351b8679c6429151ef9649bba08ef2528ff2c423b2"},
+ {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ef8fb25e52663a1c85d608f6dd72e19bd390e2ecaf29c17fb08f730226e3a08"},
+ {file = "yarl-1.8.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bcd7bb1e5c45274af9a1dd7494d3c52b2be5e6bd8d7e49c612705fd45420b12d"},
+ {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:44ceac0450e648de86da8e42674f9b7077d763ea80c8ceb9d1c3e41f0f0a9951"},
+ {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:97209cc91189b48e7cfe777237c04af8e7cc51eb369004e061809bcdf4e55220"},
+ {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:48dd18adcf98ea9cd721a25313aef49d70d413a999d7d89df44f469edfb38a06"},
+ {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:e59399dda559688461762800d7fb34d9e8a6a7444fd76ec33220a926c8be1516"},
+ {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d617c241c8c3ad5c4e78a08429fa49e4b04bedfc507b34b4d8dceb83b4af3588"},
+ {file = "yarl-1.8.2-cp39-cp39-win32.whl", hash = "sha256:cb6d48d80a41f68de41212f3dfd1a9d9898d7841c8f7ce6696cf2fd9cb57ef83"},
+ {file = "yarl-1.8.2-cp39-cp39-win_amd64.whl", hash = "sha256:6604711362f2dbf7160df21c416f81fac0de6dbcf0b5445a2ef25478ecc4c778"},
+ {file = "yarl-1.8.2.tar.gz", hash = "sha256:49d43402c6e3013ad0978602bf6bf5328535c48d192304b91b97a3c6790b1562"},
+]
+
+[package.dependencies]
+idna = ">=2.0"
+multidict = ">=4.0"
+
+[[package]]
+name = "zipp"
+version = "3.15.0"
+description = "Backport of pathlib-compatible object wrapper for zip files"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "zipp-3.15.0-py3-none-any.whl", hash = "sha256:48904fc76a60e542af151aded95726c1a5c34ed43ab4134b597665c86d7ad556"},
+ {file = "zipp-3.15.0.tar.gz", hash = "sha256:112929ad649da941c23de50f356a2b5570c954b65150642bccdd66bf194d224b"},
+]
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+testing = ["big-O", "flake8 (<5)", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.8,<3.11"
+content-hash = "309a8ea8b898a89daf57e99dc285f7a36914aa7eb821b5a24253bc034277293e"
diff --git a/pretrained/.gitignore b/pretrained/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..d6b7ef32c8478a48c3994dcadc86837f4371184d
--- /dev/null
+++ b/pretrained/.gitignore
@@ -0,0 +1,2 @@
+*
+!.gitignore
diff --git a/pretrained_v2/.gitignore b/pretrained_v2/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..d6b7ef32c8478a48c3994dcadc86837f4371184d
--- /dev/null
+++ b/pretrained_v2/.gitignore
@@ -0,0 +1,2 @@
+*
+!.gitignore
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000000000000000000000000000000000000..2e9b8d3fd14d5edecc45d19d325e30869d7f1cef
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,61 @@
+[tool.poetry]
+name = "rvc-beta"
+version = "0.1.0"
+description = ""
+authors = ["lj1995"]
+license = "MIT"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+torch = "^2.0.0"
+torchaudio = "^2.0.1"
+Cython = "^0.29.34"
+gradio = "^3.24.1"
+future = "^0.18.3"
+pydub = "^0.25.1"
+soundfile = "^0.12.1"
+ffmpeg-python = "^0.2.0"
+tensorboardX = "^2.6"
+functorch = "^2.0.0"
+fairseq = "^0.12.2"
+faiss-cpu = "^1.7.2"
+Jinja2 = "^3.1.2"
+json5 = "^0.9.11"
+librosa = "0.9.2"
+llvmlite = "0.39.0"
+Markdown = "^3.4.3"
+matplotlib = "^3.7.1"
+matplotlib-inline = "^0.1.6"
+numba = "0.56.4"
+numpy = "1.23.5"
+scipy = "1.9.3"
+praat-parselmouth = "^0.4.3"
+Pillow = "9.3.0"
+pyworld = "^0.3.2"
+resampy = "^0.4.2"
+scikit-learn = "^1.2.2"
+starlette = "^0.27.0"
+tensorboard = "^2.12.1"
+tensorboard-data-server = "^0.7.0"
+tensorboard-plugin-wit = "^1.8.1"
+torchgen = "^0.0.1"
+tqdm = "^4.65.0"
+tornado = "^6.3"
+Werkzeug = "^2.2.3"
+uc-micro-py = "^1.0.1"
+sympy = "^1.11.1"
+tabulate = "^0.9.0"
+PyYAML = "^6.0"
+pyasn1 = "^0.4.8"
+pyasn1-modules = "^0.2.8"
+fsspec = "^2023.3.0"
+absl-py = "^1.4.0"
+audioread = "^3.0.0"
+uvicorn = "^0.21.1"
+colorama = "^0.4.6"
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
diff --git a/requirements-win-for-realtime_vc_gui.txt b/requirements-win-for-realtime_vc_gui.txt
new file mode 100644
index 0000000000000000000000000000000000000000..37ca23823fb800612369078bbb8908204442937a
--- /dev/null
+++ b/requirements-win-for-realtime_vc_gui.txt
@@ -0,0 +1,28 @@
+#1.Install torch from pytorch.org:
+#torch 2.0 with cuda 11.8
+#pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+#torch 1.11.0 with cuda 11.3
+#pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
+einops
+fairseq
+flask
+flask_cors
+gin
+gin_config
+librosa
+local_attention
+matplotlib
+praat-parselmouth
+pyworld
+PyYAML
+resampy
+scikit_learn
+scipy
+SoundFile
+tensorboard
+tqdm
+wave
+PySimpleGUI
+sounddevice
+gradio
+noisereduce
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..1f75ffda7ff000aa7b6b4d7d6d8426e06e59e2e7
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,42 @@
+joblib>=1.1.0
+numba==0.56.4
+numpy==1.23.5
+scipy==1.9.3
+librosa==0.9.1
+llvmlite==0.39.0
+fairseq==0.12.2
+faiss-cpu==1.7.3
+gradio
+Cython
+pydub>=0.25.1
+soundfile>=0.12.1
+ffmpeg-python>=0.2.0
+tensorboardX
+Jinja2>=3.1.2
+json5
+Markdown
+matplotlib>=3.7.0
+matplotlib-inline>=0.1.3
+praat-parselmouth>=0.4.2
+Pillow>=9.1.1
+resampy>=0.4.2
+scikit-learn
+starlette>=0.25.0
+tensorboard
+tqdm>=4.63.1
+tornado>=6.1
+Werkzeug>=2.2.3
+uc-micro-py>=1.0.1
+sympy>=1.11.1
+tabulate>=0.8.10
+PyYAML>=6.0
+pyasn1>=0.4.8
+pyasn1-modules>=0.2.8
+fsspec>=2022.11.0
+absl-py>=1.2.0
+audioread
+uvicorn>=0.21.1
+colorama>=0.4.5
+pyworld>=0.3.2
+httpx==0.23.0
+torchcrepe==0.0.20
diff --git a/slicer2.py b/slicer2.py
new file mode 100644
index 0000000000000000000000000000000000000000..5b29ee262aa54045e807be2cffeb41687499ba58
--- /dev/null
+++ b/slicer2.py
@@ -0,0 +1,260 @@
+import numpy as np
+
+
+# This function is obtained from librosa.
+def get_rms(
+ y,
+ frame_length=2048,
+ hop_length=512,
+ pad_mode="constant",
+):
+ padding = (int(frame_length // 2), int(frame_length // 2))
+ y = np.pad(y, padding, mode=pad_mode)
+
+ axis = -1
+ # put our new within-frame axis at the end for now
+ out_strides = y.strides + tuple([y.strides[axis]])
+ # Reduce the shape on the framing axis
+ x_shape_trimmed = list(y.shape)
+ x_shape_trimmed[axis] -= frame_length - 1
+ out_shape = tuple(x_shape_trimmed) + tuple([frame_length])
+ xw = np.lib.stride_tricks.as_strided(y, shape=out_shape, strides=out_strides)
+ if axis < 0:
+ target_axis = axis - 1
+ else:
+ target_axis = axis + 1
+ xw = np.moveaxis(xw, -1, target_axis)
+ # Downsample along the target axis
+ slices = [slice(None)] * xw.ndim
+ slices[axis] = slice(0, None, hop_length)
+ x = xw[tuple(slices)]
+
+ # Calculate power
+ power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True)
+
+ return np.sqrt(power)
+
+
+class Slicer:
+ def __init__(
+ self,
+ sr: int,
+ threshold: float = -40.0,
+ min_length: int = 5000,
+ min_interval: int = 300,
+ hop_size: int = 20,
+ max_sil_kept: int = 5000,
+ ):
+ if not min_length >= min_interval >= hop_size:
+ raise ValueError(
+ "The following condition must be satisfied: min_length >= min_interval >= hop_size"
+ )
+ if not max_sil_kept >= hop_size:
+ raise ValueError(
+ "The following condition must be satisfied: max_sil_kept >= hop_size"
+ )
+ min_interval = sr * min_interval / 1000
+ self.threshold = 10 ** (threshold / 20.0)
+ self.hop_size = round(sr * hop_size / 1000)
+ self.win_size = min(round(min_interval), 4 * self.hop_size)
+ self.min_length = round(sr * min_length / 1000 / self.hop_size)
+ self.min_interval = round(min_interval / self.hop_size)
+ self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size)
+
+ def _apply_slice(self, waveform, begin, end):
+ if len(waveform.shape) > 1:
+ return waveform[
+ :, begin * self.hop_size : min(waveform.shape[1], end * self.hop_size)
+ ]
+ else:
+ return waveform[
+ begin * self.hop_size : min(waveform.shape[0], end * self.hop_size)
+ ]
+
+ # @timeit
+ def slice(self, waveform):
+ if len(waveform.shape) > 1:
+ samples = waveform.mean(axis=0)
+ else:
+ samples = waveform
+ if samples.shape[0] <= self.min_length:
+ return [waveform]
+ rms_list = get_rms(
+ y=samples, frame_length=self.win_size, hop_length=self.hop_size
+ ).squeeze(0)
+ sil_tags = []
+ silence_start = None
+ clip_start = 0
+ for i, rms in enumerate(rms_list):
+ # Keep looping while frame is silent.
+ if rms < self.threshold:
+ # Record start of silent frames.
+ if silence_start is None:
+ silence_start = i
+ continue
+ # Keep looping while frame is not silent and silence start has not been recorded.
+ if silence_start is None:
+ continue
+ # Clear recorded silence start if interval is not enough or clip is too short
+ is_leading_silence = silence_start == 0 and i > self.max_sil_kept
+ need_slice_middle = (
+ i - silence_start >= self.min_interval
+ and i - clip_start >= self.min_length
+ )
+ if not is_leading_silence and not need_slice_middle:
+ silence_start = None
+ continue
+ # Need slicing. Record the range of silent frames to be removed.
+ if i - silence_start <= self.max_sil_kept:
+ pos = rms_list[silence_start : i + 1].argmin() + silence_start
+ if silence_start == 0:
+ sil_tags.append((0, pos))
+ else:
+ sil_tags.append((pos, pos))
+ clip_start = pos
+ elif i - silence_start <= self.max_sil_kept * 2:
+ pos = rms_list[
+ i - self.max_sil_kept : silence_start + self.max_sil_kept + 1
+ ].argmin()
+ pos += i - self.max_sil_kept
+ pos_l = (
+ rms_list[
+ silence_start : silence_start + self.max_sil_kept + 1
+ ].argmin()
+ + silence_start
+ )
+ pos_r = (
+ rms_list[i - self.max_sil_kept : i + 1].argmin()
+ + i
+ - self.max_sil_kept
+ )
+ if silence_start == 0:
+ sil_tags.append((0, pos_r))
+ clip_start = pos_r
+ else:
+ sil_tags.append((min(pos_l, pos), max(pos_r, pos)))
+ clip_start = max(pos_r, pos)
+ else:
+ pos_l = (
+ rms_list[
+ silence_start : silence_start + self.max_sil_kept + 1
+ ].argmin()
+ + silence_start
+ )
+ pos_r = (
+ rms_list[i - self.max_sil_kept : i + 1].argmin()
+ + i
+ - self.max_sil_kept
+ )
+ if silence_start == 0:
+ sil_tags.append((0, pos_r))
+ else:
+ sil_tags.append((pos_l, pos_r))
+ clip_start = pos_r
+ silence_start = None
+ # Deal with trailing silence.
+ total_frames = rms_list.shape[0]
+ if (
+ silence_start is not None
+ and total_frames - silence_start >= self.min_interval
+ ):
+ silence_end = min(total_frames, silence_start + self.max_sil_kept)
+ pos = rms_list[silence_start : silence_end + 1].argmin() + silence_start
+ sil_tags.append((pos, total_frames + 1))
+ # Apply and return slices.
+ if len(sil_tags) == 0:
+ return [waveform]
+ else:
+ chunks = []
+ if sil_tags[0][0] > 0:
+ chunks.append(self._apply_slice(waveform, 0, sil_tags[0][0]))
+ for i in range(len(sil_tags) - 1):
+ chunks.append(
+ self._apply_slice(waveform, sil_tags[i][1], sil_tags[i + 1][0])
+ )
+ if sil_tags[-1][1] < total_frames:
+ chunks.append(
+ self._apply_slice(waveform, sil_tags[-1][1], total_frames)
+ )
+ return chunks
+
+
+def main():
+ import os.path
+ from argparse import ArgumentParser
+
+ import librosa
+ import soundfile
+
+ parser = ArgumentParser()
+ parser.add_argument("audio", type=str, help="The audio to be sliced")
+ parser.add_argument(
+ "--out", type=str, help="Output directory of the sliced audio clips"
+ )
+ parser.add_argument(
+ "--db_thresh",
+ type=float,
+ required=False,
+ default=-40,
+ help="The dB threshold for silence detection",
+ )
+ parser.add_argument(
+ "--min_length",
+ type=int,
+ required=False,
+ default=5000,
+ help="The minimum milliseconds required for each sliced audio clip",
+ )
+ parser.add_argument(
+ "--min_interval",
+ type=int,
+ required=False,
+ default=300,
+ help="The minimum milliseconds for a silence part to be sliced",
+ )
+ parser.add_argument(
+ "--hop_size",
+ type=int,
+ required=False,
+ default=10,
+ help="Frame length in milliseconds",
+ )
+ parser.add_argument(
+ "--max_sil_kept",
+ type=int,
+ required=False,
+ default=500,
+ help="The maximum silence length kept around the sliced clip, presented in milliseconds",
+ )
+ args = parser.parse_args()
+ out = args.out
+ if out is None:
+ out = os.path.dirname(os.path.abspath(args.audio))
+ audio, sr = librosa.load(args.audio, sr=None, mono=False)
+ slicer = Slicer(
+ sr=sr,
+ threshold=args.db_thresh,
+ min_length=args.min_length,
+ min_interval=args.min_interval,
+ hop_size=args.hop_size,
+ max_sil_kept=args.max_sil_kept,
+ )
+ chunks = slicer.slice(audio)
+ if not os.path.exists(out):
+ os.makedirs(out)
+ for i, chunk in enumerate(chunks):
+ if len(chunk.shape) > 1:
+ chunk = chunk.T
+ soundfile.write(
+ os.path.join(
+ out,
+ f"%s_%d.wav"
+ % (os.path.basename(args.audio).rsplit(".", maxsplit=1)[0], i),
+ ),
+ chunk,
+ sr,
+ )
+
+
+if __name__ == "__main__":
+ main()
diff --git a/train/cmd.txt b/train/cmd.txt
new file mode 100644
index 0000000000000000000000000000000000000000..e4b895e54fbcd4ffa5ba4ded7d0f37f04f67392f
--- /dev/null
+++ b/train/cmd.txt
@@ -0,0 +1 @@
+python train_nsf_sim_cache_sid.py -c configs/mi_mix40k_nsf_co256_cs1sid_ms2048.json -m ft-mi
\ No newline at end of file
diff --git a/train/data_utils.py b/train/data_utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..71c0eff1815469a52399dc90a093a2f8a29223eb
--- /dev/null
+++ b/train/data_utils.py
@@ -0,0 +1,512 @@
+import os, traceback
+import numpy as np
+import torch
+import torch.utils.data
+
+from mel_processing import spectrogram_torch
+from utils import load_wav_to_torch, load_filepaths_and_text
+
+
+class TextAudioLoaderMultiNSFsid(torch.utils.data.Dataset):
+ """
+ 1) loads audio, text pairs
+ 2) normalizes text and converts them to sequences of integers
+ 3) computes spectrograms from audio files.
+ """
+
+ def __init__(self, audiopaths_and_text, hparams):
+ self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
+ self.max_wav_value = hparams.max_wav_value
+ self.sampling_rate = hparams.sampling_rate
+ self.filter_length = hparams.filter_length
+ self.hop_length = hparams.hop_length
+ self.win_length = hparams.win_length
+ self.sampling_rate = hparams.sampling_rate
+ self.min_text_len = getattr(hparams, "min_text_len", 1)
+ self.max_text_len = getattr(hparams, "max_text_len", 5000)
+ self._filter()
+
+ def _filter(self):
+ """
+ Filter text & store spec lengths
+ """
+ # Store spectrogram lengths for Bucketing
+ # wav_length ~= file_size / (wav_channels * Bytes per dim) = file_size / (1 * 2)
+ # spec_length = wav_length // hop_length
+ audiopaths_and_text_new = []
+ lengths = []
+ for audiopath, text, pitch, pitchf, dv in self.audiopaths_and_text:
+ if self.min_text_len <= len(text) and len(text) <= self.max_text_len:
+ audiopaths_and_text_new.append([audiopath, text, pitch, pitchf, dv])
+ lengths.append(os.path.getsize(audiopath) // (3 * self.hop_length))
+ self.audiopaths_and_text = audiopaths_and_text_new
+ self.lengths = lengths
+
+ def get_sid(self, sid):
+ sid = torch.LongTensor([int(sid)])
+ return sid
+
+ def get_audio_text_pair(self, audiopath_and_text):
+ # separate filename and text
+ file = audiopath_and_text[0]
+ phone = audiopath_and_text[1]
+ pitch = audiopath_and_text[2]
+ pitchf = audiopath_and_text[3]
+ dv = audiopath_and_text[4]
+
+ phone, pitch, pitchf = self.get_labels(phone, pitch, pitchf)
+ spec, wav = self.get_audio(file)
+ dv = self.get_sid(dv)
+
+ len_phone = phone.size()[0]
+ len_spec = spec.size()[-1]
+ # print(123,phone.shape,pitch.shape,spec.shape)
+ if len_phone != len_spec:
+ len_min = min(len_phone, len_spec)
+ # amor
+ len_wav = len_min * self.hop_length
+
+ spec = spec[:, :len_min]
+ wav = wav[:, :len_wav]
+
+ phone = phone[:len_min, :]
+ pitch = pitch[:len_min]
+ pitchf = pitchf[:len_min]
+
+ return (spec, wav, phone, pitch, pitchf, dv)
+
+ def get_labels(self, phone, pitch, pitchf):
+ phone = np.load(phone)
+ phone = np.repeat(phone, 2, axis=0)
+ pitch = np.load(pitch)
+ pitchf = np.load(pitchf)
+ n_num = min(phone.shape[0], 900) # DistributedBucketSampler
+ # print(234,phone.shape,pitch.shape)
+ phone = phone[:n_num, :]
+ pitch = pitch[:n_num]
+ pitchf = pitchf[:n_num]
+ phone = torch.FloatTensor(phone)
+ pitch = torch.LongTensor(pitch)
+ pitchf = torch.FloatTensor(pitchf)
+ return phone, pitch, pitchf
+
+ def get_audio(self, filename):
+ audio, sampling_rate = load_wav_to_torch(filename)
+ if sampling_rate != self.sampling_rate:
+ raise ValueError(
+ "{} SR doesn't match target {} SR".format(
+ sampling_rate, self.sampling_rate
+ )
+ )
+ audio_norm = audio
+ # audio_norm = audio / self.max_wav_value
+ # audio_norm = audio / np.abs(audio).max()
+
+ audio_norm = audio_norm.unsqueeze(0)
+ spec_filename = filename.replace(".wav", ".spec.pt")
+ if os.path.exists(spec_filename):
+ try:
+ spec = torch.load(spec_filename)
+ except:
+ print(spec_filename, traceback.format_exc())
+ spec = spectrogram_torch(
+ audio_norm,
+ self.filter_length,
+ self.sampling_rate,
+ self.hop_length,
+ self.win_length,
+ center=False,
+ )
+ spec = torch.squeeze(spec, 0)
+ torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+ else:
+ spec = spectrogram_torch(
+ audio_norm,
+ self.filter_length,
+ self.sampling_rate,
+ self.hop_length,
+ self.win_length,
+ center=False,
+ )
+ spec = torch.squeeze(spec, 0)
+ torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+ return spec, audio_norm
+
+ def __getitem__(self, index):
+ return self.get_audio_text_pair(self.audiopaths_and_text[index])
+
+ def __len__(self):
+ return len(self.audiopaths_and_text)
+
+
+class TextAudioCollateMultiNSFsid:
+ """Zero-pads model inputs and targets"""
+
+ def __init__(self, return_ids=False):
+ self.return_ids = return_ids
+
+ def __call__(self, batch):
+ """Collate's training batch from normalized text and aduio
+ PARAMS
+ ------
+ batch: [text_normalized, spec_normalized, wav_normalized]
+ """
+ # Right zero-pad all one-hot text sequences to max input length
+ _, ids_sorted_decreasing = torch.sort(
+ torch.LongTensor([x[0].size(1) for x in batch]), dim=0, descending=True
+ )
+
+ max_spec_len = max([x[0].size(1) for x in batch])
+ max_wave_len = max([x[1].size(1) for x in batch])
+ spec_lengths = torch.LongTensor(len(batch))
+ wave_lengths = torch.LongTensor(len(batch))
+ spec_padded = torch.FloatTensor(len(batch), batch[0][0].size(0), max_spec_len)
+ wave_padded = torch.FloatTensor(len(batch), 1, max_wave_len)
+ spec_padded.zero_()
+ wave_padded.zero_()
+
+ max_phone_len = max([x[2].size(0) for x in batch])
+ phone_lengths = torch.LongTensor(len(batch))
+ phone_padded = torch.FloatTensor(
+ len(batch), max_phone_len, batch[0][2].shape[1]
+ ) # (spec, wav, phone, pitch)
+ pitch_padded = torch.LongTensor(len(batch), max_phone_len)
+ pitchf_padded = torch.FloatTensor(len(batch), max_phone_len)
+ phone_padded.zero_()
+ pitch_padded.zero_()
+ pitchf_padded.zero_()
+ # dv = torch.FloatTensor(len(batch), 256)#gin=256
+ sid = torch.LongTensor(len(batch))
+
+ for i in range(len(ids_sorted_decreasing)):
+ row = batch[ids_sorted_decreasing[i]]
+
+ spec = row[0]
+ spec_padded[i, :, : spec.size(1)] = spec
+ spec_lengths[i] = spec.size(1)
+
+ wave = row[1]
+ wave_padded[i, :, : wave.size(1)] = wave
+ wave_lengths[i] = wave.size(1)
+
+ phone = row[2]
+ phone_padded[i, : phone.size(0), :] = phone
+ phone_lengths[i] = phone.size(0)
+
+ pitch = row[3]
+ pitch_padded[i, : pitch.size(0)] = pitch
+ pitchf = row[4]
+ pitchf_padded[i, : pitchf.size(0)] = pitchf
+
+ # dv[i] = row[5]
+ sid[i] = row[5]
+
+ return (
+ phone_padded,
+ phone_lengths,
+ pitch_padded,
+ pitchf_padded,
+ spec_padded,
+ spec_lengths,
+ wave_padded,
+ wave_lengths,
+ # dv
+ sid,
+ )
+
+
+class TextAudioLoader(torch.utils.data.Dataset):
+ """
+ 1) loads audio, text pairs
+ 2) normalizes text and converts them to sequences of integers
+ 3) computes spectrograms from audio files.
+ """
+
+ def __init__(self, audiopaths_and_text, hparams):
+ self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
+ self.max_wav_value = hparams.max_wav_value
+ self.sampling_rate = hparams.sampling_rate
+ self.filter_length = hparams.filter_length
+ self.hop_length = hparams.hop_length
+ self.win_length = hparams.win_length
+ self.sampling_rate = hparams.sampling_rate
+ self.min_text_len = getattr(hparams, "min_text_len", 1)
+ self.max_text_len = getattr(hparams, "max_text_len", 5000)
+ self._filter()
+
+ def _filter(self):
+ """
+ Filter text & store spec lengths
+ """
+ # Store spectrogram lengths for Bucketing
+ # wav_length ~= file_size / (wav_channels * Bytes per dim) = file_size / (1 * 2)
+ # spec_length = wav_length // hop_length
+ audiopaths_and_text_new = []
+ lengths = []
+ for audiopath, text, dv in self.audiopaths_and_text:
+ if self.min_text_len <= len(text) and len(text) <= self.max_text_len:
+ audiopaths_and_text_new.append([audiopath, text, dv])
+ lengths.append(os.path.getsize(audiopath) // (3 * self.hop_length))
+ self.audiopaths_and_text = audiopaths_and_text_new
+ self.lengths = lengths
+
+ def get_sid(self, sid):
+ sid = torch.LongTensor([int(sid)])
+ return sid
+
+ def get_audio_text_pair(self, audiopath_and_text):
+ # separate filename and text
+ file = audiopath_and_text[0]
+ phone = audiopath_and_text[1]
+ dv = audiopath_and_text[2]
+
+ phone = self.get_labels(phone)
+ spec, wav = self.get_audio(file)
+ dv = self.get_sid(dv)
+
+ len_phone = phone.size()[0]
+ len_spec = spec.size()[-1]
+ if len_phone != len_spec:
+ len_min = min(len_phone, len_spec)
+ len_wav = len_min * self.hop_length
+ spec = spec[:, :len_min]
+ wav = wav[:, :len_wav]
+ phone = phone[:len_min, :]
+ return (spec, wav, phone, dv)
+
+ def get_labels(self, phone):
+ phone = np.load(phone)
+ phone = np.repeat(phone, 2, axis=0)
+ n_num = min(phone.shape[0], 900) # DistributedBucketSampler
+ phone = phone[:n_num, :]
+ phone = torch.FloatTensor(phone)
+ return phone
+
+ def get_audio(self, filename):
+ audio, sampling_rate = load_wav_to_torch(filename)
+ if sampling_rate != self.sampling_rate:
+ raise ValueError(
+ "{} SR doesn't match target {} SR".format(
+ sampling_rate, self.sampling_rate
+ )
+ )
+ audio_norm = audio
+ # audio_norm = audio / self.max_wav_value
+ # audio_norm = audio / np.abs(audio).max()
+
+ audio_norm = audio_norm.unsqueeze(0)
+ spec_filename = filename.replace(".wav", ".spec.pt")
+ if os.path.exists(spec_filename):
+ try:
+ spec = torch.load(spec_filename)
+ except:
+ print(spec_filename, traceback.format_exc())
+ spec = spectrogram_torch(
+ audio_norm,
+ self.filter_length,
+ self.sampling_rate,
+ self.hop_length,
+ self.win_length,
+ center=False,
+ )
+ spec = torch.squeeze(spec, 0)
+ torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+ else:
+ spec = spectrogram_torch(
+ audio_norm,
+ self.filter_length,
+ self.sampling_rate,
+ self.hop_length,
+ self.win_length,
+ center=False,
+ )
+ spec = torch.squeeze(spec, 0)
+ torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+ return spec, audio_norm
+
+ def __getitem__(self, index):
+ return self.get_audio_text_pair(self.audiopaths_and_text[index])
+
+ def __len__(self):
+ return len(self.audiopaths_and_text)
+
+
+class TextAudioCollate:
+ """Zero-pads model inputs and targets"""
+
+ def __init__(self, return_ids=False):
+ self.return_ids = return_ids
+
+ def __call__(self, batch):
+ """Collate's training batch from normalized text and aduio
+ PARAMS
+ ------
+ batch: [text_normalized, spec_normalized, wav_normalized]
+ """
+ # Right zero-pad all one-hot text sequences to max input length
+ _, ids_sorted_decreasing = torch.sort(
+ torch.LongTensor([x[0].size(1) for x in batch]), dim=0, descending=True
+ )
+
+ max_spec_len = max([x[0].size(1) for x in batch])
+ max_wave_len = max([x[1].size(1) for x in batch])
+ spec_lengths = torch.LongTensor(len(batch))
+ wave_lengths = torch.LongTensor(len(batch))
+ spec_padded = torch.FloatTensor(len(batch), batch[0][0].size(0), max_spec_len)
+ wave_padded = torch.FloatTensor(len(batch), 1, max_wave_len)
+ spec_padded.zero_()
+ wave_padded.zero_()
+
+ max_phone_len = max([x[2].size(0) for x in batch])
+ phone_lengths = torch.LongTensor(len(batch))
+ phone_padded = torch.FloatTensor(
+ len(batch), max_phone_len, batch[0][2].shape[1]
+ )
+ phone_padded.zero_()
+ sid = torch.LongTensor(len(batch))
+
+ for i in range(len(ids_sorted_decreasing)):
+ row = batch[ids_sorted_decreasing[i]]
+
+ spec = row[0]
+ spec_padded[i, :, : spec.size(1)] = spec
+ spec_lengths[i] = spec.size(1)
+
+ wave = row[1]
+ wave_padded[i, :, : wave.size(1)] = wave
+ wave_lengths[i] = wave.size(1)
+
+ phone = row[2]
+ phone_padded[i, : phone.size(0), :] = phone
+ phone_lengths[i] = phone.size(0)
+
+ sid[i] = row[3]
+
+ return (
+ phone_padded,
+ phone_lengths,
+ spec_padded,
+ spec_lengths,
+ wave_padded,
+ wave_lengths,
+ sid,
+ )
+
+
+class DistributedBucketSampler(torch.utils.data.distributed.DistributedSampler):
+ """
+ Maintain similar input lengths in a batch.
+ Length groups are specified by boundaries.
+ Ex) boundaries = [b1, b2, b3] -> any batch is included either {x | b1 < length(x) <=b2} or {x | b2 < length(x) <= b3}.
+
+ It removes samples which are not included in the boundaries.
+ Ex) boundaries = [b1, b2, b3] -> any x s.t. length(x) <= b1 or length(x) > b3 are discarded.
+ """
+
+ def __init__(
+ self,
+ dataset,
+ batch_size,
+ boundaries,
+ num_replicas=None,
+ rank=None,
+ shuffle=True,
+ ):
+ super().__init__(dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle)
+ self.lengths = dataset.lengths
+ self.batch_size = batch_size
+ self.boundaries = boundaries
+
+ self.buckets, self.num_samples_per_bucket = self._create_buckets()
+ self.total_size = sum(self.num_samples_per_bucket)
+ self.num_samples = self.total_size // self.num_replicas
+
+ def _create_buckets(self):
+ buckets = [[] for _ in range(len(self.boundaries) - 1)]
+ for i in range(len(self.lengths)):
+ length = self.lengths[i]
+ idx_bucket = self._bisect(length)
+ if idx_bucket != -1:
+ buckets[idx_bucket].append(i)
+
+ for i in range(len(buckets) - 1, -1, -1): #
+ if len(buckets[i]) == 0:
+ buckets.pop(i)
+ self.boundaries.pop(i + 1)
+
+ num_samples_per_bucket = []
+ for i in range(len(buckets)):
+ len_bucket = len(buckets[i])
+ total_batch_size = self.num_replicas * self.batch_size
+ rem = (
+ total_batch_size - (len_bucket % total_batch_size)
+ ) % total_batch_size
+ num_samples_per_bucket.append(len_bucket + rem)
+ return buckets, num_samples_per_bucket
+
+ def __iter__(self):
+ # deterministically shuffle based on epoch
+ g = torch.Generator()
+ g.manual_seed(self.epoch)
+
+ indices = []
+ if self.shuffle:
+ for bucket in self.buckets:
+ indices.append(torch.randperm(len(bucket), generator=g).tolist())
+ else:
+ for bucket in self.buckets:
+ indices.append(list(range(len(bucket))))
+
+ batches = []
+ for i in range(len(self.buckets)):
+ bucket = self.buckets[i]
+ len_bucket = len(bucket)
+ ids_bucket = indices[i]
+ num_samples_bucket = self.num_samples_per_bucket[i]
+
+ # add extra samples to make it evenly divisible
+ rem = num_samples_bucket - len_bucket
+ ids_bucket = (
+ ids_bucket
+ + ids_bucket * (rem // len_bucket)
+ + ids_bucket[: (rem % len_bucket)]
+ )
+
+ # subsample
+ ids_bucket = ids_bucket[self.rank :: self.num_replicas]
+
+ # batching
+ for j in range(len(ids_bucket) // self.batch_size):
+ batch = [
+ bucket[idx]
+ for idx in ids_bucket[
+ j * self.batch_size : (j + 1) * self.batch_size
+ ]
+ ]
+ batches.append(batch)
+
+ if self.shuffle:
+ batch_ids = torch.randperm(len(batches), generator=g).tolist()
+ batches = [batches[i] for i in batch_ids]
+ self.batches = batches
+
+ assert len(self.batches) * self.batch_size == self.num_samples
+ return iter(self.batches)
+
+ def _bisect(self, x, lo=0, hi=None):
+ if hi is None:
+ hi = len(self.boundaries) - 1
+
+ if hi > lo:
+ mid = (hi + lo) // 2
+ if self.boundaries[mid] < x and x <= self.boundaries[mid + 1]:
+ return mid
+ elif x <= self.boundaries[mid]:
+ return self._bisect(x, lo, mid)
+ else:
+ return self._bisect(x, mid + 1, hi)
+ else:
+ return -1
+
+ def __len__(self):
+ return self.num_samples // self.batch_size
diff --git a/train/losses.py b/train/losses.py
new file mode 100644
index 0000000000000000000000000000000000000000..b89038f14d06d7fae43628183e9ffb465e4edafd
--- /dev/null
+++ b/train/losses.py
@@ -0,0 +1,59 @@
+import torch
+from torch.nn import functional as F
+
+
+def feature_loss(fmap_r, fmap_g):
+ loss = 0
+ for dr, dg in zip(fmap_r, fmap_g):
+ for rl, gl in zip(dr, dg):
+ rl = rl.float().detach()
+ gl = gl.float()
+ loss += torch.mean(torch.abs(rl - gl))
+
+ return loss * 2
+
+
+def discriminator_loss(disc_real_outputs, disc_generated_outputs):
+ loss = 0
+ r_losses = []
+ g_losses = []
+ for dr, dg in zip(disc_real_outputs, disc_generated_outputs):
+ dr = dr.float()
+ dg = dg.float()
+ r_loss = torch.mean((1 - dr) ** 2)
+ g_loss = torch.mean(dg**2)
+ loss += r_loss + g_loss
+ r_losses.append(r_loss.item())
+ g_losses.append(g_loss.item())
+
+ return loss, r_losses, g_losses
+
+
+def generator_loss(disc_outputs):
+ loss = 0
+ gen_losses = []
+ for dg in disc_outputs:
+ dg = dg.float()
+ l = torch.mean((1 - dg) ** 2)
+ gen_losses.append(l)
+ loss += l
+
+ return loss, gen_losses
+
+
+def kl_loss(z_p, logs_q, m_p, logs_p, z_mask):
+ """
+ z_p, logs_q: [b, h, t_t]
+ m_p, logs_p: [b, h, t_t]
+ """
+ z_p = z_p.float()
+ logs_q = logs_q.float()
+ m_p = m_p.float()
+ logs_p = logs_p.float()
+ z_mask = z_mask.float()
+
+ kl = logs_p - logs_q - 0.5
+ kl += 0.5 * ((z_p - m_p) ** 2) * torch.exp(-2.0 * logs_p)
+ kl = torch.sum(kl * z_mask)
+ l = kl / torch.sum(z_mask)
+ return l
diff --git a/train/mel_processing.py b/train/mel_processing.py
new file mode 100644
index 0000000000000000000000000000000000000000..1c871ab6b838b174407d163c201df899cc3e2b14
--- /dev/null
+++ b/train/mel_processing.py
@@ -0,0 +1,130 @@
+import torch
+import torch.utils.data
+from librosa.filters import mel as librosa_mel_fn
+
+
+MAX_WAV_VALUE = 32768.0
+
+
+def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
+ """
+ PARAMS
+ ------
+ C: compression factor
+ """
+ return torch.log(torch.clamp(x, min=clip_val) * C)
+
+
+def dynamic_range_decompression_torch(x, C=1):
+ """
+ PARAMS
+ ------
+ C: compression factor used to compress
+ """
+ return torch.exp(x) / C
+
+
+def spectral_normalize_torch(magnitudes):
+ return dynamic_range_compression_torch(magnitudes)
+
+
+def spectral_de_normalize_torch(magnitudes):
+ return dynamic_range_decompression_torch(magnitudes)
+
+
+# Reusable banks
+mel_basis = {}
+hann_window = {}
+
+
+def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False):
+ """Convert waveform into Linear-frequency Linear-amplitude spectrogram.
+
+ Args:
+ y :: (B, T) - Audio waveforms
+ n_fft
+ sampling_rate
+ hop_size
+ win_size
+ center
+ Returns:
+ :: (B, Freq, Frame) - Linear-frequency Linear-amplitude spectrogram
+ """
+ # Validation
+ if torch.min(y) < -1.07:
+ print("min value is ", torch.min(y))
+ if torch.max(y) > 1.07:
+ print("max value is ", torch.max(y))
+
+ # Window - Cache if needed
+ global hann_window
+ dtype_device = str(y.dtype) + "_" + str(y.device)
+ wnsize_dtype_device = str(win_size) + "_" + dtype_device
+ if wnsize_dtype_device not in hann_window:
+ hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(
+ dtype=y.dtype, device=y.device
+ )
+
+ # Padding
+ y = torch.nn.functional.pad(
+ y.unsqueeze(1),
+ (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)),
+ mode="reflect",
+ )
+ y = y.squeeze(1)
+
+ # Complex Spectrogram :: (B, T) -> (B, Freq, Frame, RealComplex=2)
+ spec = torch.stft(
+ y,
+ n_fft,
+ hop_length=hop_size,
+ win_length=win_size,
+ window=hann_window[wnsize_dtype_device],
+ center=center,
+ pad_mode="reflect",
+ normalized=False,
+ onesided=True,
+ return_complex=False,
+ )
+
+ # Linear-frequency Linear-amplitude spectrogram :: (B, Freq, Frame, RealComplex=2) -> (B, Freq, Frame)
+ spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
+ return spec
+
+
+def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
+ # MelBasis - Cache if needed
+ global mel_basis
+ dtype_device = str(spec.dtype) + "_" + str(spec.device)
+ fmax_dtype_device = str(fmax) + "_" + dtype_device
+ if fmax_dtype_device not in mel_basis:
+ mel = librosa_mel_fn(
+ sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax
+ )
+ mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
+ dtype=spec.dtype, device=spec.device
+ )
+
+ # Mel-frequency Log-amplitude spectrogram :: (B, Freq=num_mels, Frame)
+ melspec = torch.matmul(mel_basis[fmax_dtype_device], spec)
+ melspec = spectral_normalize_torch(melspec)
+ return melspec
+
+
+def mel_spectrogram_torch(
+ y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False
+):
+ """Convert waveform into Mel-frequency Log-amplitude spectrogram.
+
+ Args:
+ y :: (B, T) - Waveforms
+ Returns:
+ melspec :: (B, Freq, Frame) - Mel-frequency Log-amplitude spectrogram
+ """
+ # Linear-frequency Linear-amplitude spectrogram :: (B, T) -> (B, Freq, Frame)
+ spec = spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center)
+
+ # Mel-frequency Log-amplitude spectrogram :: (B, Freq, Frame) -> (B, Freq=num_mels, Frame)
+ melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax)
+
+ return melspec
diff --git a/train/process_ckpt.py b/train/process_ckpt.py
new file mode 100644
index 0000000000000000000000000000000000000000..ac608aeb709e7821d30e920f69512511191b2cf1
--- /dev/null
+++ b/train/process_ckpt.py
@@ -0,0 +1,215 @@
+import torch, traceback, os, pdb, sys
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+from collections import OrderedDict
+from i18n import I18nAuto
+
+i18n = I18nAuto()
+
+
+def savee(ckpt, sr, if_f0, name, epoch, version, hps):
+ try:
+ opt = OrderedDict()
+ opt["weight"] = {}
+ for key in ckpt.keys():
+ if "enc_q" in key:
+ continue
+ opt["weight"][key] = ckpt[key].half()
+ opt["config"] = [
+ hps.data.filter_length // 2 + 1,
+ 32,
+ hps.model.inter_channels,
+ hps.model.hidden_channels,
+ hps.model.filter_channels,
+ hps.model.n_heads,
+ hps.model.n_layers,
+ hps.model.kernel_size,
+ hps.model.p_dropout,
+ hps.model.resblock,
+ hps.model.resblock_kernel_sizes,
+ hps.model.resblock_dilation_sizes,
+ hps.model.upsample_rates,
+ hps.model.upsample_initial_channel,
+ hps.model.upsample_kernel_sizes,
+ hps.model.spk_embed_dim,
+ hps.model.gin_channels,
+ hps.data.sampling_rate,
+ ]
+ opt["info"] = "%sepoch" % epoch
+ opt["sr"] = sr
+ opt["f0"] = if_f0
+ opt["version"] = version
+ torch.save(opt, "weights/%s.pth" % name)
+ return "Success."
+ except:
+ return traceback.format_exc()
+
+
+def show_info(path):
+ try:
+ a = torch.load(path, map_location="cpu")
+ return "模型信息:%s\n采样率:%s\n模型是否输入音高引导:%s\n版本:%s" % (
+ a.get("info", "None"),
+ a.get("sr", "None"),
+ a.get("f0", "None"),
+ a.get("version", "None"),
+ )
+ except:
+ return traceback.format_exc()
+
+
+def extract_small_model(path, name, sr, if_f0, info, version):
+ try:
+ ckpt = torch.load(path, map_location="cpu")
+ if "model" in ckpt:
+ ckpt = ckpt["model"]
+ opt = OrderedDict()
+ opt["weight"] = {}
+ for key in ckpt.keys():
+ if "enc_q" in key:
+ continue
+ opt["weight"][key] = ckpt[key].half()
+ if sr == "40k":
+ opt["config"] = [
+ 1025,
+ 32,
+ 192,
+ 192,
+ 768,
+ 2,
+ 6,
+ 3,
+ 0,
+ "1",
+ [3, 7, 11],
+ [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+ [10, 10, 2, 2],
+ 512,
+ [16, 16, 4, 4],
+ 109,
+ 256,
+ 40000,
+ ]
+ elif sr == "48k":
+ opt["config"] = [
+ 1025,
+ 32,
+ 192,
+ 192,
+ 768,
+ 2,
+ 6,
+ 3,
+ 0,
+ "1",
+ [3, 7, 11],
+ [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+ [10, 6, 2, 2, 2],
+ 512,
+ [16, 16, 4, 4, 4],
+ 109,
+ 256,
+ 48000,
+ ]
+ elif sr == "32k":
+ opt["config"] = [
+ 513,
+ 32,
+ 192,
+ 192,
+ 768,
+ 2,
+ 6,
+ 3,
+ 0,
+ "1",
+ [3, 7, 11],
+ [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+ [10, 4, 2, 2, 2],
+ 512,
+ [16, 16, 4, 4, 4],
+ 109,
+ 256,
+ 32000,
+ ]
+ if info == "":
+ info = "Extracted model."
+ opt["info"] = info
+ opt["version"] = version
+ opt["sr"] = sr
+ opt["f0"] = int(if_f0)
+ torch.save(opt, "weights/%s.pth" % name)
+ return "Success."
+ except:
+ return traceback.format_exc()
+
+
+def change_info(path, info, name):
+ try:
+ ckpt = torch.load(path, map_location="cpu")
+ ckpt["info"] = info
+ if name == "":
+ name = os.path.basename(path)
+ torch.save(ckpt, "weights/%s" % name)
+ return "Success."
+ except:
+ return traceback.format_exc()
+
+
+def merge(path1, path2, alpha1, sr, f0, info, name, version):
+ try:
+
+ def extract(ckpt):
+ a = ckpt["model"]
+ opt = OrderedDict()
+ opt["weight"] = {}
+ for key in a.keys():
+ if "enc_q" in key:
+ continue
+ opt["weight"][key] = a[key]
+ return opt
+
+ ckpt1 = torch.load(path1, map_location="cpu")
+ ckpt2 = torch.load(path2, map_location="cpu")
+ cfg = ckpt1["config"]
+ if "model" in ckpt1:
+ ckpt1 = extract(ckpt1)
+ else:
+ ckpt1 = ckpt1["weight"]
+ if "model" in ckpt2:
+ ckpt2 = extract(ckpt2)
+ else:
+ ckpt2 = ckpt2["weight"]
+ if sorted(list(ckpt1.keys())) != sorted(list(ckpt2.keys())):
+ return "Fail to merge the models. The model architectures are not the same."
+ opt = OrderedDict()
+ opt["weight"] = {}
+ for key in ckpt1.keys():
+ # try:
+ if key == "emb_g.weight" and ckpt1[key].shape != ckpt2[key].shape:
+ min_shape0 = min(ckpt1[key].shape[0], ckpt2[key].shape[0])
+ opt["weight"][key] = (
+ alpha1 * (ckpt1[key][:min_shape0].float())
+ + (1 - alpha1) * (ckpt2[key][:min_shape0].float())
+ ).half()
+ else:
+ opt["weight"][key] = (
+ alpha1 * (ckpt1[key].float()) + (1 - alpha1) * (ckpt2[key].float())
+ ).half()
+ # except:
+ # pdb.set_trace()
+ opt["config"] = cfg
+ """
+ if(sr=="40k"):opt["config"] = [1025, 32, 192, 192, 768, 2, 6, 3, 0, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10, 10, 2, 2], 512, [16, 16, 4, 4,4], 109, 256, 40000]
+ elif(sr=="48k"):opt["config"] = [1025, 32, 192, 192, 768, 2, 6, 3, 0, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10,6,2,2,2], 512, [16, 16, 4, 4], 109, 256, 48000]
+ elif(sr=="32k"):opt["config"] = [513, 32, 192, 192, 768, 2, 6, 3, 0, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10, 4, 2, 2, 2], 512, [16, 16, 4, 4,4], 109, 256, 32000]
+ """
+ opt["sr"] = sr
+ opt["f0"] = 1 if f0 == i18n("是") else 0
+ opt["version"] = version
+ opt["info"] = info
+ torch.save(opt, "weights/%s.pth" % name)
+ return "Success."
+ except:
+ return traceback.format_exc()
diff --git a/train/utils.py b/train/utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..b7d294a72e17972503719d91465b892f54f1efa0
--- /dev/null
+++ b/train/utils.py
@@ -0,0 +1,483 @@
+import os, traceback
+import glob
+import sys
+import argparse
+import logging
+import json
+import subprocess
+import numpy as np
+from scipy.io.wavfile import read
+import torch
+
+MATPLOTLIB_FLAG = False
+
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+logger = logging
+
+
+def load_checkpoint_d(checkpoint_path, combd, sbd, optimizer=None, load_opt=1):
+ assert os.path.isfile(checkpoint_path)
+ checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
+
+ ##################
+ def go(model, bkey):
+ saved_state_dict = checkpoint_dict[bkey]
+ if hasattr(model, "module"):
+ state_dict = model.module.state_dict()
+ else:
+ state_dict = model.state_dict()
+ new_state_dict = {}
+ for k, v in state_dict.items(): # 模型需要的shape
+ try:
+ new_state_dict[k] = saved_state_dict[k]
+ if saved_state_dict[k].shape != state_dict[k].shape:
+ print(
+ "shape-%s-mismatch|need-%s|get-%s"
+ % (k, state_dict[k].shape, saved_state_dict[k].shape)
+ ) #
+ raise KeyError
+ except:
+ # logger.info(traceback.format_exc())
+ logger.info("%s is not in the checkpoint" % k) # pretrain缺失的
+ new_state_dict[k] = v # 模型自带的随机值
+ if hasattr(model, "module"):
+ model.module.load_state_dict(new_state_dict, strict=False)
+ else:
+ model.load_state_dict(new_state_dict, strict=False)
+
+ go(combd, "combd")
+ go(sbd, "sbd")
+ #############
+ logger.info("Loaded model weights")
+
+ iteration = checkpoint_dict["iteration"]
+ learning_rate = checkpoint_dict["learning_rate"]
+ if (
+ optimizer is not None and load_opt == 1
+ ): ###加载不了，如果是空的的话，重新初始化，可能还会影响lr时间表的更新，因此在train文件最外围catch
+ # try:
+ optimizer.load_state_dict(checkpoint_dict["optimizer"])
+ # except:
+ # traceback.print_exc()
+ logger.info("Loaded checkpoint '{}' (epoch {})".format(checkpoint_path, iteration))
+ return model, optimizer, learning_rate, iteration
+
+
+# def load_checkpoint(checkpoint_path, model, optimizer=None):
+# assert os.path.isfile(checkpoint_path)
+# checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
+# iteration = checkpoint_dict['iteration']
+# learning_rate = checkpoint_dict['learning_rate']
+# if optimizer is not None:
+# optimizer.load_state_dict(checkpoint_dict['optimizer'])
+# # print(1111)
+# saved_state_dict = checkpoint_dict['model']
+# # print(1111)
+#
+# if hasattr(model, 'module'):
+# state_dict = model.module.state_dict()
+# else:
+# state_dict = model.state_dict()
+# new_state_dict= {}
+# for k, v in state_dict.items():
+# try:
+# new_state_dict[k] = saved_state_dict[k]
+# except:
+# logger.info("%s is not in the checkpoint" % k)
+# new_state_dict[k] = v
+# if hasattr(model, 'module'):
+# model.module.load_state_dict(new_state_dict)
+# else:
+# model.load_state_dict(new_state_dict)
+# logger.info("Loaded checkpoint '{}' (epoch {})" .format(
+# checkpoint_path, iteration))
+# return model, optimizer, learning_rate, iteration
+def load_checkpoint(checkpoint_path, model, optimizer=None, load_opt=1):
+ assert os.path.isfile(checkpoint_path)
+ checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
+
+ saved_state_dict = checkpoint_dict["model"]
+ if hasattr(model, "module"):
+ state_dict = model.module.state_dict()
+ else:
+ state_dict = model.state_dict()
+ new_state_dict = {}
+ for k, v in state_dict.items(): # 模型需要的shape
+ try:
+ new_state_dict[k] = saved_state_dict[k]
+ if saved_state_dict[k].shape != state_dict[k].shape:
+ print(
+ "shape-%s-mismatch|need-%s|get-%s"
+ % (k, state_dict[k].shape, saved_state_dict[k].shape)
+ ) #
+ raise KeyError
+ except:
+ # logger.info(traceback.format_exc())
+ logger.info("%s is not in the checkpoint" % k) # pretrain缺失的
+ new_state_dict[k] = v # 模型自带的随机值
+ if hasattr(model, "module"):
+ model.module.load_state_dict(new_state_dict, strict=False)
+ else:
+ model.load_state_dict(new_state_dict, strict=False)
+ logger.info("Loaded model weights")
+
+ iteration = checkpoint_dict["iteration"]
+ learning_rate = checkpoint_dict["learning_rate"]
+ if (
+ optimizer is not None and load_opt == 1
+ ): ###加载不了，如果是空的的话，重新初始化，可能还会影响lr时间表的更新，因此在train文件最外围catch
+ # try:
+ optimizer.load_state_dict(checkpoint_dict["optimizer"])
+ # except:
+ # traceback.print_exc()
+ logger.info("Loaded checkpoint '{}' (epoch {})".format(checkpoint_path, iteration))
+ return model, optimizer, learning_rate, iteration
+
+
+def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
+ logger.info(
+ "Saving model and optimizer state at epoch {} to {}".format(
+ iteration, checkpoint_path
+ )
+ )
+ if hasattr(model, "module"):
+ state_dict = model.module.state_dict()
+ else:
+ state_dict = model.state_dict()
+ torch.save(
+ {
+ "model": state_dict,
+ "iteration": iteration,
+ "optimizer": optimizer.state_dict(),
+ "learning_rate": learning_rate,
+ },
+ checkpoint_path,
+ )
+
+
+def save_checkpoint_d(combd, sbd, optimizer, learning_rate, iteration, checkpoint_path):
+ logger.info(
+ "Saving model and optimizer state at epoch {} to {}".format(
+ iteration, checkpoint_path
+ )
+ )
+ if hasattr(combd, "module"):
+ state_dict_combd = combd.module.state_dict()
+ else:
+ state_dict_combd = combd.state_dict()
+ if hasattr(sbd, "module"):
+ state_dict_sbd = sbd.module.state_dict()
+ else:
+ state_dict_sbd = sbd.state_dict()
+ torch.save(
+ {
+ "combd": state_dict_combd,
+ "sbd": state_dict_sbd,
+ "iteration": iteration,
+ "optimizer": optimizer.state_dict(),
+ "learning_rate": learning_rate,
+ },
+ checkpoint_path,
+ )
+
+
+def summarize(
+ writer,
+ global_step,
+ scalars={},
+ histograms={},
+ images={},
+ audios={},
+ audio_sampling_rate=22050,
+):
+ for k, v in scalars.items():
+ writer.add_scalar(k, v, global_step)
+ for k, v in histograms.items():
+ writer.add_histogram(k, v, global_step)
+ for k, v in images.items():
+ writer.add_image(k, v, global_step, dataformats="HWC")
+ for k, v in audios.items():
+ writer.add_audio(k, v, global_step, audio_sampling_rate)
+
+
+def latest_checkpoint_path(dir_path, regex="G_*.pth"):
+ f_list = glob.glob(os.path.join(dir_path, regex))
+ f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
+ x = f_list[-1]
+ print(x)
+ return x
+
+
+def plot_spectrogram_to_numpy(spectrogram):
+ global MATPLOTLIB_FLAG
+ if not MATPLOTLIB_FLAG:
+ import matplotlib
+
+ matplotlib.use("Agg")
+ MATPLOTLIB_FLAG = True
+ mpl_logger = logging.getLogger("matplotlib")
+ mpl_logger.setLevel(logging.WARNING)
+ import matplotlib.pylab as plt
+ import numpy as np
+
+ fig, ax = plt.subplots(figsize=(10, 2))
+ im = ax.imshow(spectrogram, aspect="auto", origin="lower", interpolation="none")
+ plt.colorbar(im, ax=ax)
+ plt.xlabel("Frames")
+ plt.ylabel("Channels")
+ plt.tight_layout()
+
+ fig.canvas.draw()
+ data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
+ data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
+ plt.close()
+ return data
+
+
+def plot_alignment_to_numpy(alignment, info=None):
+ global MATPLOTLIB_FLAG
+ if not MATPLOTLIB_FLAG:
+ import matplotlib
+
+ matplotlib.use("Agg")
+ MATPLOTLIB_FLAG = True
+ mpl_logger = logging.getLogger("matplotlib")
+ mpl_logger.setLevel(logging.WARNING)
+ import matplotlib.pylab as plt
+ import numpy as np
+
+ fig, ax = plt.subplots(figsize=(6, 4))
+ im = ax.imshow(
+ alignment.transpose(), aspect="auto", origin="lower", interpolation="none"
+ )
+ fig.colorbar(im, ax=ax)
+ xlabel = "Decoder timestep"
+ if info is not None:
+ xlabel += "\n\n" + info
+ plt.xlabel(xlabel)
+ plt.ylabel("Encoder timestep")
+ plt.tight_layout()
+
+ fig.canvas.draw()
+ data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
+ data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
+ plt.close()
+ return data
+
+
+def load_wav_to_torch(full_path):
+ sampling_rate, data = read(full_path)
+ return torch.FloatTensor(data.astype(np.float32)), sampling_rate
+
+
+def load_filepaths_and_text(filename, split="|"):
+ with open(filename, encoding="utf-8") as f:
+ filepaths_and_text = [line.strip().split(split) for line in f]
+ return filepaths_and_text
+
+
+def get_hparams(init=True):
+ """
+ todo:
+ 结尾七人组：
+ 保存频率、总epoch done
+ bs done
+ pretrainG、pretrainD done
+ 卡号：os.en["CUDA_VISIBLE_DEVICES"] done
+ if_latest done
+ 模型：if_f0 done
+ 采样率：自动选择config done
+ 是否缓存数据集进GPU:if_cache_data_in_gpu done
+
+ -m:
+ 自动决定training_files路径,改掉train_nsf_load_pretrain.py里的hps.data.training_files done
+ -c不要了
+ """
+ parser = argparse.ArgumentParser()
+ # parser.add_argument('-c', '--config', type=str, default="configs/40k.json",help='JSON file for configuration')
+ parser.add_argument(
+ "-se",
+ "--save_every_epoch",
+ type=int,
+ required=True,
+ help="checkpoint save frequency (epoch)",
+ )
+ parser.add_argument(
+ "-te", "--total_epoch", type=int, required=True, help="total_epoch"
+ )
+ parser.add_argument(
+ "-pg", "--pretrainG", type=str, default="", help="Pretrained Discriminator path"
+ )
+ parser.add_argument(
+ "-pd", "--pretrainD", type=str, default="", help="Pretrained Generator path"
+ )
+ parser.add_argument("-g", "--gpus", type=str, default="0", help="split by -")
+ parser.add_argument(
+ "-bs", "--batch_size", type=int, required=True, help="batch size"
+ )
+ parser.add_argument(
+ "-e", "--experiment_dir", type=str, required=True, help="experiment dir"
+ ) # -m
+ parser.add_argument(
+ "-sr", "--sample_rate", type=str, required=True, help="sample rate, 32k/40k/48k"
+ )
+ parser.add_argument(
+ "-sw",
+ "--save_every_weights",
+ type=str,
+ default="0",
+ help="save the extracted model in weights directory when saving checkpoints",
+ )
+ parser.add_argument(
+ "-v", "--version", type=str, required=True, help="model version"
+ )
+ parser.add_argument(
+ "-f0",
+ "--if_f0",
+ type=int,
+ required=True,
+ help="use f0 as one of the inputs of the model, 1 or 0",
+ )
+ parser.add_argument(
+ "-l",
+ "--if_latest",
+ type=int,
+ required=True,
+ help="if only save the latest G/D pth file, 1 or 0",
+ )
+ parser.add_argument(
+ "-c",
+ "--if_cache_data_in_gpu",
+ type=int,
+ required=True,
+ help="if caching the dataset in GPU memory, 1 or 0",
+ )
+
+ args = parser.parse_args()
+ name = args.experiment_dir
+ experiment_dir = os.path.join("./logs", args.experiment_dir)
+
+ if not os.path.exists(experiment_dir):
+ os.makedirs(experiment_dir)
+
+ config_path = "configs/%s.json" % args.sample_rate
+ config_save_path = os.path.join(experiment_dir, "config.json")
+ if init:
+ with open(config_path, "r") as f:
+ data = f.read()
+ with open(config_save_path, "w") as f:
+ f.write(data)
+ else:
+ with open(config_save_path, "r") as f:
+ data = f.read()
+ config = json.loads(data)
+
+ hparams = HParams(**config)
+ hparams.model_dir = hparams.experiment_dir = experiment_dir
+ hparams.save_every_epoch = args.save_every_epoch
+ hparams.name = name
+ hparams.total_epoch = args.total_epoch
+ hparams.pretrainG = args.pretrainG
+ hparams.pretrainD = args.pretrainD
+ hparams.version = args.version
+ hparams.gpus = args.gpus
+ hparams.train.batch_size = args.batch_size
+ hparams.sample_rate = args.sample_rate
+ hparams.if_f0 = args.if_f0
+ hparams.if_latest = args.if_latest
+ hparams.save_every_weights = args.save_every_weights
+ hparams.if_cache_data_in_gpu = args.if_cache_data_in_gpu
+ hparams.data.training_files = "%s/filelist.txt" % experiment_dir
+ return hparams
+
+
+def get_hparams_from_dir(model_dir):
+ config_save_path = os.path.join(model_dir, "config.json")
+ with open(config_save_path, "r") as f:
+ data = f.read()
+ config = json.loads(data)
+
+ hparams = HParams(**config)
+ hparams.model_dir = model_dir
+ return hparams
+
+
+def get_hparams_from_file(config_path):
+ with open(config_path, "r") as f:
+ data = f.read()
+ config = json.loads(data)
+
+ hparams = HParams(**config)
+ return hparams
+
+
+def check_git_hash(model_dir):
+ source_dir = os.path.dirname(os.path.realpath(__file__))
+ if not os.path.exists(os.path.join(source_dir, ".git")):
+ logger.warn(
+ "{} is not a git repository, therefore hash value comparison will be ignored.".format(
+ source_dir
+ )
+ )
+ return
+
+ cur_hash = subprocess.getoutput("git rev-parse HEAD")
+
+ path = os.path.join(model_dir, "githash")
+ if os.path.exists(path):
+ saved_hash = open(path).read()
+ if saved_hash != cur_hash:
+ logger.warn(
+ "git hash values are different. {}(saved) != {}(current)".format(
+ saved_hash[:8], cur_hash[:8]
+ )
+ )
+ else:
+ open(path, "w").write(cur_hash)
+
+
+def get_logger(model_dir, filename="train.log"):
+ global logger
+ logger = logging.getLogger(os.path.basename(model_dir))
+ logger.setLevel(logging.DEBUG)
+
+ formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
+ if not os.path.exists(model_dir):
+ os.makedirs(model_dir)
+ h = logging.FileHandler(os.path.join(model_dir, filename))
+ h.setLevel(logging.DEBUG)
+ h.setFormatter(formatter)
+ logger.addHandler(h)
+ return logger
+
+
+class HParams:
+ def __init__(self, **kwargs):
+ for k, v in kwargs.items():
+ if type(v) == dict:
+ v = HParams(**v)
+ self[k] = v
+
+ def keys(self):
+ return self.__dict__.keys()
+
+ def items(self):
+ return self.__dict__.items()
+
+ def values(self):
+ return self.__dict__.values()
+
+ def __len__(self):
+ return len(self.__dict__)
+
+ def __getitem__(self, key):
+ return getattr(self, key)
+
+ def __setitem__(self, key, value):
+ return setattr(self, key, value)
+
+ def __contains__(self, key):
+ return key in self.__dict__
+
+ def __repr__(self):
+ return self.__dict__.__repr__()
diff --git a/train_nsf_sim_cache_sid_load_pretrain.py b/train_nsf_sim_cache_sid_load_pretrain.py
new file mode 100644
index 0000000000000000000000000000000000000000..8dbc4c2bc86878b864baa625aad0a2f11cfd2b4f
--- /dev/null
+++ b/train_nsf_sim_cache_sid_load_pretrain.py
@@ -0,0 +1,591 @@
+import sys, os
+
+now_dir = os.getcwd()
+sys.path.append(os.path.join(now_dir))
+sys.path.append(os.path.join(now_dir, "train"))
+import utils
+import datetime
+
+hps = utils.get_hparams()
+os.environ["CUDA_VISIBLE_DEVICES"] = hps.gpus.replace("-", ",")
+n_gpus = len(hps.gpus.split("-"))
+from random import shuffle, randint
+import traceback, json, argparse, itertools, math, torch, pdb
+
+torch.backends.cudnn.deterministic = False
+torch.backends.cudnn.benchmark = False
+from torch import nn, optim
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torch.utils.tensorboard import SummaryWriter
+import torch.multiprocessing as mp
+import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel as DDP
+from torch.cuda.amp import autocast, GradScaler
+from infer_pack import commons
+from time import sleep
+from time import time as ttime
+from data_utils import (
+ TextAudioLoaderMultiNSFsid,
+ TextAudioLoader,
+ TextAudioCollateMultiNSFsid,
+ TextAudioCollate,
+ DistributedBucketSampler,
+)
+
+if hps.version == "v1":
+ from infer_pack.models import (
+ SynthesizerTrnMs256NSFsid as RVC_Model_f0,
+ SynthesizerTrnMs256NSFsid_nono as RVC_Model_nof0,
+ MultiPeriodDiscriminator,
+ )
+else:
+ from infer_pack.models import (
+ SynthesizerTrnMs768NSFsid as RVC_Model_f0,
+ SynthesizerTrnMs768NSFsid_nono as RVC_Model_nof0,
+ MultiPeriodDiscriminatorV2 as MultiPeriodDiscriminator,
+ )
+from losses import generator_loss, discriminator_loss, feature_loss, kl_loss
+from mel_processing import mel_spectrogram_torch, spec_to_mel_torch
+from process_ckpt import savee
+
+global_step = 0
+
+
+class EpochRecorder:
+ def __init__(self):
+ self.last_time = ttime()
+
+ def record(self):
+ now_time = ttime()
+ elapsed_time = now_time - self.last_time
+ self.last_time = now_time
+ elapsed_time_str = str(datetime.timedelta(seconds=elapsed_time))
+ current_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+ return f"[{current_time}] | ({elapsed_time_str})"
+
+
+def main():
+ n_gpus = torch.cuda.device_count()
+ if torch.cuda.is_available() == False and torch.backends.mps.is_available() == True:
+ n_gpus = 1
+ os.environ["MASTER_ADDR"] = "localhost"
+ os.environ["MASTER_PORT"] = str(randint(20000, 55555))
+ children = []
+ for i in range(n_gpus):
+ subproc = mp.Process(
+ target=run,
+ args=(
+ i,
+ n_gpus,
+ hps,
+ ),
+ )
+ children.append(subproc)
+ subproc.start()
+
+ for i in range(n_gpus):
+ children[i].join()
+
+
+def run(rank, n_gpus, hps):
+ global global_step
+ if rank == 0:
+ logger = utils.get_logger(hps.model_dir)
+ logger.info(hps)
+ # utils.check_git_hash(hps.model_dir)
+ writer = SummaryWriter(log_dir=hps.model_dir)
+ writer_eval = SummaryWriter(log_dir=os.path.join(hps.model_dir, "eval"))
+
+ dist.init_process_group(
+ backend="gloo", init_method="env://", world_size=n_gpus, rank=rank
+ )
+ torch.manual_seed(hps.train.seed)
+ if torch.cuda.is_available():
+ torch.cuda.set_device(rank)
+
+ if hps.if_f0 == 1:
+ train_dataset = TextAudioLoaderMultiNSFsid(hps.data.training_files, hps.data)
+ else:
+ train_dataset = TextAudioLoader(hps.data.training_files, hps.data)
+ train_sampler = DistributedBucketSampler(
+ train_dataset,
+ hps.train.batch_size * n_gpus,
+ # [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1200,1400], # 16s
+ [100, 200, 300, 400, 500, 600, 700, 800, 900], # 16s
+ num_replicas=n_gpus,
+ rank=rank,
+ shuffle=True,
+ )
+ # It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.
+ # num_workers=8 -> num_workers=4
+ if hps.if_f0 == 1:
+ collate_fn = TextAudioCollateMultiNSFsid()
+ else:
+ collate_fn = TextAudioCollate()
+ train_loader = DataLoader(
+ train_dataset,
+ num_workers=4,
+ shuffle=False,
+ pin_memory=True,
+ collate_fn=collate_fn,
+ batch_sampler=train_sampler,
+ persistent_workers=True,
+ prefetch_factor=8,
+ )
+ if hps.if_f0 == 1:
+ net_g = RVC_Model_f0(
+ hps.data.filter_length // 2 + 1,
+ hps.train.segment_size // hps.data.hop_length,
+ **hps.model,
+ is_half=hps.train.fp16_run,
+ sr=hps.sample_rate,
+ )
+ else:
+ net_g = RVC_Model_nof0(
+ hps.data.filter_length // 2 + 1,
+ hps.train.segment_size // hps.data.hop_length,
+ **hps.model,
+ is_half=hps.train.fp16_run,
+ )
+ if torch.cuda.is_available():
+ net_g = net_g.cuda(rank)
+ net_d = MultiPeriodDiscriminator(hps.model.use_spectral_norm)
+ if torch.cuda.is_available():
+ net_d = net_d.cuda(rank)
+ optim_g = torch.optim.AdamW(
+ net_g.parameters(),
+ hps.train.learning_rate,
+ betas=hps.train.betas,
+ eps=hps.train.eps,
+ )
+ optim_d = torch.optim.AdamW(
+ net_d.parameters(),
+ hps.train.learning_rate,
+ betas=hps.train.betas,
+ eps=hps.train.eps,
+ )
+ # net_g = DDP(net_g, device_ids=[rank], find_unused_parameters=True)
+ # net_d = DDP(net_d, device_ids=[rank], find_unused_parameters=True)
+ if torch.cuda.is_available():
+ net_g = DDP(net_g, device_ids=[rank])
+ net_d = DDP(net_d, device_ids=[rank])
+ else:
+ net_g = DDP(net_g)
+ net_d = DDP(net_d)
+
+ try: # 如果能加载自动resume
+ _, _, _, epoch_str = utils.load_checkpoint(
+ utils.latest_checkpoint_path(hps.model_dir, "D_*.pth"), net_d, optim_d
+ ) # D多半加载没事
+ if rank == 0:
+ logger.info("loaded D")
+ # _, _, _, epoch_str = utils.load_checkpoint(utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"), net_g, optim_g,load_opt=0)
+ _, _, _, epoch_str = utils.load_checkpoint(
+ utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"), net_g, optim_g
+ )
+ global_step = (epoch_str - 1) * len(train_loader)
+ # epoch_str = 1
+ # global_step = 0
+ except: # 如果首次不能加载，加载pretrain
+ # traceback.print_exc()
+ epoch_str = 1
+ global_step = 0
+ if rank == 0:
+ logger.info("loaded pretrained %s %s" % (hps.pretrainG, hps.pretrainD))
+ print(
+ net_g.module.load_state_dict(
+ torch.load(hps.pretrainG, map_location="cpu")["model"]
+ )
+ ) ##测试不加载优化器
+ print(
+ net_d.module.load_state_dict(
+ torch.load(hps.pretrainD, map_location="cpu")["model"]
+ )
+ )
+
+ scheduler_g = torch.optim.lr_scheduler.ExponentialLR(
+ optim_g, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
+ )
+ scheduler_d = torch.optim.lr_scheduler.ExponentialLR(
+ optim_d, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
+ )
+
+ scaler = GradScaler(enabled=hps.train.fp16_run)
+
+ cache = []
+ for epoch in range(epoch_str, hps.train.epochs + 1):
+ if rank == 0:
+ train_and_evaluate(
+ rank,
+ epoch,
+ hps,
+ [net_g, net_d],
+ [optim_g, optim_d],
+ [scheduler_g, scheduler_d],
+ scaler,
+ [train_loader, None],
+ logger,
+ [writer, writer_eval],
+ cache,
+ )
+ else:
+ train_and_evaluate(
+ rank,
+ epoch,
+ hps,
+ [net_g, net_d],
+ [optim_g, optim_d],
+ [scheduler_g, scheduler_d],
+ scaler,
+ [train_loader, None],
+ None,
+ None,
+ cache,
+ )
+ scheduler_g.step()
+ scheduler_d.step()
+
+
+def train_and_evaluate(
+ rank, epoch, hps, nets, optims, schedulers, scaler, loaders, logger, writers, cache
+):
+ net_g, net_d = nets
+ optim_g, optim_d = optims
+ train_loader, eval_loader = loaders
+ if writers is not None:
+ writer, writer_eval = writers
+
+ train_loader.batch_sampler.set_epoch(epoch)
+ global global_step
+
+ net_g.train()
+ net_d.train()
+
+ # Prepare data iterator
+ if hps.if_cache_data_in_gpu == True:
+ # Use Cache
+ data_iterator = cache
+ if cache == []:
+ # Make new cache
+ for batch_idx, info in enumerate(train_loader):
+ # Unpack
+ if hps.if_f0 == 1:
+ (
+ phone,
+ phone_lengths,
+ pitch,
+ pitchf,
+ spec,
+ spec_lengths,
+ wave,
+ wave_lengths,
+ sid,
+ ) = info
+ else:
+ (
+ phone,
+ phone_lengths,
+ spec,
+ spec_lengths,
+ wave,
+ wave_lengths,
+ sid,
+ ) = info
+ # Load on CUDA
+ if torch.cuda.is_available():
+ phone = phone.cuda(rank, non_blocking=True)
+ phone_lengths = phone_lengths.cuda(rank, non_blocking=True)
+ if hps.if_f0 == 1:
+ pitch = pitch.cuda(rank, non_blocking=True)
+ pitchf = pitchf.cuda(rank, non_blocking=True)
+ sid = sid.cuda(rank, non_blocking=True)
+ spec = spec.cuda(rank, non_blocking=True)
+ spec_lengths = spec_lengths.cuda(rank, non_blocking=True)
+ wave = wave.cuda(rank, non_blocking=True)
+ wave_lengths = wave_lengths.cuda(rank, non_blocking=True)
+ # Cache on list
+ if hps.if_f0 == 1:
+ cache.append(
+ (
+ batch_idx,
+ (
+ phone,
+ phone_lengths,
+ pitch,
+ pitchf,
+ spec,
+ spec_lengths,
+ wave,
+ wave_lengths,
+ sid,
+ ),
+ )
+ )
+ else:
+ cache.append(
+ (
+ batch_idx,
+ (
+ phone,
+ phone_lengths,
+ spec,
+ spec_lengths,
+ wave,
+ wave_lengths,
+ sid,
+ ),
+ )
+ )
+ else:
+ # Load shuffled cache
+ shuffle(cache)
+ else:
+ # Loader
+ data_iterator = enumerate(train_loader)
+
+ # Run steps
+ epoch_recorder = EpochRecorder()
+ for batch_idx, info in data_iterator:
+ # Data
+ ## Unpack
+ if hps.if_f0 == 1:
+ (
+ phone,
+ phone_lengths,
+ pitch,
+ pitchf,
+ spec,
+ spec_lengths,
+ wave,
+ wave_lengths,
+ sid,
+ ) = info
+ else:
+ phone, phone_lengths, spec, spec_lengths, wave, wave_lengths, sid = info
+ ## Load on CUDA
+ if (hps.if_cache_data_in_gpu == False) and torch.cuda.is_available():
+ phone = phone.cuda(rank, non_blocking=True)
+ phone_lengths = phone_lengths.cuda(rank, non_blocking=True)
+ if hps.if_f0 == 1:
+ pitch = pitch.cuda(rank, non_blocking=True)
+ pitchf = pitchf.cuda(rank, non_blocking=True)
+ sid = sid.cuda(rank, non_blocking=True)
+ spec = spec.cuda(rank, non_blocking=True)
+ spec_lengths = spec_lengths.cuda(rank, non_blocking=True)
+ wave = wave.cuda(rank, non_blocking=True)
+ # wave_lengths = wave_lengths.cuda(rank, non_blocking=True)
+
+ # Calculate
+ with autocast(enabled=hps.train.fp16_run):
+ if hps.if_f0 == 1:
+ (
+ y_hat,
+ ids_slice,
+ x_mask,
+ z_mask,
+ (z, z_p, m_p, logs_p, m_q, logs_q),
+ ) = net_g(phone, phone_lengths, pitch, pitchf, spec, spec_lengths, sid)
+ else:
+ (
+ y_hat,
+ ids_slice,
+ x_mask,
+ z_mask,
+ (z, z_p, m_p, logs_p, m_q, logs_q),
+ ) = net_g(phone, phone_lengths, spec, spec_lengths, sid)
+ mel = spec_to_mel_torch(
+ spec,
+ hps.data.filter_length,
+ hps.data.n_mel_channels,
+ hps.data.sampling_rate,
+ hps.data.mel_fmin,
+ hps.data.mel_fmax,
+ )
+ y_mel = commons.slice_segments(
+ mel, ids_slice, hps.train.segment_size // hps.data.hop_length
+ )
+ with autocast(enabled=False):
+ y_hat_mel = mel_spectrogram_torch(
+ y_hat.float().squeeze(1),
+ hps.data.filter_length,
+ hps.data.n_mel_channels,
+ hps.data.sampling_rate,
+ hps.data.hop_length,
+ hps.data.win_length,
+ hps.data.mel_fmin,
+ hps.data.mel_fmax,
+ )
+ if hps.train.fp16_run == True:
+ y_hat_mel = y_hat_mel.half()
+ wave = commons.slice_segments(
+ wave, ids_slice * hps.data.hop_length, hps.train.segment_size
+ ) # slice
+
+ # Discriminator
+ y_d_hat_r, y_d_hat_g, _, _ = net_d(wave, y_hat.detach())
+ with autocast(enabled=False):
+ loss_disc, losses_disc_r, losses_disc_g = discriminator_loss(
+ y_d_hat_r, y_d_hat_g
+ )
+ optim_d.zero_grad()
+ scaler.scale(loss_disc).backward()
+ scaler.unscale_(optim_d)
+ grad_norm_d = commons.clip_grad_value_(net_d.parameters(), None)
+ scaler.step(optim_d)
+
+ with autocast(enabled=hps.train.fp16_run):
+ # Generator
+ y_d_hat_r, y_d_hat_g, fmap_r, fmap_g = net_d(wave, y_hat)
+ with autocast(enabled=False):
+ loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
+ loss_kl = kl_loss(z_p, logs_q, m_p, logs_p, z_mask) * hps.train.c_kl
+ loss_fm = feature_loss(fmap_r, fmap_g)
+ loss_gen, losses_gen = generator_loss(y_d_hat_g)
+ loss_gen_all = loss_gen + loss_fm + loss_mel + loss_kl
+ optim_g.zero_grad()
+ scaler.scale(loss_gen_all).backward()
+ scaler.unscale_(optim_g)
+ grad_norm_g = commons.clip_grad_value_(net_g.parameters(), None)
+ scaler.step(optim_g)
+ scaler.update()
+
+ if rank == 0:
+ if global_step % hps.train.log_interval == 0:
+ lr = optim_g.param_groups[0]["lr"]
+ logger.info(
+ "Train Epoch: {} [{:.0f}%]".format(
+ epoch, 100.0 * batch_idx / len(train_loader)
+ )
+ )
+ # Amor For Tensorboard display
+ if loss_mel > 75:
+ loss_mel = 75
+ if loss_kl > 9:
+ loss_kl = 9
+
+ logger.info([global_step, lr])
+ logger.info(
+ f"loss_disc={loss_disc:.3f}, loss_gen={loss_gen:.3f}, loss_fm={loss_fm:.3f},loss_mel={loss_mel:.3f}, loss_kl={loss_kl:.3f}"
+ )
+ scalar_dict = {
+ "loss/g/total": loss_gen_all,
+ "loss/d/total": loss_disc,
+ "learning_rate": lr,
+ "grad_norm_d": grad_norm_d,
+ "grad_norm_g": grad_norm_g,
+ }
+ scalar_dict.update(
+ {
+ "loss/g/fm": loss_fm,
+ "loss/g/mel": loss_mel,
+ "loss/g/kl": loss_kl,
+ }
+ )
+
+ scalar_dict.update(
+ {"loss/g/{}".format(i): v for i, v in enumerate(losses_gen)}
+ )
+ scalar_dict.update(
+ {"loss/d_r/{}".format(i): v for i, v in enumerate(losses_disc_r)}
+ )
+ scalar_dict.update(
+ {"loss/d_g/{}".format(i): v for i, v in enumerate(losses_disc_g)}
+ )
+ image_dict = {
+ "slice/mel_org": utils.plot_spectrogram_to_numpy(
+ y_mel[0].data.cpu().numpy()
+ ),
+ "slice/mel_gen": utils.plot_spectrogram_to_numpy(
+ y_hat_mel[0].data.cpu().numpy()
+ ),
+ "all/mel": utils.plot_spectrogram_to_numpy(
+ mel[0].data.cpu().numpy()
+ ),
+ }
+ utils.summarize(
+ writer=writer,
+ global_step=global_step,
+ images=image_dict,
+ scalars=scalar_dict,
+ )
+ global_step += 1
+ # /Run steps
+
+ if epoch % hps.save_every_epoch == 0 and rank == 0:
+ if hps.if_latest == 0:
+ utils.save_checkpoint(
+ net_g,
+ optim_g,
+ hps.train.learning_rate,
+ epoch,
+ os.path.join(hps.model_dir, "G_{}.pth".format(global_step)),
+ )
+ utils.save_checkpoint(
+ net_d,
+ optim_d,
+ hps.train.learning_rate,
+ epoch,
+ os.path.join(hps.model_dir, "D_{}.pth".format(global_step)),
+ )
+ else:
+ utils.save_checkpoint(
+ net_g,
+ optim_g,
+ hps.train.learning_rate,
+ epoch,
+ os.path.join(hps.model_dir, "G_{}.pth".format(2333333)),
+ )
+ utils.save_checkpoint(
+ net_d,
+ optim_d,
+ hps.train.learning_rate,
+ epoch,
+ os.path.join(hps.model_dir, "D_{}.pth".format(2333333)),
+ )
+ if rank == 0 and hps.save_every_weights == "1":
+ if hasattr(net_g, "module"):
+ ckpt = net_g.module.state_dict()
+ else:
+ ckpt = net_g.state_dict()
+ logger.info(
+ "saving ckpt %s_e%s:%s"
+ % (
+ hps.name,
+ epoch,
+ savee(
+ ckpt,
+ hps.sample_rate,
+ hps.if_f0,
+ hps.name + "_e%s_s%s" % (epoch, global_step),
+ epoch,
+ hps.version,
+ hps,
+ ),
+ )
+ )
+
+ if rank == 0:
+ logger.info("====> Epoch: {} {}".format(epoch, epoch_recorder.record()))
+ if epoch >= hps.total_epoch and rank == 0:
+ logger.info("Training is done. The program is closed.")
+
+ if hasattr(net_g, "module"):
+ ckpt = net_g.module.state_dict()
+ else:
+ ckpt = net_g.state_dict()
+ logger.info(
+ "saving final ckpt:%s"
+ % (
+ savee(
+ ckpt, hps.sample_rate, hps.if_f0, hps.name, epoch, hps.version, hps
+ )
+ )
+ )
+ sleep(1)
+ os._exit(2333333)
+
+
+if __name__ == "__main__":
+ torch.multiprocessing.set_start_method("spawn")
+ main()
diff --git a/trainset_preprocess_pipeline_print.py b/trainset_preprocess_pipeline_print.py
new file mode 100644
index 0000000000000000000000000000000000000000..fe1643deefd8795ecea676aab981508650d65128
--- /dev/null
+++ b/trainset_preprocess_pipeline_print.py
@@ -0,0 +1,135 @@
+import sys, os, multiprocessing
+from scipy import signal
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+
+inp_root = sys.argv[1]
+sr = int(sys.argv[2])
+n_p = int(sys.argv[3])
+exp_dir = sys.argv[4]
+noparallel = sys.argv[5] == "True"
+import numpy as np, os, traceback
+from slicer2 import Slicer
+import librosa, traceback
+from scipy.io import wavfile
+import multiprocessing
+from my_utils import load_audio
+
+mutex = multiprocessing.Lock()
+f = open("%s/preprocess.log" % exp_dir, "a+")
+
+
+def println(strr):
+ mutex.acquire()
+ print(strr)
+ f.write("%s\n" % strr)
+ f.flush()
+ mutex.release()
+
+
+class PreProcess:
+ def __init__(self, sr, exp_dir):
+ self.slicer = Slicer(
+ sr=sr,
+ threshold=-42,
+ min_length=1500,
+ min_interval=400,
+ hop_size=15,
+ max_sil_kept=500,
+ )
+ self.sr = sr
+ self.bh, self.ah = signal.butter(N=5, Wn=48, btype="high", fs=self.sr)
+ self.per = 3.7
+ self.overlap = 0.3
+ self.tail = self.per + self.overlap
+ self.max = 0.9
+ self.alpha = 0.75
+ self.exp_dir = exp_dir
+ self.gt_wavs_dir = "%s/0_gt_wavs" % exp_dir
+ self.wavs16k_dir = "%s/1_16k_wavs" % exp_dir
+ os.makedirs(self.exp_dir, exist_ok=True)
+ os.makedirs(self.gt_wavs_dir, exist_ok=True)
+ os.makedirs(self.wavs16k_dir, exist_ok=True)
+
+ def norm_write(self, tmp_audio, idx0, idx1):
+ tmp_audio = (tmp_audio / np.abs(tmp_audio).max() * (self.max * self.alpha)) + (
+ 1 - self.alpha
+ ) * tmp_audio
+ wavfile.write(
+ "%s/%s_%s.wav" % (self.gt_wavs_dir, idx0, idx1),
+ self.sr,
+ tmp_audio.astype(np.float32),
+ )
+ tmp_audio = librosa.resample(
+ tmp_audio, orig_sr=self.sr, target_sr=16000
+ ) # , res_type="soxr_vhq"
+ wavfile.write(
+ "%s/%s_%s.wav" % (self.wavs16k_dir, idx0, idx1),
+ 16000,
+ tmp_audio.astype(np.float32),
+ )
+
+ def pipeline(self, path, idx0):
+ try:
+ audio = load_audio(path, self.sr)
+ # zero phased digital filter cause pre-ringing noise...
+ # audio = signal.filtfilt(self.bh, self.ah, audio)
+ audio = signal.lfilter(self.bh, self.ah, audio)
+
+ idx1 = 0
+ for audio in self.slicer.slice(audio):
+ i = 0
+ while 1:
+ start = int(self.sr * (self.per - self.overlap) * i)
+ i += 1
+ if len(audio[start:]) > self.tail * self.sr:
+ tmp_audio = audio[start : start + int(self.per * self.sr)]
+ self.norm_write(tmp_audio, idx0, idx1)
+ idx1 += 1
+ else:
+ tmp_audio = audio[start:]
+ idx1 += 1
+ break
+ self.norm_write(tmp_audio, idx0, idx1)
+ println("%s->Suc." % path)
+ except:
+ println("%s->%s" % (path, traceback.format_exc()))
+
+ def pipeline_mp(self, infos):
+ for path, idx0 in infos:
+ self.pipeline(path, idx0)
+
+ def pipeline_mp_inp_dir(self, inp_root, n_p):
+ try:
+ infos = [
+ ("%s/%s" % (inp_root, name), idx)
+ for idx, name in enumerate(sorted(list(os.listdir(inp_root))))
+ ]
+ if noparallel:
+ for i in range(n_p):
+ self.pipeline_mp(infos[i::n_p])
+ else:
+ ps = []
+ for i in range(n_p):
+ p = multiprocessing.Process(
+ target=self.pipeline_mp, args=(infos[i::n_p],)
+ )
+ ps.append(p)
+ p.start()
+ for i in range(n_p):
+ ps[i].join()
+ except:
+ println("Fail. %s" % traceback.format_exc())
+
+
+def preprocess_trainset(inp_root, sr, n_p, exp_dir):
+ pp = PreProcess(sr, exp_dir)
+ println("start preprocess")
+ println(sys.argv)
+ pp.pipeline_mp_inp_dir(inp_root, n_p)
+ println("end preprocess")
+
+
+if __name__ == "__main__":
+ preprocess_trainset(inp_root, sr, n_p, exp_dir)
diff --git a/uvr5_pack/lib_v5/dataset.py b/uvr5_pack/lib_v5/dataset.py
new file mode 100644
index 0000000000000000000000000000000000000000..ba0e45be1e8878da0b07eb2128e218bbd7de82ef
--- /dev/null
+++ b/uvr5_pack/lib_v5/dataset.py
@@ -0,0 +1,183 @@
+import os
+import random
+
+import numpy as np
+import torch
+import torch.utils.data
+from tqdm import tqdm
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class VocalRemoverValidationSet(torch.utils.data.Dataset):
+ def __init__(self, patch_list):
+ self.patch_list = patch_list
+
+ def __len__(self):
+ return len(self.patch_list)
+
+ def __getitem__(self, idx):
+ path = self.patch_list[idx]
+ data = np.load(path)
+
+ X, y = data["X"], data["y"]
+
+ X_mag = np.abs(X)
+ y_mag = np.abs(y)
+
+ return X_mag, y_mag
+
+
+def make_pair(mix_dir, inst_dir):
+ input_exts = [".wav", ".m4a", ".mp3", ".mp4", ".flac"]
+
+ X_list = sorted(
+ [
+ os.path.join(mix_dir, fname)
+ for fname in os.listdir(mix_dir)
+ if os.path.splitext(fname)[1] in input_exts
+ ]
+ )
+ y_list = sorted(
+ [
+ os.path.join(inst_dir, fname)
+ for fname in os.listdir(inst_dir)
+ if os.path.splitext(fname)[1] in input_exts
+ ]
+ )
+
+ filelist = list(zip(X_list, y_list))
+
+ return filelist
+
+
+def train_val_split(dataset_dir, split_mode, val_rate, val_filelist):
+ if split_mode == "random":
+ filelist = make_pair(
+ os.path.join(dataset_dir, "mixtures"),
+ os.path.join(dataset_dir, "instruments"),
+ )
+
+ random.shuffle(filelist)
+
+ if len(val_filelist) == 0:
+ val_size = int(len(filelist) * val_rate)
+ train_filelist = filelist[:-val_size]
+ val_filelist = filelist[-val_size:]
+ else:
+ train_filelist = [
+ pair for pair in filelist if list(pair) not in val_filelist
+ ]
+ elif split_mode == "subdirs":
+ if len(val_filelist) != 0:
+ raise ValueError(
+ "The `val_filelist` option is not available in `subdirs` mode"
+ )
+
+ train_filelist = make_pair(
+ os.path.join(dataset_dir, "training/mixtures"),
+ os.path.join(dataset_dir, "training/instruments"),
+ )
+
+ val_filelist = make_pair(
+ os.path.join(dataset_dir, "validation/mixtures"),
+ os.path.join(dataset_dir, "validation/instruments"),
+ )
+
+ return train_filelist, val_filelist
+
+
+def augment(X, y, reduction_rate, reduction_mask, mixup_rate, mixup_alpha):
+ perm = np.random.permutation(len(X))
+ for i, idx in enumerate(tqdm(perm)):
+ if np.random.uniform() < reduction_rate:
+ y[idx] = spec_utils.reduce_vocal_aggressively(
+ X[idx], y[idx], reduction_mask
+ )
+
+ if np.random.uniform() < 0.5:
+ # swap channel
+ X[idx] = X[idx, ::-1]
+ y[idx] = y[idx, ::-1]
+ if np.random.uniform() < 0.02:
+ # mono
+ X[idx] = X[idx].mean(axis=0, keepdims=True)
+ y[idx] = y[idx].mean(axis=0, keepdims=True)
+ if np.random.uniform() < 0.02:
+ # inst
+ X[idx] = y[idx]
+
+ if np.random.uniform() < mixup_rate and i < len(perm) - 1:
+ lam = np.random.beta(mixup_alpha, mixup_alpha)
+ X[idx] = lam * X[idx] + (1 - lam) * X[perm[i + 1]]
+ y[idx] = lam * y[idx] + (1 - lam) * y[perm[i + 1]]
+
+ return X, y
+
+
+def make_padding(width, cropsize, offset):
+ left = offset
+ roi_size = cropsize - left * 2
+ if roi_size == 0:
+ roi_size = cropsize
+ right = roi_size - (width % roi_size) + left
+
+ return left, right, roi_size
+
+
+def make_training_set(filelist, cropsize, patches, sr, hop_length, n_fft, offset):
+ len_dataset = patches * len(filelist)
+
+ X_dataset = np.zeros((len_dataset, 2, n_fft // 2 + 1, cropsize), dtype=np.complex64)
+ y_dataset = np.zeros((len_dataset, 2, n_fft // 2 + 1, cropsize), dtype=np.complex64)
+
+ for i, (X_path, y_path) in enumerate(tqdm(filelist)):
+ X, y = spec_utils.cache_or_load(X_path, y_path, sr, hop_length, n_fft)
+ coef = np.max([np.abs(X).max(), np.abs(y).max()])
+ X, y = X / coef, y / coef
+
+ l, r, roi_size = make_padding(X.shape[2], cropsize, offset)
+ X_pad = np.pad(X, ((0, 0), (0, 0), (l, r)), mode="constant")
+ y_pad = np.pad(y, ((0, 0), (0, 0), (l, r)), mode="constant")
+
+ starts = np.random.randint(0, X_pad.shape[2] - cropsize, patches)
+ ends = starts + cropsize
+ for j in range(patches):
+ idx = i * patches + j
+ X_dataset[idx] = X_pad[:, :, starts[j] : ends[j]]
+ y_dataset[idx] = y_pad[:, :, starts[j] : ends[j]]
+
+ return X_dataset, y_dataset
+
+
+def make_validation_set(filelist, cropsize, sr, hop_length, n_fft, offset):
+ patch_list = []
+ patch_dir = "cs{}_sr{}_hl{}_nf{}_of{}".format(
+ cropsize, sr, hop_length, n_fft, offset
+ )
+ os.makedirs(patch_dir, exist_ok=True)
+
+ for i, (X_path, y_path) in enumerate(tqdm(filelist)):
+ basename = os.path.splitext(os.path.basename(X_path))[0]
+
+ X, y = spec_utils.cache_or_load(X_path, y_path, sr, hop_length, n_fft)
+ coef = np.max([np.abs(X).max(), np.abs(y).max()])
+ X, y = X / coef, y / coef
+
+ l, r, roi_size = make_padding(X.shape[2], cropsize, offset)
+ X_pad = np.pad(X, ((0, 0), (0, 0), (l, r)), mode="constant")
+ y_pad = np.pad(y, ((0, 0), (0, 0), (l, r)), mode="constant")
+
+ len_dataset = int(np.ceil(X.shape[2] / roi_size))
+ for j in range(len_dataset):
+ outpath = os.path.join(patch_dir, "{}_p{}.npz".format(basename, j))
+ start = j * roi_size
+ if not os.path.exists(outpath):
+ np.savez(
+ outpath,
+ X=X_pad[:, :, start : start + cropsize],
+ y=y_pad[:, :, start : start + cropsize],
+ )
+ patch_list.append(outpath)
+
+ return VocalRemoverValidationSet(patch_list)
diff --git a/uvr5_pack/lib_v5/layers.py b/uvr5_pack/lib_v5/layers.py
new file mode 100644
index 0000000000000000000000000000000000000000..9835dc0f0dd66a7ef3517101180ec2c54eb6011d
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers.py
@@ -0,0 +1,118 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(SeperableConv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nin,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ groups=nin,
+ bias=False,
+ ),
+ nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+ def __call__(self, x):
+ skip = self.conv1(x)
+ h = self.conv2(skip)
+
+ return h, skip
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+ h = self.conv(x)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+ self.conv3 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = nn.Sequential(
+ Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+ )
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+ bottle = self.bottleneck(out)
+ return bottle
diff --git a/uvr5_pack/lib_v5/layers_123812KB .py b/uvr5_pack/lib_v5/layers_123812KB .py
new file mode 100644
index 0000000000000000000000000000000000000000..9835dc0f0dd66a7ef3517101180ec2c54eb6011d
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers_123812KB .py
@@ -0,0 +1,118 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(SeperableConv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nin,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ groups=nin,
+ bias=False,
+ ),
+ nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+ def __call__(self, x):
+ skip = self.conv1(x)
+ h = self.conv2(skip)
+
+ return h, skip
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+ h = self.conv(x)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+ self.conv3 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = nn.Sequential(
+ Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+ )
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+ bottle = self.bottleneck(out)
+ return bottle
diff --git a/uvr5_pack/lib_v5/layers_123821KB.py b/uvr5_pack/lib_v5/layers_123821KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..9835dc0f0dd66a7ef3517101180ec2c54eb6011d
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers_123821KB.py
@@ -0,0 +1,118 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(SeperableConv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nin,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ groups=nin,
+ bias=False,
+ ),
+ nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+ def __call__(self, x):
+ skip = self.conv1(x)
+ h = self.conv2(skip)
+
+ return h, skip
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+ h = self.conv(x)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+ self.conv3 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = nn.Sequential(
+ Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+ )
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+ bottle = self.bottleneck(out)
+ return bottle
diff --git a/uvr5_pack/lib_v5/layers_33966KB.py b/uvr5_pack/lib_v5/layers_33966KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..78e539250075d7fed2f349d05e3317dfe2c96804
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers_33966KB.py
@@ -0,0 +1,126 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(SeperableConv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nin,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ groups=nin,
+ bias=False,
+ ),
+ nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+ def __call__(self, x):
+ skip = self.conv1(x)
+ h = self.conv2(skip)
+
+ return h, skip
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+ h = self.conv(x)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+ self.conv3 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.conv6 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.conv7 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = nn.Sequential(
+ Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+ )
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ feat6 = self.conv6(x)
+ feat7 = self.conv7(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1)
+ bottle = self.bottleneck(out)
+ return bottle
diff --git a/uvr5_pack/lib_v5/layers_537227KB.py b/uvr5_pack/lib_v5/layers_537227KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..78e539250075d7fed2f349d05e3317dfe2c96804
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers_537227KB.py
@@ -0,0 +1,126 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(SeperableConv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nin,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ groups=nin,
+ bias=False,
+ ),
+ nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+ def __call__(self, x):
+ skip = self.conv1(x)
+ h = self.conv2(skip)
+
+ return h, skip
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+ h = self.conv(x)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+ self.conv3 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.conv6 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.conv7 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = nn.Sequential(
+ Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+ )
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ feat6 = self.conv6(x)
+ feat7 = self.conv7(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1)
+ bottle = self.bottleneck(out)
+ return bottle
diff --git a/uvr5_pack/lib_v5/layers_537238KB.py b/uvr5_pack/lib_v5/layers_537238KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..78e539250075d7fed2f349d05e3317dfe2c96804
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers_537238KB.py
@@ -0,0 +1,126 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(SeperableConv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nin,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ groups=nin,
+ bias=False,
+ ),
+ nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+ def __call__(self, x):
+ skip = self.conv1(x)
+ h = self.conv2(skip)
+
+ return h, skip
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+ h = self.conv(x)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+ self.conv3 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.conv6 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.conv7 = SeperableConv2DBNActiv(
+ nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = nn.Sequential(
+ Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+ )
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ feat6 = self.conv6(x)
+ feat7 = self.conv7(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1)
+ bottle = self.bottleneck(out)
+ return bottle
diff --git a/uvr5_pack/lib_v5/layers_new.py b/uvr5_pack/lib_v5/layers_new.py
new file mode 100644
index 0000000000000000000000000000000000000000..2441f2deab51cd2eb3c3a3eefcfd4743bf2ec321
--- /dev/null
+++ b/uvr5_pack/lib_v5/layers_new.py
@@ -0,0 +1,125 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+ super(Conv2DBNActiv, self).__init__()
+ self.conv = nn.Sequential(
+ nn.Conv2d(
+ nin,
+ nout,
+ kernel_size=ksize,
+ stride=stride,
+ padding=pad,
+ dilation=dilation,
+ bias=False,
+ ),
+ nn.BatchNorm2d(nout),
+ activ(),
+ )
+
+ def __call__(self, x):
+ return self.conv(x)
+
+
+class Encoder(nn.Module):
+ def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+ super(Encoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, stride, pad, activ=activ)
+ self.conv2 = Conv2DBNActiv(nout, nout, ksize, 1, pad, activ=activ)
+
+ def __call__(self, x):
+ h = self.conv1(x)
+ h = self.conv2(h)
+
+ return h
+
+
+class Decoder(nn.Module):
+ def __init__(
+ self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+ ):
+ super(Decoder, self).__init__()
+ self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+ # self.conv2 = Conv2DBNActiv(nout, nout, ksize, 1, pad, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def __call__(self, x, skip=None):
+ x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+
+ if skip is not None:
+ skip = spec_utils.crop_center(skip, x)
+ x = torch.cat([x, skip], dim=1)
+
+ h = self.conv1(x)
+ # h = self.conv2(h)
+
+ if self.dropout is not None:
+ h = self.dropout(h)
+
+ return h
+
+
+class ASPPModule(nn.Module):
+ def __init__(self, nin, nout, dilations=(4, 8, 12), activ=nn.ReLU, dropout=False):
+ super(ASPPModule, self).__init__()
+ self.conv1 = nn.Sequential(
+ nn.AdaptiveAvgPool2d((1, None)),
+ Conv2DBNActiv(nin, nout, 1, 1, 0, activ=activ),
+ )
+ self.conv2 = Conv2DBNActiv(nin, nout, 1, 1, 0, activ=activ)
+ self.conv3 = Conv2DBNActiv(
+ nin, nout, 3, 1, dilations[0], dilations[0], activ=activ
+ )
+ self.conv4 = Conv2DBNActiv(
+ nin, nout, 3, 1, dilations[1], dilations[1], activ=activ
+ )
+ self.conv5 = Conv2DBNActiv(
+ nin, nout, 3, 1, dilations[2], dilations[2], activ=activ
+ )
+ self.bottleneck = Conv2DBNActiv(nout * 5, nout, 1, 1, 0, activ=activ)
+ self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+ def forward(self, x):
+ _, _, h, w = x.size()
+ feat1 = F.interpolate(
+ self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+ )
+ feat2 = self.conv2(x)
+ feat3 = self.conv3(x)
+ feat4 = self.conv4(x)
+ feat5 = self.conv5(x)
+ out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+ out = self.bottleneck(out)
+
+ if self.dropout is not None:
+ out = self.dropout(out)
+
+ return out
+
+
+class LSTMModule(nn.Module):
+ def __init__(self, nin_conv, nin_lstm, nout_lstm):
+ super(LSTMModule, self).__init__()
+ self.conv = Conv2DBNActiv(nin_conv, 1, 1, 1, 0)
+ self.lstm = nn.LSTM(
+ input_size=nin_lstm, hidden_size=nout_lstm // 2, bidirectional=True
+ )
+ self.dense = nn.Sequential(
+ nn.Linear(nout_lstm, nin_lstm), nn.BatchNorm1d(nin_lstm), nn.ReLU()
+ )
+
+ def forward(self, x):
+ N, _, nbins, nframes = x.size()
+ h = self.conv(x)[:, 0] # N, nbins, nframes
+ h = h.permute(2, 0, 1) # nframes, N, nbins
+ h, _ = self.lstm(h)
+ h = self.dense(h.reshape(-1, h.size()[-1])) # nframes * N, nbins
+ h = h.reshape(nframes, N, 1, nbins)
+ h = h.permute(1, 2, 3, 0)
+
+ return h
diff --git a/uvr5_pack/lib_v5/model_param_init.py b/uvr5_pack/lib_v5/model_param_init.py
new file mode 100644
index 0000000000000000000000000000000000000000..b995c0bfb1194746187692e2ab1c2a6dbaaaec6c
--- /dev/null
+++ b/uvr5_pack/lib_v5/model_param_init.py
@@ -0,0 +1,69 @@
+import json
+import os
+import pathlib
+
+default_param = {}
+default_param["bins"] = 768
+default_param["unstable_bins"] = 9 # training only
+default_param["reduction_bins"] = 762 # training only
+default_param["sr"] = 44100
+default_param["pre_filter_start"] = 757
+default_param["pre_filter_stop"] = 768
+default_param["band"] = {}
+
+
+default_param["band"][1] = {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 960,
+ "crop_start": 0,
+ "crop_stop": 245,
+ "lpf_start": 61, # inference only
+ "res_type": "polyphase",
+}
+
+default_param["band"][2] = {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 1536,
+ "crop_start": 24,
+ "crop_stop": 547,
+ "hpf_start": 81, # inference only
+ "res_type": "sinc_best",
+}
+
+
+def int_keys(d):
+ r = {}
+ for k, v in d:
+ if k.isdigit():
+ k = int(k)
+ r[k] = v
+ return r
+
+
+class ModelParameters(object):
+ def __init__(self, config_path=""):
+ if ".pth" == pathlib.Path(config_path).suffix:
+ import zipfile
+
+ with zipfile.ZipFile(config_path, "r") as zip:
+ self.param = json.loads(
+ zip.read("param.json"), object_pairs_hook=int_keys
+ )
+ elif ".json" == pathlib.Path(config_path).suffix:
+ with open(config_path, "r") as f:
+ self.param = json.loads(f.read(), object_pairs_hook=int_keys)
+ else:
+ self.param = default_param
+
+ for k in [
+ "mid_side",
+ "mid_side_b",
+ "mid_side_b2",
+ "stereo_w",
+ "stereo_n",
+ "reverse",
+ ]:
+ if not k in self.param:
+ self.param[k] = False
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json b/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json
new file mode 100644
index 0000000000000000000000000000000000000000..72cb4499867ad2827185e85687f06fb73d33eced
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json
@@ -0,0 +1,19 @@
+{
+ "bins": 1024,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 16000,
+ "hl": 512,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 1024,
+ "hpf_start": -1,
+ "res_type": "sinc_best"
+ }
+ },
+ "sr": 16000,
+ "pre_filter_start": 1023,
+ "pre_filter_stop": 1024
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json b/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c00ecf0a105e55a6a86a3c32db301a2635b5b41
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json
@@ -0,0 +1,19 @@
+{
+ "bins": 1024,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 32000,
+ "hl": 512,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 1024,
+ "hpf_start": -1,
+ "res_type": "kaiser_fast"
+ }
+ },
+ "sr": 32000,
+ "pre_filter_start": 1000,
+ "pre_filter_stop": 1021
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json b/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json
new file mode 100644
index 0000000000000000000000000000000000000000..55666ac9a8d0547751fb4b4d3bffb1ee2c956913
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json
@@ -0,0 +1,19 @@
+{
+ "bins": 1024,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 33075,
+ "hl": 384,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 1024,
+ "hpf_start": -1,
+ "res_type": "sinc_best"
+ }
+ },
+ "sr": 33075,
+ "pre_filter_start": 1000,
+ "pre_filter_stop": 1021
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json
new file mode 100644
index 0000000000000000000000000000000000000000..665abe20eb3cc39fe0f8493dad8f25f6ef634a14
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json
@@ -0,0 +1,19 @@
+{
+ "bins": 1024,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 44100,
+ "hl": 1024,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 1024,
+ "hpf_start": -1,
+ "res_type": "sinc_best"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 1023,
+ "pre_filter_stop": 1024
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json
new file mode 100644
index 0000000000000000000000000000000000000000..0e8b16f89b0231d06eabe8d2f7c2670c7caa2272
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json
@@ -0,0 +1,19 @@
+{
+ "bins": 256,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 44100,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 0,
+ "crop_stop": 256,
+ "hpf_start": -1,
+ "res_type": "sinc_best"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 256,
+ "pre_filter_stop": 256
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json
new file mode 100644
index 0000000000000000000000000000000000000000..3b38fcaf60ba204e03a47f5bd3f5bcfe75e1983a
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json
@@ -0,0 +1,19 @@
+{
+ "bins": 1024,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 1024,
+ "hpf_start": -1,
+ "res_type": "sinc_best"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 1023,
+ "pre_filter_stop": 1024
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512_cut.json b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512_cut.json
new file mode 100644
index 0000000000000000000000000000000000000000..630df3524e340f43a1ddb7b33ff02cc91fc1cb47
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512_cut.json
@@ -0,0 +1,19 @@
+{
+ "bins": 1024,
+ "unstable_bins": 0,
+ "reduction_bins": 0,
+ "band": {
+ "1": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 700,
+ "hpf_start": -1,
+ "res_type": "sinc_best"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 1023,
+ "pre_filter_stop": 700
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/2band_32000.json b/uvr5_pack/lib_v5/modelparams/2band_32000.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab9cf1150a818eb6252105408311be0a40d423b3
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/2band_32000.json
@@ -0,0 +1,30 @@
+{
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 705,
+ "band": {
+ "1": {
+ "sr": 6000,
+ "hl": 66,
+ "n_fft": 512,
+ "crop_start": 0,
+ "crop_stop": 240,
+ "lpf_start": 60,
+ "lpf_stop": 118,
+ "res_type": "sinc_fastest"
+ },
+ "2": {
+ "sr": 32000,
+ "hl": 352,
+ "n_fft": 1024,
+ "crop_start": 22,
+ "crop_stop": 505,
+ "hpf_start": 44,
+ "hpf_stop": 23,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 32000,
+ "pre_filter_start": 710,
+ "pre_filter_stop": 731
+}
diff --git a/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json b/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json
new file mode 100644
index 0000000000000000000000000000000000000000..7faa216d7b49aeece24123dbdd868847a1dbc03c
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json
@@ -0,0 +1,30 @@
+{
+ "bins": 512,
+ "unstable_bins": 7,
+ "reduction_bins": 510,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 160,
+ "n_fft": 768,
+ "crop_start": 0,
+ "crop_stop": 192,
+ "lpf_start": 41,
+ "lpf_stop": 139,
+ "res_type": "sinc_fastest"
+ },
+ "2": {
+ "sr": 44100,
+ "hl": 640,
+ "n_fft": 1024,
+ "crop_start": 10,
+ "crop_stop": 320,
+ "hpf_start": 47,
+ "hpf_stop": 15,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 510,
+ "pre_filter_stop": 512
+}
diff --git a/uvr5_pack/lib_v5/modelparams/2band_48000.json b/uvr5_pack/lib_v5/modelparams/2band_48000.json
new file mode 100644
index 0000000000000000000000000000000000000000..7e78175052b09cb1a32345e54006475992712f9a
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/2band_48000.json
@@ -0,0 +1,30 @@
+{
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 705,
+ "band": {
+ "1": {
+ "sr": 6000,
+ "hl": 66,
+ "n_fft": 512,
+ "crop_start": 0,
+ "crop_stop": 240,
+ "lpf_start": 60,
+ "lpf_stop": 240,
+ "res_type": "sinc_fastest"
+ },
+ "2": {
+ "sr": 48000,
+ "hl": 528,
+ "n_fft": 1536,
+ "crop_start": 22,
+ "crop_stop": 505,
+ "hpf_start": 82,
+ "hpf_stop": 22,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 48000,
+ "pre_filter_start": 710,
+ "pre_filter_stop": 731
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/3band_44100.json b/uvr5_pack/lib_v5/modelparams/3band_44100.json
new file mode 100644
index 0000000000000000000000000000000000000000..d881d767ff83fbac0e18dfe2587ef16925b29b3c
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/3band_44100.json
@@ -0,0 +1,42 @@
+{
+ "bins": 768,
+ "unstable_bins": 5,
+ "reduction_bins": 733,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 768,
+ "crop_start": 0,
+ "crop_stop": 278,
+ "lpf_start": 28,
+ "lpf_stop": 140,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 768,
+ "crop_start": 14,
+ "crop_stop": 322,
+ "hpf_start": 70,
+ "hpf_stop": 14,
+ "lpf_start": 283,
+ "lpf_stop": 314,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 131,
+ "crop_stop": 313,
+ "hpf_start": 154,
+ "hpf_stop": 141,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 757,
+ "pre_filter_stop": 768
+}
diff --git a/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json b/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json
new file mode 100644
index 0000000000000000000000000000000000000000..77ec198573b19f36519a028a509767d30764c0e2
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json
@@ -0,0 +1,43 @@
+{
+ "mid_side": true,
+ "bins": 768,
+ "unstable_bins": 5,
+ "reduction_bins": 733,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 768,
+ "crop_start": 0,
+ "crop_stop": 278,
+ "lpf_start": 28,
+ "lpf_stop": 140,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 768,
+ "crop_start": 14,
+ "crop_stop": 322,
+ "hpf_start": 70,
+ "hpf_stop": 14,
+ "lpf_start": 283,
+ "lpf_stop": 314,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 131,
+ "crop_stop": 313,
+ "hpf_start": 154,
+ "hpf_stop": 141,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 757,
+ "pre_filter_stop": 768
+}
diff --git a/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json b/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json
new file mode 100644
index 0000000000000000000000000000000000000000..85ee8a7d44541c9176e85ea3dce8728d34990938
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json
@@ -0,0 +1,43 @@
+{
+ "mid_side_b2": true,
+ "bins": 640,
+ "unstable_bins": 7,
+ "reduction_bins": 565,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 108,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 187,
+ "lpf_start": 92,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 22050,
+ "hl": 216,
+ "n_fft": 768,
+ "crop_start": 0,
+ "crop_stop": 212,
+ "hpf_start": 68,
+ "hpf_stop": 34,
+ "lpf_start": 174,
+ "lpf_stop": 209,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 44100,
+ "hl": 432,
+ "n_fft": 640,
+ "crop_start": 66,
+ "crop_stop": 307,
+ "hpf_start": 86,
+ "hpf_stop": 72,
+ "res_type": "kaiser_fast"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 639,
+ "pre_filter_stop": 640
+}
diff --git a/uvr5_pack/lib_v5/modelparams/4band_44100.json b/uvr5_pack/lib_v5/modelparams/4band_44100.json
new file mode 100644
index 0000000000000000000000000000000000000000..df123754204372aa50d464fbe9102a401f48cc73
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_44100.json
@@ -0,0 +1,54 @@
+{
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 668,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 186,
+ "lpf_start": 37,
+ "lpf_stop": 73,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 512,
+ "crop_start": 4,
+ "crop_stop": 185,
+ "hpf_start": 36,
+ "hpf_stop": 18,
+ "lpf_start": 93,
+ "lpf_stop": 185,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 46,
+ "crop_stop": 186,
+ "hpf_start": 93,
+ "hpf_stop": 46,
+ "lpf_start": 164,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 121,
+ "crop_stop": 382,
+ "hpf_start": 138,
+ "hpf_stop": 123,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 740,
+ "pre_filter_stop": 768
+}
diff --git a/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json b/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json
new file mode 100644
index 0000000000000000000000000000000000000000..e91b699eb63d3382c3b9e9edf46d40ed91d6122b
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json
@@ -0,0 +1,55 @@
+{
+ "bins": 768,
+ "unstable_bins": 7,
+ "mid_side": true,
+ "reduction_bins": 668,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 186,
+ "lpf_start": 37,
+ "lpf_stop": 73,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 512,
+ "crop_start": 4,
+ "crop_stop": 185,
+ "hpf_start": 36,
+ "hpf_stop": 18,
+ "lpf_start": 93,
+ "lpf_stop": 185,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 46,
+ "crop_stop": 186,
+ "hpf_start": 93,
+ "hpf_stop": 46,
+ "lpf_start": 164,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 121,
+ "crop_stop": 382,
+ "hpf_start": 138,
+ "hpf_stop": 123,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 740,
+ "pre_filter_stop": 768
+}
diff --git a/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json b/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json
new file mode 100644
index 0000000000000000000000000000000000000000..f852f280ec9d98fc1b65cec688290eaafec61b84
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json
@@ -0,0 +1,55 @@
+{
+ "mid_side_b": true,
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 668,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 186,
+ "lpf_start": 37,
+ "lpf_stop": 73,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 512,
+ "crop_start": 4,
+ "crop_stop": 185,
+ "hpf_start": 36,
+ "hpf_stop": 18,
+ "lpf_start": 93,
+ "lpf_stop": 185,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 46,
+ "crop_stop": 186,
+ "hpf_start": 93,
+ "hpf_stop": 46,
+ "lpf_start": 164,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 121,
+ "crop_stop": 382,
+ "hpf_start": 138,
+ "hpf_stop": 123,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 740,
+ "pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json b/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json
new file mode 100644
index 0000000000000000000000000000000000000000..f852f280ec9d98fc1b65cec688290eaafec61b84
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json
@@ -0,0 +1,55 @@
+{
+ "mid_side_b": true,
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 668,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 186,
+ "lpf_start": 37,
+ "lpf_stop": 73,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 512,
+ "crop_start": 4,
+ "crop_stop": 185,
+ "hpf_start": 36,
+ "hpf_stop": 18,
+ "lpf_start": 93,
+ "lpf_stop": 185,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 46,
+ "crop_stop": 186,
+ "hpf_start": 93,
+ "hpf_stop": 46,
+ "lpf_start": 164,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 121,
+ "crop_stop": 382,
+ "hpf_start": 138,
+ "hpf_stop": 123,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 740,
+ "pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json b/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json
new file mode 100644
index 0000000000000000000000000000000000000000..7a07d5541bd83dc1caa20b531c3b43a2ffccac88
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json
@@ -0,0 +1,55 @@
+{
+ "reverse": true,
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 668,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 186,
+ "lpf_start": 37,
+ "lpf_stop": 73,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 512,
+ "crop_start": 4,
+ "crop_stop": 185,
+ "hpf_start": 36,
+ "hpf_stop": 18,
+ "lpf_start": 93,
+ "lpf_stop": 185,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 46,
+ "crop_stop": 186,
+ "hpf_start": 93,
+ "hpf_stop": 46,
+ "lpf_start": 164,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 121,
+ "crop_stop": 382,
+ "hpf_start": 138,
+ "hpf_stop": 123,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 740,
+ "pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json b/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json
new file mode 100644
index 0000000000000000000000000000000000000000..ba0cf342106de793e6ec3e876854c7fd451fbf76
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json
@@ -0,0 +1,55 @@
+{
+ "stereo_w": true,
+ "bins": 768,
+ "unstable_bins": 7,
+ "reduction_bins": 668,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 1024,
+ "crop_start": 0,
+ "crop_stop": 186,
+ "lpf_start": 37,
+ "lpf_stop": 73,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 11025,
+ "hl": 128,
+ "n_fft": 512,
+ "crop_start": 4,
+ "crop_stop": 185,
+ "hpf_start": 36,
+ "hpf_stop": 18,
+ "lpf_start": 93,
+ "lpf_stop": 185,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 22050,
+ "hl": 256,
+ "n_fft": 512,
+ "crop_start": 46,
+ "crop_stop": 186,
+ "hpf_start": 93,
+ "hpf_stop": 46,
+ "lpf_start": 164,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 512,
+ "n_fft": 768,
+ "crop_start": 121,
+ "crop_stop": 382,
+ "hpf_start": 138,
+ "hpf_stop": 123,
+ "res_type": "sinc_medium"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 740,
+ "pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/4band_v2.json b/uvr5_pack/lib_v5/modelparams/4band_v2.json
new file mode 100644
index 0000000000000000000000000000000000000000..33281a0cf9916fc33558ddfda7a0287a2547faf4
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_v2.json
@@ -0,0 +1,54 @@
+{
+ "bins": 672,
+ "unstable_bins": 8,
+ "reduction_bins": 637,
+ "band": {
+ "1": {
+ "sr": 7350,
+ "hl": 80,
+ "n_fft": 640,
+ "crop_start": 0,
+ "crop_stop": 85,
+ "lpf_start": 25,
+ "lpf_stop": 53,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 7350,
+ "hl": 80,
+ "n_fft": 320,
+ "crop_start": 4,
+ "crop_stop": 87,
+ "hpf_start": 25,
+ "hpf_stop": 12,
+ "lpf_start": 31,
+ "lpf_stop": 62,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 14700,
+ "hl": 160,
+ "n_fft": 512,
+ "crop_start": 17,
+ "crop_stop": 216,
+ "hpf_start": 48,
+ "hpf_stop": 24,
+ "lpf_start": 139,
+ "lpf_stop": 210,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 480,
+ "n_fft": 960,
+ "crop_start": 78,
+ "crop_stop": 383,
+ "hpf_start": 130,
+ "hpf_stop": 86,
+ "res_type": "kaiser_fast"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 668,
+ "pre_filter_stop": 672
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json b/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json
new file mode 100644
index 0000000000000000000000000000000000000000..2e5c770fe188779bf6b0873190b7a324d6a867b2
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json
@@ -0,0 +1,55 @@
+{
+ "bins": 672,
+ "unstable_bins": 8,
+ "reduction_bins": 637,
+ "band": {
+ "1": {
+ "sr": 7350,
+ "hl": 80,
+ "n_fft": 640,
+ "crop_start": 0,
+ "crop_stop": 85,
+ "lpf_start": 25,
+ "lpf_stop": 53,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 7350,
+ "hl": 80,
+ "n_fft": 320,
+ "crop_start": 4,
+ "crop_stop": 87,
+ "hpf_start": 25,
+ "hpf_stop": 12,
+ "lpf_start": 31,
+ "lpf_stop": 62,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 14700,
+ "hl": 160,
+ "n_fft": 512,
+ "crop_start": 17,
+ "crop_stop": 216,
+ "hpf_start": 48,
+ "hpf_stop": 24,
+ "lpf_start": 139,
+ "lpf_stop": 210,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 480,
+ "n_fft": 960,
+ "crop_start": 78,
+ "crop_stop": 383,
+ "hpf_start": 130,
+ "hpf_stop": 86,
+ "convert_channels": "stereo_n",
+ "res_type": "kaiser_fast"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 668,
+ "pre_filter_stop": 672
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/4band_v3.json b/uvr5_pack/lib_v5/modelparams/4band_v3.json
new file mode 100644
index 0000000000000000000000000000000000000000..edb908b8853c6359d1e98ae381888d1a9906ca0f
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/4band_v3.json
@@ -0,0 +1,54 @@
+{
+ "bins": 672,
+ "unstable_bins": 8,
+ "reduction_bins": 530,
+ "band": {
+ "1": {
+ "sr": 7350,
+ "hl": 80,
+ "n_fft": 640,
+ "crop_start": 0,
+ "crop_stop": 85,
+ "lpf_start": 25,
+ "lpf_stop": 53,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 7350,
+ "hl": 80,
+ "n_fft": 320,
+ "crop_start": 4,
+ "crop_stop": 87,
+ "hpf_start": 25,
+ "hpf_stop": 12,
+ "lpf_start": 31,
+ "lpf_stop": 62,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 14700,
+ "hl": 160,
+ "n_fft": 512,
+ "crop_start": 17,
+ "crop_stop": 216,
+ "hpf_start": 48,
+ "hpf_stop": 24,
+ "lpf_start": 139,
+ "lpf_stop": 210,
+ "res_type": "polyphase"
+ },
+ "4": {
+ "sr": 44100,
+ "hl": 480,
+ "n_fft": 960,
+ "crop_start": 78,
+ "crop_stop": 383,
+ "hpf_start": 130,
+ "hpf_stop": 86,
+ "res_type": "kaiser_fast"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 668,
+ "pre_filter_stop": 672
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/modelparams/ensemble.json b/uvr5_pack/lib_v5/modelparams/ensemble.json
new file mode 100644
index 0000000000000000000000000000000000000000..ee69beb46fc82f34619c5e48761e329fcabbbd00
--- /dev/null
+++ b/uvr5_pack/lib_v5/modelparams/ensemble.json
@@ -0,0 +1,43 @@
+{
+ "mid_side_b2": true,
+ "bins": 1280,
+ "unstable_bins": 7,
+ "reduction_bins": 565,
+ "band": {
+ "1": {
+ "sr": 11025,
+ "hl": 108,
+ "n_fft": 2048,
+ "crop_start": 0,
+ "crop_stop": 374,
+ "lpf_start": 92,
+ "lpf_stop": 186,
+ "res_type": "polyphase"
+ },
+ "2": {
+ "sr": 22050,
+ "hl": 216,
+ "n_fft": 1536,
+ "crop_start": 0,
+ "crop_stop": 424,
+ "hpf_start": 68,
+ "hpf_stop": 34,
+ "lpf_start": 348,
+ "lpf_stop": 418,
+ "res_type": "polyphase"
+ },
+ "3": {
+ "sr": 44100,
+ "hl": 432,
+ "n_fft": 1280,
+ "crop_start": 132,
+ "crop_stop": 614,
+ "hpf_start": 172,
+ "hpf_stop": 144,
+ "res_type": "polyphase"
+ }
+ },
+ "sr": 44100,
+ "pre_filter_start": 1280,
+ "pre_filter_stop": 1280
+}
\ No newline at end of file
diff --git a/uvr5_pack/lib_v5/nets.py b/uvr5_pack/lib_v5/nets.py
new file mode 100644
index 0000000000000000000000000000000000000000..d4c376ed8715f9e85d71609e348add0a6550a4ba
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets.py
@@ -0,0 +1,123 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers
+from uvr5_pack.lib_v5 import spec_utils
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 16)
+ self.stg1_high_band_net = BaseASPPNet(2, 16)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(18, 8, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(8, 16)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(16, 32)
+
+ self.out = nn.Conv2d(32, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(16, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(16, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_123812KB.py b/uvr5_pack/lib_v5/nets_123812KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..ea6c45c968d66c75e577e8a0fcca9bf800eb4ed6
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_123812KB.py
@@ -0,0 +1,122 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers_123821KB as layers
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 32)
+ self.stg1_high_band_net = BaseASPPNet(2, 32)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(16, 32)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(32, 64)
+
+ self.out = nn.Conv2d(64, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(32, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(32, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_123821KB.py b/uvr5_pack/lib_v5/nets_123821KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..ea6c45c968d66c75e577e8a0fcca9bf800eb4ed6
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_123821KB.py
@@ -0,0 +1,122 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers_123821KB as layers
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 32)
+ self.stg1_high_band_net = BaseASPPNet(2, 32)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(16, 32)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(32, 64)
+
+ self.out = nn.Conv2d(64, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(32, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(32, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_33966KB.py b/uvr5_pack/lib_v5/nets_33966KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..d2bddb14716202fee3f3b0b461ff335741d04ba8
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_33966KB.py
@@ -0,0 +1,122 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers_33966KB as layers
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16, 32)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 16)
+ self.stg1_high_band_net = BaseASPPNet(2, 16)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(18, 8, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(8, 16)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(16, 32)
+
+ self.out = nn.Conv2d(32, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(16, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(16, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_537227KB.py b/uvr5_pack/lib_v5/nets_537227KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..1ceac4a470ca311d594818d52e5f96919cfddb26
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_537227KB.py
@@ -0,0 +1,123 @@
+import torch
+import numpy as np
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers_537238KB as layers
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 64)
+ self.stg1_high_band_net = BaseASPPNet(2, 64)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(32, 64)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(130, 64, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(64, 128)
+
+ self.out = nn.Conv2d(128, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(64, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(64, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_537238KB.py b/uvr5_pack/lib_v5/nets_537238KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..1ceac4a470ca311d594818d52e5f96919cfddb26
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_537238KB.py
@@ -0,0 +1,123 @@
+import torch
+import numpy as np
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers_537238KB as layers
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 64)
+ self.stg1_high_band_net = BaseASPPNet(2, 64)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(32, 64)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(130, 64, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(64, 128)
+
+ self.out = nn.Conv2d(128, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(64, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(64, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_61968KB.py b/uvr5_pack/lib_v5/nets_61968KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..ea6c45c968d66c75e577e8a0fcca9bf800eb4ed6
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_61968KB.py
@@ -0,0 +1,122 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from uvr5_pack.lib_v5 import layers_123821KB as layers
+
+
+class BaseASPPNet(nn.Module):
+ def __init__(self, nin, ch, dilations=(4, 8, 16)):
+ super(BaseASPPNet, self).__init__()
+ self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+ self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+ self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+ self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+ self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+ def __call__(self, x):
+ h, e1 = self.enc1(x)
+ h, e2 = self.enc2(h)
+ h, e3 = self.enc3(h)
+ h, e4 = self.enc4(h)
+
+ h = self.aspp(h)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedASPPNet(nn.Module):
+ def __init__(self, n_fft):
+ super(CascadedASPPNet, self).__init__()
+ self.stg1_low_band_net = BaseASPPNet(2, 32)
+ self.stg1_high_band_net = BaseASPPNet(2, 32)
+
+ self.stg2_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+ self.stg2_full_band_net = BaseASPPNet(16, 32)
+
+ self.stg3_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+ self.stg3_full_band_net = BaseASPPNet(32, 64)
+
+ self.out = nn.Conv2d(64, 2, 1, bias=False)
+ self.aux1_out = nn.Conv2d(32, 2, 1, bias=False)
+ self.aux2_out = nn.Conv2d(32, 2, 1, bias=False)
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+
+ self.offset = 128
+
+ def forward(self, x, aggressiveness=None):
+ mix = x.detach()
+ x = x.clone()
+
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ aux1 = torch.cat(
+ [
+ self.stg1_low_band_net(x[:, :, :bandw]),
+ self.stg1_high_band_net(x[:, :, bandw:]),
+ ],
+ dim=2,
+ )
+
+ h = torch.cat([x, aux1], dim=1)
+ aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+ h = torch.cat([x, aux1, aux2], dim=1)
+ h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+ mask = torch.sigmoid(self.out(h))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux1 = torch.sigmoid(self.aux1_out(aux1))
+ aux1 = F.pad(
+ input=aux1,
+ pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+ mode="replicate",
+ )
+ aux2 = torch.sigmoid(self.aux2_out(aux2))
+ aux2 = F.pad(
+ input=aux2,
+ pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+ mode="replicate",
+ )
+ return mask * mix, aux1 * mix, aux2 * mix
+ else:
+ if aggressiveness:
+ mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+ mask[:, :, : aggressiveness["split_bin"]],
+ 1 + aggressiveness["value"] / 3,
+ )
+ mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+ mask[:, :, aggressiveness["split_bin"] :],
+ 1 + aggressiveness["value"],
+ )
+
+ return mask * mix
+
+ def predict(self, x_mag, aggressiveness=None):
+ h = self.forward(x_mag, aggressiveness)
+
+ if self.offset > 0:
+ h = h[:, :, :, self.offset : -self.offset]
+ assert h.size()[3] > 0
+
+ return h
diff --git a/uvr5_pack/lib_v5/nets_new.py b/uvr5_pack/lib_v5/nets_new.py
new file mode 100644
index 0000000000000000000000000000000000000000..c9898f63e3f320597b96c45a3df22d941e467614
--- /dev/null
+++ b/uvr5_pack/lib_v5/nets_new.py
@@ -0,0 +1,132 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+from uvr5_pack.lib_v5 import layers_new as layers
+
+
+class BaseNet(nn.Module):
+ def __init__(
+ self, nin, nout, nin_lstm, nout_lstm, dilations=((4, 2), (8, 4), (12, 6))
+ ):
+ super(BaseNet, self).__init__()
+ self.enc1 = layers.Conv2DBNActiv(nin, nout, 3, 1, 1)
+ self.enc2 = layers.Encoder(nout, nout * 2, 3, 2, 1)
+ self.enc3 = layers.Encoder(nout * 2, nout * 4, 3, 2, 1)
+ self.enc4 = layers.Encoder(nout * 4, nout * 6, 3, 2, 1)
+ self.enc5 = layers.Encoder(nout * 6, nout * 8, 3, 2, 1)
+
+ self.aspp = layers.ASPPModule(nout * 8, nout * 8, dilations, dropout=True)
+
+ self.dec4 = layers.Decoder(nout * (6 + 8), nout * 6, 3, 1, 1)
+ self.dec3 = layers.Decoder(nout * (4 + 6), nout * 4, 3, 1, 1)
+ self.dec2 = layers.Decoder(nout * (2 + 4), nout * 2, 3, 1, 1)
+ self.lstm_dec2 = layers.LSTMModule(nout * 2, nin_lstm, nout_lstm)
+ self.dec1 = layers.Decoder(nout * (1 + 2) + 1, nout * 1, 3, 1, 1)
+
+ def __call__(self, x):
+ e1 = self.enc1(x)
+ e2 = self.enc2(e1)
+ e3 = self.enc3(e2)
+ e4 = self.enc4(e3)
+ e5 = self.enc5(e4)
+
+ h = self.aspp(e5)
+
+ h = self.dec4(h, e4)
+ h = self.dec3(h, e3)
+ h = self.dec2(h, e2)
+ h = torch.cat([h, self.lstm_dec2(h)], dim=1)
+ h = self.dec1(h, e1)
+
+ return h
+
+
+class CascadedNet(nn.Module):
+ def __init__(self, n_fft, nout=32, nout_lstm=128):
+ super(CascadedNet, self).__init__()
+
+ self.max_bin = n_fft // 2
+ self.output_bin = n_fft // 2 + 1
+ self.nin_lstm = self.max_bin // 2
+ self.offset = 64
+
+ self.stg1_low_band_net = nn.Sequential(
+ BaseNet(2, nout // 2, self.nin_lstm // 2, nout_lstm),
+ layers.Conv2DBNActiv(nout // 2, nout // 4, 1, 1, 0),
+ )
+
+ self.stg1_high_band_net = BaseNet(
+ 2, nout // 4, self.nin_lstm // 2, nout_lstm // 2
+ )
+
+ self.stg2_low_band_net = nn.Sequential(
+ BaseNet(nout // 4 + 2, nout, self.nin_lstm // 2, nout_lstm),
+ layers.Conv2DBNActiv(nout, nout // 2, 1, 1, 0),
+ )
+ self.stg2_high_band_net = BaseNet(
+ nout // 4 + 2, nout // 2, self.nin_lstm // 2, nout_lstm // 2
+ )
+
+ self.stg3_full_band_net = BaseNet(
+ 3 * nout // 4 + 2, nout, self.nin_lstm, nout_lstm
+ )
+
+ self.out = nn.Conv2d(nout, 2, 1, bias=False)
+ self.aux_out = nn.Conv2d(3 * nout // 4, 2, 1, bias=False)
+
+ def forward(self, x):
+ x = x[:, :, : self.max_bin]
+
+ bandw = x.size()[2] // 2
+ l1_in = x[:, :, :bandw]
+ h1_in = x[:, :, bandw:]
+ l1 = self.stg1_low_band_net(l1_in)
+ h1 = self.stg1_high_band_net(h1_in)
+ aux1 = torch.cat([l1, h1], dim=2)
+
+ l2_in = torch.cat([l1_in, l1], dim=1)
+ h2_in = torch.cat([h1_in, h1], dim=1)
+ l2 = self.stg2_low_band_net(l2_in)
+ h2 = self.stg2_high_band_net(h2_in)
+ aux2 = torch.cat([l2, h2], dim=2)
+
+ f3_in = torch.cat([x, aux1, aux2], dim=1)
+ f3 = self.stg3_full_band_net(f3_in)
+
+ mask = torch.sigmoid(self.out(f3))
+ mask = F.pad(
+ input=mask,
+ pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+ mode="replicate",
+ )
+
+ if self.training:
+ aux = torch.cat([aux1, aux2], dim=1)
+ aux = torch.sigmoid(self.aux_out(aux))
+ aux = F.pad(
+ input=aux,
+ pad=(0, 0, 0, self.output_bin - aux.size()[2]),
+ mode="replicate",
+ )
+ return mask, aux
+ else:
+ return mask
+
+ def predict_mask(self, x):
+ mask = self.forward(x)
+
+ if self.offset > 0:
+ mask = mask[:, :, :, self.offset : -self.offset]
+ assert mask.size()[3] > 0
+
+ return mask
+
+ def predict(self, x, aggressiveness=None):
+ mask = self.forward(x)
+ pred_mag = x * mask
+
+ if self.offset > 0:
+ pred_mag = pred_mag[:, :, :, self.offset : -self.offset]
+ assert pred_mag.size()[3] > 0
+
+ return pred_mag
diff --git a/uvr5_pack/lib_v5/spec_utils.py b/uvr5_pack/lib_v5/spec_utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..a3fd46d333da7becc7f09f42c084ac7cde661035
--- /dev/null
+++ b/uvr5_pack/lib_v5/spec_utils.py
@@ -0,0 +1,667 @@
+import os, librosa
+import numpy as np
+import soundfile as sf
+from tqdm import tqdm
+import json, math, hashlib
+
+
+def crop_center(h1, h2):
+ h1_shape = h1.size()
+ h2_shape = h2.size()
+
+ if h1_shape[3] == h2_shape[3]:
+ return h1
+ elif h1_shape[3] < h2_shape[3]:
+ raise ValueError("h1_shape[3] must be greater than h2_shape[3]")
+
+ # s_freq = (h2_shape[2] - h1_shape[2]) // 2
+ # e_freq = s_freq + h1_shape[2]
+ s_time = (h1_shape[3] - h2_shape[3]) // 2
+ e_time = s_time + h2_shape[3]
+ h1 = h1[:, :, :, s_time:e_time]
+
+ return h1
+
+
+def wave_to_spectrogram(
+ wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
+):
+ if reverse:
+ wave_left = np.flip(np.asfortranarray(wave[0]))
+ wave_right = np.flip(np.asfortranarray(wave[1]))
+ elif mid_side:
+ wave_left = np.asfortranarray(np.add(wave[0], wave[1]) / 2)
+ wave_right = np.asfortranarray(np.subtract(wave[0], wave[1]))
+ elif mid_side_b2:
+ wave_left = np.asfortranarray(np.add(wave[1], wave[0] * 0.5))
+ wave_right = np.asfortranarray(np.subtract(wave[0], wave[1] * 0.5))
+ else:
+ wave_left = np.asfortranarray(wave[0])
+ wave_right = np.asfortranarray(wave[1])
+
+ spec_left = librosa.stft(wave_left, n_fft, hop_length=hop_length)
+ spec_right = librosa.stft(wave_right, n_fft, hop_length=hop_length)
+
+ spec = np.asfortranarray([spec_left, spec_right])
+
+ return spec
+
+
+def wave_to_spectrogram_mt(
+ wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
+):
+ import threading
+
+ if reverse:
+ wave_left = np.flip(np.asfortranarray(wave[0]))
+ wave_right = np.flip(np.asfortranarray(wave[1]))
+ elif mid_side:
+ wave_left = np.asfortranarray(np.add(wave[0], wave[1]) / 2)
+ wave_right = np.asfortranarray(np.subtract(wave[0], wave[1]))
+ elif mid_side_b2:
+ wave_left = np.asfortranarray(np.add(wave[1], wave[0] * 0.5))
+ wave_right = np.asfortranarray(np.subtract(wave[0], wave[1] * 0.5))
+ else:
+ wave_left = np.asfortranarray(wave[0])
+ wave_right = np.asfortranarray(wave[1])
+
+ def run_thread(**kwargs):
+ global spec_left
+ spec_left = librosa.stft(**kwargs)
+
+ thread = threading.Thread(
+ target=run_thread,
+ kwargs={"y": wave_left, "n_fft": n_fft, "hop_length": hop_length},
+ )
+ thread.start()
+ spec_right = librosa.stft(wave_right, n_fft, hop_length=hop_length)
+ thread.join()
+
+ spec = np.asfortranarray([spec_left, spec_right])
+
+ return spec
+
+
+def combine_spectrograms(specs, mp):
+ l = min([specs[i].shape[2] for i in specs])
+ spec_c = np.zeros(shape=(2, mp.param["bins"] + 1, l), dtype=np.complex64)
+ offset = 0
+ bands_n = len(mp.param["band"])
+
+ for d in range(1, bands_n + 1):
+ h = mp.param["band"][d]["crop_stop"] - mp.param["band"][d]["crop_start"]
+ spec_c[:, offset : offset + h, :l] = specs[d][
+ :, mp.param["band"][d]["crop_start"] : mp.param["band"][d]["crop_stop"], :l
+ ]
+ offset += h
+
+ if offset > mp.param["bins"]:
+ raise ValueError("Too much bins")
+
+ # lowpass fiter
+ if (
+ mp.param["pre_filter_start"] > 0
+ ): # and mp.param['band'][bands_n]['res_type'] in ['scipy', 'polyphase']:
+ if bands_n == 1:
+ spec_c = fft_lp_filter(
+ spec_c, mp.param["pre_filter_start"], mp.param["pre_filter_stop"]
+ )
+ else:
+ gp = 1
+ for b in range(
+ mp.param["pre_filter_start"] + 1, mp.param["pre_filter_stop"]
+ ):
+ g = math.pow(
+ 10, -(b - mp.param["pre_filter_start"]) * (3.5 - gp) / 20.0
+ )
+ gp = g
+ spec_c[:, b, :] *= g
+
+ return np.asfortranarray(spec_c)
+
+
+def spectrogram_to_image(spec, mode="magnitude"):
+ if mode == "magnitude":
+ if np.iscomplexobj(spec):
+ y = np.abs(spec)
+ else:
+ y = spec
+ y = np.log10(y**2 + 1e-8)
+ elif mode == "phase":
+ if np.iscomplexobj(spec):
+ y = np.angle(spec)
+ else:
+ y = spec
+
+ y -= y.min()
+ y *= 255 / y.max()
+ img = np.uint8(y)
+
+ if y.ndim == 3:
+ img = img.transpose(1, 2, 0)
+ img = np.concatenate([np.max(img, axis=2, keepdims=True), img], axis=2)
+
+ return img
+
+
+def reduce_vocal_aggressively(X, y, softmask):
+ v = X - y
+ y_mag_tmp = np.abs(y)
+ v_mag_tmp = np.abs(v)
+
+ v_mask = v_mag_tmp > y_mag_tmp
+ y_mag = np.clip(y_mag_tmp - v_mag_tmp * v_mask * softmask, 0, np.inf)
+
+ return y_mag * np.exp(1.0j * np.angle(y))
+
+
+def mask_silence(mag, ref, thres=0.2, min_range=64, fade_size=32):
+ if min_range < fade_size * 2:
+ raise ValueError("min_range must be >= fade_area * 2")
+
+ mag = mag.copy()
+
+ idx = np.where(ref.mean(axis=(0, 1)) < thres)[0]
+ starts = np.insert(idx[np.where(np.diff(idx) != 1)[0] + 1], 0, idx[0])
+ ends = np.append(idx[np.where(np.diff(idx) != 1)[0]], idx[-1])
+ uninformative = np.where(ends - starts > min_range)[0]
+ if len(uninformative) > 0:
+ starts = starts[uninformative]
+ ends = ends[uninformative]
+ old_e = None
+ for s, e in zip(starts, ends):
+ if old_e is not None and s - old_e < fade_size:
+ s = old_e - fade_size * 2
+
+ if s != 0:
+ weight = np.linspace(0, 1, fade_size)
+ mag[:, :, s : s + fade_size] += weight * ref[:, :, s : s + fade_size]
+ else:
+ s -= fade_size
+
+ if e != mag.shape[2]:
+ weight = np.linspace(1, 0, fade_size)
+ mag[:, :, e - fade_size : e] += weight * ref[:, :, e - fade_size : e]
+ else:
+ e += fade_size
+
+ mag[:, :, s + fade_size : e - fade_size] += ref[
+ :, :, s + fade_size : e - fade_size
+ ]
+ old_e = e
+
+ return mag
+
+
+def align_wave_head_and_tail(a, b):
+ l = min([a[0].size, b[0].size])
+
+ return a[:l, :l], b[:l, :l]
+
+
+def cache_or_load(mix_path, inst_path, mp):
+ mix_basename = os.path.splitext(os.path.basename(mix_path))[0]
+ inst_basename = os.path.splitext(os.path.basename(inst_path))[0]
+
+ cache_dir = "mph{}".format(
+ hashlib.sha1(json.dumps(mp.param, sort_keys=True).encode("utf-8")).hexdigest()
+ )
+ mix_cache_dir = os.path.join("cache", cache_dir)
+ inst_cache_dir = os.path.join("cache", cache_dir)
+
+ os.makedirs(mix_cache_dir, exist_ok=True)
+ os.makedirs(inst_cache_dir, exist_ok=True)
+
+ mix_cache_path = os.path.join(mix_cache_dir, mix_basename + ".npy")
+ inst_cache_path = os.path.join(inst_cache_dir, inst_basename + ".npy")
+
+ if os.path.exists(mix_cache_path) and os.path.exists(inst_cache_path):
+ X_spec_m = np.load(mix_cache_path)
+ y_spec_m = np.load(inst_cache_path)
+ else:
+ X_wave, y_wave, X_spec_s, y_spec_s = {}, {}, {}, {}
+
+ for d in range(len(mp.param["band"]), 0, -1):
+ bp = mp.param["band"][d]
+
+ if d == len(mp.param["band"]): # high-end band
+ X_wave[d], _ = librosa.load(
+ mix_path, bp["sr"], False, dtype=np.float32, res_type=bp["res_type"]
+ )
+ y_wave[d], _ = librosa.load(
+ inst_path,
+ bp["sr"],
+ False,
+ dtype=np.float32,
+ res_type=bp["res_type"],
+ )
+ else: # lower bands
+ X_wave[d] = librosa.resample(
+ X_wave[d + 1],
+ mp.param["band"][d + 1]["sr"],
+ bp["sr"],
+ res_type=bp["res_type"],
+ )
+ y_wave[d] = librosa.resample(
+ y_wave[d + 1],
+ mp.param["band"][d + 1]["sr"],
+ bp["sr"],
+ res_type=bp["res_type"],
+ )
+
+ X_wave[d], y_wave[d] = align_wave_head_and_tail(X_wave[d], y_wave[d])
+
+ X_spec_s[d] = wave_to_spectrogram(
+ X_wave[d],
+ bp["hl"],
+ bp["n_fft"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ )
+ y_spec_s[d] = wave_to_spectrogram(
+ y_wave[d],
+ bp["hl"],
+ bp["n_fft"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ )
+
+ del X_wave, y_wave
+
+ X_spec_m = combine_spectrograms(X_spec_s, mp)
+ y_spec_m = combine_spectrograms(y_spec_s, mp)
+
+ if X_spec_m.shape != y_spec_m.shape:
+ raise ValueError("The combined spectrograms are different: " + mix_path)
+
+ _, ext = os.path.splitext(mix_path)
+
+ np.save(mix_cache_path, X_spec_m)
+ np.save(inst_cache_path, y_spec_m)
+
+ return X_spec_m, y_spec_m
+
+
+def spectrogram_to_wave(spec, hop_length, mid_side, mid_side_b2, reverse):
+ spec_left = np.asfortranarray(spec[0])
+ spec_right = np.asfortranarray(spec[1])
+
+ wave_left = librosa.istft(spec_left, hop_length=hop_length)
+ wave_right = librosa.istft(spec_right, hop_length=hop_length)
+
+ if reverse:
+ return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
+ elif mid_side:
+ return np.asfortranarray(
+ [np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
+ )
+ elif mid_side_b2:
+ return np.asfortranarray(
+ [
+ np.add(wave_right / 1.25, 0.4 * wave_left),
+ np.subtract(wave_left / 1.25, 0.4 * wave_right),
+ ]
+ )
+ else:
+ return np.asfortranarray([wave_left, wave_right])
+
+
+def spectrogram_to_wave_mt(spec, hop_length, mid_side, reverse, mid_side_b2):
+ import threading
+
+ spec_left = np.asfortranarray(spec[0])
+ spec_right = np.asfortranarray(spec[1])
+
+ def run_thread(**kwargs):
+ global wave_left
+ wave_left = librosa.istft(**kwargs)
+
+ thread = threading.Thread(
+ target=run_thread, kwargs={"stft_matrix": spec_left, "hop_length": hop_length}
+ )
+ thread.start()
+ wave_right = librosa.istft(spec_right, hop_length=hop_length)
+ thread.join()
+
+ if reverse:
+ return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
+ elif mid_side:
+ return np.asfortranarray(
+ [np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
+ )
+ elif mid_side_b2:
+ return np.asfortranarray(
+ [
+ np.add(wave_right / 1.25, 0.4 * wave_left),
+ np.subtract(wave_left / 1.25, 0.4 * wave_right),
+ ]
+ )
+ else:
+ return np.asfortranarray([wave_left, wave_right])
+
+
+def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
+ wave_band = {}
+ bands_n = len(mp.param["band"])
+ offset = 0
+
+ for d in range(1, bands_n + 1):
+ bp = mp.param["band"][d]
+ spec_s = np.ndarray(
+ shape=(2, bp["n_fft"] // 2 + 1, spec_m.shape[2]), dtype=complex
+ )
+ h = bp["crop_stop"] - bp["crop_start"]
+ spec_s[:, bp["crop_start"] : bp["crop_stop"], :] = spec_m[
+ :, offset : offset + h, :
+ ]
+
+ offset += h
+ if d == bands_n: # higher
+ if extra_bins_h: # if --high_end_process bypass
+ max_bin = bp["n_fft"] // 2
+ spec_s[:, max_bin - extra_bins_h : max_bin, :] = extra_bins[
+ :, :extra_bins_h, :
+ ]
+ if bp["hpf_start"] > 0:
+ spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
+ if bands_n == 1:
+ wave = spectrogram_to_wave(
+ spec_s,
+ bp["hl"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ )
+ else:
+ wave = np.add(
+ wave,
+ spectrogram_to_wave(
+ spec_s,
+ bp["hl"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ ),
+ )
+ else:
+ sr = mp.param["band"][d + 1]["sr"]
+ if d == 1: # lower
+ spec_s = fft_lp_filter(spec_s, bp["lpf_start"], bp["lpf_stop"])
+ wave = librosa.resample(
+ spectrogram_to_wave(
+ spec_s,
+ bp["hl"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ ),
+ bp["sr"],
+ sr,
+ res_type="sinc_fastest",
+ )
+ else: # mid
+ spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
+ spec_s = fft_lp_filter(spec_s, bp["lpf_start"], bp["lpf_stop"])
+ wave2 = np.add(
+ wave,
+ spectrogram_to_wave(
+ spec_s,
+ bp["hl"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ ),
+ )
+ # wave = librosa.core.resample(wave2, bp['sr'], sr, res_type="sinc_fastest")
+ wave = librosa.core.resample(wave2, bp["sr"], sr, res_type="scipy")
+
+ return wave.T
+
+
+def fft_lp_filter(spec, bin_start, bin_stop):
+ g = 1.0
+ for b in range(bin_start, bin_stop):
+ g -= 1 / (bin_stop - bin_start)
+ spec[:, b, :] = g * spec[:, b, :]
+
+ spec[:, bin_stop:, :] *= 0
+
+ return spec
+
+
+def fft_hp_filter(spec, bin_start, bin_stop):
+ g = 1.0
+ for b in range(bin_start, bin_stop, -1):
+ g -= 1 / (bin_start - bin_stop)
+ spec[:, b, :] = g * spec[:, b, :]
+
+ spec[:, 0 : bin_stop + 1, :] *= 0
+
+ return spec
+
+
+def mirroring(a, spec_m, input_high_end, mp):
+ if "mirroring" == a:
+ mirror = np.flip(
+ np.abs(
+ spec_m[
+ :,
+ mp.param["pre_filter_start"]
+ - 10
+ - input_high_end.shape[1] : mp.param["pre_filter_start"]
+ - 10,
+ :,
+ ]
+ ),
+ 1,
+ )
+ mirror = mirror * np.exp(1.0j * np.angle(input_high_end))
+
+ return np.where(
+ np.abs(input_high_end) <= np.abs(mirror), input_high_end, mirror
+ )
+
+ if "mirroring2" == a:
+ mirror = np.flip(
+ np.abs(
+ spec_m[
+ :,
+ mp.param["pre_filter_start"]
+ - 10
+ - input_high_end.shape[1] : mp.param["pre_filter_start"]
+ - 10,
+ :,
+ ]
+ ),
+ 1,
+ )
+ mi = np.multiply(mirror, input_high_end * 1.7)
+
+ return np.where(np.abs(input_high_end) <= np.abs(mi), input_high_end, mi)
+
+
+def ensembling(a, specs):
+ for i in range(1, len(specs)):
+ if i == 1:
+ spec = specs[0]
+
+ ln = min([spec.shape[2], specs[i].shape[2]])
+ spec = spec[:, :, :ln]
+ specs[i] = specs[i][:, :, :ln]
+
+ if "min_mag" == a:
+ spec = np.where(np.abs(specs[i]) <= np.abs(spec), specs[i], spec)
+ if "max_mag" == a:
+ spec = np.where(np.abs(specs[i]) >= np.abs(spec), specs[i], spec)
+
+ return spec
+
+
+def stft(wave, nfft, hl):
+ wave_left = np.asfortranarray(wave[0])
+ wave_right = np.asfortranarray(wave[1])
+ spec_left = librosa.stft(wave_left, nfft, hop_length=hl)
+ spec_right = librosa.stft(wave_right, nfft, hop_length=hl)
+ spec = np.asfortranarray([spec_left, spec_right])
+
+ return spec
+
+
+def istft(spec, hl):
+ spec_left = np.asfortranarray(spec[0])
+ spec_right = np.asfortranarray(spec[1])
+
+ wave_left = librosa.istft(spec_left, hop_length=hl)
+ wave_right = librosa.istft(spec_right, hop_length=hl)
+ wave = np.asfortranarray([wave_left, wave_right])
+
+
+if __name__ == "__main__":
+ import cv2
+ import sys
+ import time
+ import argparse
+ from model_param_init import ModelParameters
+
+ p = argparse.ArgumentParser()
+ p.add_argument(
+ "--algorithm",
+ "-a",
+ type=str,
+ choices=["invert", "invert_p", "min_mag", "max_mag", "deep", "align"],
+ default="min_mag",
+ )
+ p.add_argument(
+ "--model_params",
+ "-m",
+ type=str,
+ default=os.path.join("modelparams", "1band_sr44100_hl512.json"),
+ )
+ p.add_argument("--output_name", "-o", type=str, default="output")
+ p.add_argument("--vocals_only", "-v", action="store_true")
+ p.add_argument("input", nargs="+")
+ args = p.parse_args()
+
+ start_time = time.time()
+
+ if args.algorithm.startswith("invert") and len(args.input) != 2:
+ raise ValueError("There should be two input files.")
+
+ if not args.algorithm.startswith("invert") and len(args.input) < 2:
+ raise ValueError("There must be at least two input files.")
+
+ wave, specs = {}, {}
+ mp = ModelParameters(args.model_params)
+
+ for i in range(len(args.input)):
+ spec = {}
+
+ for d in range(len(mp.param["band"]), 0, -1):
+ bp = mp.param["band"][d]
+
+ if d == len(mp.param["band"]): # high-end band
+ wave[d], _ = librosa.load(
+ args.input[i],
+ bp["sr"],
+ False,
+ dtype=np.float32,
+ res_type=bp["res_type"],
+ )
+
+ if len(wave[d].shape) == 1: # mono to stereo
+ wave[d] = np.array([wave[d], wave[d]])
+ else: # lower bands
+ wave[d] = librosa.resample(
+ wave[d + 1],
+ mp.param["band"][d + 1]["sr"],
+ bp["sr"],
+ res_type=bp["res_type"],
+ )
+
+ spec[d] = wave_to_spectrogram(
+ wave[d],
+ bp["hl"],
+ bp["n_fft"],
+ mp.param["mid_side"],
+ mp.param["mid_side_b2"],
+ mp.param["reverse"],
+ )
+
+ specs[i] = combine_spectrograms(spec, mp)
+
+ del wave
+
+ if args.algorithm == "deep":
+ d_spec = np.where(np.abs(specs[0]) <= np.abs(spec[1]), specs[0], spec[1])
+ v_spec = d_spec - specs[1]
+ sf.write(
+ os.path.join("{}.wav".format(args.output_name)),
+ cmb_spectrogram_to_wave(v_spec, mp),
+ mp.param["sr"],
+ )
+
+ if args.algorithm.startswith("invert"):
+ ln = min([specs[0].shape[2], specs[1].shape[2]])
+ specs[0] = specs[0][:, :, :ln]
+ specs[1] = specs[1][:, :, :ln]
+
+ if "invert_p" == args.algorithm:
+ X_mag = np.abs(specs[0])
+ y_mag = np.abs(specs[1])
+ max_mag = np.where(X_mag >= y_mag, X_mag, y_mag)
+ v_spec = specs[1] - max_mag * np.exp(1.0j * np.angle(specs[0]))
+ else:
+ specs[1] = reduce_vocal_aggressively(specs[0], specs[1], 0.2)
+ v_spec = specs[0] - specs[1]
+
+ if not args.vocals_only:
+ X_mag = np.abs(specs[0])
+ y_mag = np.abs(specs[1])
+ v_mag = np.abs(v_spec)
+
+ X_image = spectrogram_to_image(X_mag)
+ y_image = spectrogram_to_image(y_mag)
+ v_image = spectrogram_to_image(v_mag)
+
+ cv2.imwrite("{}_X.png".format(args.output_name), X_image)
+ cv2.imwrite("{}_y.png".format(args.output_name), y_image)
+ cv2.imwrite("{}_v.png".format(args.output_name), v_image)
+
+ sf.write(
+ "{}_X.wav".format(args.output_name),
+ cmb_spectrogram_to_wave(specs[0], mp),
+ mp.param["sr"],
+ )
+ sf.write(
+ "{}_y.wav".format(args.output_name),
+ cmb_spectrogram_to_wave(specs[1], mp),
+ mp.param["sr"],
+ )
+
+ sf.write(
+ "{}_v.wav".format(args.output_name),
+ cmb_spectrogram_to_wave(v_spec, mp),
+ mp.param["sr"],
+ )
+ else:
+ if not args.algorithm == "deep":
+ sf.write(
+ os.path.join("ensembled", "{}.wav".format(args.output_name)),
+ cmb_spectrogram_to_wave(ensembling(args.algorithm, specs), mp),
+ mp.param["sr"],
+ )
+
+ if args.algorithm == "align":
+ trackalignment = [
+ {
+ "file1": '"{}"'.format(args.input[0]),
+ "file2": '"{}"'.format(args.input[1]),
+ }
+ ]
+
+ for i, e in tqdm(enumerate(trackalignment), desc="Performing Alignment..."):
+ os.system(f"python lib/align_tracks.py {e['file1']} {e['file2']}")
+
+ # print('Total time: {0:.{1}f}s'.format(time.time() - start_time, 1))
diff --git a/uvr5_pack/name_params.json b/uvr5_pack/name_params.json
new file mode 100644
index 0000000000000000000000000000000000000000..cb6609134a3831799b9ed190fac09e1eef59f9cb
--- /dev/null
+++ b/uvr5_pack/name_params.json
@@ -0,0 +1,263 @@
+{
+ "equivalent" : [
+ {
+ "model_hash_name" : [
+ {
+ "hash_name": "47939caf0cfe52a0e81442b85b971dfd",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100"
+ },
+ {
+ "hash_name": "4e4ecb9764c50a8c414fee6e10395bbe",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_v2.json",
+ "param_name": "4band_v2"
+ },
+ {
+ "hash_name": "ca106edd563e034bde0bdec4bb7a4b36",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_v2.json",
+ "param_name": "4band_v2"
+ },
+ {
+ "hash_name": "e60a1e84803ce4efc0a6551206cc4b71",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100"
+ },
+ {
+ "hash_name": "a82f14e75892e55e994376edbf0c8435",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100"
+ },
+ {
+ "hash_name": "6dd9eaa6f0420af9f1d403aaafa4cc06",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_v2_sn.json",
+ "param_name": "4band_v2_sn"
+ },
+ {
+ "hash_name": "08611fb99bd59eaa79ad27c58d137727",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_v2_sn.json",
+ "param_name": "4band_v2_sn"
+ },
+ {
+ "hash_name": "5c7bbca45a187e81abbbd351606164e5",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json",
+ "param_name": "3band_44100_msb2"
+ },
+ {
+ "hash_name": "d6b2cb685a058a091e5e7098192d3233",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json",
+ "param_name": "3band_44100_msb2"
+ },
+ {
+ "hash_name": "c1b9f38170a7c90e96f027992eb7c62b",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100"
+ },
+ {
+ "hash_name": "c3448ec923fa0edf3d03a19e633faa53",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100"
+ },
+ {
+ "hash_name": "68aa2c8093d0080704b200d140f59e54",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100.json",
+ "param_name": "3band_44100"
+ },
+ {
+ "hash_name": "fdc83be5b798e4bd29fe00fe6600e147",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100_mid.json",
+ "param_name": "3band_44100_mid.json"
+ },
+ {
+ "hash_name": "2ce34bc92fd57f55db16b7a4def3d745",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100_mid.json",
+ "param_name": "3band_44100_mid.json"
+ },
+ {
+ "hash_name": "52fdca89576f06cf4340b74a4730ee5f",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100.json"
+ },
+ {
+ "hash_name": "41191165b05d38fc77f072fa9e8e8a30",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100.json"
+ },
+ {
+ "hash_name": "89e83b511ad474592689e562d5b1f80e",
+ "model_params": "uvr5_pack/lib_v5/modelparams/2band_32000.json",
+ "param_name": "2band_32000.json"
+ },
+ {
+ "hash_name": "0b954da81d453b716b114d6d7c95177f",
+ "model_params": "uvr5_pack/lib_v5/modelparams/2band_32000.json",
+ "param_name": "2band_32000.json"
+ }
+
+ ],
+ "v4 Models": [
+ {
+ "hash_name": "6a00461c51c2920fd68937d4609ed6c8",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json",
+ "param_name": "1band_sr16000_hl512"
+ },
+ {
+ "hash_name": "0ab504864d20f1bd378fe9c81ef37140",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+ "param_name": "1band_sr32000_hl512"
+ },
+ {
+ "hash_name": "7dd21065bf91c10f7fccb57d7d83b07f",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+ "param_name": "1band_sr32000_hl512"
+ },
+ {
+ "hash_name": "80ab74d65e515caa3622728d2de07d23",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+ "param_name": "1band_sr32000_hl512"
+ },
+ {
+ "hash_name": "edc115e7fc523245062200c00caa847f",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json",
+ "param_name": "1band_sr33075_hl384"
+ },
+ {
+ "hash_name": "28063e9f6ab5b341c5f6d3c67f2045b7",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json",
+ "param_name": "1band_sr33075_hl384"
+ },
+ {
+ "hash_name": "b58090534c52cbc3e9b5104bad666ef2",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json",
+ "param_name": "1band_sr44100_hl512"
+ },
+ {
+ "hash_name": "0cdab9947f1b0928705f518f3c78ea8f",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json",
+ "param_name": "1band_sr44100_hl512"
+ },
+ {
+ "hash_name": "ae702fed0238afb5346db8356fe25f13",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json",
+ "param_name": "1band_sr44100_hl1024"
+ }
+ ]
+ }
+ ],
+ "User Models" : [
+ {
+ "1 Band": [
+ {
+ "hash_name": "1band_sr16000_hl512",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json",
+ "param_name": "1band_sr16000_hl512"
+ },
+ {
+ "hash_name": "1band_sr32000_hl512",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+ "param_name": "1band_sr16000_hl512"
+ },
+ {
+ "hash_name": "1band_sr33075_hl384",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json",
+ "param_name": "1band_sr33075_hl384"
+ },
+ {
+ "hash_name": "1band_sr44100_hl256",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json",
+ "param_name": "1band_sr44100_hl256"
+ },
+ {
+ "hash_name": "1band_sr44100_hl512",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json",
+ "param_name": "1band_sr44100_hl512"
+ },
+ {
+ "hash_name": "1band_sr44100_hl1024",
+ "model_params": "uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json",
+ "param_name": "1band_sr44100_hl1024"
+ }
+ ],
+ "2 Band": [
+ {
+ "hash_name": "2band_44100_lofi",
+ "model_params": "uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json",
+ "param_name": "2band_44100_lofi"
+ },
+ {
+ "hash_name": "2band_32000",
+ "model_params": "uvr5_pack/lib_v5/modelparams/2band_32000.json",
+ "param_name": "2band_32000"
+ },
+ {
+ "hash_name": "2band_48000",
+ "model_params": "uvr5_pack/lib_v5/modelparams/2band_48000.json",
+ "param_name": "2band_48000"
+ }
+ ],
+ "3 Band": [
+ {
+ "hash_name": "3band_44100",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100.json",
+ "param_name": "3band_44100"
+ },
+ {
+ "hash_name": "3band_44100_mid",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100_mid.json",
+ "param_name": "3band_44100_mid"
+ },
+ {
+ "hash_name": "3band_44100_msb2",
+ "model_params": "uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json",
+ "param_name": "3band_44100_msb2"
+ }
+ ],
+ "4 Band": [
+ {
+ "hash_name": "4band_44100",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100.json",
+ "param_name": "4band_44100"
+ },
+ {
+ "hash_name": "4band_44100_mid",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100_mid.json",
+ "param_name": "4band_44100_mid"
+ },
+ {
+ "hash_name": "4band_44100_msb",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100_msb.json",
+ "param_name": "4band_44100_msb"
+ },
+ {
+ "hash_name": "4band_44100_msb2",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json",
+ "param_name": "4band_44100_msb2"
+ },
+ {
+ "hash_name": "4band_44100_reverse",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json",
+ "param_name": "4band_44100_reverse"
+ },
+ {
+ "hash_name": "4band_44100_sw",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_44100_sw.json",
+ "param_name": "4band_44100_sw"
+ },
+ {
+ "hash_name": "4band_v2",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_v2.json",
+ "param_name": "4band_v2"
+ },
+ {
+ "hash_name": "4band_v2_sn",
+ "model_params": "uvr5_pack/lib_v5/modelparams/4band_v2_sn.json",
+ "param_name": "4band_v2_sn"
+ },
+ {
+ "hash_name": "tmodelparam",
+ "model_params": "uvr5_pack/lib_v5/modelparams/tmodelparam.json",
+ "param_name": "User Model Param Set"
+ }
+ ]
+ }
+ ]
+}
\ No newline at end of file
diff --git a/uvr5_pack/utils.py b/uvr5_pack/utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..1d91f963370321cf093c7fb9adefaa018463c8da
--- /dev/null
+++ b/uvr5_pack/utils.py
@@ -0,0 +1,120 @@
+import torch
+import numpy as np
+from tqdm import tqdm
+import json
+
+
+def load_data(file_name: str = "./uvr5_pack/name_params.json") -> dict:
+ with open(file_name, "r") as f:
+ data = json.load(f)
+
+ return data
+
+
+def make_padding(width, cropsize, offset):
+ left = offset
+ roi_size = cropsize - left * 2
+ if roi_size == 0:
+ roi_size = cropsize
+ right = roi_size - (width % roi_size) + left
+
+ return left, right, roi_size
+
+
+def inference(X_spec, device, model, aggressiveness, data):
+ """
+ data ： dic configs
+ """
+
+ def _execute(
+ X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half=True
+ ):
+ model.eval()
+ with torch.no_grad():
+ preds = []
+
+ iterations = [n_window]
+
+ total_iterations = sum(iterations)
+ for i in tqdm(range(n_window)):
+ start = i * roi_size
+ X_mag_window = X_mag_pad[
+ None, :, :, start : start + data["window_size"]
+ ]
+ X_mag_window = torch.from_numpy(X_mag_window)
+ if is_half:
+ X_mag_window = X_mag_window.half()
+ X_mag_window = X_mag_window.to(device)
+
+ pred = model.predict(X_mag_window, aggressiveness)
+
+ pred = pred.detach().cpu().numpy()
+ preds.append(pred[0])
+
+ pred = np.concatenate(preds, axis=2)
+ return pred
+
+ def preprocess(X_spec):
+ X_mag = np.abs(X_spec)
+ X_phase = np.angle(X_spec)
+
+ return X_mag, X_phase
+
+ X_mag, X_phase = preprocess(X_spec)
+
+ coef = X_mag.max()
+ X_mag_pre = X_mag / coef
+
+ n_frame = X_mag_pre.shape[2]
+ pad_l, pad_r, roi_size = make_padding(n_frame, data["window_size"], model.offset)
+ n_window = int(np.ceil(n_frame / roi_size))
+
+ X_mag_pad = np.pad(X_mag_pre, ((0, 0), (0, 0), (pad_l, pad_r)), mode="constant")
+
+ if list(model.state_dict().values())[0].dtype == torch.float16:
+ is_half = True
+ else:
+ is_half = False
+ pred = _execute(
+ X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half
+ )
+ pred = pred[:, :, :n_frame]
+
+ if data["tta"]:
+ pad_l += roi_size // 2
+ pad_r += roi_size // 2
+ n_window += 1
+
+ X_mag_pad = np.pad(X_mag_pre, ((0, 0), (0, 0), (pad_l, pad_r)), mode="constant")
+
+ pred_tta = _execute(
+ X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half
+ )
+ pred_tta = pred_tta[:, :, roi_size // 2 :]
+ pred_tta = pred_tta[:, :, :n_frame]
+
+ return (pred + pred_tta) * 0.5 * coef, X_mag, np.exp(1.0j * X_phase)
+ else:
+ return pred * coef, X_mag, np.exp(1.0j * X_phase)
+
+
+def _get_name_params(model_path, model_hash):
+ data = load_data()
+ flag = False
+ ModelName = model_path
+ for type in list(data):
+ for model in list(data[type][0]):
+ for i in range(len(data[type][0][model])):
+ if str(data[type][0][model][i]["hash_name"]) == model_hash:
+ flag = True
+ elif str(data[type][0][model][i]["hash_name"]) in ModelName:
+ flag = True
+
+ if flag:
+ model_params_auto = data[type][0][model][i]["model_params"]
+ param_name_auto = data[type][0][model][i]["param_name"]
+ if type == "equivalent":
+ return param_name_auto, model_params_auto
+ else:
+ flag = False
+ return param_name_auto, model_params_auto
diff --git a/uvr5_weights/.gitignore b/uvr5_weights/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..d6b7ef32c8478a48c3994dcadc86837f4371184d
--- /dev/null
+++ b/uvr5_weights/.gitignore
@@ -0,0 +1,2 @@
+*
+!.gitignore
diff --git a/vc_infer_pipeline.py b/vc_infer_pipeline.py
new file mode 100644
index 0000000000000000000000000000000000000000..7adf5ce0b6ec782ad0f436d8d19dea2b0d0c6663
--- /dev/null
+++ b/vc_infer_pipeline.py
@@ -0,0 +1,436 @@
+import numpy as np, parselmouth, torch, pdb
+from time import time as ttime
+import torch.nn.functional as F
+import scipy.signal as signal
+import pyworld, os, traceback, faiss, librosa, torchcrepe
+from scipy import signal
+from functools import lru_cache
+
+bh, ah = signal.butter(N=5, Wn=48, btype="high", fs=16000)
+
+input_audio_path2wav = {}
+
+
+@lru_cache
+def cache_harvest_f0(input_audio_path, fs, f0max, f0min, frame_period):
+ audio = input_audio_path2wav[input_audio_path]
+ f0, t = pyworld.harvest(
+ audio,
+ fs=fs,
+ f0_ceil=f0max,
+ f0_floor=f0min,
+ frame_period=frame_period,
+ )
+ f0 = pyworld.stonemask(audio, f0, t, fs)
+ return f0
+
+
+def change_rms(data1, sr1, data2, sr2, rate): # 1是输入音频，2是输出音频,rate是2的占比
+ # print(data1.max(),data2.max())
+ rms1 = librosa.feature.rms(
+ y=data1, frame_length=sr1 // 2 * 2, hop_length=sr1 // 2
+ ) # 每半秒一个点
+ rms2 = librosa.feature.rms(y=data2, frame_length=sr2 // 2 * 2, hop_length=sr2 // 2)
+ rms1 = torch.from_numpy(rms1)
+ rms1 = F.interpolate(
+ rms1.unsqueeze(0), size=data2.shape[0], mode="linear"
+ ).squeeze()
+ rms2 = torch.from_numpy(rms2)
+ rms2 = F.interpolate(
+ rms2.unsqueeze(0), size=data2.shape[0], mode="linear"
+ ).squeeze()
+ rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-6)
+ data2 *= (
+ torch.pow(rms1, torch.tensor(1 - rate))
+ * torch.pow(rms2, torch.tensor(rate - 1))
+ ).numpy()
+ return data2
+
+
+class VC(object):
+ def __init__(self, tgt_sr, config):
+ self.x_pad, self.x_query, self.x_center, self.x_max, self.is_half = (
+ config.x_pad,
+ config.x_query,
+ config.x_center,
+ config.x_max,
+ config.is_half,
+ )
+ self.sr = 16000 # hubert输入采样率
+ self.window = 160 # 每帧点数
+ self.t_pad = int(self.sr * self.x_pad) # 每条前后pad时间
+ self.t_pad_tgt = int(tgt_sr * self.x_pad)
+ self.t_pad2 = self.t_pad * 2
+ self.t_query = self.sr * self.x_query # 查询切点前后查询时间
+ self.t_center = self.sr * self.x_center # 查询切点位置
+ self.t_max = self.sr * self.x_max # 免查询时长阈值
+ self.device = config.device
+
+ def get_f0(
+ self,
+ input_audio_path,
+ x,
+ p_len,
+ f0_up_key,
+ f0_method,
+ filter_radius,
+ inp_f0=None,
+ ):
+ global input_audio_path2wav
+ time_step = self.window / self.sr * 1000
+ f0_min = 50
+ f0_max = 1100
+ f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+ f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+ if f0_method == "pm":
+ f0 = (
+ parselmouth.Sound(x, self.sr)
+ .to_pitch_ac(
+ time_step=time_step / 1000,
+ voicing_threshold=0.6,
+ pitch_floor=f0_min,
+ pitch_ceiling=f0_max,
+ )
+ .selected_array["frequency"]
+ )
+ pad_size = (p_len - len(f0) + 1) // 2
+ if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+ f0 = np.pad(
+ f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
+ )
+ # elif f0_method == "harvest":
+ # input_audio_path2wav[input_audio_path] = x.astype(np.double)
+ # f0 = cache_harvest_f0(input_audio_path, self.sr, f0_max, f0_min, 10)
+ # if filter_radius > 2:
+ # f0 = signal.medfilt(f0, 3)
+ elif f0_method == "dio":
+ input_audio_path2wav[input_audio_path] = x.astype(np.double)
+ f0 = cache_harvest_f0(input_audio_path, self.sr, f0_max, f0_min, 10)
+ if filter_radius > 2:
+ f0 = signal.medfilt(f0, 3)
+ elif f0_method == "crepe":
+ model = "full"
+ # Pick a batch size that doesn't cause memory errors on your gpu
+ batch_size = 512
+ # Compute pitch using first gpu
+ audio = torch.tensor(np.copy(x))[None].float()
+ f0, pd = torchcrepe.predict(
+ audio,
+ self.sr,
+ self.window,
+ f0_min,
+ f0_max,
+ model,
+ batch_size=batch_size,
+ device=self.device,
+ return_periodicity=True,
+ )
+ pd = torchcrepe.filter.median(pd, 3)
+ f0 = torchcrepe.filter.mean(f0, 3)
+ f0[pd < 0.1] = 0
+ f0 = f0[0].cpu().numpy()
+ f0 *= pow(2, f0_up_key / 12)
+ # with open("test.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+ tf0 = self.sr // self.window # 每秒f0点数
+ if inp_f0 is not None:
+ delta_t = np.round(
+ (inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1
+ ).astype("int16")
+ replace_f0 = np.interp(
+ list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1]
+ )
+ shape = f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)].shape[0]
+ f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)] = replace_f0[
+ :shape
+ ]
+ # with open("test_opt.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+ f0bak = f0.copy()
+ f0_mel = 1127 * np.log(1 + f0 / 700)
+ f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+ f0_mel_max - f0_mel_min
+ ) + 1
+ f0_mel[f0_mel <= 1] = 1
+ f0_mel[f0_mel > 255] = 255
+ f0_coarse = np.rint(f0_mel).astype(np.int)
+ return f0_coarse, f0bak # 1-0
+
+ def vc(
+ self,
+ model,
+ net_g,
+ sid,
+ audio0,
+ pitch,
+ pitchf,
+ times,
+ index,
+ big_npy,
+ index_rate,
+ version,
+ protect,
+ ): # ,file_index,file_big_npy
+ feats = torch.from_numpy(audio0)
+ if self.is_half:
+ feats = feats.half()
+ else:
+ feats = feats.float()
+ if feats.dim() == 2: # double channels
+ feats = feats.mean(-1)
+ assert feats.dim() == 1, feats.dim()
+ feats = feats.view(1, -1)
+ padding_mask = torch.BoolTensor(feats.shape).to(self.device).fill_(False)
+
+ inputs = {
+ "source": feats.to(self.device),
+ "padding_mask": padding_mask,
+ "output_layer": 9 if version == "v1" else 12,
+ }
+ t0 = ttime()
+ with torch.no_grad():
+ logits = model.extract_features(**inputs)
+ feats = model.final_proj(logits[0]) if version == "v1" else logits[0]
+ if protect < 0.5:
+ feats0 = feats.clone()
+ if (
+ isinstance(index, type(None)) == False
+ and isinstance(big_npy, type(None)) == False
+ and index_rate != 0
+ ):
+ npy = feats[0].cpu().numpy()
+ if self.is_half:
+ npy = npy.astype("float32")
+
+ # _, I = index.search(npy, 1)
+ # npy = big_npy[I.squeeze()]
+
+ score, ix = index.search(npy, k=8)
+ weight = np.square(1 / score)
+ weight /= weight.sum(axis=1, keepdims=True)
+ npy = np.sum(big_npy[ix] * np.expand_dims(weight, axis=2), axis=1)
+
+ if self.is_half:
+ npy = npy.astype("float16")
+ feats = (
+ torch.from_numpy(npy).unsqueeze(0).to(self.device) * index_rate
+ + (1 - index_rate) * feats
+ )
+
+ feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
+ if protect < 0.5:
+ feats0 = F.interpolate(feats0.permute(0, 2, 1), scale_factor=2).permute(
+ 0, 2, 1
+ )
+ t1 = ttime()
+ p_len = audio0.shape[0] // self.window
+ if feats.shape[1] < p_len:
+ p_len = feats.shape[1]
+ if pitch != None and pitchf != None:
+ pitch = pitch[:, :p_len]
+ pitchf = pitchf[:, :p_len]
+
+ if protect < 0.5:
+ pitchff = pitchf.clone()
+ pitchff[pitchf > 0] = 1
+ pitchff[pitchf < 1] = protect
+ pitchff = pitchff.unsqueeze(-1)
+ feats = feats * pitchff + feats0 * (1 - pitchff)
+ feats = feats.to(feats0.dtype)
+ p_len = torch.tensor([p_len], device=self.device).long()
+ with torch.no_grad():
+ if pitch != None and pitchf != None:
+ audio1 = (
+ (net_g.infer(feats, p_len, pitch, pitchf, sid)[0][0, 0])
+ .data.cpu()
+ .float()
+ .numpy()
+ )
+ else:
+ audio1 = (
+ (net_g.infer(feats, p_len, sid)[0][0, 0]).data.cpu().float().numpy()
+ )
+ del feats, p_len, padding_mask
+ if torch.cuda.is_available():
+ torch.cuda.empty_cache()
+ t2 = ttime()
+ times[0] += t1 - t0
+ times[2] += t2 - t1
+ return audio1
+
+ def pipeline(
+ self,
+ model,
+ net_g,
+ sid,
+ audio,
+ input_audio_path,
+ times,
+ f0_up_key,
+ f0_method,
+ file_index,
+ # file_big_npy,
+ index_rate,
+ if_f0,
+ filter_radius,
+ tgt_sr,
+ resample_sr,
+ rms_mix_rate,
+ version,
+ protect,
+ f0_file=None,
+ ):
+ if (
+ file_index != ""
+ # and file_big_npy != ""
+ # and os.path.exists(file_big_npy) == True
+ and os.path.exists(file_index) == True
+ and index_rate != 0
+ ):
+ try:
+ index = faiss.read_index(file_index)
+ # big_npy = np.load(file_big_npy)
+ big_npy = index.reconstruct_n(0, index.ntotal)
+ except:
+ traceback.print_exc()
+ index = big_npy = None
+ else:
+ index = big_npy = None
+ audio = signal.filtfilt(bh, ah, audio)
+ audio_pad = np.pad(audio, (self.window // 2, self.window // 2), mode="reflect")
+ opt_ts = []
+ if audio_pad.shape[0] > self.t_max:
+ audio_sum = np.zeros_like(audio)
+ for i in range(self.window):
+ audio_sum += audio_pad[i : i - self.window]
+ for t in range(self.t_center, audio.shape[0], self.t_center):
+ opt_ts.append(
+ t
+ - self.t_query
+ + np.where(
+ np.abs(audio_sum[t - self.t_query : t + self.t_query])
+ == np.abs(audio_sum[t - self.t_query : t + self.t_query]).min()
+ )[0][0]
+ )
+ s = 0
+ audio_opt = []
+ t = None
+ t1 = ttime()
+ audio_pad = np.pad(audio, (self.t_pad, self.t_pad), mode="reflect")
+ p_len = audio_pad.shape[0] // self.window
+ inp_f0 = None
+ if hasattr(f0_file, "name") == True:
+ try:
+ with open(f0_file.name, "r") as f:
+ lines = f.read().strip("\n").split("\n")
+ inp_f0 = []
+ for line in lines:
+ inp_f0.append([float(i) for i in line.split(",")])
+ inp_f0 = np.array(inp_f0, dtype="float32")
+ except:
+ traceback.print_exc()
+ sid = torch.tensor(sid, device=self.device).unsqueeze(0).long()
+ pitch, pitchf = None, None
+ if if_f0 == 1:
+ pitch, pitchf = self.get_f0(
+ input_audio_path,
+ audio_pad,
+ p_len,
+ f0_up_key,
+ f0_method,
+ filter_radius,
+ inp_f0,
+ )
+ pitch = pitch[:p_len]
+ pitchf = pitchf[:p_len]
+ if self.device == "mps":
+ pitchf = pitchf.astype(np.float32)
+ pitch = torch.tensor(pitch, device=self.device).unsqueeze(0).long()
+ pitchf = torch.tensor(pitchf, device=self.device).unsqueeze(0).float()
+ t2 = ttime()
+ times[1] += t2 - t1
+ for t in opt_ts:
+ t = t // self.window * self.window
+ if if_f0 == 1:
+ audio_opt.append(
+ self.vc(
+ model,
+ net_g,
+ sid,
+ audio_pad[s : t + self.t_pad2 + self.window],
+ pitch[:, s // self.window : (t + self.t_pad2) // self.window],
+ pitchf[:, s // self.window : (t + self.t_pad2) // self.window],
+ times,
+ index,
+ big_npy,
+ index_rate,
+ version,
+ protect,
+ )[self.t_pad_tgt : -self.t_pad_tgt]
+ )
+ else:
+ audio_opt.append(
+ self.vc(
+ model,
+ net_g,
+ sid,
+ audio_pad[s : t + self.t_pad2 + self.window],
+ None,
+ None,
+ times,
+ index,
+ big_npy,
+ index_rate,
+ version,
+ protect,
+ )[self.t_pad_tgt : -self.t_pad_tgt]
+ )
+ s = t
+ if if_f0 == 1:
+ audio_opt.append(
+ self.vc(
+ model,
+ net_g,
+ sid,
+ audio_pad[t:],
+ pitch[:, t // self.window :] if t is not None else pitch,
+ pitchf[:, t // self.window :] if t is not None else pitchf,
+ times,
+ index,
+ big_npy,
+ index_rate,
+ version,
+ protect,
+ )[self.t_pad_tgt : -self.t_pad_tgt]
+ )
+ else:
+ audio_opt.append(
+ self.vc(
+ model,
+ net_g,
+ sid,
+ audio_pad[t:],
+ None,
+ None,
+ times,
+ index,
+ big_npy,
+ index_rate,
+ version,
+ protect,
+ )[self.t_pad_tgt : -self.t_pad_tgt]
+ )
+ audio_opt = np.concatenate(audio_opt)
+ if rms_mix_rate != 1:
+ audio_opt = change_rms(audio, 16000, audio_opt, tgt_sr, rms_mix_rate)
+ if resample_sr >= 16000 and tgt_sr != resample_sr:
+ audio_opt = librosa.resample(
+ audio_opt, orig_sr=tgt_sr, target_sr=resample_sr
+ )
+ audio_max = np.abs(audio_opt).max() / 0.99
+ max_int16 = 32768
+ if audio_max > 1:
+ max_int16 /= audio_max
+ audio_opt = (audio_opt * max_int16).astype(np.int16)
+ del pitch, pitchf, sid
+ if torch.cuda.is_available():
+ torch.cuda.empty_cache()
+ return audio_opt
diff --git a/weights/.gitignore b/weights/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..d6b7ef32c8478a48c3994dcadc86837f4371184d
--- /dev/null
+++ b/weights/.gitignore
@@ -0,0 +1,2 @@
+*
+!.gitignore
diff --git a/weights/simple-guitar-crepe-guolv_e1000.pth b/weights/simple-guitar-crepe-guolv_e1000.pth
new file mode 100644
index 0000000000000000000000000000000000000000..60bf195811780aad0e891c112c488b4433e9b768
--- /dev/null
+++ b/weights/simple-guitar-crepe-guolv_e1000.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee309c6696f4cd93eb2a8db0d27d62098a070b94a42ef961cb09060da1e1806
+size 55234359