Upload 11 files

100epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bae8667fd213c3b5a093e8122fb93e0a2d7dc3e8a502543c97940354bdaea10
+size 373275392

README.md

@@ -1,10 +1,10 @@
 ---
-title: AI Kishida Fumio Speaker
-emoji: 🐢
-colorFrom: red
-colorTo: pink
+title: AI岸田文雄メーカー
+emoji: 🔥
+colorFrom: indigo
+colorTo: blue
 sdk: streamlit
-sdk_version: 1.27.2
+sdk_version: 1.27.0
 app_file: app.py
 pinned: false
 license: openrail

app.py

@@ -0,0 +1,37 @@
+import time
+
+import streamlit as st
+import numpy as np
+import torch
+from espnet2.bin.tts_inference import Text2Speech
+from scipy.io.wavfile import write
+from PIL import Image
+
+
+fs, lang = 44100, "Japanese"
+model= "./100epoch.pth"
+x = "これはテストメッセージです"
+
+text2speech = Text2Speech.from_pretrained(
+    model_file=model,
+    device="cpu",
+    speed_control_alpha=1.0,
+    noise_scale=0.333,
+    noise_scale_dur=0.333,
+)
+pause = np.zeros(30000, dtype=np.float32)
+
+st.title("おしゃべりAI岸田文雄メーカー")
+image = Image.open('kishida.jpg')
+st.image(image)
+text = st.text_area(label='ここにテキストを入力 (Input Text)↓', height=100, max_chars=2048)
+
+
+if st.button("生成（Generate）"):
+    with torch.no_grad():
+        wav = text2speech(text)["wav"]
+
+    wav_list = []
+    wav_list.append(np.concatenate([wav.view(-1).cpu().numpy(), pause]))
+    final_wav = np.concatenate(wav_list)
+    st.audio(final_wav, sample_rate=fs)

config.yaml

@@ -0,0 +1,404 @@
+config: ./conf/tuning/finetune_full_band_vits.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/tts_full_band_vits
+ngpu: 1
+seed: 777
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: null
+dist_rank: null
+local_rank: 0
+dist_master_addr: null
+dist_master_port: null
+dist_launcher: null
+multiprocessing_distributed: false
+unused_parameters: true
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 100
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - train
+    - total_count
+    - max
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: -1
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: 50
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+pretrain_path: null
+init_param:
+- downloads/full_band_vits_accent_with_pause_pretrain/exp/tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_accent_with_pause/train.total_count.ave_10best.pth:tts:tts
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 1000
+batch_size: 20
+valid_batch_size: null
+batch_bins: 100000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_jaconv_pyopenjtalk_accent_with_pause/train/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_jaconv_pyopenjtalk_accent_with_pause/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_jaconv_pyopenjtalk_accent_with_pause/valid/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_jaconv_pyopenjtalk_accent_with_pause/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 409600
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+train_data_path_and_name_and_type:
+-   - dump/44k/raw/tr_no_dev/text
+    - text
+    - text
+-   - dump/44k/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/44k/raw/dev/text
+    - text
+    - text
+-   - dump/44k/raw/dev/wav.scp
+    - speech
+    - sound
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adamw
+optim_conf:
+    lr: 0.0001
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler: exponentiallr
+scheduler_conf:
+    gamma: 0.999875
+optim2: adamw
+optim2_conf:
+    lr: 0.0001
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler2: exponentiallr
+scheduler2_conf:
+    gamma: 0.999875
+generator_first: false
+token_list:
+- <blank>
+- <unk>
+- '1'
+- '2'
+- '0'
+- '3'
+- '4'
+- '-1'
+- '5'
+- a
+- o
+- '-2'
+- i
+- '-3'
+- u
+- e
+- k
+- n
+- t
+- '6'
+- r
+- '-4'
+- s
+- N
+- m
+- pau
+- '7'
+- sh
+- d
+- g
+- w
+- '8'
+- U
+- '-5'
+- I
+- cl
+- h
+- y
+- b
+- '9'
+- j
+- ts
+- ch
+- '-6'
+- z
+- p
+- '-7'
+- f
+- ky
+- ry
+- '-8'
+- gy
+- '-9'
+- hy
+- ny
+- '-10'
+- by
+- my
+- '-11'
+- '-12'
+- '-13'
+- py
+- '-14'
+- '-15'
+- v
+- '10'
+- '-16'
+- '-17'
+- '11'
+- '-21'
+- '-20'
+- '12'
+- '-19'
+- '13'
+- '-18'
+- '14'
+- dy
+- '15'
+- ty
+- '-22'
+- '16'
+- '18'
+- '19'
+- '17'
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: jaconv
+g2p: pyopenjtalk_accent_with_pause
+feats_extract: linear_spectrogram
+feats_extract_conf:
+    n_fft: 2048
+    hop_length: 512
+    win_length: null
+normalize: null
+normalize_conf: {}
+tts: vits
+tts_conf:
+    generator_type: vits_generator
+    generator_params:
+        hidden_channels: 192
+        spks: -1
+        global_channels: -1
+        segment_size: 32
+        text_encoder_attention_heads: 2
+        text_encoder_ffn_expand: 4
+        text_encoder_blocks: 6
+        text_encoder_positionwise_layer_type: conv1d
+        text_encoder_positionwise_conv_kernel_size: 3
+        text_encoder_positional_encoding_layer_type: rel_pos
+        text_encoder_self_attention_layer_type: rel_selfattn
+        text_encoder_activation_type: swish
+        text_encoder_normalize_before: true
+        text_encoder_dropout_rate: 0.1
+        text_encoder_positional_dropout_rate: 0.0
+        text_encoder_attention_dropout_rate: 0.1
+        use_macaron_style_in_text_encoder: true
+        use_conformer_conv_in_text_encoder: false
+        text_encoder_conformer_kernel_size: -1
+        decoder_kernel_size: 7
+        decoder_channels: 512
+        decoder_upsample_scales:
+        - 8
+        - 8
+        - 2
+        - 2
+        - 2
+        decoder_upsample_kernel_sizes:
+        - 16
+        - 16
+        - 4
+        - 4
+        - 4
+        decoder_resblock_kernel_sizes:
+        - 3
+        - 7
+        - 11
+        decoder_resblock_dilations:
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        use_weight_norm_in_decoder: true
+        posterior_encoder_kernel_size: 5
+        posterior_encoder_layers: 16
+        posterior_encoder_stacks: 1
+        posterior_encoder_base_dilation: 1
+        posterior_encoder_dropout_rate: 0.0
+        use_weight_norm_in_posterior_encoder: true
+        flow_flows: 4
+        flow_kernel_size: 5
+        flow_base_dilation: 1
+        flow_layers: 4
+        flow_dropout_rate: 0.0
+        use_weight_norm_in_flow: true
+        use_only_mean_in_flow: true
+        stochastic_duration_predictor_kernel_size: 3
+        stochastic_duration_predictor_dropout_rate: 0.5
+        stochastic_duration_predictor_flows: 4
+        stochastic_duration_predictor_dds_conv_layers: 3
+        vocabs: 85
+        aux_channels: 1025
+    discriminator_type: hifigan_multi_scale_multi_period_discriminator
+    discriminator_params:
+        scales: 1
+        scale_downsample_pooling: AvgPool1d
+        scale_downsample_pooling_params:
+            kernel_size: 4
+            stride: 2
+            padding: 2
+        scale_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 15
+            - 41
+            - 5
+            - 3
+            channels: 128
+            max_downsample_channels: 1024
+            max_groups: 16
+            bias: true
+            downsample_scales:
+            - 2
+            - 2
+            - 4
+            - 4
+            - 1
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+        follow_official_norm: false
+        periods:
+        - 2
+        - 3
+        - 5
+        - 7
+        - 11
+        period_discriminator_params:
+            in_channels: 1
+            out_channels: 1
+            kernel_sizes:
+            - 5
+            - 3
+            channels: 32
+            downsample_scales:
+            - 3
+            - 3
+            - 3
+            - 3
+            - 1
+            max_downsample_channels: 1024
+            bias: true
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            use_weight_norm: true
+            use_spectral_norm: false
+    generator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    discriminator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    feat_match_loss_params:
+        average_by_discriminators: false
+        average_by_layers: false
+        include_final_outputs: true
+    mel_loss_params:
+        fs: 44100
+        n_fft: 2048
+        hop_length: 512
+        win_length: null
+        window: hann
+        n_mels: 80
+        fmin: 0
+        fmax: null
+        log_base: null
+    lambda_adv: 1.0
+    lambda_mel: 45.0
+    lambda_feat_match: 2.0
+    lambda_dur: 1.0
+    lambda_kl: 1.0
+    sampling_rate: 44100
+    cache_generator_outputs: true
+pitch_extract: null
+pitch_extract_conf: {}
+pitch_normalize: null
+pitch_normalize_conf: {}
+energy_extract: null
+energy_extract_conf: {}
+energy_normalize: null
+energy_normalize_conf: {}
+required:
+- output_dir
+- token_list
+version: '202308'
+distributed: false

hooks/hook-espnet.py

@@ -0,0 +1,3 @@
+from PyInstaller.utils.hooks import copy_metadata
+
+datas = copy_metadata('espnet')

hooks/hook-jamo.py

@@ -0,0 +1,3 @@
+from PyInstaller.utils.hooks import copy_metadata
+
+datas = copy_metadata('jamo')

hooks/hook-librosa.py

@@ -0,0 +1,3 @@
+from PyInstaller.utils.hooks import copy_metadata
+
+datas = copy_metadata('librosa')

hooks/hook-streamlit.py

@@ -0,0 +1,3 @@
+from PyInstaller.utils.hooks import copy_metadata
+
+datas = copy_metadata('streamlit')

pre-fix/librosa/__init__.py

@@ -0,0 +1,10 @@
+# https://github.com/librosa/librosa/issues/1682
+
+import lazy_loader as lazy
+from .version import version as __version__
+
+_filename = __file__
+if _filename.endswith('.pyc'):
+    _filename = _filename[:-1]
+
+__getattr__, __dir__, __all__ = lazy.attach_stub(__name__, _filename)

requirements.txt

@@ -0,0 +1,20 @@
+streamlit
+
+# Install CPU version of pytorch
+--extra-index-url https://download.pytorch.org/whl/cpu
+torch
+
+soundfile
+espnet
+espnet_model_zoo
+
+# pyopenjtalk version must be 0.2
+pyopenjtalk-prebuilt==0.2.0
+
+# typeguard version must be 2.13.3(latest version python 3.8 is supported)
+typeguard==2.13.3
+
+# Use version < 3.7.0 as a workaround, otherwise pyinstallr fails to install some dlls
+# https://github.com/pyinstaller/pyinstaller/pull/7505
+# To visualize audio data
+matplotlib<3.7.0