Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

README.md

@@ -0,0 +1,67 @@
+---
+license:
+- mit
+- apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: audio-classification
+tags:
+- audio
+- tts
+---
+
+# StyleTTS 2 Detector
+
+This is a model trained for audio classification on a dataset of almost 10,000 samples of human and StyleTTS 2-generated audio clips. The model is based on [Whisper](https://huggingface.co/openai/whisper-base).
+
+**NOTE: This model is not affiliated with the author(s) of StyleTTS 2 in any way.**
+
+**NOTE: This model only aims to detect audio generated by StyleTTS 2 and DOES NOT work for audio generated by other TTS models or finetunes. I'm aiming to create a universal classifier in the future.**
+
+## Online Demo
+
+An online demo is available [here](https://huggingface.co/spaces/mrfakename/styletts2-detector).
+
+## Usage
+
+**IMPORTANT:** Please read the license, disclaimer, and model card before using the model. You may not use the model if you do not agree to the license and disclaimer.
+
+```python
+from transformers import pipeline
+import torch
+
+pipe = pipeline('audio-classification', model='mrfakename/styletts2-detector', device='cuda' if torch.cuda.is_available() else 'cpu')
+
+result = pipe('audio.wav')
+
+print(result)
+```
+
+## Tags
+
+The audio will be classified as either `real` or `fake` (human-generated or StyleTTS 2-spoken).
+
+## Disclaimer
+
+The author(s) of this model cannot guarantee complete accuracy. False positives or negatives may occur.
+
+Usage of this model should not replace other precautions, such as invisible watermarking or audio watermarking.
+
+This model has been trained on outputs from the StyleTTS 2 base model, not fine-tunes. The model may not identify fine-tunes properly.
+
+The author(s) of this model disclaim all liability related to or in connection with the usage of this model.
+
+## Training Data
+
+This model was trained on the following data:
+
+* A dataset of real human audio and synthetic audio generated by StyleTTS 2
+  * A subset of the LibriTTS-R dataset, which is licensed under the CC-BY 4.0 license and includes public domain audio.
+  * A custom synthetic dataset derived from a subset of the LibriTTS-R dataset and synthesized using StyleTTS 2. Text from the LibriTTS-R dataset were used as prompts for StyleTTS 2. The StyleTTS 2 model used was trained on the LibriTTS dataset.
+
+## License
+
+You may use this model under either the **MIT** or **Apache 2.0** license, at your choice, so long as you include the disclaimer above in all redistributions, and require all future redistributions to include the disclaimer.
+
+This model was trained partially on data from the [LibriTTS dataset](http://www.openslr.org/60/), the [LibriTTS-R dataset](https://google.github.io/df-conformer/librittsr/), and/or data generated using [StyleTTS 2](https://arxiv.org/abs/2306.07691) (which was trained on the LibriTTS dataset).

config.json

@@ -0,0 +1,163 @@
+{
+  "_name_or_path": "openai/whisper-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50257,
+  "finetuning_task": "audio-classification",
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "id2label": {
+    "0": "real",
+    "1": "fake"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "fake": "1",
+    "real": "0"
+  },
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6371663d68bb05bf9829ed9b799ae100f211c15ed7346322b9200f5751bd9bff
+size 82923230