diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..308535fe9c8be91ed08bd9333b540694b7144dd5 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* 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 +*.yaml filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..dedfdecbbf3a746a91a9d0b2039b2d1cad0994de --- /dev/null +++ b/README.md @@ -0,0 +1,102 @@ +--- +language: +- en +tags: +- speech +license: +- cc-by-sa-3.0 +- cc-by-4.0 +--- + +# Wave-Trainer-Fit | Neural vocoder from SSL features + +[[Code of Wave-Trainer-Fit](https://github.com/line/WaveTrainerFit)][[audio samples](https://i17oonaka-h.github.io/projects/research_topics/wave_trainer_fit/)] + +>**Abstract:**
+We propose WaveTrainerFit, a neural vocoder that performs high-quality waveform generation from data-driven features such as SSL features. WaveTrainerFit builds upon the WaveFit vocoder, which integrates diffusion model and generative adversarial network. Furthermore, the proposed method incorporates the following key improvements: 1. By introducing trainable priors, the inference process starts from noise close to the target speech instead of Gaussian noise. 2. Reference-aware gain adjustment is performed by imposing constraints on the trainable prior to matching the speech energy. These improvements are expected to reduce the complexity of waveform modeling from data-driven features, enabling high-quality waveform generation with fewer inference steps. Through experiments, we showed that WaveTrainerFit can generate highly natural waveforms with improved speaker similarity from data-driven features, while requiring fewer iterations than WaveFit. Moreover, we showed that the proposed method works robustly with respect to the depth at which SSL features are extracted. + +![concept.png](./assets/concept.png) + +This repository provides pre-trained models and their optimizers. +The models were pre-trained on [LibriTTS-R](https://www.openslr.org/141/) (train-clean-360). +Also, these models operate to reconstruct 24kHz audio by taking SSL features from 16kHz audio as input. + +## Pre-trained model list +> [!IMPORTANT] +⚠️ **License Notice**: The model weights provided in this repository are licensed under different terms. The `xlsr*` and `whisper*` models are licensed differently from the `wavlm*` models. Please refer to the [License](#license) section for details. + +The list of available models is as follows: + +| Model-name | Conditional features | Layer num | #iters of model | +|:------| :---------: | :---: | :---: | +| wavlm2_wavetrainerfit5 | [WavLM-large](https://huggingface.co/microsoft/wavlm-large) | 2 | 5 | +| wavlm2_wavefit5 | [WavLM-large](https://huggingface.co/microsoft/wavlm-large) | 2 | 5 | +| wavlm8_wavetrainerfit5 | [WavLM-large](https://huggingface.co/microsoft/wavlm-large) | 8| 5 | +| wavlm8_wavefit5 | [WavLM-large](https://huggingface.co/microsoft/wavlm-large) | 8| 5 | +| wavlm24_wavetrainerfit5 | [WavLM-large](https://huggingface.co/microsoft/wavlm-large) | 24| 5 | +| wavlm24_wavefit5 | [WavLM-large](https://huggingface.co/microsoft/wavlm-large) | 24| 5 | +| xlsr8_wavetrainerfit5 | [XLS-R-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) | 8| 5 | +| xlsr8_wavefit5 | [XLS-R-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) | 8| 5 | +| whisper8_wavetrainerfit5 | ※ [Whisper-medium](https://huggingface.co/openai/whisper-medium) | 8| 5 | +| whisper8_wavefit5 | ※ [Whisper-medium](https://huggingface.co/openai/whisper-medium) | 8| 5 | + +※ As a result of our verification, we found that amplitude decay occurs in Whisper features after about 2.0 seconds. +During evaluation, our model processed inputs by dividing them into `2.0-second segments → extracting features with the Whisper encoder → recombining → resynthesizing`. +If you use this model in your application, the upstream feature extraction must also follow this flow. + +## Usage +Please refer to [our GitHub repository](https://github.com/line/WaveTrainerFit) for instructions on how to use the models provided here. +The following is reproduced from the GitHub repository: +```python +import torchaudio +import torch +from wavetrainerfit import load_pretrained_vocoder +from transformers import WavLMModel, AutoFeatureExtractor + +ssl_preprocessor = AutoFeatureExtractor.from_pretrained('microsoft/wavlm-large') +ssl_model: WavLMModel = WavLMModel.from_pretrained('microsoft/wavlm-large') + +layer = 2 +ssl_vocoder, cfg = load_pretrained_vocoder(f'wavlm{layer}_wavetrainerfit5') +waveform, sr = torchaudio.load('./assets/ljspeech-samples/LJ037-0171.wav') +if sr != 16000: + waveform = torchaudio.transforms.Resample( + orig_freq=sr, + new_freq=16000 + )(waveform) +inputs = ssl_preprocessor( + waveform[0].numpy(), + sampling_rate=16000, + return_tensors="pt" +) + +with torch.no_grad(): + inputs = ssl_model(**inputs, output_hidden_states=True) + inputs = inputs.hidden_states[layer] # (Batch, Timeframe, Featuredim) + generated_waveform = ssl_vocoder.pred( + conditional_feature=inputs, # (Batch, Timeframe, Featuredim) + T_=5 # num of iteration + ) + +torchaudio.save( + './assets/ljspeech-samples/LJ037-0171-reconstructed.wav', + generated_waveform[-1][:, 0].cpu(), 24000 +) +``` + +## License + +### Model Weights + +**`xlsr*` and `whisper*` models**: Licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) +- Based on XLS-R by facebook (Apache 2.0) - https://huggingface.co/facebook/wav2vec2-xls-r-300m +- Based on Whisper by OpenAI (Apache 2.0) - https://huggingface.co/openai/whisper-medium + +**`wavlm*` models**: Licensed under [CC BY-SA 3.0](https://creativecommons.org/licenses/by-sa/3.0/) +- Based on WavLM by Microsoft Corporation ([CC BY-SA 3.0](https://github.com/microsoft/UniSpeech/blob/main/LICENSE)) - https://huggingface.co/microsoft/wavlm-large +- ⚠️ Derivative works must also use CC BY-SA 3.0 + +**Training data**: LibriTTS-R (CC BY 4.0) - https://www.openslr.org/141/ + +When using these models, you must comply with both our license and the original upstream model licenses. + diff --git a/assets/concept.png b/assets/concept.png new file mode 100644 index 0000000000000000000000000000000000000000..cc574b73d2ff66c672e4a167148a2bfe07ec4476 --- /dev/null +++ b/assets/concept.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d958ed9ebca18768d27781c81878bc60f530fdac55e179b9afa3301fee45117a +size 1315210 diff --git a/wavlm24_wavefit5/config.yaml b/wavlm24_wavefit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..90f4f05650423acdffcefa77a88a3db5ec0dbcd0 --- /dev/null +++ b/wavlm24_wavefit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d586588d05a9b642ac80abbb32f01c3191425dc448bcda40bbea6f517e0a0ff +size 3677 diff --git a/wavlm24_wavefit5/discriminator.pth b/wavlm24_wavefit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..35c55be08fb65c7ba53a4015b3413652c706691a --- /dev/null +++ b/wavlm24_wavefit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aee01df939ed25c322d28762afc88674afe2d33b4a48f541446c54de758542b +size 67725739 diff --git a/wavlm24_wavefit5/generator.pth b/wavlm24_wavefit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae2a3c2f9850c7346cc500d2ee57919aa7744085 --- /dev/null +++ b/wavlm24_wavefit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1b80a25af03d99141090b152db8810239d07573d86c1ef1633655a9e985b47 +size 70381754 diff --git a/wavlm24_wavefit5/opt_d.pth b/wavlm24_wavefit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..47689ae18f2c1d216e009f78bfbdb063813b0b01 --- /dev/null +++ b/wavlm24_wavefit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5c03b48398fc3105ccd5bb3ef77f963c37244caaf9912ab31d5523b39cbc9a +size 135436790 diff --git a/wavlm24_wavefit5/opt_g.pth b/wavlm24_wavefit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..3bc870edefaa8270557b2b3e104d250195c4482f --- /dev/null +++ b/wavlm24_wavefit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09a1159985eda4d9c2d1823970b3ee4d98c5981ca27c51809bcab5960e4268e +size 140717450 diff --git a/wavlm24_wavefit5/sche_d.pth b/wavlm24_wavefit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/wavlm24_wavefit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/wavlm24_wavefit5/sche_g.pth b/wavlm24_wavefit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/wavlm24_wavefit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/wavlm24_wavetrainerfit5/config.yaml b/wavlm24_wavetrainerfit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7a127391c1241c12740db48c305facb421f47dfa --- /dev/null +++ b/wavlm24_wavetrainerfit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a701b56b2f165cac78fbea42ba31c232c770fffafa80b306ac665a2d17df54e7 +size 3912 diff --git a/wavlm24_wavetrainerfit5/discriminator.pth b/wavlm24_wavetrainerfit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac1bb73b286f05d1582e4b056df5f467b0762e04 --- /dev/null +++ b/wavlm24_wavetrainerfit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d347f5a97a9fd57dcafdcef74ff39b26f49128c0718ecf4c7c75543a48f161d1 +size 67725739 diff --git a/wavlm24_wavetrainerfit5/generator.pth b/wavlm24_wavetrainerfit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..54d37fcb5a4e3da6e313d0514303cfccc2bd0c46 --- /dev/null +++ b/wavlm24_wavetrainerfit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468c8db191e4a20882255daf2d2fa2b1362f62d823968d546f9a2d5e9d962a84 +size 91213626 diff --git a/wavlm24_wavetrainerfit5/opt_d.pth b/wavlm24_wavetrainerfit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..efea7a07061d752b823ad8eb125b6431bbd2d881 --- /dev/null +++ b/wavlm24_wavetrainerfit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707cb0713154b1476a0accccbd8252912ba8ee46d10c133382aa7439f5cad606 +size 135436790 diff --git a/wavlm24_wavetrainerfit5/opt_g.pth b/wavlm24_wavetrainerfit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fe07534a05d512ef924b4869d6e86ed06bb7882 --- /dev/null +++ b/wavlm24_wavetrainerfit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc004ee2bcc1a461804565790849da25f044df55bd7da857e4dfbc963446b57 +size 182384602 diff --git a/wavlm24_wavetrainerfit5/sche_d.pth b/wavlm24_wavetrainerfit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/wavlm24_wavetrainerfit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/wavlm24_wavetrainerfit5/sche_g.pth b/wavlm24_wavetrainerfit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/wavlm24_wavetrainerfit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/wavlm2_wavefit5/config.yaml b/wavlm2_wavefit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3de34568f37ec12c91b3beb8472da884c7eba1f4 --- /dev/null +++ b/wavlm2_wavefit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e85396f18f084867faa6fdb1354e4e3bc35a7c48add5e95025bb6d411c38dcd +size 3673 diff --git a/wavlm2_wavefit5/discriminator.pth b/wavlm2_wavefit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ff74c043498a0111fe0e69a1e53dec81584ca3f --- /dev/null +++ b/wavlm2_wavefit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6aa5baf6c74fc46750287a29a23fa4546ff2730e7864ab2055d79abe370818 +size 67725739 diff --git a/wavlm2_wavefit5/generator.pth b/wavlm2_wavefit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c8784a7b37eac3eedb22aaf2710f9c328651550 --- /dev/null +++ b/wavlm2_wavefit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52de0f0156bd59aeac61ae07f5ddb016f82064b22fe047c607ebbd6426113e3d +size 70381754 diff --git a/wavlm2_wavefit5/opt_d.pth b/wavlm2_wavefit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..f1ea3df490f3a835262ef36c971a667a84b95398 --- /dev/null +++ b/wavlm2_wavefit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37abef47b4ed918754329e0e846712de923f322ae955a972b4d5563fce612428 +size 135436790 diff --git a/wavlm2_wavefit5/opt_g.pth b/wavlm2_wavefit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..81fbd384dedd218822595a8dffc8671bdfbe3f9b --- /dev/null +++ b/wavlm2_wavefit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c3f532b8bf92fd7c6fadb246ac59bd5d8fc20d353b4abcd4ea9824fe1946d1 +size 140717450 diff --git a/wavlm2_wavefit5/sche_d.pth b/wavlm2_wavefit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/wavlm2_wavefit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/wavlm2_wavefit5/sche_g.pth b/wavlm2_wavefit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/wavlm2_wavefit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/wavlm2_wavetrainerfit5/config.yaml b/wavlm2_wavetrainerfit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..09541daba8577849781632fd1f127ca0c1a8ebb9 --- /dev/null +++ b/wavlm2_wavetrainerfit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf522aa9c5767f128ff303572d342185a4202068ef7776b3a32e0c5b40a7181 +size 3908 diff --git a/wavlm2_wavetrainerfit5/discriminator.pth b/wavlm2_wavetrainerfit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c2370cefbd1124e949fe86ce8abdb6c64552fad --- /dev/null +++ b/wavlm2_wavetrainerfit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a36ffaf39439d1658a480c832992679fd6d4689089bf2a3b220919b179d4c8d +size 67725739 diff --git a/wavlm2_wavetrainerfit5/generator.pth b/wavlm2_wavetrainerfit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f86d053265d981f48b0edc6f0e992aa3c992924 --- /dev/null +++ b/wavlm2_wavetrainerfit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:877098b6e68cbd5f3aebab53eace69ac9da2e19c3427715e59c41db9307fac5e +size 91213626 diff --git a/wavlm2_wavetrainerfit5/opt_d.pth b/wavlm2_wavetrainerfit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec6a1edb158ab4d62628ada17decede0f8bd2b83 --- /dev/null +++ b/wavlm2_wavetrainerfit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2b82acce5d21d8cc2080f312e63aa4892db1cd5d3f82ea5c49f9d57ac6d99f +size 135436790 diff --git a/wavlm2_wavetrainerfit5/opt_g.pth b/wavlm2_wavetrainerfit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0991cf8b057070a8be746fa2510edeefe30caa4 --- /dev/null +++ b/wavlm2_wavetrainerfit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdd25c65f8e667081218e455ed112508afd71fae9ce43111104fab1f1fc7593 +size 182384602 diff --git a/wavlm2_wavetrainerfit5/sche_d.pth b/wavlm2_wavetrainerfit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..17f9d2c3edf8971b610b25af6ae2d0fb77c27d00 --- /dev/null +++ b/wavlm2_wavetrainerfit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdb702a665e174fdb6a3143aa3339da61f0029022afa7569c641098aa643475 +size 1052 diff --git a/wavlm2_wavetrainerfit5/sche_g.pth b/wavlm2_wavetrainerfit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..a37711cc608a6ef05fb9079d3812489a265e4150 --- /dev/null +++ b/wavlm2_wavetrainerfit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac4aba57e808c8fcf7e561404c578a6c2a5134d9ce4b6ec40e0ceb5e3436e73 +size 1052 diff --git a/wavlm8_wavefit5/config.yaml b/wavlm8_wavefit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fee70a78fe7c737977ebd67e038d36cd1c920ecc --- /dev/null +++ b/wavlm8_wavefit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e4e1d6a28bc0de9adcaa0e8d77e2732482b78dd4c1783ddba5ea7f4c990fe1 +size 3673 diff --git a/wavlm8_wavefit5/discriminator.pth b/wavlm8_wavefit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..2105e696c5f7c2e0b77c59c1613f0a1524b71327 --- /dev/null +++ b/wavlm8_wavefit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83eb614cd4c210680945a5770159f0993d19baec822214366f4ab7174e9384f4 +size 67725739 diff --git a/wavlm8_wavefit5/generator.pth b/wavlm8_wavefit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ce30fc98ab6271f3bfbb84ffd0a9f274c0a4d57 --- /dev/null +++ b/wavlm8_wavefit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9d1c589c7d18956f81a66dbf00836e417960a6e542f424381d305ebbe1811f +size 70381754 diff --git a/wavlm8_wavefit5/opt_d.pth b/wavlm8_wavefit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6ae8fdeb483e4859983e8e4f48ed294544439ca --- /dev/null +++ b/wavlm8_wavefit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b8c76e303322ab79e1f63ff225b5d6e24eeecc0f5bbb5ec3fa785a42b3096a +size 135436790 diff --git a/wavlm8_wavefit5/opt_g.pth b/wavlm8_wavefit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..d17768691fb37811faf1a30570960a8889c97a4c --- /dev/null +++ b/wavlm8_wavefit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02919a98e60f811e09df28b96555443e79f502f9aa60f07761233b9e0ea9b59 +size 140717450 diff --git a/wavlm8_wavefit5/sche_d.pth b/wavlm8_wavefit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/wavlm8_wavefit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/wavlm8_wavefit5/sche_g.pth b/wavlm8_wavefit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/wavlm8_wavefit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/wavlm8_wavetrainerfit5/config.yaml b/wavlm8_wavetrainerfit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5c9d3dc20737f552a3bb4d5a6e9fb5bf20162ac1 --- /dev/null +++ b/wavlm8_wavetrainerfit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eeca4b9b0ca8714fda83c131b9afa4c23645fedda1d2f1c39195a1b8aa7b8f0 +size 3908 diff --git a/wavlm8_wavetrainerfit5/discriminator.pth b/wavlm8_wavetrainerfit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..510a0c006a2c3403fc73c26cc3817a1278b96df9 --- /dev/null +++ b/wavlm8_wavetrainerfit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7246427cdaa1eb4195f1e6654dcb429c39ac18be704170efab70c04e443527a +size 67725739 diff --git a/wavlm8_wavetrainerfit5/generator.pth b/wavlm8_wavetrainerfit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..9fadde629e8a92b6644cb313abb543c71d8f352a --- /dev/null +++ b/wavlm8_wavetrainerfit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ab744075817741909515bb7158baf61aa2086ff3c031b74d5c888109cb8a04 +size 91213626 diff --git a/wavlm8_wavetrainerfit5/opt_d.pth b/wavlm8_wavetrainerfit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..21047d0e529b767d7d0c9dec6bb6a23259af9027 --- /dev/null +++ b/wavlm8_wavetrainerfit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fee63b67aac8f4def14d7fd4c2ebe151eafb49093020d1f70bb245fc8b5f8ba +size 135436790 diff --git a/wavlm8_wavetrainerfit5/opt_g.pth b/wavlm8_wavetrainerfit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f5a93a77216dbce79fb3f164a4c78a1804baba1 --- /dev/null +++ b/wavlm8_wavetrainerfit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bee39ba66414fb4566eb0cc9ce84d1fd71af048d2185e04b15a81a58088d3db +size 182384602 diff --git a/wavlm8_wavetrainerfit5/sche_d.pth b/wavlm8_wavetrainerfit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/wavlm8_wavetrainerfit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/wavlm8_wavetrainerfit5/sche_g.pth b/wavlm8_wavetrainerfit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/wavlm8_wavetrainerfit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/whisper8_wavefit5/config.yaml b/whisper8_wavefit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9c0bac21e3a52ef368dcc240220ccc7e360c7376 --- /dev/null +++ b/whisper8_wavefit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1c5e6bf31cb139aca11dc672dd0f1dd24e84870059308b7a551f2639c0fd26 +size 3681 diff --git a/whisper8_wavefit5/discriminator.pth b/whisper8_wavefit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fdff26940f59c411e5afb395536afad0c96e5bc --- /dev/null +++ b/whisper8_wavefit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e8fafbf5a9d606065279ba4c919018c652f4d4ace7564e793b1ab24a0c847a +size 67725739 diff --git a/whisper8_wavefit5/generator.pth b/whisper8_wavefit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..43ba51791f773a407f2b1b18a244bee1d8a97596 --- /dev/null +++ b/whisper8_wavefit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862254c7c6fee39023ee20950d7e843d154eadb258893680b3824d48a9262ff0 +size 70381754 diff --git a/whisper8_wavefit5/opt_d.pth b/whisper8_wavefit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..35db10365678651bf2f97ad40cc3d01bbc54017e --- /dev/null +++ b/whisper8_wavefit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9734c216ba0bc72314d3910b764b4284dd9e51fcabe3d81885cc8b8ac35b6d90 +size 135436790 diff --git a/whisper8_wavefit5/opt_g.pth b/whisper8_wavefit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..a45fd66a05155ca2c1531fd490c2babd49bd31ba --- /dev/null +++ b/whisper8_wavefit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f18eb7c1927042d49bfa2c2afb46784bb92d5bb21a0163ad5821ca02d26ab8c +size 140717130 diff --git a/whisper8_wavefit5/sche_d.pth b/whisper8_wavefit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/whisper8_wavefit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/whisper8_wavefit5/sche_g.pth b/whisper8_wavefit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/whisper8_wavefit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/whisper8_wavetrainerfit5/config.yaml b/whisper8_wavetrainerfit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fad30b430c8904fffd854c8cccc52bec63de473e --- /dev/null +++ b/whisper8_wavetrainerfit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72aea0fb904633af462986d7544842acd51873c94044f5ebefb1416b6291f56f +size 3916 diff --git a/whisper8_wavetrainerfit5/discriminator.pth b/whisper8_wavetrainerfit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a296867a4a95cace9767470894925b82822c3d7 --- /dev/null +++ b/whisper8_wavetrainerfit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9b333e2bb81dd2df68c405608e2d2b60df152f2783605bcf4882000c3d4335 +size 67725739 diff --git a/whisper8_wavetrainerfit5/generator.pth b/whisper8_wavetrainerfit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..f733d21e3649b8c824af4649d958ad20d2b7f63a --- /dev/null +++ b/whisper8_wavetrainerfit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1e8badc8635c5f105ad16aedd4cade2327a3b9a316f4a53bf5bd525ed4399e +size 91213626 diff --git a/whisper8_wavetrainerfit5/opt_d.pth b/whisper8_wavetrainerfit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec612e4db14541819c7959cc3a686b1eee228108 --- /dev/null +++ b/whisper8_wavetrainerfit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf694116accc348655d29ef60e3ac67792ddb883d19900dff266199353753cbf +size 135436790 diff --git a/whisper8_wavetrainerfit5/opt_g.pth b/whisper8_wavetrainerfit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..d39d173129e128c644ae9c74d7b70877b11e90ee --- /dev/null +++ b/whisper8_wavetrainerfit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a9fa04f33902089b1a6c251e9b80719d9f148bcc760801b297b65ab2738549 +size 182384218 diff --git a/whisper8_wavetrainerfit5/sche_d.pth b/whisper8_wavetrainerfit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/whisper8_wavetrainerfit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/whisper8_wavetrainerfit5/sche_g.pth b/whisper8_wavetrainerfit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/whisper8_wavetrainerfit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/xlsr8_wavefit5/config.yaml b/xlsr8_wavefit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..301774c618dc014d08a919e0562609317ce0ab88 --- /dev/null +++ b/xlsr8_wavefit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b5e9c65349cb24854ffcdfee4fae79ee48aeb04e8f6d11b566dbb80f819353 +size 3687 diff --git a/xlsr8_wavefit5/discriminator.pth b/xlsr8_wavefit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..268c02796f81d0be2d2b45c28214c224b790b042 --- /dev/null +++ b/xlsr8_wavefit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a51e86e38896cbed6f2be584600b90ff5e3bb250661533a649477359a3147d32 +size 67725739 diff --git a/xlsr8_wavefit5/generator.pth b/xlsr8_wavefit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..ddd19178cb33b876a9c474d468cf40dccee9f1d1 --- /dev/null +++ b/xlsr8_wavefit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989a6fc7fbe9411044fea9ebcae04e065f9ba960b9843e58144d3dad8f2ee881 +size 70381754 diff --git a/xlsr8_wavefit5/opt_d.pth b/xlsr8_wavefit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..4cd7f3f55ad8d190414b291f4a1739e4f536d73c --- /dev/null +++ b/xlsr8_wavefit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8428ab32b07924219773ab07be83c7d6b32025ac1c7602593297c03c5775e5 +size 135436790 diff --git a/xlsr8_wavefit5/opt_g.pth b/xlsr8_wavefit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e29283394336eef2fc1150eb804fb945d910042 --- /dev/null +++ b/xlsr8_wavefit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6e9db8fb1d33dea9469dd80c511d53b1e2405a0c156dc19bd14880146fe1ce +size 140717258 diff --git a/xlsr8_wavefit5/sche_d.pth b/xlsr8_wavefit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/xlsr8_wavefit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/xlsr8_wavefit5/sche_g.pth b/xlsr8_wavefit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/xlsr8_wavefit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052 diff --git a/xlsr8_wavetrainerfit5/config.yaml b/xlsr8_wavetrainerfit5/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6b7ccb8901d35d3b78693a4009e6e65b5a6e3e57 --- /dev/null +++ b/xlsr8_wavetrainerfit5/config.yaml @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d5ae6ec6c064885828fabe2f36dfd979acf13349b3a92c5933dba9fbcb9c20 +size 3926 diff --git a/xlsr8_wavetrainerfit5/discriminator.pth b/xlsr8_wavetrainerfit5/discriminator.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b56a97042e320160b7b00d3c1376ffc683841b8 --- /dev/null +++ b/xlsr8_wavetrainerfit5/discriminator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cb42364a4d08f34c8ed64bf0cc219b48f3de06bf83633ce72bc28d62eafea7 +size 67725739 diff --git a/xlsr8_wavetrainerfit5/generator.pth b/xlsr8_wavetrainerfit5/generator.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d1c5dd27bb152ce2dda2a8c13d1442eaf8915ee --- /dev/null +++ b/xlsr8_wavetrainerfit5/generator.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a97c043624f1b0a360aacc6cbb38d5da8307ee1cf7e0bb60efd02fe12021deb +size 91213626 diff --git a/xlsr8_wavetrainerfit5/opt_d.pth b/xlsr8_wavetrainerfit5/opt_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..687e483e27517fa3bf348a0d1d7d84a643f3dd5b --- /dev/null +++ b/xlsr8_wavetrainerfit5/opt_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd288623697969c1b07a311575b67bf4497208d9048ca7495fb5b9d225ff25b +size 135436790 diff --git a/xlsr8_wavetrainerfit5/opt_g.pth b/xlsr8_wavetrainerfit5/opt_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..3cf10390a7d458f107d6b198b86932eec214f76b --- /dev/null +++ b/xlsr8_wavetrainerfit5/opt_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ee4dc0f0bdf753307cd75d7e9af46ea12b2b9eed43ff2feff388ddbb913129 +size 182384410 diff --git a/xlsr8_wavetrainerfit5/sche_d.pth b/xlsr8_wavetrainerfit5/sche_d.pth new file mode 100644 index 0000000000000000000000000000000000000000..96d6791b5fd6b35df929672ea9fd365ef6b0e113 --- /dev/null +++ b/xlsr8_wavetrainerfit5/sche_d.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ccff4d21f36dc59881448522898302255373b0fd88643993f30c892d74c3c3 +size 1052 diff --git a/xlsr8_wavetrainerfit5/sche_g.pth b/xlsr8_wavetrainerfit5/sche_g.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0411999351473ba18b0eebbea10becdee11a6d --- /dev/null +++ b/xlsr8_wavetrainerfit5/sche_g.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5e39de608aa344d36de8c5b797e21a0469120a8430cd24e6dc3c0b9bd28c37 +size 1052