├── .gitignore ├── README.md ├── audio_datasets ├── __init__.py ├── constants.py ├── librispeech.py ├── mls.py ├── preprocess_mls.py └── text_grid_utils.py ├── data └── aligned_librispeech.tar.gz ├── diffusion ├── audio_denoising_diffusion.py ├── noise_schedule.py └── optimizer.py ├── evaluation └── evaluate_transcript.py ├── models ├── modules │ ├── __init__.py │ ├── conformer.py │ ├── conv.py │ ├── norm.py │ └── transformer.py └── unet.py ├── neural_codec └── encodec_wrapper.py ├── requirements.txt ├── scripts ├── sample │ └── sample_16_ls_testclean.sh └── train │ ├── train.sh │ └── train_distributed.sh ├── train_audio_diffusion.py ├── training.md └── utils └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/README.md -------------------------------------------------------------------------------- /audio_datasets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/audio_datasets/__init__.py -------------------------------------------------------------------------------- /audio_datasets/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/audio_datasets/constants.py -------------------------------------------------------------------------------- /audio_datasets/librispeech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/audio_datasets/librispeech.py -------------------------------------------------------------------------------- /audio_datasets/mls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/audio_datasets/mls.py -------------------------------------------------------------------------------- /audio_datasets/preprocess_mls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/audio_datasets/preprocess_mls.py -------------------------------------------------------------------------------- /audio_datasets/text_grid_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/audio_datasets/text_grid_utils.py -------------------------------------------------------------------------------- /data/aligned_librispeech.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/data/aligned_librispeech.tar.gz -------------------------------------------------------------------------------- /diffusion/audio_denoising_diffusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/diffusion/audio_denoising_diffusion.py -------------------------------------------------------------------------------- /diffusion/noise_schedule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/diffusion/noise_schedule.py -------------------------------------------------------------------------------- /diffusion/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/diffusion/optimizer.py -------------------------------------------------------------------------------- /evaluation/evaluate_transcript.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/evaluation/evaluate_transcript.py -------------------------------------------------------------------------------- /models/modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/models/modules/__init__.py -------------------------------------------------------------------------------- /models/modules/conformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/models/modules/conformer.py -------------------------------------------------------------------------------- /models/modules/conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/models/modules/conv.py -------------------------------------------------------------------------------- /models/modules/norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/models/modules/norm.py -------------------------------------------------------------------------------- /models/modules/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/models/modules/transformer.py -------------------------------------------------------------------------------- /models/unet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/models/unet.py -------------------------------------------------------------------------------- /neural_codec/encodec_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/neural_codec/encodec_wrapper.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/sample/sample_16_ls_testclean.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/scripts/sample/sample_16_ls_testclean.sh -------------------------------------------------------------------------------- /scripts/train/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/scripts/train/train.sh -------------------------------------------------------------------------------- /scripts/train/train_distributed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/scripts/train/train_distributed.sh -------------------------------------------------------------------------------- /train_audio_diffusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/train_audio_diffusion.py -------------------------------------------------------------------------------- /training.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/training.md -------------------------------------------------------------------------------- /utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asappresearch/simple-tts/HEAD/utils/utils.py --------------------------------------------------------------------------------