├── .gitignore ├── LICENCE ├── README.md ├── configs ├── accelerate_config.yaml ├── train_ar.yaml └── train_nar.yaml ├── examples ├── actor_ref.wav └── example_instructions.txt ├── infer.sh ├── inference.py ├── meta_files └── textrolspeech │ └── metadata_train.json ├── model ├── __init__.py ├── ar.py └── nar.py ├── requirements.txt ├── train_ar.py ├── train_nar.py └── utils ├── __init__.py ├── dataset.py ├── extract_encodec.py ├── extract_hubert.py ├── optimizer.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENCE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/LICENCE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/README.md -------------------------------------------------------------------------------- /configs/accelerate_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/configs/accelerate_config.yaml -------------------------------------------------------------------------------- /configs/train_ar.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/configs/train_ar.yaml -------------------------------------------------------------------------------- /configs/train_nar.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/configs/train_nar.yaml -------------------------------------------------------------------------------- /examples/actor_ref.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/examples/actor_ref.wav -------------------------------------------------------------------------------- /examples/example_instructions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/examples/example_instructions.txt -------------------------------------------------------------------------------- /infer.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/infer.sh -------------------------------------------------------------------------------- /inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/inference.py -------------------------------------------------------------------------------- /meta_files/textrolspeech/metadata_train.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/meta_files/textrolspeech/metadata_train.json -------------------------------------------------------------------------------- /model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /model/ar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/model/ar.py -------------------------------------------------------------------------------- /model/nar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/model/nar.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/requirements.txt -------------------------------------------------------------------------------- /train_ar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/train_ar.py -------------------------------------------------------------------------------- /train_nar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/train_nar.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/utils/dataset.py -------------------------------------------------------------------------------- /utils/extract_encodec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/utils/extract_encodec.py -------------------------------------------------------------------------------- /utils/extract_hubert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/utils/extract_hubert.py -------------------------------------------------------------------------------- /utils/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/utils/optimizer.py -------------------------------------------------------------------------------- /utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thuhcsi/VoxInstruct/HEAD/utils/utils.py --------------------------------------------------------------------------------