├── README.md ├── alm ├── callback │ ├── __init__.py │ └── progress.py ├── config.py ├── data │ ├── BIWI │ │ ├── __init__.py │ │ └── dataset.py │ ├── __init__.py │ ├── base.py │ ├── biwi.py │ ├── get_data.py │ ├── voca │ │ ├── __init__.py │ │ └── dataset.py │ └── vocaset.py ├── models │ ├── __init__.py │ ├── architectures │ │ ├── __init__.py │ │ ├── adpt_bias_denoiser.py │ │ └── tools │ │ │ ├── embeddings.py │ │ │ ├── transformer_adpt.py │ │ │ └── utils.py │ ├── get_model.py │ ├── losses │ │ ├── __init__.py │ │ ├── utils.py │ │ └── voca.py │ └── modeltype │ │ ├── __init__.py │ │ ├── base.py │ │ └── diffusion_bias.py └── utils │ ├── __init__.py │ ├── demo_utils.py │ ├── logger.py │ └── temos_utils.py ├── configs ├── assets │ ├── biwi.yaml │ └── vocaset.yaml ├── base.yaml └── diffusion │ ├── biwi │ ├── diffspeaker_hubert_biwi.yaml │ └── diffspeaker_wav2vec2_biwi.yaml │ ├── diffusion_bias_modules │ ├── denoiser.yaml │ └── scheduler.yaml │ └── vocaset │ ├── diffspeaker_hubert_vocaset.yaml │ └── diffspeaker_wav2vec2_vocaset.yaml ├── datasets ├── biwi │ ├── README.md │ ├── regions │ │ ├── fdd.txt │ │ └── lve.txt │ ├── templates.pkl │ └── templates │ │ └── BIWI.ply └── vocaset │ ├── FLAME_masks.pkl │ ├── README.md │ ├── templates.pkl │ └── templates │ ├── FLAME_sample.ply │ └── README.md ├── demo └── wavs │ ├── speech_british.wav │ ├── speech_long.wav │ └── speech_obama.wav ├── demo_biwi.py ├── demo_vocaset.py ├── demo_vocaset_text.py ├── eval_biwi.py ├── eval_vocaset.py ├── requirements.txt ├── scripts ├── demo │ ├── demo_biwi.sh │ └── demo_vocaset.sh └── diffusion │ ├── biwi_evaluation │ ├── diffspeaker_hubert_biwi.sh │ └── diffspeaker_wav2vec2_biwi.sh │ ├── biwi_training │ ├── diffspeaker_hubert_biwi.sh │ └── diffspeaker_wav2vec2_biwi.sh │ ├── vocaset_evaluation │ ├── diffspeaker_hubert_vocaset.sh │ └── diffspeaker_wav2vec2_vocaset.sh │ └── vocaset_training │ ├── diffspeaker_hubert_vocaset.sh │ └── diffspeaker_wav2vec2_vocaset.sh └── train.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/README.md -------------------------------------------------------------------------------- /alm/callback/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/callback/__init__.py -------------------------------------------------------------------------------- /alm/callback/progress.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/callback/progress.py -------------------------------------------------------------------------------- /alm/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/config.py -------------------------------------------------------------------------------- /alm/data/BIWI/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/BIWI/__init__.py -------------------------------------------------------------------------------- /alm/data/BIWI/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/BIWI/dataset.py -------------------------------------------------------------------------------- /alm/data/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alm/data/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/base.py -------------------------------------------------------------------------------- /alm/data/biwi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/biwi.py -------------------------------------------------------------------------------- /alm/data/get_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/get_data.py -------------------------------------------------------------------------------- /alm/data/voca/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/voca/__init__.py -------------------------------------------------------------------------------- /alm/data/voca/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/voca/dataset.py -------------------------------------------------------------------------------- /alm/data/vocaset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/data/vocaset.py -------------------------------------------------------------------------------- /alm/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alm/models/architectures/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alm/models/architectures/adpt_bias_denoiser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/architectures/adpt_bias_denoiser.py -------------------------------------------------------------------------------- /alm/models/architectures/tools/embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/architectures/tools/embeddings.py -------------------------------------------------------------------------------- /alm/models/architectures/tools/transformer_adpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/architectures/tools/transformer_adpt.py -------------------------------------------------------------------------------- /alm/models/architectures/tools/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/architectures/tools/utils.py -------------------------------------------------------------------------------- /alm/models/get_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/get_model.py -------------------------------------------------------------------------------- /alm/models/losses/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alm/models/losses/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/losses/utils.py -------------------------------------------------------------------------------- /alm/models/losses/voca.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/losses/voca.py -------------------------------------------------------------------------------- /alm/models/modeltype/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alm/models/modeltype/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/modeltype/base.py -------------------------------------------------------------------------------- /alm/models/modeltype/diffusion_bias.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/models/modeltype/diffusion_bias.py -------------------------------------------------------------------------------- /alm/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alm/utils/demo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/utils/demo_utils.py -------------------------------------------------------------------------------- /alm/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/utils/logger.py -------------------------------------------------------------------------------- /alm/utils/temos_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/alm/utils/temos_utils.py -------------------------------------------------------------------------------- /configs/assets/biwi.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/assets/biwi.yaml -------------------------------------------------------------------------------- /configs/assets/vocaset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/assets/vocaset.yaml -------------------------------------------------------------------------------- /configs/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/base.yaml -------------------------------------------------------------------------------- /configs/diffusion/biwi/diffspeaker_hubert_biwi.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/diffusion/biwi/diffspeaker_hubert_biwi.yaml -------------------------------------------------------------------------------- /configs/diffusion/biwi/diffspeaker_wav2vec2_biwi.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/diffusion/biwi/diffspeaker_wav2vec2_biwi.yaml -------------------------------------------------------------------------------- /configs/diffusion/diffusion_bias_modules/denoiser.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/diffusion/diffusion_bias_modules/denoiser.yaml -------------------------------------------------------------------------------- /configs/diffusion/diffusion_bias_modules/scheduler.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/diffusion/diffusion_bias_modules/scheduler.yaml -------------------------------------------------------------------------------- /configs/diffusion/vocaset/diffspeaker_hubert_vocaset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/diffusion/vocaset/diffspeaker_hubert_vocaset.yaml -------------------------------------------------------------------------------- /configs/diffusion/vocaset/diffspeaker_wav2vec2_vocaset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/configs/diffusion/vocaset/diffspeaker_wav2vec2_vocaset.yaml -------------------------------------------------------------------------------- /datasets/biwi/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/biwi/README.md -------------------------------------------------------------------------------- /datasets/biwi/regions/fdd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/biwi/regions/fdd.txt -------------------------------------------------------------------------------- /datasets/biwi/regions/lve.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/biwi/regions/lve.txt -------------------------------------------------------------------------------- /datasets/biwi/templates.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/biwi/templates.pkl -------------------------------------------------------------------------------- /datasets/biwi/templates/BIWI.ply: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/biwi/templates/BIWI.ply -------------------------------------------------------------------------------- /datasets/vocaset/FLAME_masks.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/vocaset/FLAME_masks.pkl -------------------------------------------------------------------------------- /datasets/vocaset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/vocaset/README.md -------------------------------------------------------------------------------- /datasets/vocaset/templates.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/vocaset/templates.pkl -------------------------------------------------------------------------------- /datasets/vocaset/templates/FLAME_sample.ply: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/vocaset/templates/FLAME_sample.ply -------------------------------------------------------------------------------- /datasets/vocaset/templates/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/datasets/vocaset/templates/README.md -------------------------------------------------------------------------------- /demo/wavs/speech_british.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/demo/wavs/speech_british.wav -------------------------------------------------------------------------------- /demo/wavs/speech_long.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/demo/wavs/speech_long.wav -------------------------------------------------------------------------------- /demo/wavs/speech_obama.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/demo/wavs/speech_obama.wav -------------------------------------------------------------------------------- /demo_biwi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/demo_biwi.py -------------------------------------------------------------------------------- /demo_vocaset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/demo_vocaset.py -------------------------------------------------------------------------------- /demo_vocaset_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/demo_vocaset_text.py -------------------------------------------------------------------------------- /eval_biwi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/eval_biwi.py -------------------------------------------------------------------------------- /eval_vocaset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/eval_vocaset.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/demo/demo_biwi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/demo/demo_biwi.sh -------------------------------------------------------------------------------- /scripts/demo/demo_vocaset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/demo/demo_vocaset.sh -------------------------------------------------------------------------------- /scripts/diffusion/biwi_evaluation/diffspeaker_hubert_biwi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/biwi_evaluation/diffspeaker_hubert_biwi.sh -------------------------------------------------------------------------------- /scripts/diffusion/biwi_evaluation/diffspeaker_wav2vec2_biwi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/biwi_evaluation/diffspeaker_wav2vec2_biwi.sh -------------------------------------------------------------------------------- /scripts/diffusion/biwi_training/diffspeaker_hubert_biwi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/biwi_training/diffspeaker_hubert_biwi.sh -------------------------------------------------------------------------------- /scripts/diffusion/biwi_training/diffspeaker_wav2vec2_biwi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/biwi_training/diffspeaker_wav2vec2_biwi.sh -------------------------------------------------------------------------------- /scripts/diffusion/vocaset_evaluation/diffspeaker_hubert_vocaset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/vocaset_evaluation/diffspeaker_hubert_vocaset.sh -------------------------------------------------------------------------------- /scripts/diffusion/vocaset_evaluation/diffspeaker_wav2vec2_vocaset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/vocaset_evaluation/diffspeaker_wav2vec2_vocaset.sh -------------------------------------------------------------------------------- /scripts/diffusion/vocaset_training/diffspeaker_hubert_vocaset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/vocaset_training/diffspeaker_hubert_vocaset.sh -------------------------------------------------------------------------------- /scripts/diffusion/vocaset_training/diffspeaker_wav2vec2_vocaset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/scripts/diffusion/vocaset_training/diffspeaker_wav2vec2_vocaset.sh -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/theEricMa/DiffSpeaker/HEAD/train.py --------------------------------------------------------------------------------