├── .gitmodules ├── LICENSE ├── README.md ├── code ├── LICENSE_audioldm ├── __init__.py ├── __pycache__ │ ├── models.cpython-39.pyc │ └── utils.cpython-39.pyc ├── audioldm │ ├── __init__.py │ ├── __main__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── ldm.cpython-39.pyc │ │ ├── pipeline.cpython-39.pyc │ │ └── utils.cpython-39.pyc │ ├── audio │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── audio_processing.cpython-310.pyc │ │ │ ├── audio_processing.cpython-39.pyc │ │ │ ├── stft.cpython-310.pyc │ │ │ ├── stft.cpython-39.pyc │ │ │ ├── tools.cpython-310.pyc │ │ │ └── tools.cpython-39.pyc │ │ ├── audio_processing.py │ │ ├── stft.py │ │ └── tools.py │ ├── clap │ │ ├── __init__.py │ │ ├── encoders.py │ │ ├── open_clip │ │ │ ├── __init__.py │ │ │ ├── bert.py │ │ │ ├── bpe_simple_vocab_16e6.txt.gz │ │ │ ├── factory.py │ │ │ ├── feature_fusion.py │ │ │ ├── htsat.py │ │ │ ├── linear_probe.py │ │ │ ├── loss.py │ │ │ ├── model.py │ │ │ ├── model_configs │ │ │ │ ├── HTSAT-base.json │ │ │ │ ├── HTSAT-large.json │ │ │ │ ├── HTSAT-tiny-win-1536.json │ │ │ │ ├── HTSAT-tiny.json │ │ │ │ ├── PANN-10.json │ │ │ │ ├── PANN-14-fmax-18k.json │ │ │ │ ├── PANN-14-fmax-8k-20s.json │ │ │ │ ├── PANN-14-tiny-transformer.json │ │ │ │ ├── PANN-14-win-1536.json │ │ │ │ ├── PANN-14.json │ │ │ │ ├── PANN-6.json │ │ │ │ ├── RN101-quickgelu.json │ │ │ │ ├── RN101.json │ │ │ │ ├── RN50-quickgelu.json │ │ │ │ ├── RN50.json │ │ │ │ ├── RN50x16.json │ │ │ │ ├── RN50x4.json │ │ │ │ ├── ViT-B-16.json │ │ │ │ ├── ViT-B-32-quickgelu.json │ │ │ │ ├── ViT-B-32.json │ │ │ │ └── ViT-L-14.json │ │ │ ├── openai.py │ │ │ ├── pann_model.py │ │ │ ├── pretrained.py │ │ │ ├── timm_model.py │ │ │ ├── tokenizer.py │ │ │ ├── transform.py │ │ │ ├── utils.py │ │ │ └── version.py │ │ └── training │ │ │ ├── __init__.py │ │ │ ├── audioset_textmap.npy │ │ │ ├── data.py │ │ │ ├── distributed.py │ │ │ ├── imagenet_zeroshot_data.py │ │ │ ├── infer_demo.py │ │ │ ├── logger.py │ │ │ ├── lp_main.py │ │ │ ├── lp_train.py │ │ │ ├── main.py │ │ │ ├── params.py │ │ │ ├── scheduler.py │ │ │ ├── train.py │ │ │ └── zero_shot.py │ ├── hifigan │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── models.cpython-39.pyc │ │ │ └── utilities.cpython-39.pyc │ │ ├── models.py │ │ └── utilities.py │ ├── latent_diffusion │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── attention.cpython-39.pyc │ │ │ ├── ddim.cpython-310.pyc │ │ │ ├── ddim.cpython-39.pyc │ │ │ ├── ddpm.cpython-310.pyc │ │ │ ├── ddpm.cpython-39.pyc │ │ │ ├── ema.cpython-310.pyc │ │ │ ├── ema.cpython-39.pyc │ │ │ ├── util.cpython-310.pyc │ │ │ └── util.cpython-39.pyc │ │ ├── attention.py │ │ ├── ddim.py │ │ ├── ddpm.py │ │ ├── ema.py │ │ ├── openaimodel.py │ │ └── util.py │ ├── ldm.py │ ├── pipeline.py │ ├── utils.py │ └── variational_autoencoder │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-39.pyc │ │ ├── distributions.cpython-310.pyc │ │ ├── distributions.cpython-39.pyc │ │ └── modules.cpython-39.pyc │ │ ├── autoencoder.py │ │ ├── distributions.py │ │ └── modules.py ├── ddm_inversion │ ├── __pycache__ │ │ ├── ddim_inversion.cpython-39.pyc │ │ ├── inversion_utils.cpython-310.pyc │ │ ├── inversion_utils.cpython-38.pyc │ │ └── inversion_utils.cpython-39.pyc │ ├── ddim_inversion.py │ └── inversion_utils.py ├── demo.py ├── models.py ├── separate.py └── utils.py ├── evals ├── README.md ├── audio_metrics │ ├── __init__.py │ ├── alignment.py │ ├── bss_eval.py │ ├── clap_utils.py │ ├── encodec_metrics.py │ ├── fad_utils.py │ ├── io_utils.py │ ├── lpaps.py │ └── torch_patch.py ├── requirements.txt └── scripts │ ├── __init__.py │ └── evaluate_separation.py ├── examples ├── BMayJId0X1s_120.wav └── Barack Obama's speech to graduates.mp4 └── requirements.txt /.gitmodules: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/README.md -------------------------------------------------------------------------------- /code/LICENSE_audioldm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/LICENSE_audioldm -------------------------------------------------------------------------------- /code/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/__pycache__/models.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/__pycache__/models.cpython-39.pyc -------------------------------------------------------------------------------- /code/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/__init__.py -------------------------------------------------------------------------------- /code/audioldm/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/__main__.py -------------------------------------------------------------------------------- /code/audioldm/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/__pycache__/ldm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/__pycache__/ldm.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/__pycache__/pipeline.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/__pycache__/pipeline.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__init__.py -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/audio_processing.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/audio_processing.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/audio_processing.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/audio_processing.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/stft.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/stft.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/stft.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/stft.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/tools.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/tools.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/__pycache__/tools.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/__pycache__/tools.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/audio/audio_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/audio_processing.py -------------------------------------------------------------------------------- /code/audioldm/audio/stft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/stft.py -------------------------------------------------------------------------------- /code/audioldm/audio/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/audio/tools.py -------------------------------------------------------------------------------- /code/audioldm/clap/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/audioldm/clap/encoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/encoders.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/__init__.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/bert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/bert.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/bpe_simple_vocab_16e6.txt.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/bpe_simple_vocab_16e6.txt.gz -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/factory.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/feature_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/feature_fusion.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/htsat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/htsat.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/linear_probe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/linear_probe.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/loss.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/HTSAT-base.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/HTSAT-base.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/HTSAT-large.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/HTSAT-large.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/HTSAT-tiny-win-1536.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/HTSAT-tiny-win-1536.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/HTSAT-tiny.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/HTSAT-tiny.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-10.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-14-fmax-18k.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-14-fmax-18k.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-14-fmax-8k-20s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-14-fmax-8k-20s.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-14-tiny-transformer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-14-tiny-transformer.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-14-win-1536.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-14-win-1536.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-14.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-14.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/PANN-6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/PANN-6.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/RN101-quickgelu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/RN101-quickgelu.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/RN101.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/RN101.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/RN50-quickgelu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/RN50-quickgelu.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/RN50.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/RN50.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/RN50x16.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/RN50x16.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/RN50x4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/RN50x4.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/ViT-B-16.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/ViT-B-16.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/ViT-B-32-quickgelu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/ViT-B-32-quickgelu.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/ViT-B-32.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/ViT-B-32.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/model_configs/ViT-L-14.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/model_configs/ViT-L-14.json -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/openai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/openai.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/pann_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/pann_model.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/pretrained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/pretrained.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/timm_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/timm_model.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/tokenizer.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/transform.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/open_clip/utils.py -------------------------------------------------------------------------------- /code/audioldm/clap/open_clip/version.py: -------------------------------------------------------------------------------- 1 | __version__ = "0.2.1" 2 | -------------------------------------------------------------------------------- /code/audioldm/clap/training/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/audioldm/clap/training/audioset_textmap.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/audioset_textmap.npy -------------------------------------------------------------------------------- /code/audioldm/clap/training/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/data.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/distributed.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/imagenet_zeroshot_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/imagenet_zeroshot_data.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/infer_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/infer_demo.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/logger.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/lp_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/lp_main.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/lp_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/lp_train.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/main.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/params.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/params.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/scheduler.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/train.py -------------------------------------------------------------------------------- /code/audioldm/clap/training/zero_shot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/clap/training/zero_shot.py -------------------------------------------------------------------------------- /code/audioldm/hifigan/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/hifigan/__init__.py -------------------------------------------------------------------------------- /code/audioldm/hifigan/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/hifigan/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/hifigan/__pycache__/models.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/hifigan/__pycache__/models.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/hifigan/__pycache__/utilities.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/hifigan/__pycache__/utilities.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/hifigan/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/hifigan/models.py -------------------------------------------------------------------------------- /code/audioldm/hifigan/utilities.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/hifigan/utilities.py -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/attention.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/attention.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/ddim.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/ddim.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/ddim.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/ddim.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/ddpm.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/ddpm.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/ddpm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/ddpm.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/ema.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/ema.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/ema.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/ema.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/util.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/util.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/__pycache__/util.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/__pycache__/util.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/attention.py -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/ddim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/ddim.py -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/ddpm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/ddpm.py -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/ema.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/ema.py -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/openaimodel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/openaimodel.py -------------------------------------------------------------------------------- /code/audioldm/latent_diffusion/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/latent_diffusion/util.py -------------------------------------------------------------------------------- /code/audioldm/ldm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/ldm.py -------------------------------------------------------------------------------- /code/audioldm/pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/pipeline.py -------------------------------------------------------------------------------- /code/audioldm/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/utils.py -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/__pycache__/distributions.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/__pycache__/distributions.cpython-310.pyc -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/__pycache__/distributions.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/__pycache__/distributions.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/__pycache__/modules.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/__pycache__/modules.cpython-39.pyc -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/autoencoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/autoencoder.py -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/distributions.py -------------------------------------------------------------------------------- /code/audioldm/variational_autoencoder/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/audioldm/variational_autoencoder/modules.py -------------------------------------------------------------------------------- /code/ddm_inversion/__pycache__/ddim_inversion.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/ddm_inversion/__pycache__/ddim_inversion.cpython-39.pyc -------------------------------------------------------------------------------- /code/ddm_inversion/__pycache__/inversion_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/ddm_inversion/__pycache__/inversion_utils.cpython-310.pyc -------------------------------------------------------------------------------- /code/ddm_inversion/__pycache__/inversion_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/ddm_inversion/__pycache__/inversion_utils.cpython-38.pyc -------------------------------------------------------------------------------- /code/ddm_inversion/__pycache__/inversion_utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/ddm_inversion/__pycache__/inversion_utils.cpython-39.pyc -------------------------------------------------------------------------------- /code/ddm_inversion/ddim_inversion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/ddm_inversion/ddim_inversion.py -------------------------------------------------------------------------------- /code/ddm_inversion/inversion_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/ddm_inversion/inversion_utils.py -------------------------------------------------------------------------------- /code/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/demo.py -------------------------------------------------------------------------------- /code/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/models.py -------------------------------------------------------------------------------- /code/separate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/separate.py -------------------------------------------------------------------------------- /code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/code/utils.py -------------------------------------------------------------------------------- /evals/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/README.md -------------------------------------------------------------------------------- /evals/audio_metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evals/audio_metrics/alignment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/alignment.py -------------------------------------------------------------------------------- /evals/audio_metrics/bss_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/bss_eval.py -------------------------------------------------------------------------------- /evals/audio_metrics/clap_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/clap_utils.py -------------------------------------------------------------------------------- /evals/audio_metrics/encodec_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/encodec_metrics.py -------------------------------------------------------------------------------- /evals/audio_metrics/fad_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/fad_utils.py -------------------------------------------------------------------------------- /evals/audio_metrics/io_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/io_utils.py -------------------------------------------------------------------------------- /evals/audio_metrics/lpaps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/lpaps.py -------------------------------------------------------------------------------- /evals/audio_metrics/torch_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/audio_metrics/torch_patch.py -------------------------------------------------------------------------------- /evals/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/requirements.txt -------------------------------------------------------------------------------- /evals/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evals/scripts/evaluate_separation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/evals/scripts/evaluate_separation.py -------------------------------------------------------------------------------- /examples/BMayJId0X1s_120.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/examples/BMayJId0X1s_120.wav -------------------------------------------------------------------------------- /examples/Barack Obama's speech to graduates.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/examples/Barack Obama's speech to graduates.mp4 -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WikiChao/ZeroSep/HEAD/requirements.txt --------------------------------------------------------------------------------