Audyn 0.0.1.dev7__tar.gz → 0.4.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {audyn-0.0.1.dev7 → audyn-0.4.0}/Audyn.egg-info/PKG-INFO +75 -10
- audyn-0.4.0/Audyn.egg-info/SOURCES.txt +369 -0
- audyn-0.4.0/Audyn.egg-info/entry_points.txt +16 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/Audyn.egg-info/requires.txt +3 -7
- {audyn-0.0.1.dev7 → audyn-0.4.0}/MANIFEST.in +1 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/PKG-INFO +75 -10
- audyn-0.4.0/README.md +130 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/__init__.py +15 -3
- audyn-0.4.0/audyn/amp/__init__.py +51 -0
- audyn-0.4.0/audyn/amp/grad_scaler.py +31 -0
- audyn-0.4.0/audyn/bin/decode_musdb18.py +236 -0
- audyn-0.4.0/audyn/bin/download_beatthis.py +154 -0
- audyn-0.4.0/audyn/bin/download_dnr.py +117 -0
- audyn-0.4.0/audyn/bin/download_fma.py +110 -0
- audyn-0.4.0/audyn/bin/download_fsd50k.py +125 -0
- audyn-0.4.0/audyn/bin/download_ljspeech.py +89 -0
- audyn-0.4.0/audyn/bin/download_lsx.py +89 -0
- audyn-0.4.0/audyn/bin/download_mtat.py +139 -0
- audyn-0.4.0/audyn/bin/download_mtg_jamendo.py +136 -0
- audyn-0.4.0/audyn/bin/download_musdb18.py +126 -0
- audyn-0.4.0/audyn/bin/download_openmic2018.py +115 -0
- audyn-0.4.0/audyn/bin/download_singmos.py +110 -0
- audyn-0.4.0/audyn/bin/download_song_describer.py +111 -0
- audyn-0.4.0/audyn/bin/download_vctk.py +96 -0
- audyn-0.4.0/audyn/bin/parse_run_command.py +66 -0
- audyn-0.4.0/audyn/configs/config.yaml +17 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/criterion/vqvae.yaml +3 -0
- audyn-0.4.0/audyn/configs/data/mtg-jamendo.yaml +7 -0
- audyn-0.4.0/audyn/configs/data/wordnet-mammal.yaml +7 -0
- audyn-0.4.0/audyn/configs/decode-musdb18.yaml +11 -0
- audyn-0.4.0/audyn/configs/download-beatthis.yaml +7 -0
- audyn-0.4.0/audyn/configs/download-dnr.yaml +9 -0
- audyn-0.4.0/audyn/configs/download-fma.yaml +9 -0
- audyn-0.4.0/audyn/configs/download-fsd50k.yaml +8 -0
- audyn-0.4.0/audyn/configs/download-ljspeech.yaml +8 -0
- audyn-0.4.0/audyn/configs/download-lsx.yaml +8 -0
- audyn-0.4.0/audyn/configs/download-mtat.yaml +8 -0
- audyn-0.4.0/audyn/configs/download-mtg-jamendo.yaml +10 -0
- audyn-0.4.0/audyn/configs/download-musdb18.yaml +9 -0
- audyn-0.4.0/audyn/configs/download-openmic2018.yaml +8 -0
- audyn-0.4.0/audyn/configs/download-singmos.yaml +6 -0
- audyn-0.4.0/audyn/configs/download-song-describer.yaml +8 -0
- audyn-0.4.0/audyn/configs/download-vctk.yaml +8 -0
- audyn-0.4.0/audyn/configs/preprocess/mtg-jamendo.yaml +6 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/preprocess/text-to-feat.yaml +1 -1
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/preprocess/text-to-wave.yaml +1 -1
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/system/cpu.yaml +7 -3
- audyn-0.4.0/audyn/configs/system/cuda.yaml +8 -0
- audyn-0.4.0/audyn/configs/system/cuda_amp.yaml +6 -0
- audyn-0.4.0/audyn/configs/system/cuda_ddp.yaml +16 -0
- audyn-0.4.0/audyn/configs/system/cuda_ddp_amp.yaml +6 -0
- audyn-0.4.0/audyn/configs/system/default.yaml +28 -0
- audyn-0.4.0/audyn/configs/system/mps.yaml +11 -0
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/test/dataset/defaults.yaml → audyn-0.4.0/audyn/configs/test/dataset/default.yaml +0 -1
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/test/defaults.yaml → audyn-0.4.0/audyn/configs/test/default.yaml +2 -2
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/test/text_to_wave.yaml +2 -2
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/train/dataset/defaults.yaml → audyn-0.4.0/audyn/configs/train/dataset/default.yaml +1 -2
- audyn-0.4.0/audyn/configs/train/dataset/random-stems-dnr.yaml +27 -0
- audyn-0.4.0/audyn/configs/train/dataset/random-stems-musdb18.yaml +29 -0
- audyn-0.4.0/audyn/configs/train/dataset/stems-dnr.yaml +28 -0
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/train/defaults.yaml → audyn-0.4.0/audyn/configs/train/default.yaml +4 -4
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/gan.yaml +3 -3
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/template.yaml +4 -4
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/text-to-feat+pretrained_feat-to-wave.yaml +3 -3
- audyn-0.4.0/audyn/criterion/bsrnn.py +226 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/lsgan.py +4 -0
- audyn-0.4.0/audyn/criterion/negative_sampling.py +116 -0
- audyn-0.4.0/audyn/criterion/pit.py +114 -0
- audyn-0.4.0/audyn/criterion/poincare.py +57 -0
- audyn-0.4.0/audyn/criterion/rvqvae.py +67 -0
- audyn-0.4.0/audyn/criterion/sdr.py +153 -0
- audyn-0.4.0/audyn/criterion/tagging.py +87 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/vqvae.py +33 -2
- audyn-0.4.0/audyn/functional/__init__.py +21 -0
- audyn-0.4.0/audyn/functional/activation.py +333 -0
- audyn-0.4.0/audyn/functional/bitnet.py +168 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/functional/clustering.py +6 -6
- audyn-0.4.0/audyn/functional/hyperbolic.py +133 -0
- audyn-0.4.0/audyn/functional/loudness.py +177 -0
- audyn-0.4.0/audyn/functional/melspectrogram.py +60 -0
- audyn-0.4.0/audyn/functional/poincare.py +23 -0
- audyn-0.4.0/audyn/functional/positional_encoding.py +173 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/functional/vector_quantization.py +65 -9
- audyn-0.4.0/audyn/models/__init__.py +106 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/ast.py +68 -100
- audyn-0.4.0/audyn/models/bsrnn.py +287 -0
- audyn-0.4.0/audyn/models/bsroformer.py +301 -0
- audyn-0.4.0/audyn/models/clap.py +438 -0
- audyn-0.4.0/audyn/models/clip.py +286 -0
- audyn-0.4.0/audyn/models/conv_tasnet.py +191 -0
- audyn-0.4.0/audyn/models/dprnn_tasnet.py +192 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/encodec.py +217 -82
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/hifigan.py +19 -593
- audyn-0.4.0/audyn/models/hubert.py +368 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/lextransformer.py +3 -3
- audyn-0.4.0/audyn/models/music_tagging_transformer.py +320 -0
- audyn-0.4.0/audyn/models/musicfm.py +251 -0
- audyn-0.4.0/audyn/models/nafp.py +66 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/passt.py +7 -5
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/roformer.py +10 -24
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/rvqvae.py +129 -49
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/soundstream.py +12 -8
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/ssast.py +32 -14
- audyn-0.4.0/audyn/models/swintransformer.py +132 -0
- audyn-0.4.0/audyn/models/tasnet.py +267 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/text_to_wave.py +1 -1
- audyn-0.4.0/audyn/models/vqvae.py +426 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/waveglow.py +0 -3
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/wavenet.py +0 -1
- audyn-0.4.0/audyn/models/wavenext.py +127 -0
- audyn-0.4.0/audyn/modules/__init__.py +6 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/activation.py +502 -8
- audyn-0.4.0/audyn/modules/ast.py +218 -0
- audyn-0.4.0/audyn/modules/bitnet.py +916 -0
- audyn-0.4.0/audyn/modules/bsrnn.py +718 -0
- audyn-0.4.0/audyn/modules/bsroformer.py +638 -0
- audyn-0.4.0/audyn/modules/clap.py +408 -0
- audyn-0.4.0/audyn/modules/clip.py +96 -0
- audyn-0.4.0/audyn/modules/conv_tasnet.py +362 -0
- audyn-0.4.0/audyn/modules/convnext.py +209 -0
- audyn-0.4.0/audyn/modules/dprnn.py +301 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/encodec.py +137 -49
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/fastspeech.py +6 -6
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/flow.py +6 -4
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/glowtts.py +8 -9
- audyn-0.4.0/audyn/modules/glu.py +147 -0
- audyn-0.4.0/audyn/modules/hifigan.py +611 -0
- audyn-0.4.0/audyn/modules/lora.py +437 -0
- audyn-0.4.0/audyn/modules/manifold.py +208 -0
- audyn-0.4.0/audyn/modules/music_tagging_transformer.py +857 -0
- audyn-0.4.0/audyn/modules/musicfm.py +715 -0
- audyn-0.4.0/audyn/modules/nafp.py +244 -0
- audyn-0.4.0/audyn/modules/negative_sampling.py +73 -0
- audyn-0.4.0/audyn/modules/normalization.py +200 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/passt.py +14 -4
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/pixelsnail.py +6 -6
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/positional_encoding.py +59 -64
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/rvq.py +12 -8
- audyn-0.4.0/audyn/modules/swintransformer.py +786 -0
- audyn-0.4.0/audyn/modules/tasnet.py +74 -0
- audyn-0.4.0/audyn/modules/transformer.py +25 -0
- audyn-0.4.0/audyn/modules/transforms.py +89 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/vit.py +93 -33
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/vq.py +86 -5
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/waveglow.py +4 -4
- audyn-0.4.0/audyn/optim/__init__.py +39 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/optim/lr_scheduler.py +47 -4
- audyn-0.4.0/audyn/optim/optimizer/__init__.py +17 -0
- audyn-0.4.0/audyn/optim/optimizer/base.py +399 -0
- audyn-0.0.1.dev7/audyn/optim/optimizer.py → audyn-0.4.0/audyn/optim/optimizer/codebooks.py +123 -470
- audyn-0.4.0/audyn/optim/optimizer/manifold.py +165 -0
- audyn-0.4.0/audyn/transforms/__init__.py +73 -0
- audyn-0.4.0/audyn/transforms/clap.py +796 -0
- audyn-0.4.0/audyn/transforms/clip.py +39 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/cqt.py +12 -12
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/hifigan.py +1 -1
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/kaldi.py +1 -2
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/librosa.py +35 -2
- audyn-0.4.0/audyn/transforms/music_tagging_transformer.py +118 -0
- audyn-0.4.0/audyn/transforms/musicfm.py +215 -0
- audyn-0.4.0/audyn/transforms/resample.py +30 -0
- audyn-0.4.0/audyn/transforms/slicer.py +96 -0
- audyn-0.4.0/audyn/transforms/stft.py +77 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/__init__.py +333 -65
- {audyn-0.0.1.dev7/audyn/utils/github → audyn-0.4.0/audyn/utils/_github}/__init__.py +6 -19
- {audyn-0.0.1.dev7/audyn/utils/hydra → audyn-0.4.0/audyn/utils/_hydra}/__init__.py +1 -1
- {audyn-0.0.1.dev7/audyn/utils/hydra → audyn-0.4.0/audyn/utils/_hydra}/utils.py +136 -13
- audyn-0.4.0/audyn/utils/_torch/compile.py +64 -0
- audyn-0.4.0/audyn/utils/_torchhub/__init__.py +19 -0
- audyn-0.4.0/audyn/utils/_torchhub/ast.py +43 -0
- audyn-0.4.0/audyn/utils/_torchhub/music_tagging_transformer.py +49 -0
- audyn-0.4.0/audyn/utils/_torchhub/musicfm.py +62 -0
- audyn-0.4.0/audyn/utils/_torchhub/passt.py +39 -0
- audyn-0.4.0/audyn/utils/_torchhub/ssast.py +77 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/alignment/monotonic_align.py +14 -2
- audyn-0.4.0/audyn/utils/audio/__init__.py +57 -0
- audyn-0.4.0/audyn/utils/cache/__init__.py +33 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/__init__.py +34 -2
- audyn-0.4.0/audyn/utils/data/audioset/__init__.py +34 -0
- audyn-0.4.0/audyn/utils/data/audioset/_download.py +168 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/audioset/composer.py +4 -2
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/audioset/dataset.py +5 -12
- audyn-0.4.0/audyn/utils/data/audioset/indexer.py +118 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/audioset/sampler.py +2 -2
- audyn-0.4.0/audyn/utils/data/birdclef/__init__.py +49 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/_common/__init__.py +69 -16
- audyn-0.0.1.dev7/audyn/utils/data/birdclef/birdclef2024/collator.py → audyn-0.4.0/audyn/utils/data/birdclef/_common/collater.py +7 -4
- audyn-0.4.0/audyn/utils/data/birdclef/_common/composer.py +160 -0
- audyn-0.4.0/audyn/utils/data/birdclef/_common/dataset.py +127 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2021/__init__.py +96 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2021/_download.py +36 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2021/collator.py +26 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2021/composer.py +73 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2021/dataset.py +28 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2022/__init__.py +32 -3
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2022/_download.py +1 -1
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2022/collator.py +26 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2022/composer.py +73 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2022/dataset.py +28 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2023/__init__.py +96 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2023/_download.py +36 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2023/collator.py +26 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2023/composer.py +73 -0
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2023/dataset.py +28 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2024/__init__.py +32 -3
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2024/_download.py +1 -1
- audyn-0.4.0/audyn/utils/data/birdclef/birdclef2024/collator.py +26 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2024/composer.py +15 -96
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2024/dataset.py +3 -95
- audyn-0.4.0/audyn/utils/data/clap/__init__.py +5 -0
- audyn-0.4.0/audyn/utils/data/clap/composer.py +124 -0
- audyn-0.4.0/audyn/utils/data/clip/__init__.py +6 -0
- audyn-0.4.0/audyn/utils/data/clip/composer.py +57 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/clotho/text/indexing.py +28 -7
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/cmudict/__init__.py +2 -86
- audyn-0.4.0/audyn/utils/data/cmudict/_download.py +92 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/cmudict/indexing.py +6 -11
- audyn-0.4.0/audyn/utils/data/composer.py +708 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/dataloader.py +63 -1
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/dataset.py +26 -5
- audyn-0.4.0/audyn/utils/data/dnr/__init__.py +30 -0
- audyn-0.4.0/audyn/utils/data/dnr/_download.py +65 -0
- audyn-0.4.0/audyn/utils/data/dnr/dataset.py +1111 -0
- audyn-0.4.0/audyn/utils/data/dnr/distributed.py +86 -0
- audyn-0.4.0/audyn/utils/data/dnr/sampler.py +130 -0
- audyn-0.4.0/audyn/utils/data/download/__init__.py +73 -0
- audyn-0.4.0/audyn/utils/data/ecals/_download.py +1078 -0
- audyn-0.4.0/audyn/utils/data/fma/__init__.py +32 -0
- audyn-0.4.0/audyn/utils/data/fma/_download.py +92 -0
- audyn-0.4.0/audyn/utils/data/fma/composer.py +134 -0
- audyn-0.4.0/audyn/utils/data/gtzan/__init__.py +9 -0
- audyn-0.4.0/audyn/utils/data/gtzan/_download.py +18 -0
- audyn-0.4.0/audyn/utils/data/hifigan/__init__.py +3 -0
- audyn-0.4.0/audyn/utils/data/hifigan/composer.py +120 -0
- audyn-0.4.0/audyn/utils/data/jamendo_max_caps/__init__.py +7 -0
- audyn-0.4.0/audyn/utils/data/jamendo_max_caps/_download.py +49 -0
- audyn-0.4.0/audyn/utils/data/libritts/__init__.py +9 -0
- audyn-0.4.0/audyn/utils/data/libritts/_download.py +46 -0
- audyn-0.4.0/audyn/utils/data/msd_recommend/__init__.py +5 -0
- audyn-0.4.0/audyn/utils/data/msd_recommend/_download.py +88 -0
- audyn-0.4.0/audyn/utils/data/msd_tagging/__init__.py +11 -0
- audyn-0.4.0/audyn/utils/data/msd_tagging/_download.py +145 -0
- audyn-0.4.0/audyn/utils/data/mtat/__init__.py +9 -0
- audyn-0.4.0/audyn/utils/data/mtat/_download.py +74 -0
- audyn-0.4.0/audyn/utils/data/mtg_jamendo/__init__.py +45 -0
- audyn-0.4.0/audyn/utils/data/mtg_jamendo/_download.py +701 -0
- audyn-0.4.0/audyn/utils/data/mtg_jamendo/collator.py +45 -0
- audyn-0.4.0/audyn/utils/data/mtg_jamendo/composer.py +95 -0
- audyn-0.4.0/audyn/utils/data/musdb18/__init__.py +35 -0
- audyn-0.4.0/audyn/utils/data/musdb18/_download.py +78 -0
- audyn-0.4.0/audyn/utils/data/musdb18/dataset.py +1172 -0
- audyn-0.4.0/audyn/utils/data/musdb18/distributed.py +86 -0
- audyn-0.4.0/audyn/utils/data/musdb18/sampler.py +133 -0
- audyn-0.4.0/audyn/utils/data/openmic2018/__init__.py +10 -0
- audyn-0.4.0/audyn/utils/data/openmic2018/_download.py +65 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/tacotron/text/indexing.py +14 -7
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/tacotron/text/tokenization.py +14 -7
- audyn-0.4.0/audyn/utils/data/vctk/__init__.py +13 -0
- audyn-0.4.0/audyn/utils/data/vctk/_download.py +90 -0
- audyn-0.4.0/audyn/utils/data/wordnet/__init__.py +26 -0
- audyn-0.4.0/audyn/utils/data/wordnet/_download.py +102 -0
- audyn-0.4.0/audyn/utils/data/wordnet/composer.py +83 -0
- audyn-0.4.0/audyn/utils/data/wordnet/dataloader.py +95 -0
- audyn-0.4.0/audyn/utils/data/wordnet/dataset.py +386 -0
- audyn-0.4.0/audyn/utils/data/wordnet/indexer.py +104 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/driver/__init__.py +2 -1
- audyn-0.4.0/audyn/utils/driver/_decorator.py +81 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/driver/base.py +609 -261
- audyn-0.4.0/audyn/utils/driver/gan.py +1222 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/driver/text_to_feat.py +226 -163
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/driver/text_to_wave.py +10 -2
- audyn-0.4.0/audyn/utils/model/__init__.py +43 -0
- {audyn-0.0.1.dev7/audyn/utils/model → audyn-0.4.0/audyn/utils/modules}/__init__.py +10 -3
- audyn-0.4.0/audyn/utils/modules/bitnet.py +275 -0
- audyn-0.4.0/audyn/utils/modules/lora.py +107 -0
- audyn-0.4.0/audyn/utils/music/__init__.py +163 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/text/__init__.py +1 -1
- audyn-0.4.0/audyn/utils/text/vocab.py +13 -0
- audyn-0.4.0/csrc/monotonic_align_torch_2_4.cpp +109 -0
- audyn-0.4.0/pyproject.toml +101 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/setup.py +25 -9
- audyn-0.0.1.dev7/Audyn.egg-info/SOURCES.txt +0 -193
- audyn-0.0.1.dev7/README.md +0 -64
- audyn-0.0.1.dev7/audyn/criterion/rvqvae.py +0 -91
- audyn-0.0.1.dev7/audyn/functional/__init__.py +0 -3
- audyn-0.0.1.dev7/audyn/functional/activation.py +0 -119
- audyn-0.0.1.dev7/audyn/models/__init__.py +0 -53
- audyn-0.0.1.dev7/audyn/models/vqvae.py +0 -183
- audyn-0.0.1.dev7/audyn/modules/normalization.py +0 -3
- audyn-0.0.1.dev7/audyn/transforms/__init__.py +0 -23
- audyn-0.0.1.dev7/audyn/utils/data/audioset/_download.py +0 -53
- audyn-0.0.1.dev7/audyn/utils/data/composer.py +0 -135
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/config.yaml +0 -15
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/system/cuda.yaml +0 -11
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/system/cuda_amp.yaml +0 -11
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/system/cuda_ddp.yaml +0 -11
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/system/cuda_ddp_amp.yaml +0 -11
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/system/defaults.yaml +0 -11
- audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/system/mps.yaml +0 -11
- audyn-0.0.1.dev7/audyn/utils/driver/_decorator.py +0 -29
- audyn-0.0.1.dev7/audyn/utils/driver/gan.py +0 -1006
- audyn-0.0.1.dev7/audyn/utils/music/__init__.py +0 -66
- audyn-0.0.1.dev7/cpp_extensions/monotonic_align/monotonic_align.cpp +0 -96
- audyn-0.0.1.dev7/pyproject.toml +0 -85
- {audyn-0.0.1.dev7 → audyn-0.4.0}/Audyn.egg-info/dependency_links.txt +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/Audyn.egg-info/top_level.txt +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/LICENSE +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/criterion/cross_entropy.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/data/defaults.yaml → /audyn-0.4.0/audyn/configs/data/default.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/lr_scheduler/defaults.yaml → /audyn-0.4.0/audyn/configs/lr_scheduler/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/lr_scheduler/none.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/lr_scheduler/transformer.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/model/defaults.yaml → /audyn-0.4.0/audyn/configs/model/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/model/gan.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/optimizer/adam.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/optimizer/adam_ema.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/optimizer/adamw.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/optimizer/gan.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/preprocess/defaults.yaml → /audyn-0.4.0/audyn/configs/preprocess/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/preprocess/ljspeech_text-to-feat.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/test/dataloader/defaults.yaml → /audyn-0.4.0/audyn/configs/test/dataloader/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/test/dataset/torch.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/train/clip_gradient/defaults.yaml → /audyn-0.4.0/audyn/configs/train/clip_gradient/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/clip_gradient/gan.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/train/dataloader/defaults.yaml → /audyn-0.4.0/audyn/configs/train/dataloader/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/dataloader/sequential-batch.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/dataset/sortable-torch.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/dataset/torch.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/dataset/webdataset.yaml +0 -0
- /audyn-0.0.1.dev7/audyn/utils/driver/_conf_template/train/record/defaults.yaml → /audyn-0.4.0/audyn/configs/train/record/default.yaml +0 -0
- {audyn-0.0.1.dev7/audyn/utils/driver/_conf_template → audyn-0.4.0/audyn/configs}/train/record/template.yaml +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/autoregressive.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/base.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/contrastive.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/distance.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/fastspeech.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/flow.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/gan.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/glowtts.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/hifigan.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/melspectrogram.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/criterion/ssast.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/metrics/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/metrics/base.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/metrics/crossmodal.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/metrics/retrieval.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/fastspeech.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/gan.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/glowtts.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/pixelsnail.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/models/vae.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/duration_predictor.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/film.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/glow.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/pixelcnn.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/soundstream.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/vqvae.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/modules/wavenet.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/ast.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/birdclef.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/transforms/hubert.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/alignment/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/clip_grad.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/audioset/ast.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/audioset/distributed.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/birdclef/birdclef2024/models/baseline.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/clotho/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/clotho/text/normalization.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/clotho/text/symbols.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/clotho/text/tokenization.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/collator.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/distributed.py +0 -0
- {audyn-0.0.1.dev7/audyn/utils/data/audioset → audyn-0.4.0/audyn/utils/data/ecals}/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/postprocess.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/sampler.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/tacotron/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/tacotron/text/normalization.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/tacotron/text/numbers.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/tacotron/text/symbols.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/data/webdataset.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/distributed/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/driver/feat_to_wave.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/duration/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/lab/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/logging/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/parallel/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/tensorboard/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/text/indexing.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/text/normalization.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/text/pronunciation.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/text/tokenization.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/audyn/utils/textgrid/__init__.py +0 -0
- {audyn-0.0.1.dev7 → audyn-0.4.0}/setup.cfg +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
|
-
Metadata-Version: 2.
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
2
|
Name: Audyn
|
|
3
|
-
Version: 0.0
|
|
3
|
+
Version: 0.4.0
|
|
4
4
|
Summary: A PyTorch toolkit for audio synthesis.
|
|
5
5
|
Author: Takuya Hasumi
|
|
6
6
|
License: Apache License
|
|
@@ -206,26 +206,24 @@ License: Apache License
|
|
|
206
206
|
limitations under the License.
|
|
207
207
|
|
|
208
208
|
Project-URL: url, https://github.com/tky823/Audyn
|
|
209
|
-
Requires-Python: <4,>=3.
|
|
209
|
+
Requires-Python: <4,>=3.10
|
|
210
210
|
Description-Content-Type: text/markdown
|
|
211
211
|
License-File: LICENSE
|
|
212
|
-
Requires-Dist: importlib_resources<6.2; python_version == "3.8"
|
|
213
212
|
Requires-Dist: omegaconf
|
|
214
213
|
Requires-Dist: hydra-core
|
|
215
214
|
Requires-Dist: matplotlib
|
|
216
215
|
Requires-Dist: torch
|
|
217
216
|
Requires-Dist: torchaudio
|
|
218
|
-
Requires-Dist: torchtext
|
|
219
217
|
Requires-Dist: torchvision
|
|
220
218
|
Requires-Dist: tensorboard
|
|
219
|
+
Requires-Dist: numpy
|
|
221
220
|
Requires-Dist: webdataset
|
|
222
221
|
Requires-Dist: inflect
|
|
222
|
+
Requires-Dist: setuptools<81
|
|
223
223
|
Provides-Extra: recipes
|
|
224
224
|
Requires-Dist: tqdm; extra == "recipes"
|
|
225
225
|
Provides-Extra: dev
|
|
226
|
-
Requires-Dist:
|
|
227
|
-
Requires-Dist: black; extra == "dev"
|
|
228
|
-
Requires-Dist: isort; extra == "dev"
|
|
226
|
+
Requires-Dist: ruff; extra == "dev"
|
|
229
227
|
Provides-Extra: docs
|
|
230
228
|
Requires-Dist: sphinx; extra == "docs"
|
|
231
229
|
Requires-Dist: sphinx-autodoc-typehints; extra == "docs"
|
|
@@ -235,18 +233,51 @@ Requires-Dist: furo; extra == "docs"
|
|
|
235
233
|
Provides-Extra: tests
|
|
236
234
|
Requires-Dist: pytest; extra == "tests"
|
|
237
235
|
Requires-Dist: pytest-cov; extra == "tests"
|
|
236
|
+
Dynamic: license-file
|
|
238
237
|
|
|
239
238
|
# Audyn
|
|
239
|
+
|
|
240
240
|
[](https://codecov.io/gh/tky823/Audyn)
|
|
241
241
|
|
|
242
242
|
Audyn is PyTorch toolkit for audio synthesis.
|
|
243
243
|
|
|
244
|
+
## Build Status
|
|
245
|
+
|
|
246
|
+
| Python/PyTorch | Ubuntu | MacOS (x86_64) | MacOS (arm64) | Windows |
|
|
247
|
+
|:-:|:-:|:-:|:-:|:-:|
|
|
248
|
+
| 3.10/2.0 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.10_torch-2.0.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.10_torch-2.0.yaml) |
|
|
249
|
+
| 3.10/2.1 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.10_torch-2.1.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.10_torch-2.1.yaml) |
|
|
250
|
+
| 3.10/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.10_torch-2.2.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.10_torch-2.2.yaml) |
|
|
251
|
+
| 3.10/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.3.yaml) | | | |
|
|
252
|
+
| 3.11/2.0 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.11_torch-2.0.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.0.yaml) |
|
|
253
|
+
| 3.11/2.1 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.11_torch-2.1.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.1.yaml) |
|
|
254
|
+
| 3.11/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.11_torch-2.2.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.2.yaml) |
|
|
255
|
+
| 3.11/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.3.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.11_torch-2.3.yaml) | |
|
|
256
|
+
| 3.11/2.5 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.5.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.11_torch-2.5.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.5.yaml) |
|
|
257
|
+
| 3.11/2.6 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.6.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.11_torch-2.6.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.6.yaml) |
|
|
258
|
+
| 3.12/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.12_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-15-intel_python-3.12_torch-2.2.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.12_torch-2.2.yaml) |
|
|
259
|
+
| 3.12/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.12_torch-2.3.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.12_torch-2.3.yaml) | |
|
|
260
|
+
| 3.12/2.5 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.12_torch-2.5.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.12_torch-2.5.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.12_torch-2.5.yaml) |
|
|
261
|
+
| 3.12/2.7 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.12_torch-2.7.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.12_torch-2.7.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.12_torch-2.7.yaml) |
|
|
262
|
+
| 3.12/2.10 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.12_torch-2.10.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.12_torch-2.10.yaml) | |
|
|
263
|
+
| 3.13/2.6 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.13_torch-2.6.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.13_torch-2.6.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.13_torch-2.6.yaml) |
|
|
264
|
+
| 3.13/2.7 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.13_torch-2.7.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.13_torch-2.7.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.13_torch-2.7.yaml) |
|
|
265
|
+
| 3.13/2.8 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.13_torch-2.8.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.13_torch-2.8.yaml) | |
|
|
266
|
+
| 3.13/2.9 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.13_torch-2.9.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.13_torch-2.9.yaml) | |
|
|
267
|
+
| 3.13/2.10 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.13_torch-2.10.yaml) | | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-latest_python-3.13_torch-2.10.yaml) | |
|
|
268
|
+
|
|
244
269
|
## Installation
|
|
270
|
+
|
|
245
271
|
You can install by pip.
|
|
272
|
+
|
|
246
273
|
```shell
|
|
247
|
-
pip install
|
|
274
|
+
pip install Audyn
|
|
275
|
+
# from source
|
|
276
|
+
# pip install git+https://github.com/tky823/Audyn.git
|
|
248
277
|
```
|
|
278
|
+
|
|
249
279
|
or clone this repository.
|
|
280
|
+
|
|
250
281
|
```shell
|
|
251
282
|
git clone https://github.com/tky823/Audyn.git
|
|
252
283
|
cd Audyn
|
|
@@ -254,6 +285,7 @@ pip install -e .
|
|
|
254
285
|
```
|
|
255
286
|
|
|
256
287
|
If you need to run recipes, add `[recipes]` as follows:
|
|
288
|
+
|
|
257
289
|
```shell
|
|
258
290
|
# In Audyn/
|
|
259
291
|
pip install -e ".[recipes]"
|
|
@@ -262,6 +294,7 @@ pip install -e ".[recipes]"
|
|
|
262
294
|
If you use MacOS, you may need to set `MACOSX_DEPLOYMENT_TARGET` during installation to build C++ related modules.
|
|
263
295
|
|
|
264
296
|
### C++ extension
|
|
297
|
+
|
|
265
298
|
We use [C++ extension](https://pytorch.org/tutorials/advanced/cpp_extension.html) to search monotonic alignment in some models (e.g. GlowTTS).
|
|
266
299
|
To take full advantage of computational efficiency, set appropriate value of `OMP_NUM_THREADS` and `CXX` during installation:
|
|
267
300
|
|
|
@@ -272,31 +305,63 @@ export OMP_NUM_THREADS=<SUITABLE/VALUE/FOR/ENVIRONMENT>
|
|
|
272
305
|
pip install -e "."
|
|
273
306
|
```
|
|
274
307
|
|
|
308
|
+
### Backend of torchaudio
|
|
309
|
+
|
|
310
|
+
For `torch>=2.9`, `torchcodec` is required as backend of `torchaudio`:
|
|
311
|
+
|
|
312
|
+
```sh
|
|
313
|
+
pip install torchcodec
|
|
314
|
+
```
|
|
315
|
+
|
|
275
316
|
## Development
|
|
317
|
+
|
|
276
318
|
```shell
|
|
277
|
-
|
|
319
|
+
git clone https://github.com/tky823/Audyn.git
|
|
320
|
+
cd Audyn
|
|
278
321
|
pip install -e ".[recipes,dev,tests]"
|
|
279
322
|
```
|
|
280
323
|
|
|
281
324
|
## Build Documentation Locally (optional)
|
|
325
|
+
|
|
282
326
|
To build the documentation locally, you have to include `docs` when installing `Audyn`.
|
|
327
|
+
|
|
283
328
|
```shell
|
|
284
329
|
pip install -e ".[docs]"
|
|
285
330
|
```
|
|
286
331
|
|
|
287
332
|
When you build the documentation, run the following command.
|
|
333
|
+
|
|
288
334
|
```shell
|
|
289
335
|
cd docs/
|
|
290
336
|
make html
|
|
291
337
|
```
|
|
292
338
|
|
|
293
339
|
Or, you can build the documentation automatically using `sphinx-autobuild`.
|
|
340
|
+
|
|
294
341
|
```shell
|
|
295
342
|
# in Audyn/
|
|
296
343
|
sphinx-autobuild docs docs/_build/html
|
|
297
344
|
```
|
|
298
345
|
|
|
299
346
|
## Test
|
|
347
|
+
|
|
300
348
|
```shell
|
|
301
349
|
pytest tests/package
|
|
302
350
|
```
|
|
351
|
+
|
|
352
|
+
To include DDP tests
|
|
353
|
+
|
|
354
|
+
```shell
|
|
355
|
+
pytest tests/package --runddp
|
|
356
|
+
```
|
|
357
|
+
|
|
358
|
+
To include slow tests
|
|
359
|
+
|
|
360
|
+
```shell
|
|
361
|
+
pytest tests/package --runslow
|
|
362
|
+
```
|
|
363
|
+
|
|
364
|
+
## License
|
|
365
|
+
|
|
366
|
+
- Apache License, Version 2.0 **EXCEPT FOR WEIGHTS OF PRETRAINED MODELS**
|
|
367
|
+
- Weights for some of the pre-trained models are extracted from the official implementations. Their licenses follow the official implementations.
|
|
@@ -0,0 +1,369 @@
|
|
|
1
|
+
LICENSE
|
|
2
|
+
MANIFEST.in
|
|
3
|
+
README.md
|
|
4
|
+
pyproject.toml
|
|
5
|
+
setup.py
|
|
6
|
+
Audyn.egg-info/PKG-INFO
|
|
7
|
+
Audyn.egg-info/SOURCES.txt
|
|
8
|
+
Audyn.egg-info/dependency_links.txt
|
|
9
|
+
Audyn.egg-info/entry_points.txt
|
|
10
|
+
Audyn.egg-info/requires.txt
|
|
11
|
+
Audyn.egg-info/top_level.txt
|
|
12
|
+
audyn/__init__.py
|
|
13
|
+
audyn/amp/__init__.py
|
|
14
|
+
audyn/amp/grad_scaler.py
|
|
15
|
+
audyn/bin/decode_musdb18.py
|
|
16
|
+
audyn/bin/download_beatthis.py
|
|
17
|
+
audyn/bin/download_dnr.py
|
|
18
|
+
audyn/bin/download_fma.py
|
|
19
|
+
audyn/bin/download_fsd50k.py
|
|
20
|
+
audyn/bin/download_ljspeech.py
|
|
21
|
+
audyn/bin/download_lsx.py
|
|
22
|
+
audyn/bin/download_mtat.py
|
|
23
|
+
audyn/bin/download_mtg_jamendo.py
|
|
24
|
+
audyn/bin/download_musdb18.py
|
|
25
|
+
audyn/bin/download_openmic2018.py
|
|
26
|
+
audyn/bin/download_singmos.py
|
|
27
|
+
audyn/bin/download_song_describer.py
|
|
28
|
+
audyn/bin/download_vctk.py
|
|
29
|
+
audyn/bin/parse_run_command.py
|
|
30
|
+
audyn/configs/config.yaml
|
|
31
|
+
audyn/configs/decode-musdb18.yaml
|
|
32
|
+
audyn/configs/download-beatthis.yaml
|
|
33
|
+
audyn/configs/download-dnr.yaml
|
|
34
|
+
audyn/configs/download-fma.yaml
|
|
35
|
+
audyn/configs/download-fsd50k.yaml
|
|
36
|
+
audyn/configs/download-ljspeech.yaml
|
|
37
|
+
audyn/configs/download-lsx.yaml
|
|
38
|
+
audyn/configs/download-mtat.yaml
|
|
39
|
+
audyn/configs/download-mtg-jamendo.yaml
|
|
40
|
+
audyn/configs/download-musdb18.yaml
|
|
41
|
+
audyn/configs/download-openmic2018.yaml
|
|
42
|
+
audyn/configs/download-singmos.yaml
|
|
43
|
+
audyn/configs/download-song-describer.yaml
|
|
44
|
+
audyn/configs/download-vctk.yaml
|
|
45
|
+
audyn/configs/criterion/cross_entropy.yaml
|
|
46
|
+
audyn/configs/criterion/vqvae.yaml
|
|
47
|
+
audyn/configs/data/default.yaml
|
|
48
|
+
audyn/configs/data/mtg-jamendo.yaml
|
|
49
|
+
audyn/configs/data/wordnet-mammal.yaml
|
|
50
|
+
audyn/configs/lr_scheduler/default.yaml
|
|
51
|
+
audyn/configs/lr_scheduler/none.yaml
|
|
52
|
+
audyn/configs/lr_scheduler/transformer.yaml
|
|
53
|
+
audyn/configs/model/default.yaml
|
|
54
|
+
audyn/configs/model/gan.yaml
|
|
55
|
+
audyn/configs/optimizer/adam.yaml
|
|
56
|
+
audyn/configs/optimizer/adam_ema.yaml
|
|
57
|
+
audyn/configs/optimizer/adamw.yaml
|
|
58
|
+
audyn/configs/optimizer/gan.yaml
|
|
59
|
+
audyn/configs/preprocess/default.yaml
|
|
60
|
+
audyn/configs/preprocess/ljspeech_text-to-feat.yaml
|
|
61
|
+
audyn/configs/preprocess/mtg-jamendo.yaml
|
|
62
|
+
audyn/configs/preprocess/text-to-feat.yaml
|
|
63
|
+
audyn/configs/preprocess/text-to-wave.yaml
|
|
64
|
+
audyn/configs/system/cpu.yaml
|
|
65
|
+
audyn/configs/system/cuda.yaml
|
|
66
|
+
audyn/configs/system/cuda_amp.yaml
|
|
67
|
+
audyn/configs/system/cuda_ddp.yaml
|
|
68
|
+
audyn/configs/system/cuda_ddp_amp.yaml
|
|
69
|
+
audyn/configs/system/default.yaml
|
|
70
|
+
audyn/configs/system/mps.yaml
|
|
71
|
+
audyn/configs/test/default.yaml
|
|
72
|
+
audyn/configs/test/text_to_wave.yaml
|
|
73
|
+
audyn/configs/test/dataloader/default.yaml
|
|
74
|
+
audyn/configs/test/dataset/default.yaml
|
|
75
|
+
audyn/configs/test/dataset/torch.yaml
|
|
76
|
+
audyn/configs/train/default.yaml
|
|
77
|
+
audyn/configs/train/gan.yaml
|
|
78
|
+
audyn/configs/train/template.yaml
|
|
79
|
+
audyn/configs/train/text-to-feat+pretrained_feat-to-wave.yaml
|
|
80
|
+
audyn/configs/train/clip_gradient/default.yaml
|
|
81
|
+
audyn/configs/train/clip_gradient/gan.yaml
|
|
82
|
+
audyn/configs/train/dataloader/default.yaml
|
|
83
|
+
audyn/configs/train/dataloader/sequential-batch.yaml
|
|
84
|
+
audyn/configs/train/dataset/default.yaml
|
|
85
|
+
audyn/configs/train/dataset/random-stems-dnr.yaml
|
|
86
|
+
audyn/configs/train/dataset/random-stems-musdb18.yaml
|
|
87
|
+
audyn/configs/train/dataset/sortable-torch.yaml
|
|
88
|
+
audyn/configs/train/dataset/stems-dnr.yaml
|
|
89
|
+
audyn/configs/train/dataset/torch.yaml
|
|
90
|
+
audyn/configs/train/dataset/webdataset.yaml
|
|
91
|
+
audyn/configs/train/record/default.yaml
|
|
92
|
+
audyn/configs/train/record/template.yaml
|
|
93
|
+
audyn/criterion/__init__.py
|
|
94
|
+
audyn/criterion/autoregressive.py
|
|
95
|
+
audyn/criterion/base.py
|
|
96
|
+
audyn/criterion/bsrnn.py
|
|
97
|
+
audyn/criterion/contrastive.py
|
|
98
|
+
audyn/criterion/distance.py
|
|
99
|
+
audyn/criterion/fastspeech.py
|
|
100
|
+
audyn/criterion/flow.py
|
|
101
|
+
audyn/criterion/gan.py
|
|
102
|
+
audyn/criterion/glowtts.py
|
|
103
|
+
audyn/criterion/hifigan.py
|
|
104
|
+
audyn/criterion/lsgan.py
|
|
105
|
+
audyn/criterion/melspectrogram.py
|
|
106
|
+
audyn/criterion/negative_sampling.py
|
|
107
|
+
audyn/criterion/pit.py
|
|
108
|
+
audyn/criterion/poincare.py
|
|
109
|
+
audyn/criterion/rvqvae.py
|
|
110
|
+
audyn/criterion/sdr.py
|
|
111
|
+
audyn/criterion/ssast.py
|
|
112
|
+
audyn/criterion/tagging.py
|
|
113
|
+
audyn/criterion/vqvae.py
|
|
114
|
+
audyn/functional/__init__.py
|
|
115
|
+
audyn/functional/activation.py
|
|
116
|
+
audyn/functional/bitnet.py
|
|
117
|
+
audyn/functional/clustering.py
|
|
118
|
+
audyn/functional/hyperbolic.py
|
|
119
|
+
audyn/functional/loudness.py
|
|
120
|
+
audyn/functional/melspectrogram.py
|
|
121
|
+
audyn/functional/poincare.py
|
|
122
|
+
audyn/functional/positional_encoding.py
|
|
123
|
+
audyn/functional/vector_quantization.py
|
|
124
|
+
audyn/metrics/__init__.py
|
|
125
|
+
audyn/metrics/base.py
|
|
126
|
+
audyn/metrics/crossmodal.py
|
|
127
|
+
audyn/metrics/retrieval.py
|
|
128
|
+
audyn/models/__init__.py
|
|
129
|
+
audyn/models/ast.py
|
|
130
|
+
audyn/models/bsrnn.py
|
|
131
|
+
audyn/models/bsroformer.py
|
|
132
|
+
audyn/models/clap.py
|
|
133
|
+
audyn/models/clip.py
|
|
134
|
+
audyn/models/conv_tasnet.py
|
|
135
|
+
audyn/models/dprnn_tasnet.py
|
|
136
|
+
audyn/models/encodec.py
|
|
137
|
+
audyn/models/fastspeech.py
|
|
138
|
+
audyn/models/gan.py
|
|
139
|
+
audyn/models/glowtts.py
|
|
140
|
+
audyn/models/hifigan.py
|
|
141
|
+
audyn/models/hubert.py
|
|
142
|
+
audyn/models/lextransformer.py
|
|
143
|
+
audyn/models/music_tagging_transformer.py
|
|
144
|
+
audyn/models/musicfm.py
|
|
145
|
+
audyn/models/nafp.py
|
|
146
|
+
audyn/models/passt.py
|
|
147
|
+
audyn/models/pixelsnail.py
|
|
148
|
+
audyn/models/roformer.py
|
|
149
|
+
audyn/models/rvqvae.py
|
|
150
|
+
audyn/models/soundstream.py
|
|
151
|
+
audyn/models/ssast.py
|
|
152
|
+
audyn/models/swintransformer.py
|
|
153
|
+
audyn/models/tasnet.py
|
|
154
|
+
audyn/models/text_to_wave.py
|
|
155
|
+
audyn/models/vae.py
|
|
156
|
+
audyn/models/vqvae.py
|
|
157
|
+
audyn/models/waveglow.py
|
|
158
|
+
audyn/models/wavenet.py
|
|
159
|
+
audyn/models/wavenext.py
|
|
160
|
+
audyn/modules/__init__.py
|
|
161
|
+
audyn/modules/activation.py
|
|
162
|
+
audyn/modules/ast.py
|
|
163
|
+
audyn/modules/bitnet.py
|
|
164
|
+
audyn/modules/bsrnn.py
|
|
165
|
+
audyn/modules/bsroformer.py
|
|
166
|
+
audyn/modules/clap.py
|
|
167
|
+
audyn/modules/clip.py
|
|
168
|
+
audyn/modules/conv_tasnet.py
|
|
169
|
+
audyn/modules/convnext.py
|
|
170
|
+
audyn/modules/dprnn.py
|
|
171
|
+
audyn/modules/duration_predictor.py
|
|
172
|
+
audyn/modules/encodec.py
|
|
173
|
+
audyn/modules/fastspeech.py
|
|
174
|
+
audyn/modules/film.py
|
|
175
|
+
audyn/modules/flow.py
|
|
176
|
+
audyn/modules/glow.py
|
|
177
|
+
audyn/modules/glowtts.py
|
|
178
|
+
audyn/modules/glu.py
|
|
179
|
+
audyn/modules/hifigan.py
|
|
180
|
+
audyn/modules/lora.py
|
|
181
|
+
audyn/modules/manifold.py
|
|
182
|
+
audyn/modules/music_tagging_transformer.py
|
|
183
|
+
audyn/modules/musicfm.py
|
|
184
|
+
audyn/modules/nafp.py
|
|
185
|
+
audyn/modules/negative_sampling.py
|
|
186
|
+
audyn/modules/normalization.py
|
|
187
|
+
audyn/modules/passt.py
|
|
188
|
+
audyn/modules/pixelcnn.py
|
|
189
|
+
audyn/modules/pixelsnail.py
|
|
190
|
+
audyn/modules/positional_encoding.py
|
|
191
|
+
audyn/modules/rvq.py
|
|
192
|
+
audyn/modules/soundstream.py
|
|
193
|
+
audyn/modules/swintransformer.py
|
|
194
|
+
audyn/modules/tasnet.py
|
|
195
|
+
audyn/modules/transformer.py
|
|
196
|
+
audyn/modules/transforms.py
|
|
197
|
+
audyn/modules/vit.py
|
|
198
|
+
audyn/modules/vq.py
|
|
199
|
+
audyn/modules/vqvae.py
|
|
200
|
+
audyn/modules/waveglow.py
|
|
201
|
+
audyn/modules/wavenet.py
|
|
202
|
+
audyn/optim/__init__.py
|
|
203
|
+
audyn/optim/lr_scheduler.py
|
|
204
|
+
audyn/optim/optimizer/__init__.py
|
|
205
|
+
audyn/optim/optimizer/base.py
|
|
206
|
+
audyn/optim/optimizer/codebooks.py
|
|
207
|
+
audyn/optim/optimizer/manifold.py
|
|
208
|
+
audyn/transforms/__init__.py
|
|
209
|
+
audyn/transforms/ast.py
|
|
210
|
+
audyn/transforms/birdclef.py
|
|
211
|
+
audyn/transforms/clap.py
|
|
212
|
+
audyn/transforms/clip.py
|
|
213
|
+
audyn/transforms/cqt.py
|
|
214
|
+
audyn/transforms/hifigan.py
|
|
215
|
+
audyn/transforms/hubert.py
|
|
216
|
+
audyn/transforms/kaldi.py
|
|
217
|
+
audyn/transforms/librosa.py
|
|
218
|
+
audyn/transforms/music_tagging_transformer.py
|
|
219
|
+
audyn/transforms/musicfm.py
|
|
220
|
+
audyn/transforms/resample.py
|
|
221
|
+
audyn/transforms/slicer.py
|
|
222
|
+
audyn/transforms/stft.py
|
|
223
|
+
audyn/utils/__init__.py
|
|
224
|
+
audyn/utils/clip_grad.py
|
|
225
|
+
audyn/utils/_github/__init__.py
|
|
226
|
+
audyn/utils/_hydra/__init__.py
|
|
227
|
+
audyn/utils/_hydra/utils.py
|
|
228
|
+
audyn/utils/_torch/compile.py
|
|
229
|
+
audyn/utils/_torchhub/__init__.py
|
|
230
|
+
audyn/utils/_torchhub/ast.py
|
|
231
|
+
audyn/utils/_torchhub/music_tagging_transformer.py
|
|
232
|
+
audyn/utils/_torchhub/musicfm.py
|
|
233
|
+
audyn/utils/_torchhub/passt.py
|
|
234
|
+
audyn/utils/_torchhub/ssast.py
|
|
235
|
+
audyn/utils/alignment/__init__.py
|
|
236
|
+
audyn/utils/alignment/monotonic_align.py
|
|
237
|
+
audyn/utils/audio/__init__.py
|
|
238
|
+
audyn/utils/cache/__init__.py
|
|
239
|
+
audyn/utils/data/__init__.py
|
|
240
|
+
audyn/utils/data/collator.py
|
|
241
|
+
audyn/utils/data/composer.py
|
|
242
|
+
audyn/utils/data/dataloader.py
|
|
243
|
+
audyn/utils/data/dataset.py
|
|
244
|
+
audyn/utils/data/distributed.py
|
|
245
|
+
audyn/utils/data/postprocess.py
|
|
246
|
+
audyn/utils/data/sampler.py
|
|
247
|
+
audyn/utils/data/webdataset.py
|
|
248
|
+
audyn/utils/data/audioset/__init__.py
|
|
249
|
+
audyn/utils/data/audioset/_download.py
|
|
250
|
+
audyn/utils/data/audioset/ast.py
|
|
251
|
+
audyn/utils/data/audioset/composer.py
|
|
252
|
+
audyn/utils/data/audioset/dataset.py
|
|
253
|
+
audyn/utils/data/audioset/distributed.py
|
|
254
|
+
audyn/utils/data/audioset/indexer.py
|
|
255
|
+
audyn/utils/data/audioset/sampler.py
|
|
256
|
+
audyn/utils/data/birdclef/__init__.py
|
|
257
|
+
audyn/utils/data/birdclef/_common/__init__.py
|
|
258
|
+
audyn/utils/data/birdclef/_common/collater.py
|
|
259
|
+
audyn/utils/data/birdclef/_common/composer.py
|
|
260
|
+
audyn/utils/data/birdclef/_common/dataset.py
|
|
261
|
+
audyn/utils/data/birdclef/birdclef2021/__init__.py
|
|
262
|
+
audyn/utils/data/birdclef/birdclef2021/_download.py
|
|
263
|
+
audyn/utils/data/birdclef/birdclef2021/collator.py
|
|
264
|
+
audyn/utils/data/birdclef/birdclef2021/composer.py
|
|
265
|
+
audyn/utils/data/birdclef/birdclef2021/dataset.py
|
|
266
|
+
audyn/utils/data/birdclef/birdclef2022/__init__.py
|
|
267
|
+
audyn/utils/data/birdclef/birdclef2022/_download.py
|
|
268
|
+
audyn/utils/data/birdclef/birdclef2022/collator.py
|
|
269
|
+
audyn/utils/data/birdclef/birdclef2022/composer.py
|
|
270
|
+
audyn/utils/data/birdclef/birdclef2022/dataset.py
|
|
271
|
+
audyn/utils/data/birdclef/birdclef2023/__init__.py
|
|
272
|
+
audyn/utils/data/birdclef/birdclef2023/_download.py
|
|
273
|
+
audyn/utils/data/birdclef/birdclef2023/collator.py
|
|
274
|
+
audyn/utils/data/birdclef/birdclef2023/composer.py
|
|
275
|
+
audyn/utils/data/birdclef/birdclef2023/dataset.py
|
|
276
|
+
audyn/utils/data/birdclef/birdclef2024/__init__.py
|
|
277
|
+
audyn/utils/data/birdclef/birdclef2024/_download.py
|
|
278
|
+
audyn/utils/data/birdclef/birdclef2024/collator.py
|
|
279
|
+
audyn/utils/data/birdclef/birdclef2024/composer.py
|
|
280
|
+
audyn/utils/data/birdclef/birdclef2024/dataset.py
|
|
281
|
+
audyn/utils/data/birdclef/birdclef2024/models/baseline.py
|
|
282
|
+
audyn/utils/data/clap/__init__.py
|
|
283
|
+
audyn/utils/data/clap/composer.py
|
|
284
|
+
audyn/utils/data/clip/__init__.py
|
|
285
|
+
audyn/utils/data/clip/composer.py
|
|
286
|
+
audyn/utils/data/clotho/__init__.py
|
|
287
|
+
audyn/utils/data/clotho/text/indexing.py
|
|
288
|
+
audyn/utils/data/clotho/text/normalization.py
|
|
289
|
+
audyn/utils/data/clotho/text/symbols.py
|
|
290
|
+
audyn/utils/data/clotho/text/tokenization.py
|
|
291
|
+
audyn/utils/data/cmudict/__init__.py
|
|
292
|
+
audyn/utils/data/cmudict/_download.py
|
|
293
|
+
audyn/utils/data/cmudict/indexing.py
|
|
294
|
+
audyn/utils/data/dnr/__init__.py
|
|
295
|
+
audyn/utils/data/dnr/_download.py
|
|
296
|
+
audyn/utils/data/dnr/dataset.py
|
|
297
|
+
audyn/utils/data/dnr/distributed.py
|
|
298
|
+
audyn/utils/data/dnr/sampler.py
|
|
299
|
+
audyn/utils/data/download/__init__.py
|
|
300
|
+
audyn/utils/data/ecals/__init__.py
|
|
301
|
+
audyn/utils/data/ecals/_download.py
|
|
302
|
+
audyn/utils/data/fma/__init__.py
|
|
303
|
+
audyn/utils/data/fma/_download.py
|
|
304
|
+
audyn/utils/data/fma/composer.py
|
|
305
|
+
audyn/utils/data/gtzan/__init__.py
|
|
306
|
+
audyn/utils/data/gtzan/_download.py
|
|
307
|
+
audyn/utils/data/hifigan/__init__.py
|
|
308
|
+
audyn/utils/data/hifigan/composer.py
|
|
309
|
+
audyn/utils/data/jamendo_max_caps/__init__.py
|
|
310
|
+
audyn/utils/data/jamendo_max_caps/_download.py
|
|
311
|
+
audyn/utils/data/libritts/__init__.py
|
|
312
|
+
audyn/utils/data/libritts/_download.py
|
|
313
|
+
audyn/utils/data/msd_recommend/__init__.py
|
|
314
|
+
audyn/utils/data/msd_recommend/_download.py
|
|
315
|
+
audyn/utils/data/msd_tagging/__init__.py
|
|
316
|
+
audyn/utils/data/msd_tagging/_download.py
|
|
317
|
+
audyn/utils/data/mtat/__init__.py
|
|
318
|
+
audyn/utils/data/mtat/_download.py
|
|
319
|
+
audyn/utils/data/mtg_jamendo/__init__.py
|
|
320
|
+
audyn/utils/data/mtg_jamendo/_download.py
|
|
321
|
+
audyn/utils/data/mtg_jamendo/collator.py
|
|
322
|
+
audyn/utils/data/mtg_jamendo/composer.py
|
|
323
|
+
audyn/utils/data/musdb18/__init__.py
|
|
324
|
+
audyn/utils/data/musdb18/_download.py
|
|
325
|
+
audyn/utils/data/musdb18/dataset.py
|
|
326
|
+
audyn/utils/data/musdb18/distributed.py
|
|
327
|
+
audyn/utils/data/musdb18/sampler.py
|
|
328
|
+
audyn/utils/data/openmic2018/__init__.py
|
|
329
|
+
audyn/utils/data/openmic2018/_download.py
|
|
330
|
+
audyn/utils/data/tacotron/__init__.py
|
|
331
|
+
audyn/utils/data/tacotron/text/indexing.py
|
|
332
|
+
audyn/utils/data/tacotron/text/normalization.py
|
|
333
|
+
audyn/utils/data/tacotron/text/numbers.py
|
|
334
|
+
audyn/utils/data/tacotron/text/symbols.py
|
|
335
|
+
audyn/utils/data/tacotron/text/tokenization.py
|
|
336
|
+
audyn/utils/data/vctk/__init__.py
|
|
337
|
+
audyn/utils/data/vctk/_download.py
|
|
338
|
+
audyn/utils/data/wordnet/__init__.py
|
|
339
|
+
audyn/utils/data/wordnet/_download.py
|
|
340
|
+
audyn/utils/data/wordnet/composer.py
|
|
341
|
+
audyn/utils/data/wordnet/dataloader.py
|
|
342
|
+
audyn/utils/data/wordnet/dataset.py
|
|
343
|
+
audyn/utils/data/wordnet/indexer.py
|
|
344
|
+
audyn/utils/distributed/__init__.py
|
|
345
|
+
audyn/utils/driver/__init__.py
|
|
346
|
+
audyn/utils/driver/_decorator.py
|
|
347
|
+
audyn/utils/driver/base.py
|
|
348
|
+
audyn/utils/driver/feat_to_wave.py
|
|
349
|
+
audyn/utils/driver/gan.py
|
|
350
|
+
audyn/utils/driver/text_to_feat.py
|
|
351
|
+
audyn/utils/driver/text_to_wave.py
|
|
352
|
+
audyn/utils/duration/__init__.py
|
|
353
|
+
audyn/utils/lab/__init__.py
|
|
354
|
+
audyn/utils/logging/__init__.py
|
|
355
|
+
audyn/utils/model/__init__.py
|
|
356
|
+
audyn/utils/modules/__init__.py
|
|
357
|
+
audyn/utils/modules/bitnet.py
|
|
358
|
+
audyn/utils/modules/lora.py
|
|
359
|
+
audyn/utils/music/__init__.py
|
|
360
|
+
audyn/utils/parallel/__init__.py
|
|
361
|
+
audyn/utils/tensorboard/__init__.py
|
|
362
|
+
audyn/utils/text/__init__.py
|
|
363
|
+
audyn/utils/text/indexing.py
|
|
364
|
+
audyn/utils/text/normalization.py
|
|
365
|
+
audyn/utils/text/pronunciation.py
|
|
366
|
+
audyn/utils/text/tokenization.py
|
|
367
|
+
audyn/utils/text/vocab.py
|
|
368
|
+
audyn/utils/textgrid/__init__.py
|
|
369
|
+
csrc/monotonic_align_torch_2_4.cpp
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
[console_scripts]
|
|
2
|
+
audyn-decode-musdb18 = audyn.bin.decode_musdb18:main
|
|
3
|
+
audyn-download-beatthis = audyn.bin.download_beatthis:main
|
|
4
|
+
audyn-download-dnr = audyn.bin.download_dnr:main
|
|
5
|
+
audyn-download-fma = audyn.bin.download_fma:main
|
|
6
|
+
audyn-download-fsd50k = audyn.bin.download_fsd50k:main
|
|
7
|
+
audyn-download-ljspeech = audyn.bin.download_ljspeech:main
|
|
8
|
+
audyn-download-lsx = audyn.bin.download_lsx:main
|
|
9
|
+
audyn-download-mtat = audyn.bin.download_mtat:main
|
|
10
|
+
audyn-download-mtg-jamendo = audyn.bin.download_mtg_jamendo:main
|
|
11
|
+
audyn-download-musdb18 = audyn.bin.download_musdb18:main
|
|
12
|
+
audyn-download-openmic2018 = audyn.bin.download_openmic2018:main
|
|
13
|
+
audyn-download-singmos = audyn.bin.download_singmos:main
|
|
14
|
+
audyn-download-song-describer = audyn.bin.download_song_describer:main
|
|
15
|
+
audyn-download-vctk = audyn.bin.download_vctk:main
|
|
16
|
+
audyn-parse-run-command = audyn.bin.parse_run_command:main
|
|
@@ -3,19 +3,15 @@ hydra-core
|
|
|
3
3
|
matplotlib
|
|
4
4
|
torch
|
|
5
5
|
torchaudio
|
|
6
|
-
torchtext
|
|
7
6
|
torchvision
|
|
8
7
|
tensorboard
|
|
8
|
+
numpy
|
|
9
9
|
webdataset
|
|
10
10
|
inflect
|
|
11
|
-
|
|
12
|
-
[:python_version == "3.8"]
|
|
13
|
-
importlib_resources<6.2
|
|
11
|
+
setuptools<81
|
|
14
12
|
|
|
15
13
|
[dev]
|
|
16
|
-
|
|
17
|
-
black
|
|
18
|
-
isort
|
|
14
|
+
ruff
|
|
19
15
|
|
|
20
16
|
[docs]
|
|
21
17
|
sphinx
|