├── .gitignore ├── LICENSE.md ├── LICENSES ├── LICENSE_CLAP ├── LICENSE_OpenL3 ├── LICENSE_PaSST ├── LICENSE_frechet-audio-distance ├── LICENSE_pytorch-fid └── README.md ├── README.md ├── examples ├── README.md ├── audiocaps.py ├── audiocaps_no-audio.py ├── musiccaps.py ├── musiccaps_clap_score.py ├── musiccaps_no-audio.py ├── musiccaps_nosinging.py ├── musiccaps_nosinging_no-audio.py ├── musiccaps_openl3_fd.py ├── musiccaps_passt_kld.py ├── songdescriber.py ├── songdescriber_no-audio.py ├── songdescriber_nosinging.py └── songdescriber_nosinging_no-audio.py ├── load ├── audiocaps-test.csv ├── musiccaps-public-nosinging.csv ├── musiccaps-public.csv ├── openl3_fd │ ├── audiocaps-test__channels2__44100__openl3env__openl3hopsize0.5__batch4.npz │ ├── musiccaps-public-nosinging__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz │ ├── musiccaps-public__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz │ ├── song_describer-nosinging__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz │ └── song_describer__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz ├── passt_kld │ ├── audiocaps-test__collectmean__reference_probabilities.pkl │ ├── musiccaps-public-nosinging__collectmean__reference_probabilities.pkl │ ├── musiccaps-public__collectmean__reference_probabilities.pkl │ ├── song_describer-nosinging__collectmean__reference_probabilities.pkl │ └── song_describer__collectmean__reference_probabilities.pkl ├── song_describer-nosinging.csv └── song_describer.csv ├── requirements.txt └── src ├── __init__.py ├── clap_score.py ├── openl3_fd.py ├── passt_kld.py └── test_kld.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSE.md -------------------------------------------------------------------------------- /LICENSES/LICENSE_CLAP: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSES/LICENSE_CLAP -------------------------------------------------------------------------------- /LICENSES/LICENSE_OpenL3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSES/LICENSE_OpenL3 -------------------------------------------------------------------------------- /LICENSES/LICENSE_PaSST: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSES/LICENSE_PaSST -------------------------------------------------------------------------------- /LICENSES/LICENSE_frechet-audio-distance: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSES/LICENSE_frechet-audio-distance -------------------------------------------------------------------------------- /LICENSES/LICENSE_pytorch-fid: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSES/LICENSE_pytorch-fid -------------------------------------------------------------------------------- /LICENSES/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/LICENSES/README.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/README.md -------------------------------------------------------------------------------- /examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/README.md -------------------------------------------------------------------------------- /examples/audiocaps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/audiocaps.py -------------------------------------------------------------------------------- /examples/audiocaps_no-audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/audiocaps_no-audio.py -------------------------------------------------------------------------------- /examples/musiccaps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps.py -------------------------------------------------------------------------------- /examples/musiccaps_clap_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps_clap_score.py -------------------------------------------------------------------------------- /examples/musiccaps_no-audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps_no-audio.py -------------------------------------------------------------------------------- /examples/musiccaps_nosinging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps_nosinging.py -------------------------------------------------------------------------------- /examples/musiccaps_nosinging_no-audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps_nosinging_no-audio.py -------------------------------------------------------------------------------- /examples/musiccaps_openl3_fd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps_openl3_fd.py -------------------------------------------------------------------------------- /examples/musiccaps_passt_kld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/musiccaps_passt_kld.py -------------------------------------------------------------------------------- /examples/songdescriber.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/songdescriber.py -------------------------------------------------------------------------------- /examples/songdescriber_no-audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/songdescriber_no-audio.py -------------------------------------------------------------------------------- /examples/songdescriber_nosinging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/songdescriber_nosinging.py -------------------------------------------------------------------------------- /examples/songdescriber_nosinging_no-audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/examples/songdescriber_nosinging_no-audio.py -------------------------------------------------------------------------------- /load/audiocaps-test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/audiocaps-test.csv -------------------------------------------------------------------------------- /load/musiccaps-public-nosinging.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/musiccaps-public-nosinging.csv -------------------------------------------------------------------------------- /load/musiccaps-public.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/musiccaps-public.csv -------------------------------------------------------------------------------- /load/openl3_fd/audiocaps-test__channels2__44100__openl3env__openl3hopsize0.5__batch4.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/openl3_fd/audiocaps-test__channels2__44100__openl3env__openl3hopsize0.5__batch4.npz -------------------------------------------------------------------------------- /load/openl3_fd/musiccaps-public-nosinging__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/openl3_fd/musiccaps-public-nosinging__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz -------------------------------------------------------------------------------- /load/openl3_fd/musiccaps-public__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/openl3_fd/musiccaps-public__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz -------------------------------------------------------------------------------- /load/openl3_fd/song_describer-nosinging__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/openl3_fd/song_describer-nosinging__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz -------------------------------------------------------------------------------- /load/openl3_fd/song_describer__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/openl3_fd/song_describer__channels2__44100__openl3music__openl3hopsize0.5__batch4.npz -------------------------------------------------------------------------------- /load/passt_kld/audiocaps-test__collectmean__reference_probabilities.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/passt_kld/audiocaps-test__collectmean__reference_probabilities.pkl -------------------------------------------------------------------------------- /load/passt_kld/musiccaps-public-nosinging__collectmean__reference_probabilities.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/passt_kld/musiccaps-public-nosinging__collectmean__reference_probabilities.pkl -------------------------------------------------------------------------------- /load/passt_kld/musiccaps-public__collectmean__reference_probabilities.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/passt_kld/musiccaps-public__collectmean__reference_probabilities.pkl -------------------------------------------------------------------------------- /load/passt_kld/song_describer-nosinging__collectmean__reference_probabilities.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/passt_kld/song_describer-nosinging__collectmean__reference_probabilities.pkl -------------------------------------------------------------------------------- /load/passt_kld/song_describer__collectmean__reference_probabilities.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/passt_kld/song_describer__collectmean__reference_probabilities.pkl -------------------------------------------------------------------------------- /load/song_describer-nosinging.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/song_describer-nosinging.csv -------------------------------------------------------------------------------- /load/song_describer.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/load/song_describer.csv -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/requirements.txt -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/clap_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/src/clap_score.py -------------------------------------------------------------------------------- /src/openl3_fd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/src/openl3_fd.py -------------------------------------------------------------------------------- /src/passt_kld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/src/passt_kld.py -------------------------------------------------------------------------------- /src/test_kld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Stability-AI/stable-audio-metrics/HEAD/src/test_kld.py --------------------------------------------------------------------------------