Skip to content

Model citations and licenses

Audience: Users and maintainers checking upstream model and tool sources. Goal: Name the current upstream sources, checkpoints, and license notes. Type: reference

This page lists the optional upstream analysis tools and checkpoints used by the current adapters. It is based on pyproject.toml, sonara_features.py, genres.py, and embedding.py.

Because the project does not vendor or redistribute upstream model weights, this page gives attribution and practical license notes rather than legal advice. Optional packages download or load those assets when you run analysis. Check the upstream repositories and model cards before redistribution, hosted service use, commercial use, or published research.

Current upstream sources

Analysis familyCurrent code pathUpstream sourceLicense note
SONARAsonara==0.2.9, schema 4, playlist mode with BPM range 70.0..180.0; Core uses bundled vocalness v2 and each output has its own signaturekkollsga/sonara, v0.2.9 releaseUpstream is MIT. Preserve its license and check terms before redistribution.
MAESTdiscogs-maest-30s-pw-129e-519l via maest-inferopenmirlab/maest-infer, original palonso/MAESTmaest-infer is AGPL-3.0-only and asks research users to cite the original MAEST paper.
MERTm-a-p/MERT-v1-95M through Hugging Face Transformersyizhilll/MERT, MERT-v1-95M checkpointGitHub code is Apache-2.0. The checkpoint page is marked CC-BY-NC-4.0.
MuQOpenMuQ/MuQ-large-msd-iter through the muq packagetencent-ailab/muq, MuQ-large-msd-iter checkpointUpstream code is MIT. Released MuQ weights are CC-BY-NC-4.0.
CLAPLAION CLAP with lukewys/laion_clap/music_audioset_epoch_15_esc_90.14.ptLAION-AI/CLAP, checkpoint fileLAION CLAP code is Apache-2.0. The checkpoint listing is marked CC0-1.0.

pyproject.toml and uv.lock pin sonara==0.2.9. Pip may install a compatible wheel or build the source distribution locally. The runtime contract remains the same package and schema version.

Practical rules

  • Treat upstream code licenses and model-weight licenses separately when the upstream project separates them.
  • Do not treat this table as permission for commercial use. Non-commercial checkpoint licenses need their own review.
  • If you publish research or public evaluation results, cite the upstream papers or project pages requested by the model authors.
  • Local embeddings, labels, classifier artifacts, reports, and logs may reveal library information. Keep them out of Git unless you intentionally choose otherwise.

Local classifier note

Rhythm Lab classifiers are local artifacts trained from your labels and existing library signals. They are not a downloaded upstream model family. Their outputs still depend on upstream SONARA, MAEST, and MERT inputs when those inputs are used for training or scoring.

Local-first DJ library analysis documentation.