U-MusT audio codec (DAC, 4 codebooks)
The audio tokenizer used by U-MusT. A Descript Audio Codec retrained on classical music with 4 codebooks instead of the public model's nine, trading breadth of domain for richer representations within it at comparable reconstruction quality.
- 44.1 kHz mono, hop size 512, giving roughly 86 token sets per second
- 4 unshared codebooks of 1024 entries each, embedding size 1024
Usage
Place weights.pth where the code expects the audio tokenizer:
dac_models/unidac4/weights.pth
The loader resolves dac_models/<dac_model> from the dac_model field of a training recipe.
Licensing
This release is licensed CC BY-NC-SA 4.0.
It is derived from a training mixture whose corpora carry differing terms: MAESTRO, ASAP and MusicNetEM (CC BY-NC-SA 4.0), MusicNet and SLakh (CC BY 4.0), BPSD (CC BY 3.0), OLiMPiC (CC BY-SA 4.0), and YTSV metadata (CC BY-NC-SA 4.0). The non-commercial and share-alike terms are applied here because they are the most restrictive verified terms in that chain.
One conflict is irreducible and is disclosed rather than resolved: CC BY-SA 4.0 and CC BY-NC-SA 4.0 are mutually incompatible, since the former permits commercial use and forbids adding restrictions while the latter requires them. Any work derived from both — including these weights — cannot satisfy both simultaneously. See the code repository for the full per-corpus license table and the conflicts.
This is not legal advice. Verify the current terms with each corpus publisher before redistributing anything derived from this release or using it commercially.
Citation
@article{jung2026umust,
title = {U-MusT: A Unified Framework for Cross-Modal Translation of Score Images, Symbolic Music, and Performance Audio},
author = {Jung, Jongmin and Kim, Dongmin and Lee, Sihun and Cho, Seola and Soh, Hyungjoon and Bukey, Irmak and Donahue, Chris and Jeong, Dasaem},
journal = {IEEE Transactions on Audio, Speech and Language Processing},
volume = {34},
pages = {1876--1891},
year = {2026},
doi = {10.1109/TASLPRO.2025.3648794}
}