Add comprehensive model card for OMAR-RQ

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card for the OMAR-RQ model by providing detailed information and improving discoverability on the Hugging Face Hub.

Key additions and improvements include:

  • A clear overview and abstract of the model.
  • A link to the official paper: OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction.
  • A link to the associated GitHub repository for training and inference code.
  • Comprehensive usage instructions with runnable Python code examples.
  • A table detailing the different available model checkpoints and their performance across various music understanding tasks.
  • Relevant metadata such as pipeline_tag: audio-classification, library_name: omar_rq, license: cc-by-nc-sa-4.0, and specific tags for music-related tasks.
  • Explicit licensing information for both the code and model weights.
  • A BibTeX citation for academic referencing.

This update will make the OMAR-RQ models much more accessible and user-friendly for researchers and practitioners in the AI community.

Music Technology Group (Universitat Pompeu Fabra) org
edited Jul 8

@nielsr thank you very much for your contribution.
Could you fix the entry on this and the other versions of OMAR-RQ?



@article
	{alonso2025omarrq,
  title={OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction},
  author={Alonso-Jim\'enez, Pablo and Ramoneda, Pedro and Araz, R. Oguz and Poltronieri, Andrea and Bogdanov, Dmitry},
  journal={arXiv preprint arXiv:2507.03482},
  year={2025}
}

Thanks, updated

p-alonso changed pull request status to merged

Sign up or log in to comment