README.md

---
license: apache-2.0
language:
- en
tags:
- MuseCoco
- Text2Music
---

<p align="center" width="100%">
<a href="" target="_blank"><img src="https://ai-muzic.github.io/images/musecoco/framework.png" alt="Text2Attribute" style="width: 100%; min-width: 100px; display: block; margin: auto;"></a>
</p>

# Text-to-Attribute Understanding


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6190ab805ca89a28e9f66873/5VUl0vSMr_PQla2iykoWx.png)


This is the text-to-attribute model to extract musical attributes from text, introduced in the paper [*MuseCoco: Generating Symbolic Music from Text*](https://arxiv.org/abs/2306.00110) and [first released in this repository](https://github.com/microsoft/muzic/tree/main/musecoco).
It is based on BERT-large and has multiple classification heads for diverse musical attributes: 
```json
[
    "Instrument",
    "Rhythm Danceability",
    "Rhythm Intensity",
    "Artist",
    "Genre",
    "Bar",
    "Time Signature",
    "Key",
    "Tempo",
    "Pitch Range",
    "Emotion",
    "Time"
]
```

# BibTeX entry and citation info
```bibtex
@article{musecoco2023,
  title={MuseCoco: Generating Symbolic Music from Text},
  author={Peiling Lu, Xin Xu, Chenfei Kang, Botao Yu, Chengyi Xing, Xu Tan, Jiang Bian},
  journal={arXiv preprint arXiv:2306.00110},
  year={2023}
}
```