count-the-notes / README.md
Yoni232's picture
added spaces to requirements and also added gpu decorators in app.py
e77f67a
---
title: Count The Notes
emoji: 🎵
colorFrom: pink
colorTo: blue
sdk: gradio
sdk_version: 6.0.2
app_file: app.py
pinned: false
license: cc-by-4.0
---
# CountEM - Automatic Music Transcription
Upload a piano/music recording and transcribe it to MIDI using the CountEM framework.
## About
This is a Gradio demo for **CountEM**, a histogram-based supervision approach for Automatic Music Transcription (AMT) presented at ISMIR 2025.
**Paper:** [Count the Notes: Histogram-Based Supervision for Automatic Music Transcription](https://arxiv.org/abs/2511.14250)
## Models
- [countem-musicnet](https://huggingface.co/Yoni-Yaffe/countem-musicnet) - Trained on MusicNet dataset (recommended)
- [countem-synth](https://huggingface.co/Yoni-Yaffe/countem-synth) - Trained on synthetic data
## Links
- [GitHub Repository](https://github.com/Yoni-Yaffe/count-the-notes)
- [Project Page](https://yoni-yaffe.github.io/count-the-notes/)
- [ArXiv Paper](https://arxiv.org/abs/2511.14250)
## Citation
If you use this work, please cite:
```bibtex
@misc{yaffe2025countnoteshistogrambasedsupervision,
title={Count The Notes: Histogram-Based Supervision for Automatic Music Transcription},
author={Jonathan Yaffe and Ben Maman and Meinard Müller and Amit H. Bermano},
year={2025},
eprint={2511.14250},
archivePrefix={arXiv},
primaryClass={cs.SD},
url={https://arxiv.org/abs/2511.14250},
}
```
## License
CC-BY-4.0