EMelodyGen

The model weights for generating ABC melodies by emotions.

Demo (inference)

https://huggingface.co/spaces/monetjoe/EMelodyGen

Maintenance

GIT_LFS_SKIP_SMUDGE=1 git clone git@hf.com:monetjoe/EMelodyGen
cd EMelodyGen

Fine-tuning results

Dataset	Loss curve	Min eval loss
VGMIDI		0.23854530873296725
EMOPIA		0.26802811984950936
Rough4Q		0.2299637847539768

Usage

from huggingface_hub import snapshot_download
model_dir = snapshot_download("monetjoe/EMelodyGen")

Mirror

https://www.modelscope.cn/models/monetjoe/EMelodyGen

Cite

@inproceedings{Zhou2025EMelodyGen,
  title     = {EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template},
  author    = {Monan Zhou and Xiaobing Li and Feng Yu and Wei Li},
  month     = {Mar},
  year      = {2025},
  publisher = {GitHub},
  version   = {0.1},
  url       = {https://github.com/monetjoe/EMelodyGen}
}

Reference

[1] Wu, S., & Sun, M. (2023). TunesFormer: Forming Tunes with Control Codes. ArXiv, abs/2301.02884.