EMelodyGen

The model weights for generating ABC melodies by emotions.

Demo (inference code)

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

Usage

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

Maintenance

GIT_LFS_SKIP_SMUDGE=1 git clone [email protected]:monetjoe/EMelodyGen
cd EMelodyGen

Evaluation

https://github.com/monetjoe/EMelodyGen

Fine-tuning results

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

Mirror

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

Cite

AIART

@inproceedings{11152266,
  author    = {Zhou, Monan and Li, Xiaobing and Yu, Feng and Li, Wei},
  booktitle = {2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)},
  title     = {EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template},
  year      = {2025},
  pages     = {1-6},
  keywords  = {Correlation;Codes;Conferences;Confusion matrices;Music;Psychology;Data augmentation;Complexity theory;Reliability;Melody generation;controllable music generation;ABC notation;emotional condition},
  doi       = {10.1109/ICMEW68306.2025.11152266}
}

TAI

@article{zhou_li_yu_li_2025,
  title     = {EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with Musical Feature Templates},
  volume    = {1},
  issn      = {2982-3439},
  doi       = {10.53941/tai.2025.100013},
  number    = {1},
  journal   = {Transactions on Artificial Intelligence},
  publisher = {Scilight Press},
  author    = {Zhou, Monan and Li, Xiaobing and Yu, Feng and Li, Wei},
  year      = {2025},
  pages     = {199–211}
}