MIDI-GPT

MIDI-GPT is a GPT-2 transformer for symbolic music generation trained on the GigaMIDI dataset. It supports bar-level infill, autoregressive multi-track generation, and attribute-conditioned generation (note density, polyphony, note duration).

Paper: MIDI-GPT: A Controllable Language Model for Symbolic Music Performance Generation (AAAI 2025)
GitHub: Metacreation/MIDI-GPT
PyPI: midigpt

---

Models

File	Context (bars)	Infill	Bar masking	Microtiming	Attributes
yellow.pt	4, 8	yes	no	no	density, polyphony, note duration

---

Installation

pip install "midigpt[inference]"

Usage

from midigpt import Score
from midigpt.inference.engine import InferenceEngine
from midigpt.inference.config import GenerationRequest, InferenceConfig, TrackPrompt

# Download and cache the model automatically
engine = InferenceEngine.from_pretrained("yellow")

# Load a MIDI file
score = Score.from_midi("my_song.mid")

# Infill bars 4–7 on track 0 given surrounding context
request = GenerationRequest(
    tracks=[
        TrackPrompt(id=0, bars=list(range(4, 8))),
    ],
    config=InferenceConfig(model_dim=8),
)

session = engine.session(score, request)
result  = session.run()
result.to_midi("output.mid")

---

Training

Models were trained on GigaMIDI v2.0.0 using the midigpt training pipeline with PyTorch Lightning. Training configs and the preprocessing pipeline are available in the GitHub repository.

---

Citation

@misc{pasquier2025midigptcontrollablegenerativemodel,
      title={MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition}, 
      author={Philippe Pasquier and Jeff Ens and Nathan Fradet and Paul Triana and Davide Rizzotti and Jean-Baptiste Rolland and Maryam Safi},
      year={2025},
      eprint={2501.17011},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2501.17011}, 
}

---

License

Creative Commons Attribution-NonCommercial 4.0 International (CC-BY-NC-4.0). Copyright (c) 2026 Metacreation Lab.