README.md

---
license: cc-by-nc-4.0
tags:
- music
- midi
- symbolic-music
- music-generation
- gpt2
- pytorch
library_name: midigpt
language:
- en
datasets:
- Metacreation/GigaMIDI
---

# MIDI-GPT

MIDI-GPT is a GPT-2 transformer for symbolic music generation trained on the
[GigaMIDI](https://huggingface.co/datasets/Metacreation/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)](https://arxiv.org/abs/2501.17011)  
GitHub: [Metacreation/MIDI-GPT](https://github.com/Metacreation/MIDI-GPT)  
PyPI: [midigpt](https://pypi.org/project/midigpt/)

---

## Models

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

---

## Installation

```bash
pip install "midigpt[inference]"
```

## Usage

```python
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](https://github.com/Metacreation/MIDI-GPT).

---

## Citation

```bibtex
@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)](https://creativecommons.org/licenses/by-nc/4.0/).
Copyright (c) 2026 Metacreation Lab.