You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

You agree to use the MIDI-GPT models only for non-commercial research or education without infringing copyright laws or causing harm to the creative rights of artists, creators, or musicians.

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.

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

Models

Model	Checkpoint	`num_bars_map`	Context (tokens)	Infill	Attributes
`yellow_medium`	checkpoint	4, 8	2048	yes	note density, polyphony (min/max), note duration (min/max)
`yellow_small`	checkpoint	4, 8	2048	yes	note density, polyphony (min/max), note duration (min/max)
`prism_medium`	checkpoint	4, 8, 12, 16	4096	yes	key signature, pitch range, silence, note duration, note density (bar), polyphony (bar), pitch class set, genre
`expressive_medium`	checkpoint	4, 8, 12, 16	4096	yes	key signature, pitch range, silence, note duration, note density (bar), polyphony (bar), pitch class set, nomml, genre

InferenceEngine.from_pretrained(name) downloads the current checkpoint for that model name.

model_dim in InferenceConfig is the context window in bars, not a vocabulary dimension — pass a value from the model's num_bars_map. expressive additionally encodes sub-grid timing via delta tokens and supports switchable velocity/microtiming controls. See docs/models.md in the GitHub repository for the full breakdown.

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_medium")   # or "yellow_small", "prism_medium", "expressive_medium"

# 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")

The model is downloaded once and cached by huggingface_hub in ~/.cache/huggingface/hub/.

Training

Models are 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

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train Metacreation/MIDI-GPT

Paper for Metacreation/MIDI-GPT

MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition

Paper • 2501.17011 • Published Jan 28, 2025 • 2