Hugging Face's logo

AEmotionStudio
/
text2midi-models

Safetensors
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Text2MIDI — bundled mirror

Self-contained inference bundle for the MAESTRO desktop app.

Contents

  • text2midi/model.safetensors — decoder + projection weights (converted from amaai-lab/text2midi pytorch_model.bin)
  • text2midi/vocab_remi.pkl — pickled miditok.REMI tokenizer
  • text2midi/config.json — hyperparameters needed at load time
  • t5/ — google/flan-t5-base snapshot (Apache-2.0)

License

  • Text2MIDI: Apache-2.0 (Bhandari, Roy, Wang, Herremans, AAAI 2025)
  • FLAN-T5-base: Apache-2.0

Both upstreams permit commercial redistribution with attribution. Attribution is preserved here and in the in-app Text2MIDI panel.

Paper: https://arxiv.org/abs/2412.16526

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

Paper for AEmotionStudio/text2midi-models