MidiTok is a Python package for MIDI file tokenization, presented at the ISMIR 2021 LBDs (paper). It converts MIDI files to sequences of tokens ready to be fed to sequential Deep Learning models such as Transformers.
MidiTok features most known MIDI :ref:`tokenizations`, and is built around the idea that they all share common methods. It properly pre-process MIDI files, and supports :ref:`Byte Pair Encoding (BPE)`. Github repository
pip install miditokMidiTok uses MIDIToolkit and Mido to read and write MIDI files, and BPE is backed by Hugging Face 馃tokenizers for super fast encoding.
If you use MidiTok for your research, a citation in your manuscript would be gladly appreciated. 鉂わ笍
You can also find BibTeX :ref:`citations` of tokenizations.
@inproceedings{miditok2021,
title={{MidiTok}: A Python package for {MIDI} file tokenization},
author={Fradet, Nathan and Briot, Jean-Pierre and Chhel, Fabien and El Fallah Seghrouchni, Amal and Gutowski, Nicolas},
booktitle={Extended Abstracts for the Late-Breaking Demo Session of the 22nd International Society for Music Information Retrieval Conference},
year={2021},
url={https://archives.ismir.net/ismir2021/latebreaking/000005.pdf},
}.. toctree:: midi_tokenizer examples tokenizations bpe pytorch_data data_augmentation utils citations