Welcome to MidiTok’s documentation!

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 Tokenizations, and is built around the idea that they all share common methods. It properly pre-process MIDI files, and supports Byte Pair Encoding (BPE). Github repository

Installation

pip install miditok

MidiTok uses MIDIToolkit and Mido to read and write MIDI files.

Citation

If you use MidiTok for your research, a citation in your manuscript would be gladly appreciated. ❤️

You can also find BibTeX 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},
}

Contents