miditok: A Python package for MIDI file tokenization
Nathan Fradet, Jean-Pierre Briot, Fabien Chhel, Amal El Fallah, Seghrouchni, Nicolas Gutowski

TL;DR
Miditok is an open-source Python library that provides flexible and extended tokenization of symbolic music, facilitating the use of language models like Transformers for music generation, modeling, and transcription.
Contribution
It introduces a unified API for various popular music tokenizations, making music encoding and decoding more accessible and extensible for researchers and developers.
Findings
Supports multiple tokenization schemes with a unified API
Enhances flexibility and extensibility for symbolic music processing
Facilitates integration of language models in music applications
Abstract
Recent progress in natural language processing has been adapted to the symbolic music modality. Language models, such as Transformers, have been used with symbolic music for a variety of tasks among which music generation, modeling or transcription, with state-of-the-art performances. These models are beginning to be used in production products. To encode and decode music for the backbone model, they need to rely on tokenizers, whose role is to serialize music into sequences of distinct elements called tokens. MidiTok is an open-source library allowing to tokenize symbolic music with great flexibility and extended features. It features the most popular music tokenizations, under a unified API. It is made to be easily used and extensible for everyone.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic Technology and Sound Studies · Music and Audio Processing · Computational Physics and Python Applications
MethodsLib
