MidiTok: A Python Package for MIDI File Tokenization - Laboratoire d'Etude et de Recherche en Informatique d'Angers Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

MidiTok: A Python Package for MIDI File Tokenization

Résumé

This article presents MidiTok, a Python package to encode MIDI files into sequences of tokens to be used with sequential Deep Learning models like Transformers or Recurrent Neural Networks. It allows researchers and developers to encode datasets with various strategies built around the idea that they share common parameters. This key idea makes it easy to :1) optimize the size of the vocabulary and the elements it can represent w.r.t. the MIDI specifications; 2) compare tokenization methods to see which performs best in which case; 3) measure the relevance of additional information like chords or tempo changes. Code and documentation of MidiTok are on Github.
Fichier principal
Vignette du fichier
MidiTok_camera_ready_final.pdf (92.82 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03418930 , version 1 (15-11-2021)

Licence

Paternité

Identifiants

  • HAL Id : hal-03418930 , version 1

Citer

Nathan Fradet, Jean-Pierre Briot, Fabien Chhel, Amal El Fallah-Seghrouchni, Nicolas Gutowski. MidiTok: A Python Package for MIDI File Tokenization. 22nd International Society for Music Information Retrieval Conference, Nov 2021, Online, United States. ⟨hal-03418930⟩
840 Consultations
414 Téléchargements

Partager

Gmail Facebook X LinkedIn More