mlsanityData to 14 Oct 2026

miditok: A Python package for MIDI file tokenization

arXiv 2310.17202 ↗First posted 26 Oct 2023cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

22 of 33 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  4. 2020Rethinking Attention with Performerscited by 1,601
  5. 2022AudioGen: Textually Guided Audio Generationcited by 295
  6. 2022Diffsound: Discrete Diffusion Model for Text-to-sound Generationcited by 257
  7. 2018Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Datasetcited by 217
  8. 2017MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompanimentcited by 151
  9. 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 110
  10. 2016DeepBach: a Steerable Model for Bach Chorales Generationcited by 91
  11. 2021MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Trainingcited by 89
  12. 2021MT3: Multi-Task Multitrack Music Transcriptioncited by 71
10 more
  1. 2018This Time with Feeling: Learning Expressive Musical Performancecited by 68
  2. 2020PopMAG: Pop Music Accompaniment Generationcited by 68
  3. 2019LakhNES: Improving multi-instrumental music generation with cross-domain pre-trainingcited by 54
  4. 2020MMM : Exploring Conditional Multi-Track Music Generation with the Transformercited by 49
  5. 2021Sequence-to-Sequence Piano Transcription with Transformerscited by 48
  6. 2020MusPy: A Toolkit for Symbolic Music Generationcited by 37
  7. 2020GiantMIDI-Piano: A large-scale MIDI dataset for classical piano musiccited by 37
  8. 2022Symphony Generation with Permutation Invariant Language Modelcited by 35
  9. 2021The Piano Inpainting Applicationcited by 23
  10. 2023Byte Pair Encoding for Symbolic Musiccited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 11; 2025: 9; 2026: 6.

27 papers.

Sort:

By area:

  1. 2024Foundation Models for Music: A Surveycited by 37
  2. 2024Text2midi: Generating Symbolic Music from Captionscited by 19
  3. 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
  4. 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detectioncited by 7
  5. 2024GraphMuse: A Library for Symbolic Music Graph Processingcited by 5
  6. 2024PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variationscited by 4
  7. 2025SyMuPe: Affective and Controllable Symbolic Music Performancecited by 3
  8. 2026BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Stepscited by 3
  9. 2023Annotation-free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusioncited by 2
  10. 2025Adaptable Symbolic Music Infilling with MIDI-RWKVcited by 2
  11. 2025Optical Music Recognition of Jazz Lead Sheetscited by 2
  12. 2024Perception-Inspired Graph Convolution for Music Understanding Taskscited by 1
15 more
  1. 2024Music Proofreading with RefinPaint: Where and How to Modify Compositions given Contextcited by 1
  2. 2024TheGlueNote: Learned Representations for Robust and Flexible Note Alignmentcited by 1
  3. 2024Symbotunes: unified hub for symbolic music generative modelscited by 1
  4. 2025Fretting-Transformer: Encoder-Decoder Model for MIDI to Tablature Transcriptioncited by 1
  5. 2025On the de-duplication of the Lakh MIDI datasetcited by 1
  6. 2026BeatEdit: Symbolic Music Generation as Explicit Editingcited by 1
  7. 2024Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentationcited by 0
  8. 2024MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic musiccited by 0
  9. 2025A Traditional Approach to Symbolic Piano Continuationcited by 0
  10. 2025Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcriptioncited by 0
  11. 2025LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detectioncited by 0
  12. 2026PianoKontext: Expressive Performance Rendering from Deadpan Contextcited by 0
  13. 2026Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generationcited by 0
  14. 2026RPPNet: Perceptually-Grouped Rhythm-Pitch Primitives for Long-Term Structure Melody Generation via Boundary-Aware Modelingcited by 0
  15. 2026From One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editingcited by 0