John Thickstun's repositories
anticipation
Anticipatory Autoregressive Models
pytorch_musicnet
PyTorch DataSet and Jupyter demos for MusicNet
basis-separation
Implementation of the BASIS algorithm for source separation with deep generative priors
thickstun2018invariances
Experiments for Invariances and Data Augmentation for Supervised Music Transcription
alignment-eval
Dataset and evaluation pipeline for music-to-score alignment
mini-musicnet
The mini-MusicNet dataset
ismir2019coupled
Experiments for Coupled Recurrent Networks for Polyphonic Music Composition
jthickstun.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
bach-wtc
Digital edition of J.S. Bach's Well-tempered Clavier, Books I & II in the Humdrum file format.
beethoven-piano-sonatas
Digital edition of L. van Beethoven's piano sonatas in the Humdrum file format.
beethoven-string-quartets
Digital edition of L. van Beethoven's string quartests in the Humdrum file format.
Bus
Music of Antoine Busnoys as Humdrum digital scores.
chopin-mazurkas
Digital edition of Frédéric Chopin's mazurkas in the Humdrum file format.
datasets-1
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
humdrum-haydn-quartets
Digital edition of Joseph Haydn's string quartets in the Humdrum file format.
humdrum-mozart-quartets
Digital edition of W.A. Mozart's string quartets in the Humdrum file format.
hummel-preludes
Digital edition of Johann Nepomuk Hummel's preludes in the Humdrum file format.
joplin-rags
Music of Scott Joplin in the Humdrum file format.
levanter
Legibile, Scalable, Reproducible Foundation Models with Named Tensors and Jax
longformer
Longformer: The Long-Document Transformer
mistral
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.
scarlatti-keyboard-sonatas
Digital edition of Domenico Scarlatti's keyboard sonatas in the Humdrum file format
transformers-1
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.