Tools to train a generative model on arbitrary audio samples

An optical music recognition (OMR) system. Converts sheet music to a machine-readable version.

PyTorch wrappers for using your model in audacity!

SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

Musical Gestures Toolbox for Python

The Harmonix Set: Beats, Downbeats, and Structural Annotations for Pop Music

Code for creating a dataset of MIDI ground truth

A small package to create visualizations of PyTorch execution graphs