Code for the paper "LLark: A Multimodal Instruction-Following Language Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

Easier audio-based machine learning with TensorFlow.

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection.

Python wrapper around sox.

Latex code for making neural networks diagrams

Utils for streaming large files (S3, HDFS, gzip, bz2...)

Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

Audio processing by using pytorch 1D convolution network

A Pytorch implementation of Onsets and Frames (Hawthorne 2018)

Python bindings for SoX, aiming to replicate a subset of the command line sox utility.

TensorFlow code and pre-trained models for BERT

CANTE: Automatic transcription of flamenco singing.

Utilities for interfacing with Slakh2100

pronunciation dictionaries for multiple languages

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

DeepSpeech based forced alignment tool

Python library for handling audio datasets.

Efficient neural speech synthesis

Python library for working with Music Information Retrieval datasets

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.

Multi-voice singing voice synthesis

GuitarSet: a dataset for guitar transcription

A Python wrapper for the high-quality vocoder "World"

Wavelet scattering transforms in Python with GPU acceleration

Magenta: Music and Art Generation with Machine Intelligence