Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

A simple and general framework for signal decomposition

🌍 Fast reading of geospatial variables by GPS coordinates 📍

A Pythonic Implementation of Greedy Algorithms developped during my PhD

Python bindings for minimp3

This repo shows an easy way to download imagenet on a remote server

Painless Wiener filters for audio separation

A fast implementation of bss_eval metrics for blind source separation

Python library for downloading, loading & working with sound datasets

Official pytorch implementation of the paper: "Catch-A-Waveform: Learning to Generate Audio from a Single Short Example" (NeurIPS 2021)

museval - source separation evaluation tools for python

Zafar's Audio Functions in Python for audio signal analysis: STFT, inverse STFT, mel filterbank, mel spectrogram, MFCC, CQT kernel, CQT spectrogram, CQT chromagram, DCT, DST, MDCT, inverse MDCT.

Zafar's Audio Functions in Matlab for audio signal analysis: STFT, inverse STFT, mel filterbank, mel spectrogram, MFCC, CQT kernel, CQT spectrogram, CQT chromagram, DCT, DST, MDCT, inverse MDCT.

Hierarchical configuration framework for Python

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

Pandoc templates for conferences

Computational Tomography in PyTorch

python interface to the miniaudio audio playback, recording, decoding and conversion library

Protocol specification, white paper, high level documents, etc.

Authors' implementation of DeepSpeech Distances.

Multitrack Web Audio editor and player with canvas waveform preview. Set cues, fades and shift multiple tracks in time. Project inspired by Audacity. Export your mix to AudioBuffer or WAV !

Benchmark popular audio i/o packages

Curated list of python software and packages related to scientific research in audio

Python I/O for STEM audio files

Simulation de carrières et de retraites

REPeating Pattern Extraction Technique (REPET) in Matlab for audio source separation: original REPET, REPET extended, adaptive REPET, REPET-SIM, REPET-SIM online

Streaming source separation for music and speech files, using the Open-Unmix LSTM architecture.

Code for the paper Hybrid Spectrogram and Waveform Source Separation