Source Separation Python Packages

asteroid

The PyTorch-based audio source separation toolkit for researchers

14K 3K 452

demucs-mlx

Split any song into stems — vocals, drums, bass, and more. Fast music source separation for Apple Silicon, powered by MLX.

7K 44 6

mlx-audio-separator

MLX-native audio stem separation for Apple Silicon (Demucs, MDX, MDXC, VR, Roformer).

6K 16 4

nussl

A flexible source separation library in Python

2K 643 98

mne-denoise

Artifact removal and signal denoising for EEG and MEG.

1K 31 8

eluate

Command-line tool that removes background music from videos while keeping dialogue and sound effects, using the Bandit v2 source-separation model. For accessibility and personal use.

969 6 1

diarizationlm

This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.

708 464 41

scarlet2

Astronomical source modeling in jax

380 32 5

sidlingvo

This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.

355 464 41

vocal

A vocal source separation

325 43 5

mapss-measures

The code for the MAPSS measures for source separation evaluation (ICLR, 2026)

168 13 1

hunterformsbs

Universal frequency-band splitter for music source separation: one interface for BSRoformer, MelBandRoformer, or any Band Split. RoPE, PoPE, HyperACE. Documentation, citations, and explanations. PyTorch; CUDA-accelerated.

159 13 1