deezer/spleeter
Deezer source separation library including pretrained models.
Supports multiple separation configurations (2, 4, or 5 stems) decomposing audio into vocals, drums, bass, piano, and other instruments using TensorFlow-based deep learning. Achieves 100x real-time processing speed on GPU and provides both CLI and Python API interfaces, plus Docker deployment. Integrates with professional audio software including iZotope RX, Steinberg SpectralLayers, and Ableton Live via the Spleeter 4 Max plugin.
28,095 stars and 21,654 monthly downloads. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Stars
28,095
Forks
3,066
Language
Python
License
MIT
Category
Last pushed
Apr 02, 2025
Monthly downloads
21,654
Commits (30d)
0
Dependencies
8
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/deezer/spleeter"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
asteroid-team/asteroid
The PyTorch-based audio source separation toolkit for researchers
pytorch/audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
audeering/opensmile
The Munich Open-Source Large-Scale Multimedia Feature Extractor
drscotthawley/aeiou
(ML) audio engineering i/o utils
mindspore-lab/mindaudio
A toolbox of audio models and algorithms based on MindSpore