asteroid-team/asteroid
The PyTorch-based audio source separation toolkit for researchers
Asteroid helps audio researchers and machine learning engineers quickly experiment with different techniques for separating individual sounds from mixed audio. You provide recordings with multiple sound sources, and it outputs the separated individual audio tracks. This is useful for those working on tasks like speech enhancement, music information retrieval, or analyzing environmental sounds.
2,547 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a researcher or engineer who needs a robust, flexible toolkit to build and test advanced audio source separation models on various datasets.
Not ideal if you are looking for an out-of-the-box solution to simply separate tracks from a song or clean up a single audio recording without needing to dive into model development.
Stars
2,547
Forks
446
Language
Python
License
MIT
Category
Last pushed
Oct 06, 2025
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/asteroid-team/asteroid"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pytorch/audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
deezer/spleeter
Deezer source separation library including pretrained models.
audeering/opensmile
The Munich Open-Source Large-Scale Multimedia Feature Extractor
audeering/opensmile-python
Python package for openSMILE
markovka17/dla
Deep learning for audio processing