AppleHolic/source_separation

Deep learning based speech source separation using Pytorch

45
/ 100
Emerging

This project helps audio engineers and content creators separate individual speech and singing voices from mixed audio recordings. You feed it a sound file containing speech, music, and noise, and it outputs cleaner audio files with the speech or singing isolated. It's designed for anyone working with audio who needs to remove background noise or extract specific vocal elements.

319 stars. No commits in the last 6 months.

Use this if you need to cleanly extract human speech or a singing voice from an audio recording that contains other sounds.

Not ideal if you need to separate instrument tracks from each other, as it focuses specifically on vocal source separation.

audio-post-production sound-engineering vocal-extraction noise-reduction music-production
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

319

Forks

47

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 20, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AppleHolic/source_separation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.