lucidrains/HS-TasNet

Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet"

69
/ 100
Established

This tool helps audio engineers, music producers, and sound designers separate individual instruments or vocals from mixed music tracks in real-time. You input a stereo audio recording, and it outputs the isolated audio streams for drums, bass, vocals, and 'other' instruments. It's ideal for anyone needing to isolate components of a song for remixing, analysis, or live performance adjustments.

Available on PyPI.

Use this if you need to quickly and efficiently isolate different sound sources within a live or pre-recorded music track.

Not ideal if you need to separate extremely niche or non-standard sound sources beyond common instruments and vocals.

music production audio engineering sound design audio analysis live sound
Maintenance 13 / 25
Adoption 15 / 25
Maturity 24 / 25
Community 17 / 25

How are scores calculated?

Stars

86

Forks

15

Language

Python

License

MIT

Last pushed

Mar 25, 2026

Monthly downloads

342

Commits (30d)

0

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lucidrains/HS-TasNet"

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