facebookresearch/demucs
demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation
Builder
Meta Research
facebookresearch • ai-lab
Stars
9,921
Using upstream star count
Forks
1,455
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Oct 25, 2019
Project creation date
README Summary
Demucs is a state-of-the-art music source separation model that can isolate vocals, drums, bass, and other instruments from mixed audio tracks. The repository implements hybrid approaches combining both spectrogram and waveform-based neural networks for high-quality audio separation. It provides pre-trained models and tools for both research and practical music separation applications.
AI Dev Skills
Unmapped
Tags
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 1 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
PM Skills
Languages
Timeline
- Project created
- Oct 25, 2019
- Forked
- Mar 23, 2026
- Your last push
- 1 years ago
- Upstream last push
- 1 years ago
- Tracked since
- Apr 24, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…