Back: Catalog

Demucs

Demucs is a music and audio parsing model that uses hybrid Transformer and U-Net convolutional architecture. The project allows to split audio recordings into different sources, such as drums, bass, vocals, and other instruments. Along with version 4, cross-domain Transformer encoders that run between spectral and temporal fields are integrated.

DE

Demucs

10

facebookresearch · Voice & Text-to-Speech

STARS10.4K
FORKS1.7K
COMMITS318
CONTRIBUTORS30
VERSIONv4.0.1
UPDATED2 yr ago
PythonSes AyrıştırmaVocal ExtractionTransformerMIT

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You separate the vocals, drums, and bass from the music tracks.
  • You get instrumental and vocal tracks from the songs separately.
  • With the experimental model option, you divide audio recordings into additional resources such as guitars and pianos.
Heads up
  • • Repository is archived (no longer maintained)
  • • Last update 2 years ago
User reviews
  • ↑ PositiveHacker News

    Demucs Music Source Separation

    “This is an AI/ML system by Meta which can separate recorded music into four “stems” - drums, bass, vocals and other. It’s not the first one (Deezer open sourced Spleeter a few years back which is now widely used) but I think the results from Demucs are super impressive - it…”

  • • NeutralGitHub Issue

    How I use it?

    “I tried to install for 5 hours but I never go more far than the first step. I always got this error: 'conda env update -f environment-cpu.yml EnvironmentFileNotFound: '/Users/montserratbartoky/environment-cpu.yml' file not found' A video tutorial is the perfect thing for help us…”

GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech