Metadata-Version: 2.4
Name: tts_webui_extension.demucs
Version: 0.0.4
Summary: Demucs is a music source separation model that can separate drums, bass, vocals, and other instruments
Home-page: https://github.com/rsxdalv/tts_webui_extension.demucs
Author: rsxdalv
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: demucs
Requires-Dist: torchaudio>=2.0.0
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-dist
Dynamic: summary

# Extension adapter for Demucs

License - the source code within this repository is licensed under the MIT license.

This extension provides a music source separation model that can separate drums, bass, vocals, and other instruments from audio tracks.

## Features

- Separate audio tracks into four components:
  - Drums
  - Bass
  - Vocals
  - Other instruments
- High-quality separation using the HT-Demucs model
- Simple and intuitive interface

## Usage

1. Upload an audio file (MP3, WAV, etc.)
2. Click "Separate" to process the audio
3. Download or listen to the separated components

## About Demucs

Demucs (Deep Extractor for Music Sources) is a state-of-the-art music source separation model developed by Facebook Research. It uses a hybrid architecture combining U-Net and Transformer components to effectively separate music into its constituent parts.

For more information, visit the [official Demucs repository](https://github.com/facebookresearch/demucs).
