README.md

metadata

title: Music Splitter
emoji: 🎶
colorFrom: indigo
colorTo: yellow
sdk: docker
pinned: true

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Music Source Splitter 🎶

This is a streamlit demo of the Music Source Separation.

The model can separate the vocals, drums, bass, and other from a music track.

Usage

You can use the demo here, or run it locally with:

streamlit run app.py

Note: In order to run the demo locally, you need to install the dependencies with pip install -r requirements.txt.

How it works

The app uses a pretrained model called Hybrid Spectrogram and Waveform Source Separation from facebook/htdemucs.

Acknowledgements

• HtDemucs model from facebook/htdemucs
• Streamlit Audio Recorder from stefanrmmr/streamlit_audio_recorder