Hugging Face's logo

AXERA-TECH
/
mel_band_roformer

Model card Files
xet
Community

MelBandRoformer

Music Source Separation on AX650.
Separate songs into multiple stems like bass, drums, and vocals.

Usage

Install

  1. Download and install Miniconda3
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm ~/miniconda3/miniconda.sh

source ~/miniconda3/bin/activate

conda init --all
  1. Create virtual environment
conda create -n mel_band python=3.10
conda activate mel_band
pip install -r requirements.txt
wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc1/axengine-0.1.3-py3-none-any.whl
pip install axengine-0.1.3-py3-none-any.whl

Basic usage 

conda activate mel_band
python main.py -i song.wav -o separated_song

Separated songs will be placed at separated_song directory

Gradio app 

conda activate mel_band
python gradio_app.py

Graio gui: screenshot

Downloads last month
17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including AXERA-TECH/mel_band_roformer