Go [here on Deezer's github](https://github.com/deezer/spleeter). Easiest to use [Anacoda](AnaConda).

## Install
```bash
# install dependencies using conda
conda install -c conda-forge ffmpeg libsndfile
# install spleeter with pip
pip install spleeter
```

## Run
```bash
spleeter separate -p spleeter:2stems -o output audio_example.mp3
```
Often the longest part is downloading the pretrained models, so stash the `pretrained_models` folder somewhere.