researchdeezer/spleeter repository overview

⁠About

Spleeter is the Deezer⁠ source separation library with pretrained models written in Python⁠ and uses Tensorflow⁠. It makes it easy to train source separation model (assuming you have a dataset of isolated sources), and provides already trained state of the art model for performing various flavour of separation :

• Vocals (singing voice) / accompaniment separation (2 stems⁠)
• Vocals / drums / bass / other separation (4 stems⁠)
• Vocals / drums / bass / piano / other separation (5 stems⁠)

2 stems and 4 stems models have state of the art performances on the musdb⁠ dataset. Spleeter is also very fast as it can perform separation of audio files to 4 stems 100x faster than real-time when run on a GPU.

We designed Spleeter so you can use it straight from command line⁠ as well as directly in your own development pipeline as a Python library⁠. It can be installed with Conda⁠, with pip⁠ or be used with Docker⁠.

⁠Quick start

Want to try it out ? Just clone the repository and install a Conda⁠ environment to start separating audio file as follows:

git clone https://github.com/Deezer/spleeter
conda install -c conda-forge spleeter
spleeter separate -i spleeter/audio_example.mp3 -p spleeter:2stems -o output

You should get two separated audio files (vocals.wav and accompaniment.wav) in the output/audio_example folder.

For a more detailed documentation, please check the repository wiki⁠

Want to try it out but don't want to install anything ? we've setup a Google Colab⁠

⁠Reference

• Deezer Research - Source Separation Engine Story - deezer.io blog post:
  • English version⁠
  • Japanese version⁠
• Music Source Separation tool with pre-trained models / ISMIR2019 extended abstract⁠

If you use Spleeter in your work, please cite:

@misc{spleeter2019,
  title={Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models},
  author={Romain Hennequin and Anis Khlif and Felix Voituret and Manuel Moussallam},
  howpublished={Late-Breaking/Demo ISMIR 2019},
  month={November},
  note={Deezer Research},
  year={2019}
}

⁠License

The code of Spleeter is MIT-licensed.

⁠Disclaimer

If you plan to use Spleeter on copyrighted material, make sure you get proper authorization from right owners beforehand.

⁠Note

This repository include a demo audio file audio_example.mp3 which is an excerpt from Slow Motion Dream by Steven M Bryant (c) copyright 2011 Licensed under a Creative Commons Attribution (3.0) license. http://dig.ccmixter.org/files/stevieb357/34740⁠ Ft: CSoul,Alex Beroza & Robert Siekawitch