⚠️ See the complete documentation in the official repository.
The spleeter
package is a wrapper for the official library Spleeter, developed by Deezer 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)
Make sure the reticulate
package is installed and configured!
First, install the python lib:
reticulate::py_install(c("spleeter"), forge = TRUE)
Then install the package for R from Github:
remotes::install_github("gomesfellipe/spleeteR")
To use the package, just run the function bellow where <audio_file>
is the name of the .mp3 file and n_stem
is the flavour of separation:
spleeteR::separator(audio_path = "<audio_file>", n_stem = 2)
You should get two separated audio files (vocals.wav
and accompaniment.wav
) in the output/<audio_file>
folder.
⚠️ For now this is the only function of the package. Feel free to add new features.
For a detailed documentation of Python package, check the repository wiki
- Deezer Research - Source Separation Engine Story - deezer.io blog post:
- Music Source Separation tool with pre-trained models / ISMIR2019 extended abstract
If you use Spleeter in your work, please cite:
@article{spleeter2020,
doi = {10.21105/joss.02154},
url = {https://doi.org/10.21105/joss.02154},
year = {2020},
publisher = {The Open Journal},
volume = {5},
number = {50},
pages = {2154},
author = {Romain Hennequin and Anis Khlif and Felix Voituret and Manuel Moussallam},
title = {Spleeter: a fast and efficient music source separation tool with pre-trained models},
journal = {Journal of Open Source Software},
note = {Deezer Research}
}
The code of Spleeter is MIT-licensed.
Consult currently open issues for Troubleshooting
See Projects