Spleeter

Spleeter: a fast and efficient music source separation tool with pre-trained models - Published in JOSS (2020)

https://github.com/deezer/spleeter

Keywords

audio-processing bass deep-learning deezer drums model pretrained-models python tensorflow vocals

Scientific Fields

Engineering Computer Science - 60% confidence

Last synced: 4 months ago · JSON representation

Repository

Deezer source separation library including pretrained models.

Basic Info

Host: GitHub
Owner: deezer
License: mit
Language: Python
Default Branch: master
Homepage: https://research.deezer.com/projects/spleeter.html
Size: 9.18 MB

Statistics

Stars: 27,328
Watchers: 397
Forks: 2,995
Open Issues: 270
Releases: 2

Topics

audio-processing bass deep-learning deezer drums model pretrained-models python tensorflow vocals

Created about 6 years ago · Last pushed 9 months ago

Metadata Files

Readme Changelog Contributing License Codeowners

README.md

PyPI - Python Version

:warning: Spleeter 2.1.0 release introduces some breaking changes, including new CLI option naming for input, and the drop of dedicated GPU package. Please read CHANGELOG for more details.

About

Spleeter is 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 high 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 pip or be used with Docker.

Projects and Softwares using Spleeter

Since it's been released, there are multiple forks exposing Spleeter through either a Guided User Interface (GUI) or a standalone free or paying website. Please note that we do not host, maintain or directly support any of these initiatives.

That being said, many cool projects have been built on top of ours. Notably the porting to the Ableton Live ecosystem through the Spleeter 4 Max project.

Spleeter pre-trained models have also been used by professionnal audio softwares. Here's a non-exhaustive list:

iZotope in its Music Rebalance feature within RX 8
SpectralLayers in its Unmix feature in SpectralLayers 7
Acon Digital within Acoustica 7
VirtualDJ in their stem isolation feature
Algoriddim in their NeuralMix and djayPRO app suite

🆕 Spleeter is a baseline in the ongoing Music Demixing Challenge!

Spleeter Pro (Commercial version)

Check out our commercial version : Spleeter Pro. Benefit from our expertise for precise audio separation, faster processing speeds, and dedicated professional support.

Quick start

Want to try it out but don't want to install anything ? We have set up a Google Colab.

Ready to dig into it ? In a few lines you can install Spleeter and separate the vocal and accompaniment parts from an example audio file. You need first to install ffmpeg and libsndfile. It can be done on most platform using Conda:

```bash

install dependencies using conda

conda install -c conda-forge ffmpeg libsndfile

install spleeter with pip

pip install spleeter

download an example audio file (if you don't have wget, use another tool for downloading)

wget https://github.com/deezer/spleeter/raw/master/audio_example.mp3

separate the example audio into two components

spleeter separate -p spleeter:2stems -o output audio_example.mp3 ```

:warning: Note that we no longer recommend using conda for installing spleeter.

⚠️ There are known issues with Apple M1 chips, mostly due to TensorFlow compatibility. Until these are fixed, you can use this workaround.

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

For a detailed documentation, please check the repository wiki

Development and Testing

This project is managed using Poetry, to run test suite you can execute the following set of commands:

```bash

Clone spleeter repository

git clone https://github.com/Deezer/spleeter && cd spleeter

Install poetry

pip install poetry

Install spleeter dependencies

poetry install

Run unit test suite

poetry run pytest tests/ ```

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:

BibTeX @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} }

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.

Troubleshooting

Spleeter is a complex piece of software and although we continously try to improve and test it you may encounter unexpected issues running it. If that's the case please check the FAQ page first as well as the list of currently open issues

Windows users

It appears that sometimes the shortcut command spleeter does not work properly on windows. This is a known issue that we will hopefully fix soon. In the meantime replace spleeter separate by python -m spleeter separate in command line and it should work.

Contributing

If you would like to participate in the development of Spleeter you are more than welcome to do so. Don't hesitate to throw us a pull request and we'll do our best to examine it quickly. Please check out our guidelines first.

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 Ft: CSoul,Alex Beroza & Robert Siekawitch

Owner

Name: Deezer
Login: deezer
Kind: organization
Email: deezerdevs@deezer.com
Location: Paris

Website: http://developers.deezer.com/
Twitter: deezerdevs
Repositories: 68
Profile: https://github.com/deezer

JOSS Publication

Spleeter: a fast and efficient music source separation tool with pre-trained models

Published

June 24, 2020

DOI

10.21105/joss.02154

Volume 5, Issue 50, Page 2154

Authors

Romain Hennequin

Deezer Research, Paris

Anis Khlif
Deezer Research, Paris

Felix Voituret
Deezer Research, Paris

Manuel Moussallam

Deezer Research, Paris

Editor

Yuan Tang

GitHub Events

Total

Issues event: 25
Watch event: 1,559
Issue comment event: 67
Member event: 3
Push event: 4
Pull request review event: 2
Pull request event: 9
Fork event: 184

Last Year

Issues event: 25
Watch event: 1,560
Issue comment event: 67
Member event: 3
Push event: 4
Pull request review event: 2
Pull request event: 9
Fork event: 186

Committers

Last synced: 5 months ago

All Time

Total Commits: 479
Total Committers: 20
Avg Commits per committer: 23.95
Development Distribution Score (DDS): 0.649

Past Year

Commits: 7
Committers: 3
Avg Commits per committer: 2.333
Development Distribution Score (DDS): 0.429

Top Committers

Name	Email	Commits
Félix Voituret	f**t@d**m	168
Faylixe	f**t@g**m	110
romi1502	r**n@d**m	63
mmoussallam	m**m@d**m	49
Dorian Desblancs	d**s@m**a	37
akhlif	a**f@d**m	15
Moussallam	m**m@g**m	14
Aurélien Hérault	ah@d****m	5
varnaudo	v**o@d**m	4
Marshall Scorcio	m**o@g**m	2
Yusuke Goto	u**o@g**m	2
Fabian-Robert Stöter	f**r@i**r	2
Ali Akbar	a**a@g**m	1
Martin Chloride	i@m****e	1
Rob Moore	r**8@g**m	1
jtagcat	g**7@j**t	1
antoine@antoine-latitude7410	a**e@d**m	1
johnwmillr	j**r@g**m	1
romi1502	e**l@a**m	1
valrus	i**n@g**m	1

Committer Domains (Top 20 + Academic)

deezer.com: 7 address.com: 1 jtag.cat: 1 martincl2.me: 1 inria.fr: 1 mail.mcgill.ca: 1

Issues and Pull Requests

Last synced: 4 months ago

All Time

Total issues: 175
Total pull requests: 47
Average time to close issues: 26 days
Average time to close pull requests: 6 months
Total issue authors: 163
Total pull request authors: 29
Average comments per issue: 2.95
Average comments per pull request: 0.45
Merged pull requests: 7
Bot issues: 0
Bot pull requests: 10

Past Year

Issues: 30
Pull requests: 11
Average time to close issues: 9 minutes
Average time to close pull requests: about 18 hours
Issue authors: 29
Pull request authors: 7
Average comments per issue: 0.53
Average comments per pull request: 0.18
Merged pull requests: 3
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

schweini (2)
bartman081523 (2)
MohammedMehdiTBER (2)
DavidDoukhan (2)
hassan8971 (2)
rikdijkstra (2)
LoboMetalurgico (2)
s2t2 (2)
suraj143rosy (2)
all-the-good-ones-are-gone (2)
mathpopo (2)
abosaqer (1)
xiota (1)
ssumitk14 (1)
Feliipe93 (1)

Pull Request Authors

dependabot[bot] (10)
d-dawg78 (5)
karlhayek (2)
antoinegob92 (2)
ivanmilevtues (2)
introinifederico (2)
Adkr1989 (2)
AniketP04 (2)
alex-ilyichov (2)
marcan (2)
ValerioArnaudo (2)
ensonic (2)
realytcracker (2)
chuttam (1)
mmoussallam (1)

Top Labels

Issue Labels

question (74) bug (71) invalid (70) enhancement (18) feature (18) RTMP (2) windows (2) model (2) training (2) ffmpeg (1) evaluation (1) wontfix (1) next release (1)

Pull Request Labels

dependencies (10) bug (1)

Packages

Total packages: 6
Total downloads:
- pypi 28,467 last-month
Total docker downloads: 198

Total dependent packages: 2
(may contain duplicates)
Total dependent repositories: 95
(may contain duplicates)
Total versions: 64
Total maintainers: 1

pypi.org: spleeter

The Deezer source separation library with pretrained models based on tensorflow.

Homepage: https://github.com/deezer/spleeter
Documentation: https://spleeter.readthedocs.io/
License: MIT
Latest release: 2.4.2
published 9 months ago

Versions: 27
Dependent Packages: 2
Dependent Repositories: 87
Downloads: 28,439 Last month
Docker Downloads: 198

Rankings

Stargazers count: 0.1%

Forks count: 0.2%

Dependent repos count: 1.6%

Average: 1.8%

Downloads: 2.2%

Dependent packages count: 3.2%

Docker downloads count: 3.7%

Maintainers (1)

deezer-research

Last synced: 4 months ago

proxy.golang.org: github.com/deezer/spleeter

Documentation: https://pkg.go.dev/github.com/deezer/spleeter#section-documentation
License: mit
Latest release: v2.3.0+incompatible
published over 4 years ago

Versions: 2
Dependent Packages: 0
Dependent Repositories: 1

Rankings

Stargazers count: 0.1%

Forks count: 0.1%

Average: 3.6%

Dependent repos count: 4.7%

Dependent packages count: 9.6%

Last synced: 4 months ago

proxy.golang.org: github.com/Deezer/spleeter

Documentation: https://pkg.go.dev/github.com/Deezer/spleeter#section-documentation
License: mit
Latest release: v2.3.0+incompatible
published over 4 years ago

Versions: 2
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Stargazers count: 0.1%

Forks count: 0.1%

Average: 4.1%

Dependent packages count: 7.0%

Dependent repos count: 9.3%

Last synced: 4 months ago

pypi.org: spleeter-gpu

The Deezer source separation library with pretrained models based on tensorflow.

Homepage: https://github.com/deezer/spleeter
Documentation: https://spleeter-gpu.readthedocs.io/
License: MIT License
Latest release: 2.0.2
published about 5 years ago

Versions: 14
Dependent Packages: 0
Dependent Repositories: 5
Downloads: 28 Last month

Rankings

Stargazers count: 0.1%

Forks count: 0.2%

Dependent repos count: 6.6%

Average: 10.0%

Dependent packages count: 10.1%

Downloads: 32.7%

Maintainers (1)

deezer-research

Last synced: 4 months ago

conda-forge.org: spleeter

Homepage: https://github.com/deezer/spleeter
License: MIT
Latest release: 1.5.3
published over 5 years ago

Versions: 10
Dependent Packages: 0
Dependent Repositories: 2

Rankings

Stargazers count: 1.5%

Forks count: 2.2%

Average: 18.9%

Dependent repos count: 20.2%

Dependent packages count: 51.6%

Last synced: 4 months ago

conda-forge.org: spleeter-gpu

Homepage: https://github.com/deezer/spleeter
License: MIT
Latest release: 1.5.3
published over 5 years ago

Versions: 9
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Stargazers count: 1.5%

Forks count: 2.1%

Average: 22.2%

Dependent repos count: 34.0%

Dependent packages count: 51.2%

Last synced: 4 months ago

Spleeter

Science Score: 95.0%

Keywords

Scientific Fields

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

About

Projects and Softwares using Spleeter

Spleeter Pro (Commercial version)

Quick start

install dependencies using conda

install spleeter with pip

download an example audio file (if you don't have wget, use another tool for downloading)

separate the example audio into two components

Development and Testing

Clone spleeter repository

Install poetry

Install spleeter dependencies

Run unit test suite

Reference

License

Disclaimer

Troubleshooting

Windows users

Contributing

Note

Owner

JOSS Publication

Spleeter: a fast and efficient music source separation tool with pre-trained models

Authors

Editor

Tags

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: spleeter

Rankings

Maintainers (1)

proxy.golang.org: github.com/deezer/spleeter

Rankings

proxy.golang.org: github.com/Deezer/spleeter

Rankings

pypi.org: spleeter-gpu

Rankings

Maintainers (1)

conda-forge.org: spleeter

Rankings

conda-forge.org: spleeter-gpu

Rankings