Papers › Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models

Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models

4 Nov 2019ISMIR 2019 Late-Breaking/Demo 2019 11archive 2025-07-28

Romain Hennequin, Anis Khlif, Felix Voituret, Manuel Moussallam

We present and release a new tool for music source separation with pre-trained models called Spleeter.Spleeter was designed with ease of use, separation performance and speed in mind. Spleeter is based onTensorflow [1] and makes it possible to:•separate audio files into2,4or5stems with a single command line using pre-trained models.•train source separation models or fine-tune pre-trained ones with Tensorflow (provided you have a dataset of isolated sources).The performance of the pre-trained models are very close to the published state of the art and is, to the authors knowledge, the best performing4stems separation model on the common musdb18 benchmark [6]to be publicly released. Spleeter is also very fast as it can separate a mix audio file into4stems100timesfaster than real-time1on a single Graphics Processing Unit (GPU) using the pre-trained4-stems model. Spleeter is packaged within Docker which makes it usable as is on various platforms.

PaperPDFCode

Code

deezer/spleeter mentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Music Source SeparationSpeech Enhancement

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Music Source Separation MUSDB18 Spleeter (MWF) SDR (avg) 5.91 #19 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Spleeter (MWF) SDR (bass) 5.51 #19 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Spleeter (MWF) SDR (drums) 6.71 #19 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Spleeter (MWF) SDR (other) 4.02 #19 of 27 Archive leaderboard report
Music Source Separation MUSDB18 Spleeter (MWF) SDR (vocals) 6.86 #19 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Batch NormalizationConcatenated Skip ConnectionConvolutionELUReLUSPEEDU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections