Datasets › Slakh2100
Slakh2100 (Synthesized Lakh Dataset)
The Synthesized Lakh (Slakh) Dataset is a dataset for audio source separation that is synthesized from the Lakh MIDI Dataset v0.1 using professional-grade sample-based virtual instruments. This first release of Slakh, called Slakh2100, contains 2100 automatically mixed tracks and accompanying MIDI files synthesized using a professional-grade sampling engine. The tracks in Slakh2100 are split into training (1500 tracks), validation (375 tracks), and test (225 tracks) subsets, totaling 145 hours of mixtures.
Source: http://www.slakh.com/ Image Source: http://www.slakh.com/ Audio Source: http://www.slakh.com/
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Music Transcription | Slakh2100 | YourMT3+ (YPTF.MoE+M) note-level F-measure-no-offset (Fno) 0.8456 | YourMT3+: Multi-instrument Music Transcription with... | mimbres/yourmt3 | 6 | Compare |
| Multi-instrument Music Transcription | Slakh2100 | YourMT3+ (YPTF.MoE+M) Multi F1 74.84 | YourMT3+: Multi-instrument Music Transcription with... | mimbres/yourmt3 | 5 | Compare |
| Music Source Separation | Slakh2100 | LQ-VAE + Scalable Transformer SDR (bass) 7.42 | Unsupervised Source Separation via Bayesian Inference in... | michelemancusi/LQVAE-separation | 2 | Compare |
Papers archive 2025-07-28
6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 38. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation | 1 | 6 | 5 Jul 2024 | not harvested |
| The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling | 1 | 2 | 28 Sep 2022 | ran 0 of 9 samples (9 unverified) |
| Jointist: Joint Learning for Multi-instrument Transcription and Its Applications | 0 | 1 | 22 Jun 2022 | not harvested |
| A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation | 1 | 1 | 18 Mar 2022 | ran 0 of 7 samples (7 unverified) |
| MT3: Multi-Task Multitrack Music Transcription | 3 | 1 | 4 Nov 2021 | ran 0 of 6 samples (6 unverified) |
| Unsupervised Source Separation via Bayesian Inference in the Latent Domain | 1 | 1 | 11 Oct 2021 | not harvested |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- Slakh2100
1 variant name, as the archive lists them.
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