StemSplit commited on
Commit
4ce66cb
Β·
verified Β·
1 Parent(s): 64a0b18

Add 3 stem-specialist repos to assets table

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -26,7 +26,10 @@ browser.
26
  |---|---|---|---|
27
  | [stem-separation-benchmark-2026](https://huggingface.co/datasets/StemSplitio/stem-separation-benchmark-2026) | Dataset | βœ… live (v1.1) | Reproducible SDR / ISR / SIR / SAR benchmark of every popular open-source separation model on MUSDB18-HQ. 850 rows, full eval methodology and source code. |
28
  | [Music Source Separation Toolkit 2026](https://huggingface.co/collections/StemSplitio/music-source-separation-toolkit-2026-6a0d059a55a1b261e939c9c6) | Collection | βœ… live | Curated list of the open-source models a developer needs in 2026 β€” plus our benchmark. The fastest way to evaluate the landscape. |
29
- | [htdemucs-ft-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-pytorch) | Model | βœ… live | HT-Demucs FT (#1 open-source vocal SDR on MUSDB18-HQ) packaged with a ready-to-deploy `handler.py` for Hugging Face Inference Endpoints. |
 
 
 
30
  | ONNX / CoreML conversions | Models | 🚧 in progress | Production-ready conversions of HT-Demucs and MDX-Net for native iOS/Android/Edge deployment. |
31
  | Demo Space | Space | 🚧 in progress | Upload a track, pick a model, compare separations in your browser. |
32
  | Live leaderboard Space | Space | πŸ“‹ planned | Community-submittable, continuously evaluated leaderboard for stem separation. |
 
26
  |---|---|---|---|
27
  | [stem-separation-benchmark-2026](https://huggingface.co/datasets/StemSplitio/stem-separation-benchmark-2026) | Dataset | βœ… live (v1.1) | Reproducible SDR / ISR / SIR / SAR benchmark of every popular open-source separation model on MUSDB18-HQ. 850 rows, full eval methodology and source code. |
28
  | [Music Source Separation Toolkit 2026](https://huggingface.co/collections/StemSplitio/music-source-separation-toolkit-2026-6a0d059a55a1b261e939c9c6) | Collection | βœ… live | Curated list of the open-source models a developer needs in 2026 β€” plus our benchmark. The fastest way to evaluate the landscape. |
29
+ | [htdemucs-ft-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-pytorch) | Model | βœ… live | HT-Demucs FT (#1 open-source vocal SDR on MUSDB18-HQ) packaged with a ready-to-deploy `handler.py` for Hugging Face Inference Endpoints. Returns all 4 stems. |
30
+ | [htdemucs-ft-drums-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-drums-pytorch) | Model | βœ… live | Drums specialist sub-model. ~160 MB, ~2.6Γ— faster than the full bag, identical drum SDR. For drum extraction, beat transcription, sample-pack creation. |
31
+ | [htdemucs-ft-bass-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-bass-pytorch) | Model | βœ… live | Bass specialist sub-model. Same speed/quality story as drums. For bassline transcription and mix rebalancing. |
32
+ | [htdemucs-ft-other-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-other-pytorch) | Model | βœ… live | "Other" / instrumental specialist. Pair with the vocals model for karaoke, sample-flipping, music-bed extraction. |
33
  | ONNX / CoreML conversions | Models | 🚧 in progress | Production-ready conversions of HT-Demucs and MDX-Net for native iOS/Android/Edge deployment. |
34
  | Demo Space | Space | 🚧 in progress | Upload a track, pick a model, compare separations in your browser. |
35
  | Live leaderboard Space | Space | πŸ“‹ planned | Community-submittable, continuously evaluated leaderboard for stem separation. |