Loading…
Loading…
BS-RoFormer & MelBand RoFormer — State-of-the-art music source separation
Pretrained weights converted to safetensors format for use with Mæstræa AI Workstation.
| Variant | SDR | Task | Path |
|---|---|---|---|
| Vocals (viperx) | 12.97 | Vocal/instrumental separation | bs_roformer/vocals_viperx/ |
| Multi-stem | 9.65 | 4-stem (bass/drums/vocals/other) | bs_roformer/multistem/ |
| Variant | SDR | Task | Path |
|---|---|---|---|
| Vocals (KimberleyJensen) | 10.98 | Best vocal isolation | mel_band_roformer/vocals_kj/ |
| Vocals (viperx) | 11.43 | Vocal/instrumental separation | mel_band_roformer/vocals_viperx/ |
| Dereverb (anvuew) | 19.17 | Remove reverb from audio | mel_band_roformer/dereverb/ |
| Denoise (aufr33) | 27.99 | Remove noise from audio | mel_band_roformer/denoise/ |
Both models use the Band-Split RoPE Transformer architecture from lucidrains/BS-RoFormer:
Both significantly outperform HTDemucs on vocal separation tasks.
Each model directory contains:
model.safetensors — Model weightsconfig.yaml — Architecture configuration (required for model instantiation)Requires bs-roformer Python package: pip install bs-roformer
MIT — same as all upstream model releases.