MSST Bible

Strings

Page 57 of 228 · Open the original GDoc ↗

- Dango.ai (e.g. violin, erhu; paid, free 30 seconds fragments) - "impressive results" for at least violin

- Music.ai (paid, “Dango.ai and Music.ai [previously] the best strings models [Dango sounds fuller meanwhile Music.ai has more accurate recognition of strings but sounds a bit too filtered]” - from before the BS Strings release)

- MVSep Bowed Strings (“doesn't disappoint”, SDR 5.41; formerly “MVSep Strings”)

- gilliaan_bsroformer_bowedstrings_v2 | yaml | metrics | MK Colab fork (only worse SDR than the MVSep’s one; “actually fire”, “goated, ridiculously good, way better than the MVSep one, especially good with demudder - straturkoise)

- BS-Roformer Bowed Strings model | yaml by gilliaan | MK Colab fork | MVSEP (fullness duality model, UVR exports only one stem and inverts it, use MSST instead. “Trained on everything except orchestral. (...) Best results at overlap 6. Overlap 1 is also worth trying in some cases! it captures more of the strings, but at the cost of some bleeding/cutting, so it depends on the track”).

- MVSep Plucked Strings

- MVSep Violin (sometimes does better than the strings model for strings)

- MVSep Synth (has synth strings stems included during training)

- MVSep SATB Choir (works with strings too)

- Moises.ai (paid, not bad)

- Audioshake


- MVSep Strings MDX23C (it’s “weak”, SDR 3.84, perhaps deleted)

- x-minus.pro/Uvronline.app Mel-Roformer model by viperx (SDR 2.87) (sometimes with this link or this link)

 

- Demix Pro (paid, free trial)

- RipX DeepRemix (once was told to be the best bass model, but it doesn’t score that good SDR-wise, probably it’s Demucs 3 (demucs_extra) and is worse than Demucs_ft and rather also vs MDX23 above; could have been updated) (paid)

 

- Sometimes Wind model in UVR5 GUI picks up strings

 

 

- MVSEP Harp

 

- MVSep Mandolin

 

- MVSep Banjo

 

- MVSep Sitar

 

- MVSep Ukulele

 

- MVSep Dobro

 

 

- BS-Roformer “MVSep Mega 53 Stems” model - 1.27GB | single models (less VRAM-hungry) - 1.27GB | MVSepless HF / HF CPU / Colab / newer (you can pick which stems you want there)

 

Violin

- MVSep Violin BS Roformer

“It can even separate violin quartets from cellos, so cool.” - smilewasfound

“Very neat model. (...) Sometimes the model does seem to pick up more than just violins imo, but yeah for separating high strings in particular it is really cool.” - Musicalman

- Dango.ai “impressive”

 

- MVSEP Viola

 

- MVSEP Chello (not included in “MVSep Mega 53 Stems” model | single models (less VRAM-hungry) - 1.27GB | MVSepless HF / HF CPU / Colab / newer (you can pick which stems you want there)