Anjok07 / ultimatevocalremovergui

GUI for a Vocal Remover that uses Deep Neural Networks.
MIT License
17.21k stars 1.29k forks source link

Does anyone know where i can find the model sami-bytedance? #593

Open thecatontheceiling opened 1 year ago

thecatontheceiling commented 1 year ago

I've seen it a couple of times on mvsep but i cant find a clear explanation on what it is and how to get it, any help would be appreacited :D

Dyslexicon commented 1 year ago

The SDR scores are off the charts. I cant bother using any other models for my workflow, knowing this model exists. Waiting impatiently :D

thecatontheceiling commented 1 year ago

this single model seems to beat full fledged MDX ensembles and htdemucs... it looks good but I can't find it ANYWHERE for the life of me

Dyslexicon commented 1 year ago

Have we any stem extraction examples from this model published publicly? You say you saw this model as an option on the mvsep website? https://mvsep.com/ or somewhere else?

Hopefully it is released publicly soon, seems a colossal engineering feat to withhold - after all this was a public competition, seems right and proper to release the results.

thecatontheceiling commented 1 year ago

https://mvsep.com/quality_checker/leaderboard2.php?id=2374

I saw it on mvsep here, god the SDR is off the charts lol

Dyslexicon commented 1 year ago

https://mvsep.com/quality_checker/leaderboard2.php?id=2374 I'm not sure what this is about, no "Other" stem

https://www.aicrowd.com/challenges/sound-demixing-challenge-2023/problems/music-demixing-track-mdx-23/leaderboards First place winning entry in SDX2023 Competition. On here, it does show results for the "Other" stem, and handily beats all other models.

Dyslexicon commented 1 year ago

@Anjok07 maybe you could convince the makers of this model to bring it to UVR??

0xdevalias commented 1 year ago

Don't think the model is there.. but here's their page in any case:

There's apparently also an audio separation feature in their new 'Ripple' tool, though unsure if it's the same one as shown on these charts:

Zokhoi commented 11 months ago

A few days ago they released a paper detailing their architecture, and we are one step closer to getting a model that is if not directly from them, recreated using their description for our use.

happyTonakai commented 11 months ago

It seems that they used 16 Nvidia V100-32GB GPUs for training. Looking forward to their pre-trained model.

owlwang commented 11 months ago

https://github.com/lucidrains/BS-RoFormer

There is code, but no pre-trained model.

Dyslexicon commented 11 months ago

Any heroic engineers who can port a functional model of this into Google Colab or UVR, please do! Colab preferable since I dont have a 40GB NVIDIA GPU :)

assocold commented 10 months ago

Wondering how good sami model is, haven't seen any example result.

zxcvqwerasdf commented 8 months ago

Still no pretrained model?

Ma5onic commented 7 months ago

https://github.com/lucidrains/BS-RoFormer

There is code, but no pre-trained model.

Is this what you are looking for https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/tag/v1.0.0? There is a pretrained mel_band_roformer model checkpoint, but it only achieves a SDR of 8.42. However, based on the SDR, I'm not sure if this will reproduce the same results as the sami-bytedance code from the SDX23 leaderboard C.

AdamGoodApp commented 5 months ago

Any updates on pre trained model?

jarredou commented 5 months ago

MVsep has a new good BS-Roformer model, it's, free to use on the website but the model is not publicly released (so can't be added to UVR).

thecatontheceiling commented 5 months ago

MVsep has a new good BS-Roformer model, it's, free to use on the website but the model is not publicly released (so can't be added to UVR).

SDR results seem pretty good, is it better than mdx23c?

XUANHLGG commented 4 months ago

https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bs_roformer_ep_368_sdr_12.9628.ckpt Requires use with this version of UVR: https://github.com/TRvlvr/model_repo/releases/download/uvr_update_patches/UVR_Patch_3_29_24_5_11_BETA_full_roformer.exe

Dyslexicon commented 4 months ago

Let us know when theres a full 4-stem model of BSRoFormer! Colab if possible...

realzsan3 commented 4 months ago

https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bs_roformer_ep_368_sdr_12.9628.ckpt Requires use with this version of UVR: https://github.com/TRvlvr/model_repo/releases/download/uvr_update_patches/UVR_Patch_3_29_24_5_11_BETA_full_roformer.exe

Does the Mac m1 have it?🙏

XUANHLGG commented 2 months ago

https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bs_roformer_ep_368_sdr_12.9628.ckpt需要与此版本的 UVR 一起使用:https://github.com/TRvlvr/model_repo/releases/download/uvr_update_patches/UVR_Patch_3_29_24_5_11_BETA_full_roformer.exe

Mac m1 有吗? 🙏

Unfortunately, the UVR that supports BS Roformer is only available for Windows, and to use it on Mac, you may need to compile it yourself :(