De-crowd
Current models struggle with female screams and singing
- MVSep FX (much better than the Crowd MelRo+MDX23C ensemble for crowd removal with the BS being constantly worse (thx lmmj2025/kai)
“works drastically better if you give it the original recording and not try to do any work prior, even including removing main vocals/speech. (...) if I fed it the noisy starting file, it basically pulled the ENTIRE crowd out, far better than anything else.” - godzfire)
- MVSEP Crowd MDX23C+Mel-Roformer Ensemble (6.07+6.06)
- MVSEP Crowd BS Roformer (SDR 7.21) (newer model, people have issues with it frequently: "The 6.27 one removed all kinds of crowd noises, sound effects and general noise, this one only removes random bits of music!")
- UVR-MDX-NET Crowd HQ 1 (UVR/x-minus.pro/model/conf in UVR) (can be more effective than Mel MVSEP’s sometimes; e.g. good for live shows)
- MVSEP Mel-Roformer Crowd by ZFTurbo (SDR 6.07) (MVSEP/files/UVR)
To use it in UVR, Go to UVR\models folder, and paste that folder there.
Then change "dim_t" value to 801 at the very bottom of: “model_mel_band_roformer_crowd.yaml” file in “mdx_c_configs” subfolder. Don’t use overlap above 4.
- Dango decrowd (paid)
- Mel-Roformer De-Crowd by Aufr33/viperx (x-minus.pro/UVR/DL/conf)
For UVR, change the model name to the one from the attached yaml, copy chkpt to models\MDX_Net_Models, and yaml to model_data subfolder, then set overlap 2 or use ZFTurbo inference script] - more effective than MDX below at times)
- MDX23C De-crowd v1/v2 (MVSEP)
- Older MSX23C MVSEP models (applause, clapping, whistling, noise)
- Aufr33’s Mel-Roformer Denoise average variant (link | yaml | Colab) can be also used as crowd removal
- models for Harmonies - potentially for people singing along
- AudioSep
- Zero Shot Audio Source Separation
- GSEP (sometimes), and e.g. drums stem is able to remove applauses
- Chant model (by HV, VR arch, e.g. works for applauses; may leave some echo to separate with other models or tools below) for Colab usage - you need to copy that model to models/v5 and then use 1 band 44100 param, turn off auto-detect arch and set it to "default". In UVR pick one of 44100 1 band parameter, possibly 512.
“For really difficult live songs (where the crowd is overwhelmingly loud to the point where you can't hear the band properly) sometimes filtering vocals with mel roformer on xminus THEN running the vocals stem through the mdx decrowd model sometimes helps”