The pretrained SCNet stem separator that the StemFX Space runs before predicting effects, mirrored because the stemfx package otherwise downloads it from a GitHub release of Music-Source-Separation-Training. The file is unchanged, under its upstream name.

model_scnet_masked_ep_111_sdr_9.8286.ckpt: from https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.17/model_scnet_masked_ep_111_sdr_9.8286.ckpt, SHA-256 b4675b0269809de27172a050e8767a857077635eda1738db0874d63a79f2b6dd, the hash stemfx checks.

Music-Source-Separation-Training, by Roman Solovyev (ZFTurbo), is licensed MIT.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

teamup-tech
/

StemFX-weights

Space using teamup-tech/StemFX-weights 1