# HDEMUCS_HIGH_MUSDB¶

torchaudio.pipelines.HDEMUCS_HIGH_MUSDB

Pre-trained music source separation pipeline with Hybrid Demucs trained on the training set of MUSDB-HQ .

The model is constructed by hdemucs_high(). Training was performed in the original HDemucs repository here.

Please refer to SourceSeparationBundle for usage instructions.