julien-c/DPRNNTasNet-ks16_WHAM_sepclean

The Asteroid model was trained by Manuel Pariente using the wham/DPRNN recipe in Asteroid . It was trained on the sep_clean task of the WHAM! dataset . Asteroid is the PyTorch-based audio source separation toolkit for researchers . The model is based on the data set of Asteroid and the data used to train Asteroid's model mpariente and DPRNNTasNet(ks=16)_WHAM!_sepclean . The data set was trained using Asteroid’s ‘sdr_imp’ and ‘Sdr_sdr’. The model was then used to,