How to use molto/sepformer-whamr16k with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "molto/sepformer-whamr16k" ) model.separate_file("file.wav")
b52dc53
1
2
3
4
5
# yamllint disable end-of-epoch: true si-snr: -7.369511792677621 unixtime: 1621680451.6093628
