speaker_extraction_SpEx icon indicating copy to clipboard operation
speaker_extraction_SpEx copied to clipboard

Published 20 hours ago • verified publisher icon xuchenglin28

Some question for training result

Open cc-cherie opened this issue 2 years ago • 1 comments

Hi, thanks for the great work. I have some question about the results. I have trained the model following the step you mentioned in README, and use the default setting except the parameter of batchsize (24 for 2 GPU). The SI-SDR was about 12dB , witch is different with the result in the paper.

cc-cherie avatar Aug 24 '21 07:08 cc-cherie