QuartzNet-ASR-pytorch icon indicating copy to clipboard operation
QuartzNet-ASR-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon Kirili4ik

Why using separable conv in C1 and C2 instead of normal conv1d?

Open mohsen-goodarzi opened this issue 2 years ago • 3 comments

Thank you for sharing your great work.

I noticed you have used sepconv_bn in C1 and C2 instead of conv_bn_act. Is it on purpose? Does it give better results?

https://github.com/Kirili4ik/QuartzNet-ASR-pytorch/blob/ec6073ef76d1ce0419bc62065ec746cb12a63efc/model.py#L49

mohsen-goodarzi avatar Sep 01 '22 07:09 mohsen-goodarzi