dual-path-RNNs-DPRNNs-based-speech-separation icon indicating copy to clipboard operation
dual-path-RNNs-DPRNNs-based-speech-separation copied to clipboard

Published 20 hours ago • verified publisher icon ShiZiqiang

class DPRNN_base in models.py

Open fncode246 opened this issue 3 years ago • 0 comments

Hello, thanks for sharing useful code. I want to implement "DUAL-PATH RNN: EFFICIENT LONG SEQUENCE MODELING FOR TIME-DOMAIN SINGLE-CHANNEL SPEECH SEPARATION" paper. So I decided to use DPRNN_base model instead of FaSNet_base that you have used in train.py. How to define the method def forward(self, input) in DPRNN_base ? What are the outputs of DPRNN_base model ?

fncode246 avatar May 14 '21 11:05 fncode246