Open wcqy-ye opened 10 months ago
for i in range(self.scale):
att_TDNNs.append(att_TDNN(width, D, **CE**))
Change the parameters , they should be
for i in range(self.scale):
att_TDNNs.append(att_TDNN(width, D, **width**))
Additionally, the MFAmodule section in this code does not use any BN or activation, which may lead to gradient issues
Hello, I'd like to ask how to run the MFA-TDNN model. I attempted to run it using the following approach, but encountered an error. Thank you for sharing your code, and I look forward to your response. I believe the size of the input x meets the requirements for input to the MFA module.