TDNN icon indicating copy to clipboard operation
TDNN copied to clipboard

Time delay neural network (TDNN) implementation in Pytorch using unfold method

Results 3 TDNN issues
Sort by recently updated
recently updated
newest added

# N, output_dim*context_size, new_t = x.shape x = x.transpose(1,2) x = self.kernel(x) x = self.nonlinearity(x) I think "output_dim" should be "input_dim"? thanks

Line 61: ` stride=(1,self.input_dim), ` in tdnn.py I think it should be ` stride=(self.stride, self.input_dim) ` isn't it? Btw, thanks for your implementation!

Hi Thank you in advance, I am trying to implement the X-vector using your TDNN model, but when I try to train it and the loss can not down and...