hi, @sacmehta!
I see that in the paper:
First, ESPNet-C was trained with down-sampled annotations. Second, a light-weight decoder was attached to ESPNet-C and then, the entire ESPNet network was trained
you freeze the parameters of encoder(ESPNet-C ) in the training of ESPNet ?
hi, @sacmehta! I see that in the paper: First, ESPNet-C was trained with down-sampled annotations. Second, a light-weight decoder was attached to ESPNet-C and then, the entire ESPNet network was trained
you freeze the parameters of encoder(ESPNet-C ) in the training of ESPNet ?