Venkatesh Shenoy Kadandale

A possible fix: In line #187 of models.py, replace `output_layer = output_layer.view(batch_size,-1,height,1)` with `output_layer = output_layer.permute(0, 2, 1, 3).contiguous().view(batch_size, height, -1, 1).permute(0, 2, 1, 3)`

Thanks for the quick response @vitrioil ! It seems another similar bug is repeated [here](https://github.com/vitrioil/Speech-Separation/blob/master/src/models/models.py#L322) and also in the [asteroid](https://github.com/asteroid-team/asteroid/blob/master/egs/avspeech/looking-to-listen/model.py#L494). Here, we are reshaping (N,298,2x257xself.num_person) into (N,2,298,257,self.num_person). Instead of view(N,...

I have raised a bug in [asteroid](https://github.com/asteroid-team/asteroid/issues/438) as well. Another thing, this [line](https://github.com/vitrioil/Speech-Separation/blob/master/src/models/models.py#L231) needs to be commented out, I guess.

please let know if you manage to overcome the overfitting problem with this fix. thanks!

Hi, I trained the model in this repository on LJSpeech dataset and I am not able to see diagonal alignment in decoder attention and encoder-decoder attention after 160K iterations. I...

Hi, did you get this working finally? While training on LJSpeech dataset, I notice that the diagonal alignment doesn't appear in decoder attention and encoder-decoder attention, but only in the...