tarun73

Results 3 comments of tarun73

@miziworld where you able to solve your issue. i am facing a similar issue with conformer - embedding layers require weight observer with dtype=torch.quint8 - convolution layers require weight observer...

Hi @sw005320, when you mention > In espnet1, we have a multiple-utterance batch beam search, and it works very well. can you please point to the part of the code...

I am also getting the same Warning, did you find any solution