Results
2
issues of
Juntae, Kim
Hello! I wanna confirm that the stop gradient problem was solved or not. I found that there is some intrinsic mathmatical problem in your implementation and after I fix that...
Question
2
It seems that your mwer loss implementation needs prior beam search for inputs for mwer_loss function. We can get 'seq_logprobs' during beam search for each hypothesis, however, your implementation seems...