CTC-OptimizedLoss
CTC-OptimizedLoss copied to clipboard
Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
Thanks for sharing the codes. Could you provide an example of the o1 loss? I've combined it with the CTC loss as shown in the following code, but it seems...
why mwer use stop gradient? just a regularization?
Thankyou very much for share the code, but when I training a model using the CTCMWER loss, it may be negative, sometime? So what's the reason could be?