mmathew( മിനേഷ് മാത്യു )
mmathew( മിനേഷ് മാത്യു )
I understand that the WFST method requires both a lexicon and a LM ( as n-gram frequencies) But in the README it is mentioned that a character level RNN-LM can...
Hey, My question is not related to the development but on using the library. I was going through the OP example here https://ahkab.readthedocs.io/en/latest/examples/Simple_OP.html I see that upon simulation it outputs...
@SakuraRiven For how many epochs did you train the pretrained model ? And how did you decide which checkpoint to use? based on the average loss per epoch?