search

hirofumi0810 / neural_sp

End-to-end ASR/LM implementation with PyTorch
Apache License 2.0
596 stars 141 forks source link

how to decoding sub task model in multi-task learning model? #143

Open shunfeichen opened 4 years ago

shunfeichen commented 4 years ago

Hello, I want to obtain the output of the sub1 task learning ,how should I do? or is there about script? Thank you.

hirofumi0810 commented 4 years ago

@shunfeichen You can get sub-task's outputs by specifying task in https://github.com/hirofumi0810/neural_sp/blob/master/neural_sp/models/seq2seq/speech2text.py#L599.

shunfeichen commented 4 years ago

Thank you , very much. I have obtained it. And by the way , I find the last wav in the test will be ignored during decoding.