search

hirofumi0810 / neural_sp

End-to-end ASR/LM implementation with PyTorch
Apache License 2.0
589 stars 140 forks source link

loss ctc fluctuates #349

Open qkrguswn2401 opened 2 years ago

qkrguswn2401 commented 2 years ago

hi, I am creating an ASR model on Korean dataset. My E2E ASR model without language model works really well, wer around 1 on dev and evaluation set. But When I apply language model fusion (deep and cold), ctc dev loss does not converge at all and around 50% WER on eval set. attention dev loss converges and accuracy is about 99%.
I can not find the cause of fluctuation of ctc loss and not performing well on eval set. Thank you image image

Yalab7 commented 5 days ago

Did you find the cause of this problem?