phoneme_ctc icon indicating copy to clipboard operation
phoneme_ctc copied to clipboard

Published 20 hours ago • verified publisher icon tbornt

Loss not decreasing

Open pranoot opened this issue 6 years ago • 2 comments

Hello,

Thank you sharing the codes. I am trying to train the model on TIMIT dataset from scratch but the loss is not decreasing. Can you please suggest something for the same?

Thanks.

pranoot avatar Jan 17 '19 04:01 pranoot

Hi pranoot, Could you share how do you train your model? Because I'm not so sure where or which is the TIMIT dataset.

Also is it possible that because both use the same dataset and hence the accuracy is not improving?

Terrance82 avatar Jan 28 '19 02:01 Terrance82

Hello,

Thank you for the revert. This is link for the timit dataset. I used the same any hyper parameters and same architecture which you used in your codes. Can you tell me,

  1. Did you try with Adam optimizer as well or Momentum performed better.
  2. While training should I try reducing ctc_loss or should I try reducing the label error rate?

If my questions are not clear please let me know. Thanks and regards.

pranoot avatar Jan 29 '19 10:01 pranoot