amazon-science/semimtr-text-recognition

NaN in input tensor

dikubab opened this issue · 2 comments

The language model gives NaN or Inf found in input tensor.
train.txt
Can help why it is failing to train on non English character?

Hi,

Thank you for the interest in our work.
Please refer in this issue, to the changes that are required for training on non-English language.
In particular, make sure that you created AmharicText_train.csv and AmharicText_eval.csv with the right character set.

Let me know if it works for you.
Aviad

Thank you for your prompt response. As per your suggestion, I have cleaned my train and valid text datasets and now it is working for me. I am closing the issue.