Thank you for your work!
I am trying to use your multilingual model for Turkish text. The model is not restoring the spaces. I am trying your model on Annotated data, therefore every character is essential to preserve the annotated char sequences. When there is a paragraph with some sentences using two spaces between words instead of one, the split version of these sentences removes these multi-spaces. Any suggestions?
Hi!
Thank you for your work! I am trying to use your multilingual model for Turkish text. The model is not restoring the spaces. I am trying your model on Annotated data, therefore every character is essential to preserve the annotated char sequences. When there is a paragraph with some sentences using two spaces between words instead of one, the split version of these sentences removes these multi-spaces. Any suggestions?