Language not being recgonized

tshrinivasan / OCR4wikisource

OCR for WikiSource using Google Drive OCR

GNU General Public License v2.0

33 stars 24 forks source link

Language not being recgonized #90

Closed satdeepgill closed 6 years ago

satdeepgill commented 7 years ago

Hi, I have tried using this tool for Punjabi (Gurmukhi) text on Multilingual Wikisource but the OCR was unable to recognize the text. On the other hand, if i upload the image on Google Drive then it is able to recognize by itself.

Check here: https://wikisource.org/wiki/Page:Sample_OCR.pdf/1

tshrinivasan commented 7 years ago

@satdeepgill can you share the link for a sample PDF in Gurmukhi language. Will check it.

tshrinivasan commented 6 years ago

provided a new file here https://github.com/tshrinivasan/OCR4wikisource/issues/99#issuecomment-389474388

hope this fixes the issue.

reopen or comment on the same #99 if you still getting the same issue.