search

tesseract-ocr / langdata_lstm

Data used for LSTM model training
Apache License 2.0
115 stars 153 forks source link

change kur_ara to kmr - Kurdish in Latin script - Kurmanji #2

Closed Shreeshrii closed 5 years ago

Shreeshrii commented 5 years ago
  1. kur_ara had files in Latin script. Changed name to kmr to match earlier changes made to tessdata_best and tessdata_fast.
  2. desired_characters had Arabic characters. Moved to kur which had Kurdish in Arabic script in tessdata.
  3. Copied okfonts.txt to kur since it seems to have Kurdish Arabic fonts.