How to train new language

tesseract-ocr / tesstrain

Train Tesseract LSTM with make

Apache License 2.0

630 stars 184 forks source link

How to train new language #329

Closed Erdene-Ochir0417 closed 1 year ago

Erdene-Ochir0417 commented 1 year ago

Hello

I'm trying to train tesseract on Mongolian language but it said that "Error opening data file /content/tessdata/eng.traineddata". There is mon.traineddata in /content/tessdata folder. Is it possible to train with renaming mon.trainneddata to eng.trainneddata?

command: make training MODEL_NAME=mon

mon-ground-truth folder: 0.png 0.gt.txt ......

zdenop commented 1 year ago

Read the documentation, follow instructions and use tesseract user forum for asking questions.