Tesseract tesstrain.sh - Error: jpn_vert is not a valid language code

412 Views Asked by At

Trying to run tesstrain.sh for jpn_vert

tesstrain.sh --fonts_dir ./tesstutorial --lang jpn_vert --linedata_only --save_box_tiff --langdata_dir ./tesstutorial --fontlist 'Font' --tessdata_dir ./tesstutorial --output_dir ./result

and I'm getting

ERROR: Error: jpn_vert is not a valid language code

(when I pass it in as --lang) I have jpn_vert.traineddata in the tessdata path I'm passing.

I think my error comes from https://github.com/mabhub/tesseract-ocr/blob/master/training/language-specific.sh, there is no case for any vert language. So as per language-specific.sh script when I pass the lang as jpn the script goes on.

Is jpn_vert supposed to be trained as jpn or am I missing something else? (jpn.config loads jpn_vert as a sublanguage but that doesn't sound right when I'm only training jpn_vert)

0

There are 0 best solutions below