tesseract-ocr / tesstrain

Train Tesseract LSTM with make
Apache License 2.0
599 stars 178 forks source link

Line images max characters/max width #314

Closed naourass closed 1 year ago

naourass commented 1 year ago

Are there any special specifications for line images? Is there a max characters length or max image size?

I'm preparing data for finetuning Arabic.traineddata on a specific font (Sakkal Majalla Regular and Bold) with both arabic and latin words/characters. Is there an existing script for generating images and their gts from multi-line training text or should I write my own?

stale[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.