I'm getting frequent segmentation faults when using the -l flag with the custom traineddata. I assume this is because the data is trained for Tesseract 3 instead of Tesseract 4. However, I don't get seg faults all the time which leads me to believe that there is some form of compatibility. Is it possible to enable Tesseract 4 to use Tesseract 3 traineddata or are there any ways to convert the Tesseract 3 traineddata into something more friendly with Tesseract 4?
Thanks in advance! -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/e2fa349f-009a-4659-83d0-ed55f4ce6597%40googlegroups.com.
