It was just a small issue. If I remembered correctly I forgot to put the ground truth files in english name. the file names originally was in japanese, and tesseract ocr training is unable to read the file if filename is Kanji format On Monday, 5 May 2025 at 19:07:12 UTC+8 [email protected] wrote:
> It is good etiquette to explain what the problem was and how you solved > it. That way, anyone with a similar problem in future finding your post > will also know the solution. > > >> -- 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 visit https://groups.google.com/d/msgid/tesseract-ocr/f6b69841-1d72-43dc-a7e4-70af6a4c71fcn%40googlegroups.com.
