Unless you provide information about what you do, and the possibility to replicate your process (providing input data) we do not know what is wrong with it. Did you check the example for official training[1]?
In my case I see this: Output has size 7485144 (`ls -l data/ocrd.traineddata`) while startmodel frk has size 12938047 (best model) and its fast model has size (6423052) [1] https://github.com/tesseract-ocr/tesstrain Zdenko st 13. 3. 2024 o 6:43 Cain Pian <bianyongfan...@gmail.com> napísal(a): > I've trained thousands of images. But the traineddata file size didn't > change at all. > Did I do something wrong? > > -- > 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 tesseract-ocr+unsubscr...@googlegroups.com. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/46067294-666a-4269-bcd1-aafa0d71fc4en%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/46067294-666a-4269-bcd1-aafa0d71fc4en%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8zy4Qi_YR%3DSOiw1asriWPYJT-XhokCGF58iiVwLhd4%2BZQ%40mail.gmail.com.
