Hi,
I am trying to fine tune tesseract for a custom dataset. I have been
referring to the Makefile used by the ocrd-train repo. I am trying to fine
tune eng.traineddata which I obtained from tessdata_best I have a few
questions:
1. What is the difference between the traineddata used for the
--traineddata parameter and the traineddata used for --old_traineddata
parameter??.
2. I know that eng.traineddata is used for --old_traineddata, but do we
need to create a traineddata using combine_lang_model??. Can we use
eng.traineddata for --old_traineddata??.
Is there somewhere I can read more about eng.traineddata. If there is not
then we need to create a tutorial for explaining what it contains and how
it is used.
--
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/1de718e9-4425-4ce1-bae4-45ceef1a89d4%40googlegroups.com.
