Hindi with cube model was included with version 3.02 (or 3.01). Marathi and
Sanskrit tessdata without cube model were released as part of version 3.04.
While there has been talk of cube model being experimental (scant
information is available for it) and plans for it to be discontinued, 3.04
did not include new traineddata for Hindi since it regressed (as per the
An alpha release (4.00 with LSTM) by Ray (chief developer for Tesseract at
Google) is supposed to happen at end of September as per some comments by
Zdenko on github, it is supposed to have better accuracy for the complex
भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com
On Tue, Sep 20, 2016 at 7:05 PM, rkvsraman <rkvsra...@gmail.com> wrote:
> In tessdata , I see cube models only for hindi and not for Marathi and
> Sanskrit thought they have the same script.
> Any particular reason for this?
> 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 post to this group, send email to email@example.com.
> Visit this group at https://groups.google.com/group/tesseract-ocr.
> To view this discussion on the web visit https://groups.google.com/d/
> For more options, visit https://groups.google.com/d/optout.
You received this message because you are subscribed to the Google Groups
To unsubscribe from this group and stop receiving emails from it, send an email
To post to this group, send email to firstname.lastname@example.org.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
For more options, visit https://groups.google.com/d/optout.