langdata_lstm has the source training data used for 4.0.0alpha traineddata files. However, the exact usage of files or scripts to use them have not been provided.
The training text in langdata_lstm is much larger. If you want only to finetune, you should consider limiting the pages when running tesstrain.sh. The unicharset is usually built from the training text so make sure that the trainingtext has all the required characters in it. On Fri, Aug 31, 2018 at 5:42 PM, <benda.kriszt...@ustream.tv> wrote: > I've seen there is a new repository in the tesseract-ocr directory called > *langdata_lstm*. Is it better to use train lstm or should I use the > simple old *langdata* repository? If *langdata_lstm* is more likely to > use which *.unicharset* file is recommended for *combine_lang_model* > script? *langdata_lstm/Latin/Latin.unicharset* or > *langdata_lstm/Latin.unicharset*? > > I did not find any documentation about 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 tesseract-ocr@googlegroups.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/ > msgid/tesseract-ocr/807d0766-ecd3-4ddd-add6-150a0c39e7a6% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/807d0766-ecd3-4ddd-add6-150a0c39e7a6%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com -- 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 tesseract-ocr@googlegroups.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/msgid/tesseract-ocr/CAG2NduXC0F1t7byHVLd1_7PCD0CcHX4juYYB1u9Dsph1%2B-T5KQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
