combine_tessdata(1) <https://manpages.debian.org/unstable/tesseract-ocr/combine_tessdata.1.en.html> is the main program to combine/extract/overwrite/list/compact tessdata components in [lang].traineddata files.
Options to list network details *-d* *.traineddata* *FILE*...: Lists directory of components from the .traineddata file. *-l* *.traineddata* *FILE*...: List the network information. On Sat, Sep 16, 2023, 2:11 PM Shree Devi Kumar <shreesh...@gmail.com> wrote: > The language name headings seem to be missing from the tessdoc page for > tessdata_fast > > Please revert to an older version of page from history > > On Sat, Sep 16, 2023, 2:08 PM Shree Devi Kumar <shreesh...@gmail.com> > wrote: > >> >> https://github.com/tesseract-ocr/tessdoc/blob/main/Data-Files-in-tessdata_best.md >> >> >> https://github.com/tesseract-ocr/tessdoc/blob/main/Data-Files-in-tessdata_fast.md >> >> Version string : 4.00.00alpha : [Network specification] for tessdata_best >> >> tessdata_best models - *incomplete list*, only till Kannada. >> >> The flags are TrainingFlags from lstmrecognizer.h. 0x40 is compress >> unicharset and 1 is integer mode. The one from best has flags 40 = >> compress + not integer mode. >> >> afr >> Version >> string:4.00.00alpha:afr:synth20170629:[1,36,0,1Ct3,3,16Mp3,3Lfys64Lfx96Lrx96Lfx512O1c1] >> LSTM training info:Network >> str:[1,36,0,1Ct3,3,16Mp3,3Lfys64Lfx96Lrx96Lfx512O1c1], >> flags=40, iteration=286700, sample_iteration=286724, null_char=95, >> learning_rate=0.001, momentum=0.5, adam_beta=0.999 >> >> amh >> Version string:4.00.00alpha:amh >> LSTM training info:Network >> str:[1,36,0,1Ct3,3,16Mp3,3Lfys48Lfx96Lrx96Lfx192O1c1], >> flags=40, iteration=6112200, sample_iteration=6112270, null_char=284, >> learning_rate=0.001, momentum=0.5, adam_beta=0.999 >> >> >> >> On Fri, Sep 15, 2023, 9:50 PM Des Bw <desaleg...@gmail.com> wrote: >> >>> For the last couple of days, I have been trying to train the amh data to >>> include some missing characters. >>> >>> I have seen that Shree was able to add the Norwegian Æ by removing the >>> top layer and training on it ( >>> https://groups.google.com/g/tesseract-ocr/c/l33zsTEPj70/m/wPzPv6HiEQAJ >>> ). >>> >>> I was trying to do the same. But, the traineddata in Amharic doesn't >>> contain the net_spec information with the version line. >>> >>> Version:4.00.00alpha:amh:synth20170629 >>> >>> 17:lstm:size=3356155, offset=192 >>> >>> 18:lstm-punc-dawg:size=3154, offset=3356347 >>> >>> 19:lstm-word-dawg:size=5007810, offset=3359501 >>> >>> 20:lstm-number-dawg:size=810, offset=8367311 >>> >>> 21:lstm-unicharset:size=18906, offset=8368121 >>> >>> 22:lstm-recoder:size=2578, offset=8387027 >>> >>> 23:version:size=30, offset=8389605 >>> >>> >>> Can sb (@Shree, please) help me on how to get the net_spec, or how to >>> proceed to add a layer to introduce the missing characters? >>> >>> -- >>> 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/5bedab52-2f9b-44ab-a97a-e2033d0e92den%40googlegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/5bedab52-2f9b-44ab-a97a-e2033d0e92den%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/CAG2NduWBVT1nrD-MSzmEzLYZfKPnSgKEnSf%2BcnSMOPT8%2BtQDZg%40mail.gmail.com.
