I ditched my 500+ font fontlist for one with just 3. It runs much faster now, and I got to Phase M before I got a ./langdata/font_properties does not exist or is not readable error.
On Sunday, September 10, 2017 at 2:08:10 PM UTC-4, Dan9er wrote: > > Did that, and it actually started training! It almost got to the end of my > font list before... > ERROR: /tmp/tmp.YLL4mGn66F/npn/npn.Aileron_Heavy.exp0.tr does not exist > or is not readable > > Also, there were some ERRORs, but there weren't any FATALITYies (lol), so > I think i'm good. > > On Sunday, September 10, 2017 at 12:13:25 PM UTC-4, shree wrote: >> >> >> 1. Fontconfig error: line 1: no element found >> 2. Fontconfig error: Cannot load default config file >> 3. Could not find font named NanumMyeongjo Semi-Bold. >> 4. Pango suggested font NanumMyeongjo Bold. >> 5. Please correct --font arg. >> 6. ERROR: /tmp/tmp.tiLxemomPr/npn/npn.NanumMyeongjo_Semi-Bold.exp0.box >> does not exist or is not readable >> >> >> ShreeDevi >> ____________________________________________________________ >> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com >> >> On Sun, Sep 10, 2017 at 9:37 PM, Dan9er <[email protected]> wrote: >> >>> I added the common.punc file. But now I'm getting the box error again: >>> https://pastebin.com/BsNL3KJv >>> >>> On Saturday, September 9, 2017 at 3:22:48 PM UTC-4, shree wrote: >>>> >>>> https://github.com/tesseract-ocr/langdata/blob/master/common.punc >>>> >>>> You should read the Readme.md in langada repo for info on the files >>>> required for training g >>>> >>>> On 10-Sep-2017 12:39 AM, "Dan9er" <[email protected]> wrote: >>>> >>>> Ok, I made a sh that runs tesstrain.sh with all 562 compatible fonts. >>>> But now I'm getting an error saying ./langdata/common.punc does not >>>> exist... https://pastebin.com/8aaMjH6k >>>> >>>> On Saturday, September 9, 2017 at 12:51:45 PM UTC-4, shree wrote: >>>> >>>>> Your command needs to be on the following lines: >>>>> >>>>> training/tesstrain.sh \ >>>>> --fonts_dir /home/shree/.fonts \ >>>>> --tessdata_dir ./tessdata \ >>>>> --training_text ../langdata/ben/ben.training_text \ >>>>> --langdata_dir ../langdata \ >>>>> --lang ben \ >>>>> --linedata_only \ >>>>> --noextract_font_properties \ >>>>> --exposures "0" \ >>>>> --fontlist "e-Grantamil" \ >>>>> "e-Grantha OT" \ >>>>> --output_dir ~/tesstutorial/ben >>>>> >>>>> See the fontlist argument, it is quoted names of the fonts. You can >>>>> put one on each line with \ >>>>> >>>>> >>>>> >>>>> ShreeDevi >>>>> ____________________________________________________________ >>>>> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com >>>>> >>>>> On Sat, Sep 9, 2017 at 10:12 PM, Dan9er <[email protected]> wrote: >>>>> >>>>>> Nope. 😢 >>>>>> https://pastebin.com/BskUsSm7 >>>>>> >>>>>> On Saturday, September 9, 2017 at 11:57:18 AM UTC-4, Dan9er wrote: >>>>>>> >>>>>>> I think I now know how to do it. >>>>>>> >>>>>>> I have to run training/text2image --find_fonts and then set the >>>>>>> tesstrain --fontlist flag to the file that is generated. >>>>>>> >>>>>>> On Thursday, September 7, 2017, at 2:19:09 PM UTC-4, Dan9er wrote: >>>>>>>> >>>>>>>> I'm trying to train tesseract using tesstrain and I'm getting this >>>>>>>> error: https://pastebin.com/xJj3w9jZ >>>>>>>> >>>>>>> -- >>>>>> 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 post to this group, send email to [email protected]. >>>>>> >>>>>> 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/ee1d68eb-a92c-4a30-905f-ac52128bccb6%40googlegroups.com >>>>>> >>>>>> <https://groups.google.com/d/msgid/tesseract-ocr/ee1d68eb-a92c-4a30-905f-ac52128bccb6%40googlegroups.com?utm_medium=email&utm_source=footer> >>>>>> . >>>>>> >>>>>> For more options, visit https://groups.google.com/d/optout. >>>>>> >>>>> >>>>> -- >>>> 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 post to this group, send email to [email protected]. >>>> 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/43979ac1-6555-4ae3-a6da-330c3b0dce16%40googlegroups.com >>>> >>>> <https://groups.google.com/d/msgid/tesseract-ocr/43979ac1-6555-4ae3-a6da-330c3b0dce16%40googlegroups.com?utm_medium=email&utm_source=footer> >>>> . >>>> >>>> For more options, visit https://groups.google.com/d/optout. >>>> >>>> >>>> -- >>> 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 post to this group, send email to [email protected]. >>> 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/5c2e194a-ffbf-44f8-b0a1-42693ea70d69%40googlegroups.com >>> >>> <https://groups.google.com/d/msgid/tesseract-ocr/5c2e194a-ffbf-44f8-b0a1-42693ea70d69%40googlegroups.com?utm_medium=email&utm_source=footer> >>> . >>> For more options, visit https://groups.google.com/d/optout. >>> >> >> -- 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 post to this group, send email to [email protected]. 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/28c96dfd-b705-4d28-a26c-616503fd665d%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
