You can check available fonts on your system by using --find_fonts with text2image, to find font names used by tesseract
example command with output - please modify path to match your setup *text2image --find_fonts --text ./langdata/eng/eng.training_text --outputbase ./langdata/eng/ --min_coverage 0.999 --fonts_dir=./fonts/* Total chars = 6694 Font AA_NAGARI_SHREE_L3 failed with 1865 hits = 27.86% Adobe Devanagari : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 0 to file ./langdata/eng/.Adobe_Devanagari.tif Akchyarunicode : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 1 to file ./langdata/eng/.Akchyarunicode.tif Akchyarunicode : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 2 to file ./langdata/eng/.Akchyarunicode.tif Arial Heavy : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 3 to file ./langdata/eng/.Arial_Heavy.tif Arial Italic Condensed : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 4 to file ./langdata/eng/.Arial_Italic_Condensed.tif Arial Unicode MS : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 5 to file ./langdata/eng/.Arial_Unicode_MS.tif Font BRH Devanagari failed with 6666 hits = 99.58% Font BRH Devanagari Extra failed with 6666 hits = 99.58% Font BRH Devanagari RN failed with 6666 hits = 99.58% Calibri Bold Italic : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 6 to file ./langdata/eng/.Calibri_Bold_Italic.tif Charter Indologique Capital : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 7 to file ./langdata/eng/.Charter_Indologique_Capital.tif Courier New Italic : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 8 to file ./langdata/eng/.Courier_New_Italic.tif Font GIST-DVOTKishor failed with 6645 hits = 99.27% Font GIST-DVOTMohini failed with 6645 hits = 99.27% Font GIST-MROTDhruv failed with 6645 hits = 99.27% Font GIST-MROTVinit failed with 6645 hits = 99.27% Font GIST-SDOTDhruv failed with 6645 hits = 99.27% Font GIST-SDOTVinit failed with 6645 hits = 99.27% Lohit Devanagari : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 9 to file ./langdata/eng/.Lohit_Devanagari.tif Old Standard Indologique Bold : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 10 to file ./langdata/eng/.Old_Standard_Indologique_Bold.tif Segoe UI : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 11 to file ./langdata/eng/.Segoe_UI.tif Segoe UI Heavy : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 12 to file ./langdata/eng/.Segoe_UI_Heavy.tif Font Sharad76 failed with 1510 hits = 22.56% Shobhika : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 13 to file ./langdata/eng/.Shobhika.tif Shobhika Bold : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 14 to file ./langdata/eng/.Shobhika_Bold.tif Tahoma Bold : 6694 hits = 100.00%, raw = 112 = 100.00% Rendered page 15 to file ./langdata/eng/.Tahoma_Bold.tif Font Yashomudra failed with 6648 hits = 99.31% Font Yashomudra Bold failed with 6648 hits = 99.31% Font Yashomudra Bold Italic failed with 6648 hits = 99.31% Font Yashomudra Italic failed with 6648 hits = 99.31% Font YashomudraLight failed with 6648 hits = 99.31% Font YashomudraLight Italic failed with 6648 hits = 99.31% Font YashomudraMedium failed with 6648 hits = 99.31% Font YashomudraMedium Italic failed with 6648 hits = 99.31% Font YashomudraSemiBold Bold failed with 6648 hits = 99.31% Font YashomudraSemiBold Bold Italic failed with 6648 hits = 99.31% ShreeDevi ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Thu, Feb 15, 2018 at 2:03 AM, Ernesto Borio <[email protected]> wrote: > When using text2image for training, I get the error: > > > $ text2image --text=charset.txt --outputbase=[eng].[ > HeroicCondensedBoldRegular].exp0 --font='Heroic Condensed Bold Regular' > --fonts_dir=. > > > (process:29818): Pango-WARNING **: couldn't load font "Heroic Bold > Condensed", modified variant/weight/stretch as fallback, expect ugly output. > > Could not find font named Heroic Condensed Bold Regular. > > Pango suggested font Helvetica. > > Please correct --font arg. > > The font is *Heroic Condensed Bold Regular* > At least, that's the full name that MacOS returns when I get info on the > font. > > What's wrong here? Am I naming the font incorrectly? > > I'm following this documentation: > https://github.com/tesseract-ocr/tesseract/wiki/Training- > Tesseract#questions-about-the-training-process > > Thanks! > > -- > 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/56836dc3-edd2-4712-b2a8-e69c8c478a0f% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/56836dc3-edd2-4712-b2a8-e69c8c478a0f%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/CAG2NduUsNQVGPXjRiGY30WDyQx1ob-_arkukUMu68HV1038H7w%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
