I would like to train the tesseract with hundreds of my fonts. My fonts name are numbers and their format like "22.ttf". For creating traineddata I use the tesstrain.sh script like this: tesseract-ocr/tesseract/src/training/tesstrain.sh \ --fonts_dir processed_fonts \ --lang eng \ --langdata_dir tesseract-ocr/langdata \ --tessdata_dir tesseract-ocr/tesseract/tessdata --training_text tesseract-ocr/langdata/eng/eng.training_text \ --output_dir output \ --linedata_only \ --fontlist "1.ttf" "2.ttf" "3.ttf" "4.ttf" "7.ttf" "8.ttf" "10.ttf" "11.ttf" "12.ttf" "13.ttf" "15.ttf" "16.ttf" "17.ttf" "18.ttf" "19.ttf" "20.ttf" "22.ttf" "23.ttf" "25.ttf" "26.ttf" "31.ttf" "32.ttf" "33.ttf" "36.ttf" "38.ttf" "39.ttf" "40.ttf" "41.ttf" "42.ttf" "44.ttf" "52.ttf" "53.ttf" "54.ttf" "55.ttf" "56.ttf" "58.ttf" "59.ttf" "60.ttf" "61.ttf" "62.ttf" "64.ttf" "65.ttf" "67.ttf" "68.ttf" "69.ttf" "70.ttf" "71.ttf" "72.ttf" "73.ttf" "75.ttf" "76.ttf" "79.ttf" "80.ttf" "81.ttf" "82.ttf" "83.ttf" "89.ttf" "90.ttf" "91.ttf" "94.ttf" "95.ttf" "96.ttf" "97.ttf" "98.ttf" "100.ttf" I did not update my cloned repo for a while but I did this a few days ago. Since then this command does not work as I expected. It process the first 8 font and than stop the procession without any error. It does not create traineddata just som tif and box files into a temp directory.
What am I doing wrong? Do some constraints come into the training data process to limit the data creating with the recent (last 3 months) updates? -- 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/f3d41ee8-4ef3-48c6-a608-6090d1826869%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
