Resolved. There were mismatch between trainedata used. Tesseract installed was of version 4.1.0. And i was giving path of downloaded tesseract 4.0. It was causing issue.
On Saturday, April 24, 2021 at 8:25:26 PM UTC+5:30 [email protected] wrote: > Hi, > > I am running the following command to create trained data: > tesstrain.sh --fonts_dir /usr/share/fonts --lang eng --linedata_only > --fontlist "FreeMono" --noextract_font_properties --langdata_dir > /home/administrator/Downloads/tesseract-4.0.0/langdata --my_boxtiff_dir > /home/administrator/pooja/testImages/ --tessdata_dir > /home/administrator/Downloads/tesseract-4.0.0/tessdata --output_dir > /home/administrator/images/output_folder_1/ > > After this it is printing: > === Starting training for language 'eng' > [Sat Apr 24 20:15:19 IST 2021] /usr/local/bin/text2image > --fonts_dir=/usr/share/fonts --font=FreeMono > --outputbase=/tmp/font_tmp.e9Fi4vFUQQ/sample_text.txt > --text=/tmp/font_tmp.e9Fi4vFUQQ/sample_text.txt > --fontconfig_tmpdir=/tmp/font_tmp.e9Fi4vFUQQ > Rendered page 0 to file /tmp/font_tmp.e9Fi4vFUQQ/sample_text.txt.tif > > === Phase I: Generating training images === > Rendering using FreeMono > [Sat Apr 24 20:15:23 IST 2021] /usr/local/bin/text2image > --fontconfig_tmpdir=/tmp/font_tmp.e9Fi4vFUQQ --fonts_dir=/usr/share/fonts > --strip_unrenderable_words --leading=32 --xsize=3600 --char_spacing=0.0 > --exposure=0 --outputbase=/tmp/eng-2021-04-24.Y8g/eng.FreeMono.exp0 > --max_pages=0 --font=FreeMono > --text=/home/administrator/Downloads/tesseract-4.0.0/langdata/eng/eng.training_text > Rendered page 0 to file /tmp/eng-2021-04-24.Y8g/eng.FreeMono.exp0.tif > Rendered page 1 to file /tmp/eng-2021-04-24.Y8g/eng.FreeMono.exp0.tif > > === Phase UP: Generating unicharset and unichar properties files === > [Sat Apr 24 20:15:25 IST 2021] /usr/local/bin/unicharset_extractor > --output_unicharset /tmp/eng-2021-04-24.Y8g/eng.unicharset --norm_mode 1 > Usage: /usr/local/bin/unicharset_extractor [--output_unicharset filename] > [--norm_mode mode] box_or_text_file [...] > Where mode means: > 1=combine graphemes (use for Latin and other simple scripts) > 2=split graphemes (use for Indic/Khmer/Myanmar) > 3=pure unicode (use for Arabic/Hebrew/Thai/Tibetan) > > As per specification it should be end with: > Created starter traineddata for LSTM training of language 'eng' > Run 'lstmtraining' command to continue LSTM training for language 'eng > > Please help. > > Regards, > Pooja > -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/f701551e-045d-4ddd-85b3-9da204e9aceen%40googlegroups.com.
