Thanks for your swift reply. It would be my pleasure to collaborate with you.
I've noticed that there is are extensive guides and tutorials regarding training tesseract 4.x, and I wanted to switch to 4.x version. I wanted to ask what would be the trade off if I used tesseract 4.x instead of 5.x ? Thanks for your time!!! On Saturday, January 13, 2024 at 12:49:36 PM UTC+3 elvi...@gmail.com wrote: > I spend some time trying to improve the default model of Amharic. I > default model has a couple of characters missing. As i have noted in many > posts in this forum, training by removing the top layer is the best method > to introduce new characters. > > But i really struggled because the training is deteriotating the base > (default) model. I also have the shortage of processing power. > Tesseract 5.3 also has some flaws which made it hard to use in the third > countries ( electric blackouts) > > Dear Menilik, we might need to put out hands together on this. > > On Sat, Jan 13, 2024, 11:21 AM Menelik Berhan <meneli...@gmail.com> wrote: > >> *Background* >> I'm trying to use tesseract 5.3.3 on scanned old books written in Amharic >> (which uses Ethiopic script). >> >> *Major Shortcomings of amh.traineddata from tesseract* >> >> *Difference in type of Ethiopic script:* there are Ethiopic script >> characters in old Amharic texts that are not used in the unicharset of >> amh.traineddata. >> >> *Difference in punctuation styles:* the old texts use some punctuations >> not used in modern Amharic, and also for some that are used in modern >> Amharic, the old texts have d/t pattern (mostly space b/n word and >> punctuation character --- while the old texts always put space b/n >> punctuation chars and both preceding and following words, in modern times >> these punctuation chars doesn't have space b/n them and the preceding word). >> >> *Very narrow training_text & wordlist (based on tesseract/langdata_lstm)* >> The amh.training_text & amh.wordlist text files used by tesseract (the >> one from langdata_lstm) is very small. (to give you an Idea: for >> tir.traineddata (another language which uses Ethiopic script) the >> tir.training_text from langdata_lstm has more than 400,000 lines while the >> amh.training_text has only around 400 lines) >> >> *Other challenges* >> >> - The old Amharic books use a font that's not in use (or available). >> - The old Amharic books contain many Ge'ez words (a liturgical >> language like latin which uses Ethiopic script). >> - The old Amharic books mostly use Ge'ez numbers, while modern >> Amharic texts use Arabic numbers. >> >> *WHAT I'VE DONE SO FAR* >> As an experiment I've tried to fine tune amh.traineddata_best (using >> `make training`) with close to 300 line images & texts (from sample pages >> of some old Amharic books) and using files from langdata_lstm (for 10,000 >> iterations). >> >> The resulting traineddata has a very satisfactory improvement in >> addressing some of the challenges mentioned above, especially those >> regarding punctuation chars. >> >> But it still fails to solve the problems I've with some characters (the >> ones not present in the unicharset of amh.traineddata) and fails for almost >> all Ge'ez numbers (eventhough the training sample pages have many Ge'ez >> nums). >> >> *WHAT I'M PLANNING TO DO* >> First I want to train tesseract with a large training_text & wordlist >> files, and also a complete unicharset file , >> Then fine tune the resulting traineddata based on sample line images from >> the old books. >> >> *QUESTIONS (for now. I'll definitely add more questions later)* >> Is there another path I should take that would get me to where I want? >> >> *Regarding training tesseract with large training_text & wordlist files, >> and also a complete unicharset file:* >> >> - How to prepare the training_text & wordlist file? (What the text >> files should contain) >> - How to prepare the unicharset file, and also how to pass it to the >> `make training` command ? >> >> >> *Regarding generating a text, image(tif) and box file from training_text:* >> >> I've looked up python scripts to do this job, but have question about the >> proper values for these params in text2image: >> --font (what criteria should I use to select the list of fonts), >> --leading, --xsize, --ysize, --char_spacing, --exposure, >> --unicharset_file and --margin. >> >> I've noticed from tesstrain repo for tesseract 5 that the line images are >> tightly cropped (with minimal margin around text line). Is the same >> property (minimal margins) required/desired of the line images generated >> using text2image from the training_text? >> >> *THANKS FOR YOUR TIME !!!* >> >> -- >> 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-oc...@googlegroups.com. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/tesseract-ocr/9bda9bc4-b07a-491b-b8fc-fbb25b54c368n%40googlegroups.com >> >> <https://groups.google.com/d/msgid/tesseract-ocr/9bda9bc4-b07a-491b-b8fc-fbb25b54c368n%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/bf4d57dc-a4ea-4157-8782-0acca178c9dan%40googlegroups.com.