Amit Dovev

Yes, thank you. Please open a draft PR with that code. I'll push the needed changes to your PR.

Stefan, There are two ways to implement `intsimdmatrixavx512vnni.cpp`: 1) The 'right and complete way', which is also the 'complex way': a) First convert `intsimdmatrixavx2.cpp` to `intsimdmatrixavx512.cpp`. b) Then convert `intsimdmatrixavx512.cpp`...

> `intsimdmatrixavx512vnni.cpp`? Fixed :-)

https://github.com/tesseract-ocr/tesseract/issues/2155#issuecomment-622163609

Using `-c paragraph_text_based=false` does not help in this case.

To be able to use @stweil suggestion, you need to install [ocr-fileformat](https://github.com/UB-Mannheim/ocr-fileformat#system-wide).

>any ideas or suggestions on how to continue, given the above info/options? I don't have any suggestion. It's hard to improve Tesseract's layout analysis code since it very complex. As...

`text2image --list_available_fonts --fonts_dir FontsRashi/Working` This is wrong usage of the command. It should be: `text2image --list_available_fonts --fonts_dir=/fullpath/to/FontsRashi/Working`

> Maybe related issue: [amitdo/text2tif-2016#5](https://github.com/amitdo/text2tif-2016/issues/5). :-) It seems that the list we produce may contain fonts that Pango can't render (not otf/ttf fonts). Maybe there is a way to filter...

https://github.com/tesseract-ocr/tesseract/issues/1900