This wasn't included in the readme file but some info for anyone else lost.
You can change the language model to download by editing this:
aria2c "https://github.com/tesseract-ocr/tessdata/blob/main/por.traineddata?raw=true" --dir="%TESSDATA_PREFIX%"
And change the language prefix to which language you want. As long as its available on the tesseract repo. For example here is Swedish - "swe":
To change default language edit pdf2pdfocr.py on line 548 from Portuguese + English - "por+eng" to whichever. For me I use Swedish + English - "swe+eng"
self.tess_langs = "por+eng" # Default
to
self.tess_langs = "swe+eng" # Default
This wasn't included in the readme file but some info for anyone else lost. You can change the language model to download by editing this:![bild](https://user-images.githubusercontent.com/49168045/194847930-fc81a6e0-3143-4c69-9874-c27bc8b64c50.png)
aria2c "https://github.com/tesseract-ocr/tessdata/blob/main/por.traineddata?raw=true" --dir="%TESSDATA_PREFIX%"
And change the language prefix to which language you want. As long as its available on the tesseract repo. For example here is Swedish - "swe":Further info here: https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#LANGUAGES
To change default language edit pdf2pdfocr.py on line 548 from Portuguese + English - "por+eng" to whichever. For me I use Swedish + English - "swe+eng"
self.tess_langs = "por+eng" # Default
toself.tess_langs = "swe+eng" # Default
For example to get Swedish![bild](https://user-images.githubusercontent.com/49168045/194847498-442ec62e-564b-4380-98ff-68810cff501c.png)