Tajik, pdf text image convert to txt
https://github.com/tesseract-ocr/tesseract
tesseract for OCR
first install tesseract
download Tajik model: tgk.traineddata from https://github.com/tesseract-ocr/tessdata
copy tgk.traineddata /tessdata
command to check path of "tessdata" and list of languages
$ tesseract --list-langs