On Thu, Oct 27, 2022 at 11:21 PM Keith Lofstrom <[email protected]> wrote:
> I will clarify a bit - > > Lately I've encountered MANY pages of photocopied Russian > and Cyrillic, some sent by my respondents, some with the > name Кит Лофстром in them, and I want to suss out roughly > what they are before I select a few for professional > translation, the $$$ kind. > > Sorry, I didn't realize that you were starting with images. The quickest way to input the text would probably be to run the image through tesseract, specifying the language it's in. I've found it does a pretty good job. (You might still have to fix the smudges, but it might even be able to figure those out from its dictionary.)
