Open freetosmash opened 1 year ago
For extracting text from PDFs, you might want to look at doctr and for translation, you can check the translation backends this project uses
@tak2hu the image is rasterized and turned into pixels. What’s needed to fix that is create an overlay and lay it over the original pdf.
so preprocess the pdf into multiple pngs and just output as pdf. I tried it with my pdf renderer and no background and overlayed the images manually. It works so it could be added to #395
What would your feature do?
I would like to inquire if there is a feature available for translating the entire PDF document. I have some Japanese vertical format books that I find difficult to read, and I am searching for relevant tools. I feel that your tool might be able to assist me, but I am unsure if it can translate the entire book. Thank you.