PDF scientific paper translation and bilingual comparison based on font rules and deep learning, preserving formula and figure layout.

pip install pdf2zh

Execute the translation command in the command line to generate the translated document example-zh.pdf and the bilingual document example-dual.pdf in the current directory.

pdf2zh example.pdf

pdf2zh example.pdf -p 1-3,5

pdf2zh example.pdf -li en -lo ja

Hint: Starting from \ufb00 is English style ligature.

pdf2zh BDA3.pdf -f "(CM[^RT].*|MS.*|XY.*|MT.*|BL.*|.*0700|.*0500|.*Italic)" -c "(\(|\||\)|\+|=|\d|[\u0080-\ufaff])"

Document merging: PyMuPDF

Document parsing: Pdfminer.six

Multi-threaded translation: MathTranslate

Layout parsing: LayoutParser