yanouyuan-bit/scanned-pdf-to-docx

Workflow + toolkit to turn scanned PDFs (classical Chinese / old typeset books, no text layer) into clean structured Word via MinerU OCR and a three-tier proofread. Packaged as a Claude skill.

语言：Python · GitHub 星标：19 · Fork：1

话题：chinese-characters · pdf-converter · translation-management

在 GitHub 上查看原仓库