scanned-

Here is 1 public repository matching this topic...

angelqb / doc-corpus-ocr-engine

把一批不能上传的 PDF / Word / 扫描件在【本机离线】读成可关键词检索的正文库：扫描件走本地 OCR，电子版按原版式还原，并另出可编辑 Word。全程不上传任何文件。Offline local OCR & document-to-text pipeline for building a searchable corpus, no upload.

pdf ocr offline docx pytho chines local-first knowledge-b corpu document-searc scanned- text-extr windoews

Updated Nov 9, 2026

Add this topic to your repo

To associate your repository with the scanned- topic, visit your repo's landing page and select "manage topics."

Learn more