开源雷达国内 GitHub 镜像站
加速通道已就绪 返回列表
全部项目

khang3004/SinoNomViet_Transliteration_OCR

🏮 OCR & transliteration pipeline for classical Sino-Vietnamese manuscripts — PaddleOCR + Right-to-Left layout analysis + 11,214-word Hán-Việt dictionary + S1∩S2 Levenshtein alignment. Digitizing "An Nam Nhất Thống Chí" (安南一統志) one character at a time.

语言:Jupyter Notebook · GitHub 星标:9 · Fork:4

话题:bounding-box · cultural-heritage · digital-humanities · document-intelligence · han-nom · han-viet · historical-texts · jupyter-notebook

在 GitHub 上查看原仓库

正在读取项目信息…