PaddleOCR-VL

GPU-accelerated document parsing and OCR via PaddleOCR-VL. Detects layout, recognizes Chinese/English text, tables, charts, and seals in images. Use when the user asks to OCR an image, extract text from a document, parse a screenshot, or recognize text in photos. Supports vertical classical Chinese text, modern newspaper layouts, and mixed-content documents.

by @jessy-huang (Jessy-Huang)·MIT-0