PaddleOCR VL

PaddleOCR VL

PaddleOCR-VL 1.5 Multilingual Document Parsing via a 0.9B VLM

78,625GitHub
❤️2
Description

The SOTA and resource-efficient model tailored for document parsing, that supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption.

Screenshots
Screenshot 1
Screenshot 2
Screenshot 3
Mobile Screenshots
Mobile Screenshot 1
Mobile Screenshot 2
Mobile Screenshot 3
App Information
Version
1.5.0
Package Size
770.75 KB
Image Size
49.53 MB
Updated
March 4, 2026
Source Code
PaddlePaddle
Platform Support
PCMobile
Keywords
paddleocrmodelapppdfprompt