LTSLegendary
PaddlePaddle/PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- Owner
- PaddlePaddle (organization)
- Stars
- Stars: 92,093
- Forks
- Forks: 11,606
- Language
- Python
- License
- Apache-2.0
- Created
- 2020
- Topics
- ocrchineseocrpdf2markdownpp-ocrpp-structuredocument-parsingdocument-translationkieai4sciencepdf-extractor-rag
- Tier
- LTS (20,000 ★ and up) What this tier means
More repos by PaddlePaddle
All 67 repos by PaddlePaddle- PaddlePaddle/PaddleStars: 24,135C++LTS
- PaddlePaddle/PaddleDetectionStars: 14,452PythonStable
- PaddlePaddle/PaddleNLPStars: 12,984PythonStable
- PaddlePaddle/PaddleFormersStars: 12,969PythonStable
- PaddlePaddle/PaddleSpeechStars: 12,701PythonStable
- PaddlePaddle/PaddleSegStars: 9,415PythonStable
Nearby in Python
All Python repos- 3b1b/manimStars: 95,978PythonLTS
- sherlock-project/sherlockStars: 95,394PythonLTS
- odysseus-dev/odysseusStars: 94,899PythonLTS
- D4Vinci/ScraplingStars: 91,937PythonLTS
- home-assistant/coreStars: 91,898PythonLTS
- django/djangoStars: 91,710PythonLTS