discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
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.
History and source changes · Reports and owner responses · Compare
Similar
- opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Why this match
topics ai4science, ocr, pdf-extractor-rag
- opendataloader-project/opendataloader-pdf
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
Why this match
topics document-parsing, ocr, pdf-parser; language differs: Python → Java
- datalab-to/chandra
OCR model that handles complex tables, forms, handwriting with full layout.
Why this match
topics ocr
- run-llama/liteparse
A fast, helpful, and open-source document parser
Why this match
topics ocr, pdf-parser; language differs: Python → Rust
- getomni-ai/zerox
OCR & Document Extraction using vision models
Why this match
topics ocr; language differs: Python → TypeScript; license differs: Apache-2.0 → MIT
- bytedance/Dolphin
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Why this match
topics ocr, pdf-parser
- mindee/doctr
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
Why this match
topics document-parsing, ocr
- tesseract-ocr/tessdata
Trained models with fast variant of the "best" LSTM models + legacy models
Why this match
topics ocr