RapidAI/RapidOCR

📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

What it solves

RapidOCR provides a fast, open-source Optical Character Recognition (OCR) tool designed for rapid offline deployment across multiple platforms and languages. It addresses the engineering hurdles of deploying deep learning OCR models on terminal devices by simplifying the inference process.

How it works

The project converts models from PaddleOCR into the highly compatible ONNX format. This conversion allows the tool to achieve high speed and low resource consumption while maintaining accuracy. It supports multiple inference engines (such as ONNX Runtime, TensorRT, OpenVINO, and PyTorch) and is ported to several programming languages including Python, C++, Java, and C#.

Who it’s for

Developers who need to integrate high-performance OCR capabilities into their applications without relying on cloud services, and those who want to customize OCR recognition for specific scenarios through fine-tuning.

Highlights

  • Multi-platform & Multi-language: Supports Linux, Windows, and Mac, with core components available in Python, C++, Java, and C#.
  • Extensive Compatibility: Works with various inference engines like ONNX Runtime, TensorRT, and OpenVINO.
  • Rapid Deployment: Designed for simple operation and fast response times with low resource overhead.
  • Customizable: Allows users to fine-tune models using their own data via PaddleOCR and then deploy them through RapidOCR.

Related

  • Project
    PaddlePaddle/PaddleOCR

    PaddleOCR is an open‑source OCR and document‑AI toolkit that converts images or PDFs into structured, LLM‑ready text, tables and markdown/JSON. It offers multilingual scene‑text models (PP‑OCRv6) and lightweight vision‑language models (PaddleOCR‑VL, PP‑StructureV3) with state‑of‑the‑art accuracy, fast CPU/GPU inference, and deployment options ranging from Docker to browser SDKs. Integrated with RAG platforms like Dify and RAGFlow, it serves as a data‑engine for building AI agents and retrieval‑augmented generation pipelines.

  • Project
    zibo-chen/ocr-rs

    A lightweight Rust OCR library based on PaddleOCR models and the MNN inference runtime, providing text detection and recognition across 50+ languages.

  • Project
    sdcb/PaddleSharp

    A .NET wrapper for the PaddleInference C API that enables C# developers to use PaddlePaddle AI models for OCR, object detection, and NLP.

  • Project
    microsoft/onnxruntime

    A cross-platform machine learning accelerator that optimizes inference and training for models from various frameworks like PyTorch and TensorFlow.

  • Project
    Topdu/OpenOCR

    OpenOCR is an open‑source OCR toolkit from Fudan University that provides lightweight (≈0.1 B‑parameter) models for full‑document parsing, unified text‑formula‑table recognition, and a high‑performance SVTRv2‑based OCR system. It includes ready‑to‑run demos, training scripts, and benchmarks, targeting both research and real‑world deployment.