RapidOCR

An open-source OCR toolkit extracts text from images offline, with Chinese and English recognition and support for CPU and GPU inference.

RapidOCR is an OCR toolkit for developers who need to extract text from images within their own applications. It uses models derived from PaddleOCR and can run recognition offline on local hardware.

Text recognition: Recognize Chinese and English with the default models, or choose other available language models for your images.
Inference backends: Use ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT or PyTorch, with CPU and GPU options for different deployment needs.
Custom models: Use models fine-tuned through PaddleOCR on your own data when the provided models don't suit the text you need to recognize.
Application integration: Work with Python, C++, Java or C# components to add OCR to existing software; projects using RapidOCR include Docling, LangChain and Umi-OCR.

RapidOCR is free and open source under Apache 2.0. Recognition can run locally without sending images to a cloud OCR service. The source code and the supplied PaddleOCR-derived model artifacts use Apache 2.0 license terms.

The main repository contains the Python component, while the other language components live in separate repositories. Docker development environments cover the supported inference engines. The full documentation is in Chinese.

OCR and Document Scanning Inference Libraries and Bindings Docker AI for a modest PC Multilingual ONNX Works offline

Nobody has claimed RapidOCR yet

Work on RapidOCR? Claim this page and we'll verify you by hand. RapidOCR gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Similar to RapidOCR

View all tools

PaddleX

An open-source AI development toolkit for OCR, computer vision and time-series models, with local CPU or GPU inference and self-hosted deployment.

6.3KUpdated 4 months agoApache-2.0

Windows · Linux · Docker#Multilingual#ONNX

PaddleX is a low-code toolkit for developers building AI applications with PaddlePaddle models. It brings pretrained pipelines and model training into one tool for applications that process documents, images or time-series data.

Document Parsing for LLMsInference Libraries and BindingsOCR and Document ScanningTraining Frameworks

docTR

An open-source Python OCR library that extracts text from PDFs and images locally with PyTorch, CPU or GPU support, and document layout detection.

6.4KUpdated 2 days agoApache-2.0

Docker · Web

docTR reads text from PDFs and images for developers building document processing applications and researchers comparing OCR models. It locates individual words and recognizes their text on your own hardware.

Document Parsing for LLMsInference Libraries and BindingsOCR and Document Scanning

EasyOCR

3 videos

An open-source Python OCR library extracts text from photos and documents, supports multilingual images, and uses the Apache 2.0 license.

30.1KUpdated 11 months agoApache-2.0

Windows#Multilingual

EasyOCR is a Python library for developers adding text recognition to an application. It reads both text in photographs and dense document text.

Inference Libraries and BindingsOCR and Document Scanning

OpenDataLoader PDF

1 video

A local PDF parser that extracts Markdown, JSON and HTML with source coordinates, with optional AI processing and Apache 2.0 licensing.

30.1KUpdated 13 hours agoApache-2.0

macOS · Linux · Docker#Guardrails#Multilingual#ONNX

OpenDataLoader PDF is a PDF parser for developers building document search and retrieval-augmented generation systems. It preserves document structure and source locations so applications can retrieve passages and point readers back to the original page.

Document Parsing for LLMsOCR and Document Scanning

FunASR

An open-source speech-to-text toolkit supports offline files and live transcription on your hardware, with speaker labels and API serving.

20.9KUpdated 21 hours agoMIT

macOS · Windows · Linux · Docker#Batch processing#GGUF#llama.cpp backend

FunASR is a speech-to-text toolkit for developers building transcription services and voice applications. It supports offline recordings and live speech on local hardware or self-hosted servers, with capabilities that depend on the model and runtime.

Inference Libraries and BindingsInference Servers and ClustersSpeech-to-Text and Transcription

PDFMathTranslate

1 video

A scientific PDF translator that preserves layouts and formulas, supports Ollama and cloud services, and runs locally or in Docker.

38.1KUpdated 8 hours agoAGPL-3.0

macOS · Windows · Docker · Web#Batch processing#Hugging Face integration#MCP

PDFMathTranslate translates scientific papers for readers who need the text in another language while keeping equations and figures in context. It produces translated and bilingual PDFs so readers can compare the result with the original.

MCP Servers and Agent SkillsOCR and Document ScanningTranslation