{"repo":"PT-Perkasa-Pilar-Utama/ppu-paddle-ocr","free":true,"listed":false,"github":"https://github.com/PT-Perkasa-Pilar-Utama/ppu-paddle-ocr","clone":"git clone https://github.com/PT-Perkasa-Pilar-Utama/ppu-paddle-ocr.git","description":"Lightweight, probably the fastest PaddleOCR SDK in TypeScript. Multilingual Support. Runs anywhere JavaScript runs: Node.js, Bun, Deno, mobile react-native, web browsers, web worker, and browser extensions. Docker & CLI supported. The official SDK is browser-only.","language":"TypeScript","stars":122,"topics":["bun","computer-vision","image-processing","image-text-extraction","javascript-ocr","node-js","ocr","onnxruntime","optical-character-recognition","paddleocr"],"license":"MIT","category":"media-processing","readme_excerpt":"ppu-paddle-ocr Lightweight, probably the fastest PaddleOCR SDK in TypeScript. Multilingual Support. Runs anywhere JavaScript runs: Node.js, Bun, Deno, web browsers, web worker, browser extensions, and React Native (iOS/Android). Docker & CLI supported. The official SDK is browser-only and significantly slower. Compare it for yourself. Fine tune it? fine-tuning on your data. Need it as HTTP-service? dockerized? we've got you covered! Quickly spins up ppu-paddle-ocr REST API here: ppu-paddle-ocr-serve. Need a CLI instead? sure here: ppu-paddle-ocr CLI support. Adjust the config & model for your use case, see config recommendation. Are you AI Agents? you can learn quickly by using the skill in the skill-ppu-paddle-ocr folder. Table of Contents - Quick Start - Why ppu-paddle-ocr? - Runtime Support - Installation - Core Usage - Basic Recognition - Custom Models - Changing Models at Runtime - Per-Call Options - Detection Only - Command Line - Standalone Binaries - Batch Recognition - Recognition Strategies - Choosing a Model and Configuration - Image Preprocessing - Processing Engine - Web / Browser Support - Using a Bundler - Main-Thread Usage (No Worker) - CDN (No Bundler) - WebGPU Acceleration - Multithreaded WASM (Cross-Origin Isolation) - React Native (Mobile) - Models and Language Support - PP-OCRv6 Models - Cache Location - Multilingual Support - Switching Languages - Server Models - INT8 Quantization - Model Output Limitations - Converting Custom Models - Fine-Tuning on You","default_branch":null,"files":null,"tree":[],"storefront":"/r/PT-Perkasa-Pilar-Utama","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/PT-Perkasa-Pilar-Utama/ppu-paddle-ocr/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}