ppu-paddle-ocr
Fast multilingual OCR for every JavaScript runtime
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install ppu-paddle-ocr?▼
Run `npx skills add PT-Perkasa-Pilar-Utama/ppu-paddle-ocr --all -g -y` in your terminal to install this skill globally.
How to run OCR in Node.js or the browser?▼
Import PaddleOcrService from the matching entry point, call initialize() once, then recognize() with an image path, URL, or buffer. The same API works across Node, Bun, Deno, browsers, and React Native.
Does ppu-paddle-ocr support multiple languages?▼
Yes. The default PP-OCRv6 model covers 50+ languages including Chinese, Japanese, Arabic, Indic, and Latin scripts, and you can swap recognition models and dictionaries at runtime.
Can I use ppu-paddle-ocr in React Native apps?▼
Yes. Use the /mobile entry point with onnxruntime-react-native and Skia, targeting RN 0.74+ or Expo SDK 51+ with a dev client.
How to speed up OCR in the browser?▼
The web build automatically uses WebGPU when available for 2-5x faster inference, falling back to WASM otherwise with no code changes needed.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core