📦 Ocr Local 1.0.0 — Ocr Local — 本地OCR文字识别
v1.0.0使用 Tesseract.js 在本地完成图片文字识别，无需 API Key，支持简体中文、繁体中文和英文三种语言。
0· 0·0 当前·0 累计
by @nvoicejacob
运行时依赖
无特殊依赖
安装命令
点击复制官方npx clawhub@latest install ocr-local-1-0-0
镜像加速npx clawhub@latest install ocr-local-1-0-0 --registry https://cn.longxiaskill.com
技能文档
Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English.
Features
- 100% Local: All OCR processing happens in your browser using Tesseract.js
- No API Key Required: No external services or API keys needed
- Multi-language Support: Supports Simplified Chinese, Traditional Chinese, and English
- Easy to Use: Simple image input and text output
Usage
Input
Provide an image file (PNG, JPG, JPEG, GIF, BMP, WebP) containing text.
Output
Returns the extracted text from the image.
Example
Input: Image with Chinese text "你好世界"
Output: "你好世界"
Limitations
- Image quality significantly affects OCR accuracy
- Complex layouts or handwritten text may not be recognized accurately
- First-time use requires downloading language models (may take time)
Technical Details
- Uses Tesseract.js v5
- Supports multiple languages: chi_sim (Simplified Chinese), chi_tra (Traditional Chinese), eng (English)
- Default language: chi_sim+eng (Chinese Simplified + English)