package.json

{
    "name": "ocr-dataset-generator",
    "version": "1.0.0",
    "description": "Synthetic Text Recognition Dataset Generator for Low-Resource Languages",
    "main": "dist/index.js",
    "type": "module",
    "scripts": {
        "build": "tsc",
        "start": "node dist/index.js",
        "dev": "tsx src/index.ts",
        "generate": "tsx src/index.ts generate",
        "stats": "tsx src/index.ts stats"
    },
    "keywords": [
        "ocr",
        "dataset",
        "synthetic",
        "text-recognition",
        "kashmiri",
        "unicode",
        "crnn",
        "trocr",
        "paddleocr"
    ],
    "author": "",
    "license": "MIT",
    "devDependencies": {
        "@types/node": "^20.10.0",
        "tsx": "^4.7.0",
        "typescript": "^5.3.0"
    },
    "dependencies": {
        "sharp": "^0.33.0",
        "yaml": "^2.3.4",
        "uuid": "^9.0.1",
        "cli-progress": "^3.12.0",
        "chalk": "^5.3.0",
        "commander": "^11.1.0",
        "lmdb": "^3.0.0",
        "text-to-svg": "^3.1.5"
    },
    "engines": {
        "node": ">=18.0.0"
    }
}