davron112/kaa-karakalpak-ocr

Tesseract OCR - Karakalpak Latin

Tesseract OCR trained data for Karakalpak language (Latin script).

Installation

Copy kaa.traineddata to your Tesseract tessdata directory:

# Linux
cp kaa.traineddata /usr/share/tesseract-ocr/4.00/tessdata/

# macOS (Homebrew)
cp kaa.traineddata /opt/homebrew/share/tessdata/

# Windows
copy kaa.traineddata C:\Program Files\Tesseract-OCR\tessdata\

Usage

CLI

tesseract image.png output -l kaa

Python

import pytesseract
from PIL import Image

text = pytesseract.image_to_string(Image.open('image.png'), lang='kaa')
print(text)

Node.js

const Tesseract = require('tesseract.js');

Tesseract.recognize('image.png', 'kaa').then(({ data: { text } }) => {
console.log(text);
});

Requirements

• Tesseract OCR 4.0+