Optical Character Recognition

Read the page. Keep the words.

Upload an image and Nawadiraat lifts the text out of it — in English, and in Urdu through urd_naw, the model we trained for Tesseract.

Recognising text

That time of year thou mayst in me behold

When yellow leaves, or none, or few, do hang

Upon those boughs which shake against the cold,

Bare ruined choirs, where late the sweet birds sang.

OCR is coming soon

We are still training the recognition models. This tool opens the moment a language is ready.

← Back to home

Open source

We gave Urdu to Tesseract

Nawadiraat trained and contributed urd_naw, an Urdu recognition model, to the Tesseract OCR project — so anyone, anywhere, can read Urdu text from images.

View urd_naw on tessdata_contrib

urd_naw.traineddata

model: urd_naw
language: Urdu · اردو
script: Nastaʼliq
project: tesseract-ocr
license: open source

Unlock the Power of Language & AI

Benefit from dictionaries, spell checkers, and character recognizers. A revolutionary step for students, teachers, researchers, and professionals from various fields and industries.

Lughaat

Empower the academic and research process through various Pakistani and international dictionaries.

Explore

Spell Checker

Detect and correct spelling mistakes across multiple languages.

Try Now

OCR

Convert images to editable text using advanced OCR technology.

Use OCR