Kashmiri AI

No Kashmiri translation of this site yet. The reason is bigger than one website.

Kashmiri AI is building tools that read, write, translate and speak Kashmiri properly, with the people who speak it. Shabrang Films founder Mir Afnaan Nissar started the project, and its foundation, a dataset for the Kashmiri language, is in progress. Until it's ready, any Kashmiri on this site is written by Kashmiri speakers, not guessed by a machine.

Help build it

ا ب پ ت ٹ ج چ ژ د ڈ ر ڑ س ش ک گ ل م ن ۄ و ہ ؠ ٲ

Kashmiri adds its own letters, such as ٲ, ۄ and ؠ, to the Perso-Arabic script.

Why it isn't live yet

Too little written down

Translation tools learn from huge amounts of written and spoken language. For Kashmiri, very little of that exists in digital form, so machine translations come out wrong.

~7 million: people in India speak Kashmiri (Census of India, 2011).
1 of 22: scheduled languages of India, and an official language of Jammu & Kashmir since 2020.
3 scripts: Perso-Arabic (the official one), Devanagari and the historic Sharada.
Little data: Very little digitised text, recorded speech or translated text for AI to learn from.

How it's built

Dataset first, then models

First

Collect

Kashmiri text and recorded speech from people who write and speak it every day, in their own words and dialects.

Then

Check & pair

Correct spelling and meaning, pair sentences with English, Urdu or Hindi, and handle the letters only Kashmiri uses.

Finally

Train & test

Combine the team's own tools with open-source models, test them against real Kashmiri, and fix what they get wrong.