An NLP library for the Urdu language. It comes with a lot of battery included features to help you process Urdu data in the easiest way possible.

Repository dedicated to a collection of resources and helping material for Urdu language Processing related tasks

A simple python based Urdu stemmer which tries to find a stem word from a list of affixes.

A list of most frequently used Roman Urdu words with different spellings and usages to help make Roman Urdu text processing easier.

The first Urdu search engine crawler for web.

AI-based Train Reservation System that uses Urdu language to chat with it.

A Simple Handy Tool That Solves All Your Problem Related To Urdu Editing.

UrduFeel: Deep Learning Sentiment Analysis for Emotional Insights

List of Most Used or Stop Words of Urdu. Approximately 300 Words

This project contains Urdu characters and some preprocessing functions

We have presented a new dataset for question and answering models. Our dataset contains 27 different Urdu paragraphs which are taken from different available resources i.e Urdu Wikipedia, youtube and news articles etc. All selected paragraphs have an average of 3 to 7 questions along with their possible answers that range from 1 to 3. The data c…

This repository contains code for Urdu Text preprocessing natural language data for use in NLP applications.

An Extension to load Urdu's Nastaleeq fonts into websites on Firefox, Opera, Safari

Simple Roman to Urdu Translitration in Javascript

Urdu Spell & Grammar Checker: A Python app for accurate spell-checking and grammar correction in Urdu text.

This project is a grapheme-to-phoneme (G2P) converter for Urdu language. It can generate lexicons for Urdu words using a deep learning model.

This project aims to generate poetry in Roman Urdu using a dataset of poems by famous Urdu poets such as Allam Iqbal and Ghalib.

The Goal of this project was to create an RNN based model to convert roman urdu to urdu.

This project develops an effective spell correction system for Roman Urdu using the Noisy Channel model. 4 components: language model, error model, candidate generation, and selection model. Suggests the most likely correction for a given incorrect word using probabilistic approach.