UrduNLP

Braille is a tactile writing system used by visually impaired people. It can be read on embossed paper or using refreshable braille displays connecting to computers and smartphone devices. Braille can be written using a slate and stylus, a braille writer, an electronic braille notetaker, or a computer connected to a braille embosser. Liblouis is an open-source braille translator and back-translator named in honor of Louis Braille. It features support for computer and literary braille, supports contracted and uncontracted translation for many languages, and has support for hyphenation. New languages can easily be added through tables that support a rule- or dictionary-based approach. Tools for testing and debugging tables are also included. Install louis on your OS. git clone https://github.com/liblouis/liblouis cd liblouis ./configure make sudo make install sudo ldconfig To use it in Python you need to install it for Python 3 cd python sudo python3 setup.py install Now you can u

Generative AI is like a creative machine, using data to dream up new things! It can write poems, paint pictures, even compose music. Imagine: feeding it words and getting a story back, or showing it a sketch and having it design a building! It's still young, but its potential is mind-blowing. To generate the summary for the Urdu language, I have trained an LLM model. Here are the steps you can follow to train your own Generative AI model for summarization. Install required packages. pip install transformers [ torch ] datasets == 2 .14.5 evaluate rouge_score --quiet Import necessary libraries. from datasets import load_dataset from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, GenerationConfig, TrainingArguments, Trainer import torch import time import evaluate import pandas as pd import numpy as np Load Dataset huggingface_dataset_name = "mirfan899/usummary" dataset = load_dataset(huggingface_dataset_name) Load pretrained LLM model model_na