Stars
A CLI used to complete coding challenges and lessons on Boot.dev
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
Simple, open source team messaging platform
project for digitizing paper versions of blood tests for future data mining into sqlite db
Overview and tutorial of the LangChain Library
Analytical and Machine Learning modelling for Assam's Flood Response and Management.
A webscraper based on the selenium webdriver to scrape data off of indian real-estate websites
KeyCastr, an open-source keystroke visualizer
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Latitude/Longitude and Name data for Indian electoral polling stations (data and scraper included)
Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"
Raspberry Pi Pico based automated watering system for your garden
A home for the data that powers the PhonePe Pulse website.
collection of Indian open government data related scripts.
Jupyter notebook client in Emacs
Worldwide building footprints derived from satellite imagery
A Unified Toolkit for Deep Learning Based Document Image Analysis
The Dakshina dataset is a collection of text in both Latin and native scripts for 12 South Asian languages. For each language, the dataset includes a large collection of native script Wikipedia tex…
Resources and tools for Indian language Natural Language Processing
The project aims on adding a state-of-the-art transliteration module for cross transliterations among all Indian languages including English.
Python package for indic script transliteration
indicTranslate v1 - Machine Translation for 11 Indic languages. For latest v2, check: https://github.com/AI4Bharat/IndicTrans2
Awesome List of Tamil NLP & AI Resources
📝A text file containing 150,000 Urdu words for all your dictionary/word-based projects e.g: auto-completion / autosuggestion.