LLMob is an intuitive framework that builds reasoning logic for LLMs in the context of personal activity trajectory generation.

Aiming to achieve ultimate Multilingual TTS pipeline with main focus on releasing COQUI🐸TTS(Text-to-Speech) based high performing neural voice cloning systems for Bangla for the first time, supporting different SOTA models for Bangla and also Multilingual (Arabic+Bengali) code mixed TTS pipeline.

An interactive educational game built for the Google Gemma 3n Impact Challenge.

Learn AI's role in addressing complex challenges. Build skills combining human and machine intelligence for positive real-world impact using AI

Cross Lingual Language models for making search engines for Holy Quran and Sahih Hadiths

Repository for the paper "Deciphering Environmental Air Pollution with Large Scale City Data", IJCAI 2022

AI-powered flood intelligence system featuring h2oGPTe Agent + NVIDIA NIM integration (A2A), NAT pipeline with Nemotron 49B, and real-time flood risk assessment. Part of NVIDIA–H2O.ai AI for Good Blueprint for disaster response and monitoring.

A Flutter mobile app prototype assisting blind and low-vision (BLV) users with real-time scene understanding, text reading (OCR), and live analysis. Powered by a clean Python/FastAPI backend that leverages Google's Gemini AI models.

AI for Good Specialisation by DeepLearning.ai

LyricMind is an AI-powered cognitive firewall that analyzes song lyrics to protect against unconscious absorption of harmful content. Using customizable frameworks and LLMs, it detects risky patterns and integrates with music players to trigger protective actions when thresholds are exceeded.

Hackathon winner at AI Engineer World Fair Hackathon: Transforming code, one function at a time, to reduce digital carbon footprints and create a more sustainable digital world.

Online Knowledge Graph Embeddings on Social Media(Twitter) in the Health care Field

AI-powered tool that translates Makaton gestures into English using computer vision and assistive AI.

Medical imaging diagnosis assistant that can detect diseases from X-rays, MRIs, and CT scans with expert-level accuracy - healthcare-focused computer vision.

An AI-powered embedded system that captures real-time images, generates descriptive captions using Qwen, and reads them out loud to assist the visually impaired.

A compassionate AI assistant that provides dignified access to social support. Built for the GNEC Hackathon 2025.

🌍 Decentralized Global Wisdom Network on Bittensor

AI-powered real-time sign language accessibility proposal for media, education, and public communication. Public-good licensed

This project is an AI-powered pothole monitoring platform that detects road defects using YOLO, allows citizens to report issues, and provides administrators with a dashboard to track and resolve them. It combines computer vision, backend automation, and user interfaces to make road maintenance faster and smarter.

Founder & CEO @HearMeTech. Building AI to give my godson and others with speech impairments their voice. Giving everyone the power to be heard.