natural-language-processing

YouTube video summarization using Whisper audio transcription and GPT-based summaries.

DrFAQ is a plug-and-play question answering NLP chatbot that can be generally applied to any organisation's text corpora.

OLD Resume Matcher Website (Not used anymore)

Advanced NLP Workshop: word-sense disambiguation with RoBERTa and text summarization with BART (Machine Learning Milan)

Generate README.md with GPT-3 few-shot learning

Easy to use Multi-Provider ASR/Speech To Text and NLP engine

A comprehensive, professional guide explaining the differences, strengths, and best practices of Retrieval-Augmented Generation (RAG) and Fine-Tuning for LLMs, including workflows, comparisons, decision frameworks, and real-world hybrid AI use cases.

Detecting Fake News using AI

Empowering Data Driven insights through hands-on projects, SQL challenges and practical tools.

Code for Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense? [COLM 2024]

[ACL 2023] The code for our ACL'23 paper Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach

In this implementation, using the Flan T5 large language model, we performed the Text Classification task on the IMDB dataset and obtained a very good accuracy of 93%.

Implementation for the different ML tasks on Kaggle platform with GPUs.

A Smart Journaling App with NLP and Sentiment Analysis

The Odin Tabs extension is a browser extension that allows you to navigate through your browser tabs using speech recognition and the Large Language Model (LLM) of your choice.

Utils and modules for Speech Language and Multimodal processing using pytorch and pytorch lightning

Flan-t5-base model was fine-tuned on Nvidia Question and Answer Pair Dataset available on Kaggle. This is a beginner level project who wants to step in to the world of Large Language Models.

Trained Neural Networks (LSTM, HybridCNN/LSTM, PyramidCNN, Transformers, etc.) & comparison for the task of Hate Speech Detection on the OLID Dataset (Tweets).

A modular framework for building and deploying Retrieval-Augmented Generation (RAG) systems with built-in evaluation and monitoring.

Generate an accurate, timestamped transcript given an audio file and its text using Google Cloud's Speech-to-Text API via gRPC.