"Open Source Models with Hugging Face" course empowers you with the skills to leverage open-source models from the Hugging Face Hub for various tasks in NLP, audio, image, and multimodal domains.

A Python-based REST API for PDF OCR using AI models with PyTorch and Transformers that runs in a Docker container.

llm-newsletter-generator transforms a valid RSS feed into a "Newsletter" using AI models via PyTorch and Transformers; this is experimental.

A real-time voice-to-text and text-to-speech AI pipeline using Whisper, an LLM, and Edge-TTS with tunable parameters for low-latency audio processing and response generation.

Examples of Ai models from Scikit-learn

Successfully developed a fine-tuned BERT transformer model which can accurately classify symptoms to their corresponding diseases upto an accuracy of 89%.

A FastAPI-powered REST API offering a comprehensive suite of natural language processing services using machine learning models with PyTorch and Transformers, packaged in a Docker container to run efficiently.

Toxic Text Detector is a production-ready web and browser extension application that identifies toxic, abusive, and inappropriate language in real-time. Built with FastAPI and Hugging Face's state-of-the-art Toxic-BERT model, it detects toxicity across six categories: toxicity, severe toxicity, obscene, threat, insult, identity attack.

This repository contains application which performs YouTube video transcription, translation, summarization and also provides Q&A chatbot.

The Ultimate Hugging Face Guide: From Beginner to Pro

Build a Secure AI App with FastAPI, LangChain, and Hugging Face Transformers

A robust pipeline for fine-tuning language models using advanced techniques like LoRA (Low-Rank Adaptation), QLoRA (Quantized LoRA), and custom tokenization.

With the use of AI, summarise your movies and bring back the colour in older films.

This project contains codes and paperwork based on the course CSI5386 at University of Ottawa (delivered by Professor Dr. Diana Inkpen).

Explore and implement Hugging Face Transformers and Pipelines for leveraging powerful pretrained AI models in NLP and more.

A CLI tool for estimating GPU VRAM requirements for Hugging Face models, supporting various data types, parallelization strategies, and fine-tuning scenarios like LoRA.

Medical document classifier by fine-tuning a pre-trained Bio_ClinicalBERT model on a dataset of clinical texts which achieved a test accuracy of 81.08% in classifying documents across 13+ medical specialties

Build a sentiment analysis tool that processes user reviews from various platforms (like Amazon or Yelp) and provides insights on sentiment trends over time. Use advanced NLP techniques like Transformers (BERT, GPT).

A Python-based intelligent chatbot built with Gradio UI and SmolAgents, capable of answering user queries using agentic reasoning, retrieval-augmented generation (RAG), and tool integrations.

An interactive, privacy-first application for querying the European Union’s AI Act using a local Retrieval-Augmented Generation (RAG) pipeline. Combines semantic search (FAISS) and a quantized TinyLlama LLM for fast, accurate, and context-aware answers—all running on your own hardware.