nlp-machine-learning

VerifAI initiative to build open-source easy-to-deploy generative question-answering engine that can reference and verify answers for correctness (using posteriori model)

Hello everyone this repo will contain my journey of machine learning and DeepLearning with some exciting projects

Retrieval Augmented Generation Examples - Original, GPT based, Semantic Search based.

FoodBERT: Food Extraction with DistilBERT

Data extraction with Donut ML model

Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.

13 projects using ChatGPT API, Whisper, Embeddings, and DALL-E with Python.

This will contain the code for the 2nd edition of NLP with TensorFlow (Edition 2)

Automatically generate multi-language subtitles using AWS AI/ML services. Machine generated subtitles can be edited to improve accuracy and downstream tracks will automatically be regenerated based on the edits. Built on Media Insights Engine (https://github.com/awslabs/aws-media-insights-engine)

Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polish Language

"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 set of jupyter notebooks

An intelligent full-stack insurance claim decision-making system that combines FastAPI backend with React TypeScript frontend, powered by Hugging Face Transformers and Gemma LLM. This AI agent analyzes insurance clauses and customer queries to predict whether a claim should be Approved or Rejected, along with justification and estimated amounts.

MinimalGPT is a concise, adaptable, and streamlined code framework that encompasses the essential components necessary for the construction, training, inference, and fine-tuning of the GPT model. This framework is implemented exclusively using Keras and TensorFlow, ensuring compatibility and coherence within the broader deep learning ecosystem.

Summarizes podcasts from RSS feed URL using whisperX and GPT3.5 APIs from OpenAI

"Solace AI: Your Empathetic Digital Confidant": Solace AI is an empathetic mental health companion that understands your emotions and personality to provide personalized support through natural conversations. It creates a judgment-free space where you can express yourself freely and receive compassionate guidance tailored just for you.

Developing a classifier to detect instances of racism and xenophobia in English sentences

Open source voice bot for Humanoid Robots and virtual digital humans

Built a GUI application using Tkinter that helps Doctors to prepare prescriptions more efficiently. This uses speech to text conversion and text extraction to prepare prescriptions in the correct format. This project is submitted for Smart India Hackathon 2020.

A Question Generation Application leveraging RAG and Weaviate vector store to be able to retrieve relative contexts and generate a more useful answer-aware questions