📜 Description

A machine learning project that generates domain-specific text using clustering and fine-tuned language models. The system analyzes text from five distinct domains (Law, Science, Math, Fantasy, and Sci-Fi), creates embeddings, clusters them using dimensionality reduction, and generates contextually appropriate text for each domain using GPT-2 as a backbone.

⚙️ Features

• Text Chunking – Process and chunk large texts from multiple domains
• Semantic Embeddings – Generate embeddings using Sentence Transformers
• K-Means Clustering – Cluster text embeddings into domain-specific groups
• GPT-2 Fine-tuning – Trains a language model on domain-specific data
• Text Generation – Generate text based on selected domain