This repo documents my exploration into natural language processing techniques through practical implementations. I also plan to add audio processing projects over time.
Current projects include:
LLM Chatbot: An conversational agent powered by model retrieval using the RAG framework
Disaster Tweet Classification: Categorizing tweets into disaster vs non-disaster tweets using text classification models
English to French Translation: Sequence-to-sequence neural machine translation from English to French
These provide hands-on experience with:
Text preprocessing and feature extraction
Sentiment analysis and text classification
Sequence modeling, attention mechanisms
Fine-tuning large language models
Over time I plan to continue expanding into other areas like:
Text generation with n-gram models and LSTMs
Named entity recognition
Question answering systems
Text summarization techniques
Additionally, I will add audio processing techniques such as:
Speech recognition
Speech synthesis
Speech to speech translation
Speaker recognition and verification
This repository serves to chart my progress in gaining practical intuition for real-world NLP and audio processing. Feedback and suggestions are always welcome.