Shashwat's Projects
Lang Chain projects showcasing my skills in the leading new LLM's and creating custom applications.
I am developing an AI solution in partnership with QMUL and WPP UK for my MSc Project.
🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI
Learning audio concepts from natural language supervision
Welcome to my Data Mining Repository! 📊💻.
This repository contains implementation of Deep Learning methods such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Artificial Neural Networks (ANN), Self Organising Maps (SOM), Boltzmann Machines (BM) and AutoEncoders.
The goal is to create models that can automatically categorize food images based on their visual content. This task is interesting because it has practical applications in dietary monitoring and personalized nutrition planning, and it requires handling challenges related to diverse food appearances.
Conversational AI with capabilities of expressing emotions and mimicking the nuances of any persons voice as well as emotional characteristics.
In this repo I am showcasing my Fine-tuning of LLMs skills and knowledge for various use cases and domains.
In this LLM project, we will use langchain, openai API, and streamlit to build a news research tool that can be used by equity research analysts to conduct their research.
My Journey of Learning about Neural Networks and Deep Learning
This project is focused on developing a sentiment analysis model, emphasizing the importance of effective text processing and feature engineering. The goal was to improve performance over a baseline model by refining preprocessing steps, feature extraction techniques, and model tuning.
Thank you
Thank you
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Document Similarity and Character Interaction Analysis Project - This project focuses on analyzing document similarity and character interactions in a textual dataset. It involves a series of data processing and feature engineering steps to enhance the model's ability to capture nuances in text data and improve similarity metrics.
EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction