Frame Level Speech Recognition
Application of feedforward neural networks to recognize phoneme states in audio recordings from the Wall Street Journal dataset.
Portfolio
MyTorch
MyTorch is a python Deep Learning framework. Implemented using Numpy, the framework supports functionality for building and training deep learning networks.
Multilingual Automatic Speech Recognition for Kinyarwanda, Swahili, and Luganda: Advancing ASR in Select East African Languages
We presents a multilingual ASR model for Kinyarwanda, Swahili, and Luganda, achieving a WER of 21.91 using a 3,900-hour curated dataset from the Common Voice project.
Download here
JSE Stock Trends Prediction
We model and predict Johannesburg Securities Exchange (JSE) stock trends using Markov Chains and benchmark them against popular machine learning techniques.
Download here
Comparison of Deep Reinforcement Learning Algorithms in Enhancing Energy Trading in Microgrids
We propose using microgrids powered by renewable energy and enhanced with machine learning for energy trading to improve electricity supply in rural Sudan.
Download here
Textual Inversion for Personalization of Diffusion-Based Image Generation.
We use textual inversion to adapt the Stable Diffusion model for text-to-image generation, fine-tuning it with a dataset including LAION 5B and images from African artists to generate culturally specific artistic styles, achieving above-average performance in evaluations.
Download here