This document presents a detailed report on the development of a speaker-dependent Urdu language speech recognition system. It outlines the project phases, including data collection, transcription, phone level transcription, feature extraction, and coding. The report discusses the challenges faced, particularly in understanding Urdu phonology and addressing the limitations of a single speaker dataset. It concludes with plans for future work, emphasizing the potential impact of this system on individuals with visual impairments and the contribution to advancing Urdu language research.