Members of the deaf and hard-of-hearing community often experience large communication gaps, constraining their interaction in audible-centric contexts. Access to education, employment, and social participation can often be hampered due to these hurdles, leading to a compelling need for solutions to bridge this communication gap. This paper presents the design and implementation of a sign language translating system that builds on this challenge by incorporating computer vision-based deep learning algorithms to detect and translate sign language gestures accurately. Depending on gestures captured in the input video recordings, the model outputs continuous spoken language through a combination of advanced computer vision architectures capable of performing sign language recognition and real-time translation. They are derived from the intermediate representations produced by the input, such as pseudo-glosses. This will ensure real-time translation between signers and non-signers, and thus create an environment that allows better integration for the deaf and hard-of-hearing.