On-premise cloud deployment of ASR system

• Main Author: Yap, Jonathan Zher Hao
• Other Authors: Chng Eng Siong
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/165957
• Institution: Nanyang Technological University

This project aims to provide a bare metal deployment to the Automatic Speech Recognition (ASR) system. The deployment is made on a bare metal system to ensure that there is an option for an on-premise deployment for the ASR. This deployment solution is constructed using containerisation technology, Docker and Kubernetes. The solution is then implemented on on-premise servers in Nanyang Technological University. This solution ensures the auto-scaling of the system and has an on-premise load balancer to ensure that the system is able to meet the needs of the incoming requests. This report presents the deployment solution in terms of the core technologies used, the design of the architecture, implementation of the solution as well as the multitude of errors faced in the implementation of the solution.