Home > Storage > PowerFlex > White Papers > NVIDIA Riva on Red Hat OpenShift with Dell PowerFlex > Overview
Deep learning (DL), machine learning (ML), and artificial intelligence (AI) technologies have enabled success in many fields, such as computer vision, natural language processing (NLP), recommendation engines, and autonomous driving. These technologies use a model to learn from the existing data and generate results based on the new data. The success of these technologies is due to a combination of improved algorithms, access to larger datasets, and the increased computational power of both the CPU and GPU.
Speech recognition has recently been developed to deliver significant values in areas of automotive, customer services, and smart home device. To achieve high level of accuracy in a speech recognition can be challenging. This paper describes a solution that achieves automated speech recognition and inference with NVIDIA GPUs on Red Hat OpenShift along with Dell Power Flex software-defined infrastructure.
NVIDIA Riva, part of the NVIDIA AI platform, is a GPU-accelerated speech AI SDK for building and deploying fully customizable, real-time AI pipelines that deliver world-class accuracy in all clouds, on premises, at the edge, and on embedded devices.
This paper also describes the integration and performance of NVIDIA Riva services with PowerFlex two-layer architecture. The laboratory set up for this environment includes PowerFlex, Dell PowerEdge servers, Dell switches, Red Hat OpenShift, and NVIDIA AI Enterprise.