Getting a Real Time Factor Over 60 for Text-To-Speech Services Using NVIDIA Riva – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2025-03-31T20:50:22Z http://www.open-lab.net/blog/feed/ Dominique LaSalle <![CDATA[Getting a Real Time Factor Over 60 for Text-To-Speech Services Using NVIDIA Riva]]> http://www.open-lab.net/blog/?p=18263 2024-07-24T21:26:47Z 2020-06-24T21:03:04Z NVIDIA Riva is an application framework that provides several pipelines for accomplishing conversational AI tasks. Generating high-quality, natural-sounding...]]> NVIDIA Riva is an application framework that provides several pipelines for accomplishing conversational AI tasks. Generating high-quality, natural-sounding...Architecture diagram for Riva server.

NVIDIA Riva is an application framework that provides several pipelines for accomplishing conversational AI tasks. Generating high-quality, natural-sounding speech from text with low latency, also known as text-to-speech (TTS), can be one of the most computationally challenging of those tasks. In this post, we focus on optimizations made to a TTS pipeline in Riva, as shown in Figure 1.

Source

]]>
0
���˳���97caoporen����