overfeed.news

How Deepgram optimized voice AI at scale with AWS Trainium

9d

Age

Published
Collected
Image: AWS Machine Learning Blog

Deepgram worked with the AWS Forward Deployed Engineering team to port its Nova-3 speech-to-text model to AWS Trainium2 for offline batch inference. This post covers porting to the AWS Neuron stack, kernel-level tuning, a data-parallel Rust runtime, and the throughput and cost results on batch transcription.

Excerpt from the source

As voice becomes a first-class modality for AI, Deepgram’s models span speech-to-text, text-to-speech, and voice agents. They now process quadrillions of audio tokens a year for more than 200,000 developers and 1,400 organizations. Customers use them through the Deepgram API or run them in their own environments, including on Amazon SageMaker AI. For Deepgram, serving efficiency determines how much audio the system can process for a given infrastructure budget. High-volume batch workloads put…

Read the full article at aws.amazon.com

overfeed.news indexes and links. We publish a short excerpt — the full article stays at AWS Machine Learning Blog.

Log in to follow this source
How Deepgram optimized voice AI at scale with AWS Trainium —…