AWS Machine Learning Blog· Pierre Lienhart·· 6 h ago
How Deepgram optimized voice AI at scale with AWS Trainium
How Deepgram optimized voice AI at scale with AWS Trainium
AI summary
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.
Selection record
Threshold 60Official, first-handFirst 28Second 31
Not admittedSum of both 59 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：Deepgram语音AI模型在Trainium上的推理优化实践
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: AWS Machine Learning Blog · aws.amazon.com