Deepgram optimizes its Nova-3 speech-to-text model on AWS Trainium2

Deepgram ported its Nova-3 speech-to-text model to AWS Trainium2 for offline batch workloads, running eight model replicas on one Amazon EC2 trn2.3xlarge instance. On its throughput-oriented batch workloads, that setup processed 11–70 percent more audio per dollar than Deepgram's previous compute options, measured at instance pricing at the time of evaluation.