{"id":"63100ef5-6719-4e7d-9ffb-3b6d54d69eb6","url":"https://api.tumn.com/news/63100ef5-6719-4e7d-9ffb-3b6d54d69eb6","title":"How Deepgram optimized voice AI at scale with AWS Trainium","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 re","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/how-deepgram-optimized-voice-ai-at-scale-with-aws-trainium/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-19T16:23:22.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-19T16:23:22.000Z","modifiedAt":"2026-10-19T20:25:34.000Z","checkedAt":"2026-10-19T20:25:34.346Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/63100ef5-6719-4e7d-9ffb-3b6d54d69eb6.json","markdown":"https://api.tumn.com/news/63100ef5-6719-4e7d-9ffb-3b6d54d69eb6.md"}}