Primary sourceAWS Machine Learning Blog
View sourceEvent ·Official first-hand
Deepgram 将 Nova-3 语音模型迁移至 AWS Trainium2 优化推理
Deepgram 与 AWS 前沿部署工程团队合作，把 Nova-3 语音转文字模型迁移到 AWS Trainium2 芯片做离线批量推理。移植过程基于 AWS Neuron 软件栈，并进行 kernel 级调优。团队还用 Rust 写了数据并行运行时来支撑批量转录。文章给出了在批量转录场景下的吞吐量和成本结果。
Current read
Deepgram 把自家 Nova-3 语音模型搬到 AWS Trainium2 芯片上跑，讲了移植细节、kernel 调优和成本数据，做语音推理的可以看看。
3 sources38° AI heatLast updated 2026/10/19 16:23:22
Evidence
3 sourcesConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.