AWS Machine Learning Blog· Belair Albahagwi·· 2 d ago
Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot
Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot
AI summary
Learn how AssemblyAI runs cost-optimized speech-to-text inference at scale on AWS, using Amazon ECS, Amazon EC2 Spot GPU instances, and an Amazon SQS-based retry architecture to achieve 70% cost savings while maintaining SLA commitments across European Regions.
Selection record
Threshold 60Official, first-handFirst 28Second 22
Not admittedSum of both 50 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：语音转文本深度学习推理架构与成本优化
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