AWS Machine LearningLabs
Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot

Speech-to-text inference is computationally intensive. Each audio file triggers a pipeline of deep learning models (acoustic models, language models, and post-processing stages) running on NVIDIA…
Read at AWS Machine Learning ↗More from AWS Machine Learning on Accept All

LabsCost attribution and controls for AI developer and productivity tools on Amazon Bedrock AWS Machine Learning

LabsBuild a model improvement flywheel with Amazon SageMaker HyperPod Data Capture AWS Machine Learning

LabsDeploy frontier AI models on AWS Trainium with SGLang-Neuron AWS Machine Learning

LabsHow Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore AWS Machine Learning

LabsFour Amazon Bedrock inference choices that affect cost AWS Machine Learning
