Learn how to deploy OpenAI’s Whisper speech-to-text model using Kubeflow pipelines on Google Cloud’s Vertex AI! In this tutorial, we’ll focus on operationalizing the Whisper model in a production-grade AI/ML pipeline, and demonstrate how to use the JAX framework for performant AI/ML deployments. Follow along as we set up the model, run it in a Vertex AI pipeline, and explore the impact of accelerators on transcription performance. Discover the flexibility and extensibility of Vertex AI as you connect your AI/ML models to applications, services, and data platforms.