Transcribing Audio with Whisper

This talk introduces developers to automatic speech transcription using Whisper, an open-source AI model. You will learn how to use Whisper to turn audio into text, what you need for good results, and how to handle audio from multiple speakers.

We’ll discuss tips on recording quality audio with the right microphones and how to separate voices in group conversations. The session includes live demos, best practices, and practical advice for building your own transcription solutions.

--------------------------------
Please also make sure you register both here and at Foo Cafe:
https://foocafe.org/event/transcribing-audio-whisper