Explore the capabilities of OpenAI's Whisper AI model in this 30-minute conference talk from EuroPython 2023. Delve into the architecture behind this powerful speech recognition and translation tool, understanding why it excels at accurately transcribing and translating human speech from audio across 96 languages. Witness a live demonstration showcasing the model's proficiency in three different languages, and learn how to harness its potential on your own computer to generate English subtitles for diverse content. Gain insights into this often-overlooked yet impressive AI technology that bridges language barriers in audio transcription and translation.
Overview
Syllabus
Whisper AI: Live English Subtitles for 96 Languages — Mathias Arens
Taught by
EuroPython Conference