Speech-to-Text opens up new ways for end users to interact with applications and devices. Instead of typing words on a keyboard or using their hands for touch screen interactions, Speech-to-Text technology allows users to operate applications and devices by voice and through dictation. Speech recognition has been possible for year, but perfecting it for every application, language, and voice has been hard. Enterprises building speech applications can now leverage Vertex AI and Chirp, a 2 billion parameter foundation model, that brings the power of large models to speech tasks, as well as the ability to fine tune speech for specific uses cases with in-domain data. Learn about how to go from getting started to the perfect voice model for your application.
Speakers: Calum Barnes, Haris Ioannou, Jeff Kurys, Omar Omran
Watch more:
All sessions from Google Cloud Next → https://goo.gle/next23
#GoogleCloudNext
AIML114