Practical AI cover image

Full-duplex, real-time dialogue with Kyutai

Practical AI

00:00

Navigating Text-to-Speech Model Training

This chapter explores the intricacies of training text-to-speech models, highlighting the need for diverse audio samples and the challenges in aligning text and audio-based responses. It further discusses the selection process between large and small transformer models, emphasizing the use of a 7 billion parameter baseline and advancements in model distillation for efficiency.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app