Better speech synthesis through scaling

05/12/2023

∙

by   James Betker, et al.

∙

0

∙

share

In recent years, the field of image generation has been revolutionized by the application of autoregressive transformers and DDPMs. These approaches model the process of image generation as a step-wise probabilistic processes and leverage large amounts of compute and data to learn the image distribution. This methodology of improving performance need not be confined to images. This paper describes a way to apply advances in the image generative domain to speech synthesis. The result is TorToise – an expressive, multi-voice text-to-speech system. All model code and trained weights have been open-sourced at https://github.com/neonbjb/tortoise-tts.