Alexander Veysov on Self-Teaching AI and Creating Open Speech-To-Text
The Gradient: Perspectives on AI
00:00
Mucad's Success With Text-to-Speech Models
Mucad has built text-to-speech models for five languages, and right now we're building these models for the minority languages in Russia. We treated it as a form of digital preservation, I don't know. Some people want to create other books for their children, for example, their national language. So, it is quite a good. Having free, pre-trained models that you can just use for shelf. It already enables a lot of stuff, so it's pretty important.
Transcript
Play full episode
