News for hackers. Stuff that matters.

A comment on Silero V3: fast high-quality text-to-speech in 20 languages with 173 voices.

Re:Silero V3: fast high-quality text-to-speech in 20 languag... by rockemsockem on Monday June 20, 2022 @04:07PM (#31815146)
What is the actual underlying technology powering this? I read several of the blog posts, the Colab notebook, and the GitHub page, but couldn't find anything saying what is actually being used? Sounds pretty great and I'm very curious to know a bit about how it's done!
[ Parent | on HN ]
Re:Silero V3: fast high-quality text-to-speech in 20 languag... by snakers41 on Tuesday June 21, 2022 @03:10AM (#31821054)
It is PyTorch
[ Parent | on HN ]
Re:Silero V3: fast high-quality text-to-speech in 20 languag... by rockemsockem on Friday June 24, 2022 @01:17PM (#31865982)
I meant what ML model or variety of ML model. Is it using Tacotron2? Old concatenative TTS? Something else?
[ Parent | on HN ]
Re:Silero V3: fast high-quality text-to-speech in 20 languag... by snakers41 on Friday June 24, 2022 @01:23PM (#31866087)
Neither of these
[ Parent | on HN ]