News for hackers. Stuff that matters.
Re:Neural Codec Language Models Are Zero-Shot Text to Speech... by cookingrobot on Friday January 06, 2023 @01:34AM (#34271673)
The first column of audio is just a sample of that person reading different text. That’s what the model gets to hear to learn what they sound like, before trying to speak the text in their voice.
Re:Neural Codec Language Models Are Zero-Shot Text to Speech... by woodson on Friday January 06, 2023 @02:05AM (#34271819)
Ah thanks! I looked at the page on a phone screen, where only the text and the first audio playback button are visible. My bad..