DEV Community

Cover image for VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to SpeechSynthesizers
Paperium
Paperium

Posted on • Originally published at paperium.net

VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to SpeechSynthesizers

{{ $json.postContent }}

Top comments (0)