Re:Neural Codec Language Models Are Zero-Shot Text to Speech...
by babakd on Friday January 06, 2023 @01:31AM
(#34271657)
The speaker prompt is the sample speaker voice reading a random text, that’s one piece that the model uses as input. The second column corresponds to the human speaker reading the text (ground truth) The two next columns are baseline and VALL-E producing text-to-speech respectively, given the first column and only the text as input.
[ Parent
| on HN ]
There are no comments on this comment yet.