VevoStage
Enums · AiDotNet.TextToSpeech.CodecBased
Which of Vevo’s networks Vevo trains.
Fields
| Field | Summary |
|---|---|
VevoStage Acoustic |
The flow-matching transformer: content-style tokens to mel (the release’s Vq8192ToMels). |
VevoStage ContentToContentStyle |
Vevo-Voice’s autoregressive transformer: content tokens or phones (half the samples each) to content-style tokens (the release’s Vq32ToVq8192). |
VevoStage TextToContentStyle |
Vevo-TTS’s autoregressive transformer: phones to content-style tokens (the release’s PhoneToVq8192). |
int value__ |