MaskGctStage
Enums · AiDotNet.TextToSpeech.FlowDiffusion
Which of MaskGCT’s networks MaskGCT trains.
Fields
| Field | Summary |
|---|---|
MaskGctStage AcousticLayers |
The semantic-to-acoustic model that predicts layers 2–12 given the first (the release’s s2a_full). |
MaskGctStage Duration |
The total-duration predictor (App. |
MaskGctStage FirstAcousticLayer |
The semantic-to-acoustic model that predicts the first acoustic layer (the release’s s2a_1layer). |
MaskGctStage TextToSemantic |
The text-to-semantic model (§3.2.2). |
int value__ |