MaskGctDurationMode
Enums · AiDotNet.TextToSpeech.FlowDiffusion
How MaskGCT chooses the target’s length.
Fields
| Field | Summary |
|---|---|
MaskGctDurationMode Predictor |
The paper’s flow-matching duration predictor (App. |
MaskGctDurationMode Rule |
The release’s rule: the prompt’s speaking rate (its 16 kHz samples per phone) times the target’s phones, at 50 semantic frames per second. |
int value__ |