DiTToTrainingStage
Enums · AiDotNet.TextToSpeech.FlowDiffusion
Diffusion and length prediction, plus the separately pretrained and optionally semantically finetuned codec.
Fields
| Field | Summary |
|---|---|
DiTToTrainingStage Diffusion |
Train the diffusion transformer. |
DiTToTrainingStage LengthPredictor |
Train the latent-length predictor. |
DiTToTrainingStage MelVaePretraining |
Pretrain the mel VAE codec. |
DiTToTrainingStage MelVaeSemanticFinetuning |
Finetune the mel VAE with semantic supervision. |
int value__ |