OpenVoiceOptions
Options & Configuration · AiDotNet.TextToSpeech.VoiceCloning
Options for OpenVoice TTS model.
Inheritance: ModelOptions → TtsModelOptions → EndToEndTtsOptions → OpenVoiceOptions
For Beginners
These options configure the OpenVoice model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
OpenVoiceOptions() |
Initializes a new instance with default values. |
OpenVoiceOptions(OpenVoiceOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OpenVoiceTrainingOptions Training { get; set; } |
Auxiliary IPA prior, waveform reconstruction and adversarial training configuration. |
double DropoutRate { get; set; } |
Dropout probability in the auxiliary IPA training encoder. |
int MelChannels { get; set; } |
Number of mel bands used by the waveform reconstruction objective. |
int NumEncoderLayers { get; set; } |
Number of layers in the auxiliary IPA training encoder. |
int NumHeads { get; set; } |
Attention heads in the auxiliary IPA training encoder. |
int NumToneColorLayers { get; set; } |
Gets or sets the number of layers in the tone-color converter. |
int SpeakerEmbeddingDim { get; set; } |
Gets or sets the width of the speaker embedding. |