EndToEndTtsOptions
Options & Configuration · AiDotNet.TextToSpeech.EndToEnd
Base options for end-to-end TTS models that generate waveforms directly from text.
Inheritance: ModelOptions → TtsModelOptions → EndToEndTtsOptions
Known derived types: CoMoSpeechOptions, DiTToTTSOptions, E3TTSOptions, KokoroOptions, MatchaTTSOptions, MeloTTSOptions, OpenVoiceOptions, VitsModelOptions, VoiceFlowOptions
For Beginners
These options configure the EndToEndTts model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
EndToEndTtsOptions() |
Initializes a new instance with default values. |
EndToEndTtsOptions(EndToEndTtsOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
int DecoderDim { get; set; } |
Gets or sets the shared encoder/decoder width through HiddenDim. |
int EncoderDim { get; set; } |
Gets or sets the shared encoder/decoder width through HiddenDim. |
int FilterChannels { get; set; } |
Gets or sets the filter channels for the text encoder. |
int InterChannels { get; set; } |
Gets or sets the inter-channel dimension for the normalizing flow. |
int NumDiffusionSteps { get; set; } |
Gets or sets the number of diffusion/denoising steps (if applicable). |
int NumFlowSteps { get; set; } |
Gets or sets the number of flow steps in the posterior encoder. |