VocoderOptions

Options & Configuration · AiDotNet.TextToSpeech.Vocoders

Base configuration options for neural vocoder models.

Inheritance: ModelOptions → TtsModelOptions → VocoderOptions

Known derived types: AmplitudePhaseVocoderOptions, BigVGANOptions, DiffWaveOptions, HiFiGANOptions, ISTFTNetOptions, MelGANOptions, MultiBandMelGANOptions, ParallelWaveGANOptions, UnivNetOptions, VocosOptions, WaveGlowOptions, WaveGradOptions, WaveNetOptions, WaveRNNOptions

For Beginners

These options configure the Vocoder model. Default values follow the original paper settings.

Constructors

Constructor Summary
VocoderOptions() Initializes a new instance with default values.
VocoderOptions(VocoderOptions other) Initializes a new instance by copying from another instance.

Properties

Property Summary
int NumDiffusionSteps { get; set; } Gets or sets the number of diffusion steps (for diffusion vocoders).
int UpsampleChannelDivisor { get; } The factor the upsampling stages halve UpsampleInitialChannels by (2 per stage), which it must therefore be a multiple of for the last stage to keep a channel.
int UpsampleInitialChannels { get; set; } Gets or sets the initial upsample channel count.
int[] ResblockKernelSizes { get; set; } Gets or sets the resblock kernel sizes.
int[] UpsampleRates { get; set; } Gets or sets the upsample rates for each upsampling block.