WavLMOptions

Options & Configuration · AiDotNet.Audio.Foundations

Configuration options for the WavLM self-supervised speech model.

Inheritance: ModelOptions → WavLMOptions

For Beginners

WavLM is an improved version of HuBERT that’s especially good at understanding noisy speech and telling different speakers apart. It was trained to understand speech even with background noise, making it more robust in real-world conditions.

How It Works

WavLM (Chen et al., 2022, Microsoft) extends HuBERT with gated relative position bias and denoising pre-training. It achieves state-of-the-art on the SUPERB benchmark across speech recognition, speaker verification, speaker diarization, and more.

Constructors

Constructor Summary
WavLMOptions()

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } Gets or sets the ONNX runtime options.
bool StableLayerNorm { get; set; } Whether to build WavLM-Large’s layout: a layer-norm feature encoder and a stable (pre-norm) Transformer.
bool UseGatedRelativePositionBias { get; set; } Gets or sets whether to use gated relative position bias.
double ActivationDropout { get; set; } Dropout inside each feed-forward block (microsoft/wavlm-base-plus: 0.0).
double DropoutRate { get; set; } Gets or sets the dropout rate.
double LayerDrop { get; set; } Probability of skipping each Transformer layer after the first during training (microsoft/wavlm-base-plus: 0.05).
double LearningRate { get; set; } Gets or sets the learning rate.
double MaskTimeProbability { get; set; } SpecAugment time-mask probability during training (microsoft/wavlm-base-plus: 0.05).
int FeatureEncoderDim { get; set; } Gets or sets the CNN feature encoder output dimension.
int FeedForwardDim { get; set; } Gets or sets the feed-forward dimension.
int HiddenDim { get; set; } Gets or sets the transformer hidden dimension.
int NumAttentionHeads { get; set; } Gets or sets the number of attention heads.
int NumLayers { get; set; } Gets or sets the number of transformer layers.
int SampleRate { get; set; } Gets or sets the expected audio sample rate in Hz.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.
string Variant { get; set; } Gets or sets the model variant (“base”, “base+”, or “large”).