WavLMASROptions

Options & Configuration · AiDotNet.SpeechRecognition.Foundation

Options for WavLM fine-tuned for speech recognition with CTC.

Inheritance: ModelOptions → WavLMASROptions

For Beginners

These options configure the WavLM recognizer. The model listens to the raw audio waveform (not a spectrogram) and outputs one character distribution per 20 ms frame.

How It Works

WavLM (Chen et al. 2022) is wav2vec 2.0’s convolutional feature encoder and Transformer with a gated relative position bias in every attention layer, pre-trained by masked prediction on denoised, overlapped speech and fine-tuned with a CTC head over raw 16 kHz audio. The defaults are the released microsoft/wavlm-base-plus configuration (group norm on the first feature-encoder layer, post-norm Transformer); set StableLayerNorm with 1024 wide, 24 layers, 16 heads and 4096 feed-forward for WavLM-Large.

Constructors

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

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } ONNX runtime options for the ONNX constructor.
bool FreezeFeatureEncoder { get; set; } Whether fine-tuning keeps the convolutional feature encoder frozen.
bool StableLayerNorm { get; set; } Whether to build the LARGE form: a layer-norm feature encoder with conv bias and a stable (pre-norm) Transformer.
double ActivationDropout { get; set; } Dropout inside each feed-forward block.
double DropoutRate { get; set; } Dropout on the Transformer’s hidden states and attention weights.
double FeatureProjectionDropout { get; set; } Dropout after the feature projection.
double FinalDropout { get; set; } Dropout before the CTC head.
double LayerDrop { get; set; } Probability of skipping each Transformer layer during training.
double MaskTimeProbability { get; set; } SpecAugment time-mask probability during training.
int EncoderDim { get; set; } Transformer width (hidden size).
int FeedForwardDim { get; set; } Feed-forward width of each Transformer layer.
int MaxAudioLengthSeconds { get; set; } Longest audio, in seconds, a transcription reads; longer input is truncated.
int MaxTextLength { get; set; } Most tokens a transcription emits.
int NumAttentionHeads { get; set; } Attention heads per layer.
int NumEncoderLayers { get; set; } Number of Transformer layers.
int PositionalConvGroups { get; set; } Groups of the convolutional positional embedding.
int SampleRate { get; set; } Audio sample rate in Hz.
int VocabSize { get; set; } CTC vocabulary size, blank (token 0) included; tokens above 0 decode as Unicode code points.
string Language { get; set; } Language reported for a transcription when none is given.
string ModelPath { get; set; } Path of an exported ONNX model, for the ONNX constructor.