Data2VecASROptions
Options & Configuration · AiDotNet.SpeechRecognition.Foundation
Options for data2vec (audio) fine-tuned for speech recognition with CTC.
Inheritance: ModelOptions → Data2VecASROptions
For Beginners
These options configure the data2vec recognizer. The model listens to the raw audio waveform (not a spectrogram) and outputs one character distribution per 20 ms frame.
How It Works
data2vec (Baevski et al. 2022) pre-trains a wav2vec 2.0-style encoder to predict its own teacher’s averaged layer representations. Its audio network keeps wav2vec 2.0’s 7-layer convolutional feature encoder (with layer norm on every layer and no conv bias) and post-norm Transformer, but replaces the single weight-normed positional convolution with five grouped convolutions of kernel 19, each followed by a parameter-free layer norm and GELU. The defaults are the released facebook/data2vec-audio-base-960h configuration.
Constructors
| Constructor | Summary |
|---|---|
Data2VecASROptions() |
Initializes a new instance with default values. |
Data2VecASROptions(Data2VecASROptions 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. |
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. |