Wav2SmallOptions
Options & Configuration · AiDotNet.Audio.Emotion
Configuration options for the Wav2Small speech emotion recognition model.
Inheritance: ModelOptions → Wav2SmallOptions
For Beginners
Wav2Small is like a student who learned from a large, expert teacher. The teacher (wav2vec 2.0) is too big to run on phones or embedded devices, so Wav2Small learns the teacher’s emotion detection skills in a much smaller model. The result is fast, accurate emotion detection that can run on resource-limited devices.
How It Works
Wav2Small (Gomez-Alanis et al., 2024) is a lightweight speech emotion recognition model that distills knowledge from large wav2vec 2.0 models into a compact architecture. It achieves competitive accuracy on IEMOCAP and RAVDESS while being small enough for edge deployment.
Constructors
| Constructor | Summary |
|---|---|
Wav2SmallOptions() |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
Gets or sets the ONNX runtime options. |
bool IncludeArousalValence { get; set; } |
Gets or sets whether to include arousal/valence estimation. |
double DistillationTemperature { get; set; } |
Gets or sets the knowledge distillation temperature. |
double DropoutRate { get; set; } |
Gets or sets the dropout rate. |
double LearningRate { get; set; } |
Gets or sets the learning rate. |
int FeatureEncoderDim { get; set; } |
Gets or sets the CNN feature encoder output dimension. |
int FeedForwardDim { get; set; } |
Gets or sets the feed-forward hidden dimension. |
int FftSize { get; set; } |
Gets or sets the FFT window size. |
int HiddenDim { get; set; } |
Gets or sets the hidden dimension of the compact encoder. |
int HopLength { get; set; } |
Gets or sets the hop length between frames. |
int NumAttentionHeads { get; set; } |
Gets or sets the number of attention heads. |
int NumClasses { get; set; } |
Gets or sets the number of emotion classes. |
int NumLayers { get; set; } |
Gets or sets the number of encoder layers. |
int NumMels { get; set; } |
Gets or sets the number of mel filterbank channels. |
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[] EmotionLabels { get; set; } |
Gets or sets the emotion label names. |