EATOptions
Options & Configuration · AiDotNet.Audio.Classification
Configuration options for the EAT (Efficient Audio Transformer) model.
Inheritance: ModelOptions → EATOptions
For Beginners
EAT is designed to be more efficient while maintaining accuracy. It uses a teacher-student framework where a smaller student model learns from a larger teacher, making training much faster. Think of it as a student who learns efficiently by watching an expert rather than figuring everything out alone.
How It Works
EAT (Chen et al., 2024) is an efficient self-supervised audio pre-training model that achieves competitive performance with significantly less compute than previous methods. It reaches 49.7% mAP on AudioSet-2M using only 10% of the pre-training data and compute of BEATs.
References:
- Paper: “EAT: Self-Supervised Pre-Training with Efficient Audio Transformer” (Chen et al., 2024)
Constructors
| Constructor | Summary |
|---|---|
EATOptions() |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
Gets or sets ONNX runtime options. |
double AttentionDropoutRate { get; set; } |
Gets or sets the attention dropout rate. |
double DropoutRate { get; set; } |
Gets or sets the dropout rate. |
double EmaDecay { get; set; } |
Gets or sets the EMA (Exponential Moving Average) decay for teacher model updates. |
double LabelSmoothing { get; set; } |
Gets or sets the label smoothing factor. |
double LearningRate { get; set; } |
Gets or sets the initial learning rate. |
double MaskRatio { get; set; } |
Gets or sets the mask ratio for self-supervised pre-training. |
double Threshold { get; set; } |
Gets or sets the confidence threshold for event detection. |
double WindowOverlap { get; set; } |
Gets or sets the window overlap ratio. |
double WindowSize { get; set; } |
Gets or sets the window size in seconds. |
int EmbeddingDim { get; set; } |
Gets or sets the embedding dimension. |
int FMax { get; set; } |
Gets or sets the maximum frequency for mel filterbank. |
int FMin { get; set; } |
Gets or sets the minimum frequency for mel filterbank. |
int FeedForwardDim { get; set; } |
Gets or sets the feed-forward network dimension. |
int FftSize { get; set; } |
Gets or sets the FFT window size. |
int HopLength { get; set; } |
Gets or sets the hop length between FFT frames. |
int MinMaskSpanLength { get; set; } |
Gets or sets the minimum span length for masking. |
int NumAttentionHeads { get; set; } |
Gets or sets the number of attention heads. |
int NumEncoderLayers { get; set; } |
Gets or sets the number of Transformer encoder layers. |
int NumMels { get; set; } |
Gets or sets the number of mel filterbank channels. |
int PatchSize { get; set; } |
Gets or sets the patch size. |
int PatchStride { get; set; } |
Gets or sets the patch stride. |
int SampleRate { get; set; } |
Gets or sets the audio sample rate in Hz. |
int WarmUpSteps { get; set; } |
Gets or sets the number of warm-up steps. |
string ModelPath { get; set; } |
Gets or sets the path to a pre-trained ONNX model file. |
string[] CustomLabels { get; set; } |
Gets or sets custom event labels. |