AudioTransformer class
A Transformer model adapted for audio classification.
This model expects pre-extracted audio features (e.g., MFCCs, spectrogram slices) as a sequence of ValueVectors.
Constructors
Properties
- embedSize → int
-
final
- featureDim → int
-
final
- featureProjection → Layer
-
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- maxAudioSequenceLength → int
-
final
- mlpHead → Layer
-
final
- numClasses → int
-
final
- numHeads → int
-
final
- numLayers → int
-
final
-
positionEmbeddings
→ List<
ValueVector> -
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- transformerEncoder → TransformerEncoder
-
final
Methods
-
forward(
List< ValueVector> audioFeatures) → List<Value> - The forward pass for the Audio Transformer.
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
parameters(
) → List< Value> -
override
-
toString(
) → String -
A string representation of this object.
inherited
-
zeroGrad(
) → void -
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited