Table of Contents

Class CLAPModel<T>

Namespace
AiDotNet.Audio.Fingerprinting
Assembly
AiDotNet.dll

CLAP (Contrastive Language-Audio Pretraining) - A neural network model that learns to align audio and text representations in a shared embedding space.

public class CLAPModel<T> : AudioNeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<T>, IFullModel<T, Tensor<T>, Tensor<T>>, IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Tensor<T>, Tensor<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>, IGradientComputable<T, Tensor<T>, Tensor<T>>, IJitCompilable<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable, IAudioFingerprinter<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance
CLAPModel<T>
Implements
IFullModel<T, Tensor<T>, Tensor<T>>
IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>
IParameterizable<T, Tensor<T>, Tensor<T>>
ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>
IGradientComputable<T, Tensor<T>, Tensor<T>>
Inherited Members
Extension Methods

Remarks

CLAP is a multimodal model trained using contrastive learning to create embeddings where similar audio-text pairs are close together and dissimilar pairs are far apart. This enables:

  • Zero-shot audio classification using text prompts
  • Audio-to-text retrieval (find descriptions matching audio)
  • Text-to-audio retrieval (find audio matching descriptions)
  • Semantic audio fingerprinting

For Beginners: CLAP understands both audio and text! It can:

  • Tell you what's in an audio clip without pre-defined categories
  • Find audio that matches a text description ("a dog barking in the rain")
  • Create embeddings for audio search and recommendation

Unlike traditional fingerprinting that matches exact audio, CLAP understands audio semantics - it knows a dog barking and a recording of barking are related!

Example use cases:

  • "Is this audio of a happy or sad scene?" (sentiment analysis)
  • "Find all audio clips with birds singing" (content-based search)
  • "Classify this sound into one of these categories: ..." (zero-shot classification)
  • Audio content moderation (detect specific sounds)

Reference: Wu, Y., et al. (2023). Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation.

Constructors

CLAPModel(NeuralNetworkArchitecture<T>, int, int, int, int, int, int, int, int, int, int, double, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?)

Initializes a new instance of the CLAPModel<T> class for native training mode.

public CLAPModel(NeuralNetworkArchitecture<T> architecture, int sampleRate = 48000, int embeddingDim = 768, int projectionDim = 512, int numMelBands = 64, int audioEncoderLayers = 12, int audioEncoderHeads = 12, int vocabSize = 49408, int maxTextLength = 77, int windowSize = 1024, int hopSize = 480, double temperature = 0.07, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture defining input/output dimensions.

sampleRate int

Sample rate of input audio (default: 48000 Hz).

embeddingDim int

Internal embedding dimension (default: 768).

projectionDim int

Projection dimension for output embeddings (default: 512).

numMelBands int

Number of mel spectrogram bands (default: 64).

audioEncoderLayers int

Number of transformer layers in audio encoder (default: 12).

audioEncoderHeads int

Number of attention heads (default: 12).

vocabSize int

Vocabulary size for text encoding (default: 49408).

maxTextLength int

Maximum text sequence length (default: 77).

windowSize int

STFT window size (default: 1024).

hopSize int

STFT hop size (default: 480).

temperature double

Temperature for contrastive loss (default: 0.07).

optimizer IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>

Optimizer for training. If null, a default Adam optimizer is used.

lossFunction ILossFunction<T>

Loss function. If null, contrastive loss is used.

CLAPModel(NeuralNetworkArchitecture<T>, string, string?, int, int, int, OnnxModelOptions?)

Initializes a new instance of the CLAPModel<T> class for ONNX inference mode.

public CLAPModel(NeuralNetworkArchitecture<T> architecture, string audioEncoderPath, string? textEncoderPath = null, int sampleRate = 48000, int embeddingDim = 768, int projectionDim = 512, OnnxModelOptions? onnxOptions = null)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture defining input/output dimensions.

audioEncoderPath string

Path to the ONNX audio encoder model.

textEncoderPath string

Optional path to the ONNX text encoder model.

sampleRate int

Sample rate of input audio (default: 48000 Hz).

embeddingDim int

Embedding dimension (default: 768).

projectionDim int

Projection dimension for output embeddings (default: 512).

onnxOptions OnnxModelOptions

Optional ONNX model options.

Exceptions

FileNotFoundException

Thrown when the ONNX model file is not found.

Properties

EmbeddingDimension

Gets the embedding dimension used internally.

public int EmbeddingDimension { get; }

Property Value

int

FingerprintLength

Gets the fingerprint length in bits or elements.

public int FingerprintLength { get; }

Property Value

int

Name

Gets the name of the fingerprinting algorithm.

public string Name { get; }

Property Value

string

ProjectionDimension

Gets the projection dimension (final embedding size).

public int ProjectionDimension { get; }

Property Value

int

Methods

ComputeSimilarity(AudioFingerprint<T>, AudioFingerprint<T>)

Computes the similarity between two fingerprints.

public double ComputeSimilarity(AudioFingerprint<T> fp1, AudioFingerprint<T> fp2)

Parameters

fp1 AudioFingerprint<T>

First fingerprint.

fp2 AudioFingerprint<T>

Second fingerprint.

Returns

double

Similarity score (0-1, higher is more similar).

CreateNewInstance()

Creates a new instance of the same type as this neural network.

protected override IFullModel<T, Tensor<T>, Tensor<T>> CreateNewInstance()

Returns

IFullModel<T, Tensor<T>, Tensor<T>>

A new instance of the same neural network type.

Remarks

For Beginners: This creates a blank version of the same type of neural network.

It's used internally by methods like DeepCopy and Clone to create the right type of network before copying the data into it.

Deserialize(byte[])

Deserializes the neural network from a byte array.

public override void Deserialize(byte[] data)

Parameters

data byte[]

The byte array containing the serialized neural network data.

DeserializeNetworkSpecificData(BinaryReader)

Deserializes network-specific data that was not covered by the general deserialization process.

protected override void DeserializeNetworkSpecificData(BinaryReader reader)

Parameters

reader BinaryReader

The BinaryReader to read the data from.

Remarks

This method is called at the end of the general deserialization process to allow derived classes to read any additional data specific to their implementation.

For Beginners: Continuing the suitcase analogy, this is like unpacking that special compartment. After the main deserialization method has unpacked the common items (layers, parameters), this method allows each specific type of neural network to unpack its own unique items that were stored during serialization.

EncodeAudio(Tensor<T>)

Encodes audio into an embedding vector.

public Tensor<T> EncodeAudio(Tensor<T> audio)

Parameters

audio Tensor<T>

Audio tensor [samples] or [batch, samples].

Returns

Tensor<T>

Audio embedding [batch, projectionDim].

EncodeText(int[])

Encodes text into an embedding vector.

public Tensor<T> EncodeText(int[] tokens)

Parameters

tokens int[]

Text token IDs [batch, seqLen].

Returns

Tensor<T>

Text embedding [batch, projectionDim].

FindMatches(AudioFingerprint<T>, AudioFingerprint<T>, int)

Finds matching segments between two fingerprints.

public IReadOnlyList<FingerprintMatch> FindMatches(AudioFingerprint<T> query, AudioFingerprint<T> reference, int minMatchLength = 10)

Parameters

query AudioFingerprint<T>

The query fingerprint.

reference AudioFingerprint<T>

The reference fingerprint to search in.

minMatchLength int

Minimum length of matching segment.

Returns

IReadOnlyList<FingerprintMatch>

List of matching segments with time offsets.

Fingerprint(Tensor<T>)

Generates a fingerprint from audio data.

public AudioFingerprint<T> Fingerprint(Tensor<T> audio)

Parameters

audio Tensor<T>

Audio samples as a tensor (mono audio).

Returns

AudioFingerprint<T>

The audio fingerprint.

Fingerprint(Vector<T>)

Generates a fingerprint from audio data.

public AudioFingerprint<T> Fingerprint(Vector<T> audio)

Parameters

audio Vector<T>

Audio samples as a vector (mono audio).

Returns

AudioFingerprint<T>

The audio fingerprint.

GetModelMetadata()

Gets the metadata for this neural network model.

public override ModelMetadata<T> GetModelMetadata()

Returns

ModelMetadata<T>

A ModelMetaData object containing information about the model.

InitializeLayers()

Initializes the neural network layers.

protected override void InitializeLayers()

PostprocessOutput(Tensor<T>)

Postprocesses model output.

protected override Tensor<T> PostprocessOutput(Tensor<T> modelOutput)

Parameters

modelOutput Tensor<T>

Returns

Tensor<T>

Predict(Tensor<T>)

Predicts audio embedding.

public override Tensor<T> Predict(Tensor<T> input)

Parameters

input Tensor<T>

Returns

Tensor<T>

PreprocessAudio(Tensor<T>)

Preprocesses raw audio waveform for model input.

protected override Tensor<T> PreprocessAudio(Tensor<T> rawAudio)

Parameters

rawAudio Tensor<T>

Returns

Tensor<T>

Serialize()

Serializes the neural network to a byte array.

public override byte[] Serialize()

Returns

byte[]

A byte array representing the serialized neural network.

SerializeNetworkSpecificData(BinaryWriter)

Serializes network-specific data that is not covered by the general serialization process.

protected override void SerializeNetworkSpecificData(BinaryWriter writer)

Parameters

writer BinaryWriter

The BinaryWriter to write the data to.

Remarks

This method is called at the end of the general serialization process to allow derived classes to write any additional data specific to their implementation.

For Beginners: Think of this as packing a special compartment in your suitcase. While the main serialization method packs the common items (layers, parameters), this method allows each specific type of neural network to pack its own unique items that other networks might not have.

Train(Tensor<T>, Tensor<T>)

Trains the model on audio-text pairs using contrastive loss.

public override void Train(Tensor<T> input, Tensor<T> expected)

Parameters

input Tensor<T>
expected Tensor<T>

UpdateParameters(Vector<T>)

Updates the network's parameters with new values.

public override void UpdateParameters(Vector<T> gradients)

Parameters

gradients Vector<T>

Remarks

For Beginners: During training, a neural network's internal values (parameters) get adjusted to improve its performance. This method allows you to update all those values at once by providing a complete set of new parameters.

This is typically used by optimization algorithms that calculate better parameter values based on training data.

ZeroShotClassify(Tensor<T>, string[], Func<string, int[]>)

Performs zero-shot classification using text prompts.

public Dictionary<string, double> ZeroShotClassify(Tensor<T> audio, string[] classLabels, Func<string, int[]> tokenizer)

Parameters

audio Tensor<T>

Audio tensor to classify.

classLabels string[]

Array of text labels to classify against.

tokenizer Func<string, int[]>

Function to tokenize text labels.

Returns

Dictionary<string, double>

Classification probabilities for each label.

Edit this page