EfficientConformer<T>

Models & Types · AiDotNet.SpeechRecognition.ConformerFamily

Efficient Conformer with progressive temporal downsampling and grouped attention.

Inheritance: NeuralNetworkBase<T> → AudioNeuralNetworkBase<T> → EfficientConformer<T>

Implements: ISpeechRecognizer<T>

How It Works

Implements the CTC architecture from “Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition” (Burchi and Vielzeuf, 2021).

Constructors

Constructor Summary
EfficientConformer(NeuralNetworkArchitecture<T> architecture, EfficientConformerOptions options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer) Creates the native paper architecture.
EfficientConformer(NeuralNetworkArchitecture<T> architecture, string modelPath, EfficientConformerOptions options) Creates the native paper architecture.

Properties

Property Summary
IReadOnlyList<string> SupportedLanguages { get; }
bool SupportsStreaming { get; }
bool SupportsWordTimestamps { get; }

Methods

Method Summary
IReadOnlyDictionary<string, T> DetectLanguageProbabilities(Tensor<T> audio)
IStreamingTranscriptionSession<T> StartStreamingSession(string language)
ModelMetadata<T> GetModelMetadata()
Task<TranscriptionResult<T>> TranscribeAsync(Tensor<T> audio, string language, bool? includeTimestamps, CancellationToken cancellationToken)
Tensor<T> ForwardForTraining(Tensor<T> input)
TranscriptionResult<T> Transcribe(Tensor<T> audio, string language, bool? includeTimestamps)
string DetectLanguage(Tensor<T> audio)