AlignTTS<T>

Models & Types · AiDotNet.TextToSpeech.Classic

AlignTTS: alignment-free non-autoregressive TTS using a feed-forward Transformer and mix density network alignment.

Inheritance: NeuralNetworkBase<T> → TtsModelBase<T> → AlignTTS<T>

Implements: IAcousticModel<T>

For Beginners

AlignTTS is a non-autoregressive text-to-speech model that converts text input into speech audio output.

How It Works

References:

  • Paper: “AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment” (Zeng et al., 2020)

Constructors

Constructor Summary
AlignTTS(NeuralNetworkArchitecture<T> architecture, AlignTTSOptions options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer)
AlignTTS(NeuralNetworkArchitecture<T> architecture, string modelPath, AlignTTSOptions options)

Properties

Property Summary
AlignTTSTrainingPhase CurrentPhase { get; set; } The paper’s training phase that Train runs (Zeng et al.
int FftSize { get; }
int HopSize { get; }
int MaxTextLength { get; }
int MelChannels { get; }

Methods

Method Summary
ModelMetadata<T> GetModelMetadata()
Tensor<T> TextToMel(string text) Generates a mel spectrogram from text (AlignTTS is an acoustic model; pair it with a vocoder).
void LoadConvertedWeights(string path) Copies {ConvertedParameterTensor} from source straight into a parameter vector.