Shortcuts

DeepSpeech

class torchaudio.models.DeepSpeech(n_feature: int, n_hidden: int = 2048, n_class: int = 40, dropout: float = 0.0)[source]

DeepSpeech architecture introduced in Deep Speech: Scaling up end-to-end speech recognition [Hannun et al., 2014].

Parameters:
  • n_feature – Number of input features

  • n_hidden – Internal hidden unit size.

  • n_class – Number of output classes

forward

DeepSpeech.forward(x: Tensor) Tensor[source]
Parameters:

x (torch.Tensor) – Tensor of dimension (batch, channel, time, feature).

Returns:

Predictor tensor of dimension (batch, time, class).

Return type:

Tensor

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources