Shortcuts

Source code for torchaudio.models.wav2letter

from torch import nn, Tensor

__all__ = [
    "Wav2Letter",
]


[docs]class Wav2Letter(nn.Module): r"""Wav2Letter model architecture from *Wav2Letter: an End-to-End ConvNet-based Speech Recognition System* :cite:`collobert2016wav2letter`. See Also: * `Training example <https://github.com/pytorch/audio/tree/release/0.12/examples/pipeline_wav2letter>`__ Args: num_classes (int, optional): Number of classes to be classified. (Default: ``40``) input_type (str, optional): Wav2Letter can use as input: ``waveform``, ``power_spectrum`` or ``mfcc`` (Default: ``waveform``). num_features (int, optional): Number of input features that the network will receive (Default: ``1``). """ def __init__(self, num_classes: int = 40, input_type: str = "waveform", num_features: int = 1) -> None: super().__init__() acoustic_num_features = 250 if input_type == "waveform" else num_features acoustic_model = nn.Sequential( nn.Conv1d(in_channels=acoustic_num_features, out_channels=250, kernel_size=48, stride=2, padding=23), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=250, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=True), nn.Conv1d(in_channels=250, out_channels=2000, kernel_size=32, stride=1, padding=16), nn.ReLU(inplace=True), nn.Conv1d(in_channels=2000, out_channels=2000, kernel_size=1, stride=1, padding=0), nn.ReLU(inplace=True), nn.Conv1d(in_channels=2000, out_channels=num_classes, kernel_size=1, stride=1, padding=0), nn.ReLU(inplace=True), ) if input_type == "waveform": waveform_model = nn.Sequential( nn.Conv1d(in_channels=num_features, out_channels=250, kernel_size=250, stride=160, padding=45), nn.ReLU(inplace=True), ) self.acoustic_model = nn.Sequential(waveform_model, acoustic_model) if input_type in ["power_spectrum", "mfcc"]: self.acoustic_model = acoustic_model
[docs] def forward(self, x: Tensor) -> Tensor: r""" Args: x (torch.Tensor): Tensor of dimension (batch_size, num_features, input_length). Returns: Tensor: Predictor tensor of dimension (batch_size, number_of_classes, input_length). """ x = self.acoustic_model(x) x = nn.functional.log_softmax(x, dim=1) return x

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