torchaudio 2.7.0__cp312-cp312-manylinux_2_28_x86_64.whl

torchaudio/models/wav2letter.py

@@ -0,0 +1,72 @@
+from torch import nn, Tensor
+
+__all__ = [
+    "Wav2Letter",
+]
+
+
+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
+
+    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

torchaudio/models/wav2vec2/__init__.py

@@ -0,0 +1,45 @@
+from . import utils
+from .model import (
+    hubert_base,
+    hubert_large,
+    hubert_pretrain_base,
+    hubert_pretrain_large,
+    hubert_pretrain_model,
+    hubert_pretrain_xlarge,
+    hubert_xlarge,
+    HuBERTPretrainModel,
+    wav2vec2_base,
+    wav2vec2_large,
+    wav2vec2_large_lv60k,
+    wav2vec2_model,
+    wav2vec2_xlsr_1b,
+    wav2vec2_xlsr_2b,
+    wav2vec2_xlsr_300m,
+    Wav2Vec2Model,
+    wavlm_base,
+    wavlm_large,
+    wavlm_model,
+)
+
+__all__ = [
+    "Wav2Vec2Model",
+    "HuBERTPretrainModel",
+    "wavlm_model",
+    "wavlm_base",
+    "wavlm_large",
+    "wav2vec2_model",
+    "wav2vec2_base",
+    "wav2vec2_large",
+    "wav2vec2_large_lv60k",
+    "hubert_base",
+    "hubert_large",
+    "hubert_xlarge",
+    "hubert_pretrain_model",
+    "hubert_pretrain_base",
+    "hubert_pretrain_large",
+    "hubert_pretrain_xlarge",
+    "utils",
+    "wav2vec2_xlsr_300m",
+    "wav2vec2_xlsr_1b",
+    "wav2vec2_xlsr_2b",
+]