fix typos

wenet/transformer/convolution.py

@@ -12,7 +12,6 @@
 
 class ConvolutionModule(nn.Module):
     """ConvolutionModule in Conformer model."""
-
     def __init__(self,
                  channels: int,
                  kernel_size: int = 15,
@@ -44,7 +43,7 @@ def __init__(self,
             padding = 0
             self.lorder = kernel_size - 1
         else:
-            # kernerl_size should be an odd number for none causal convolution
+            # kernel_size should be an odd number for none causal convolution
             assert (kernel_size - 1) % 2 == 0
             padding = (kernel_size - 1) // 2
             self.lorder = 0

wenet/transformer/encoder.py

@@ -224,7 +224,7 @@ def __init__(
                 compatibility.
             activation_type (str): Encoder activation function type.
             use_cnn_module (bool): Whether to use convolution module.
-            cnn_module_kernel (int): Kernerl size of convolution module.
+            cnn_module_kernel (int): Kernel size of convolution module.
             causal (bool): whether to use causal convolution or not.
         """
         assert check_argument_types()

wenet/transformer/positionwise_feed_forward.py

@@ -22,13 +22,13 @@ def __init__(self,
                  hidden_units: int,
                  dropout_rate: float,
                  activation: torch.nn.Module = torch.nn.ReLU()):
-        """Construct an PositionwiseFeedForward object."""
+        """Construct a PositionwiseFeedForward object."""
         super(PositionwiseFeedForward, self).__init__()
         self.w_1 = torch.nn.Linear(idim, hidden_units)
         self.w_2 = torch.nn.Linear(hidden_units, idim)
         self.dropout = torch.nn.Dropout(dropout_rate)
         self.activation = activation
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
-        """Forward funciton."""
+        """Forward function."""
         return self.w_2(self.dropout(self.activation(self.w_1(x))))

wenet/transformer/swish.py

@@ -12,5 +12,5 @@
 class Swish(torch.nn.Module):
     """Construct an Swish object."""
     def forward(self, x: torch.Tensor) -> torch.Tensor:
-        """Return Swich activation function."""
+        """Return Swish activation function."""
         return x * torch.sigmoid(x)

wenet/utils/common.py

@@ -1,4 +1,4 @@
-"""Unility funcitons for Transformer."""
+"""Unility functions for Transformer."""
 
 import math
 from typing import Tuple, List