diff --git a/egs/librispeech/ASR/pruned_transducer_stateless5/.conformer.py.swp b/egs/librispeech/ASR/pruned_transducer_stateless5/.conformer.py.swp
index 871faa871..aca0a97e7 100644
Binary files a/egs/librispeech/ASR/pruned_transducer_stateless5/.conformer.py.swp and b/egs/librispeech/ASR/pruned_transducer_stateless5/.conformer.py.swp differ
diff --git a/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/convolution.py b/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/convolution.py
new file mode 100644
index 000000000..6a5d2c30c
--- /dev/null
+++ b/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/convolution.py
@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+# Copyright 2020 Johns Hopkins University (Shinji Watanabe)
+#                Northwestern Polytechnical University (Pengcheng Guo)
+#  Apache 2.0  (http://www.apache.org/licenses/LICENSE-2.0)
+
+"""ConvolutionModule definition."""
+
+from torch import nn
+
+
+class ConvolutionModule(nn.Module):
+    """ConvolutionModule in Conformer model.
+
+    Args:
+        channels (int): The number of channels of conv layers.
+        kernel_size (int): Kernerl size of conv layers.
+
+    """
+
+    def __init__(self, channels, kernel_size, activation=nn.ReLU(), bias=True):
+        """Construct an ConvolutionModule object."""
+        super(ConvolutionModule, self).__init__()
+        # kernerl_size should be a odd number for 'SAME' padding
+        assert (kernel_size - 1) % 2 == 0
+
+        self.pointwise_conv1 = nn.Conv1d(
+            channels,
+            2 * channels,
+            kernel_size=1,
+            stride=1,
+            padding=0,
+            bias=bias,
+        )
+        self.depthwise_conv = nn.Conv1d(
+            channels,
+            channels,
+            kernel_size,
+            stride=1,
+            padding=(kernel_size - 1) // 2,
+            groups=channels,
+            bias=bias,
+        )
+        self.norm = nn.BatchNorm1d(channels)
+        self.pointwise_conv2 = nn.Conv1d(
+            channels,
+            channels,
+            kernel_size=1,
+            stride=1,
+            padding=0,
+            bias=bias,
+        )
+        self.activation = activation
+
+    def forward(self, x):
+        """Compute convolution module.
+
+        Args:
+            x (torch.Tensor): Input tensor (#batch, time, channels).
+
+        Returns:
+            torch.Tensor: Output tensor (#batch, time, channels).
+
+        """
+        # exchange the temporal dimension and the feature dimension
+        x = x.transpose(1, 2)
+
+        # GLU mechanism
+        x = self.pointwise_conv1(x)  # (batch, 2*channel, dim)
+        x = nn.functional.glu(x, dim=1)  # (batch, channel, dim)
+
+        # 1D Depthwise Conv
+        x = self.depthwise_conv(x)
+        x = self.activation(self.norm(x))
+
+        x = self.pointwise_conv2(x)
+
+        return x.transpose(1, 2)