diff --git a/parakeet/models/wavenet/wavenet.py b/parakeet/models/wavenet/wavenet.py
index b4c0d49..49778a5 100644
--- a/parakeet/models/wavenet/wavenet.py
+++ b/parakeet/models/wavenet/wavenet.py
@@ -313,6 +313,7 @@ class WaveNet(dg.Layer):
         """
         # Causal Conv
         if self.loss_type == "softmax":
+            x = F.clip(x, min=-1., max=0.99999)
             x = quantize(x, self.output_dim)
             x = self.embed(x)  # (B, T, C), T=1
         else:
diff --git a/parakeet/modules/customized.py b/parakeet/modules/customized.py
index 3b9a89b..2bb4574 100644
--- a/parakeet/modules/customized.py
+++ b/parakeet/modules/customized.py
@@ -86,7 +86,7 @@ class Conv1D(dg.Conv2D):
                  stride=1,
                  padding=0,
                  dilation=1,
-                 groups=None,
+                 groups=1,
                  param_attr=None,
                  bias_attr=None,
                  use_cudnn=True,
@@ -128,7 +128,7 @@ class Conv1DTranspose(dg.Conv2DTranspose):
                  padding=0,
                  stride=1,
                  dilation=1,
-                 groups=None,
+                 groups=1,
                  param_attr=None,
                  bias_attr=None,
                  use_cudnn=True,
@@ -179,7 +179,7 @@ class Conv1DCell(Conv1D):
                  filter_size,
                  dilation=1,
                  causal=False,
-                 groups=None,
+                 groups=1,
                  param_attr=None,
                  bias_attr=None,
                  use_cudnn=True,
diff --git a/parakeet/modules/weight_norm.py b/parakeet/modules/weight_norm.py
index 92f1085..1f05ffb 100644
--- a/parakeet/modules/weight_norm.py
+++ b/parakeet/modules/weight_norm.py
@@ -160,7 +160,7 @@ def Conv1D(num_channels,
            stride=1,
            padding=0,
            dilation=1,
-           groups=None,
+           groups=1,
            param_attr=None,
            bias_attr=None,
            use_cudnn=True,
@@ -179,7 +179,7 @@ def Conv1DTranspose(num_channels,
                     padding=0,
                     stride=1,
                     dilation=1,
-                    groups=None,
+                    groups=1,
                     param_attr=None,
                     bias_attr=None,
                     use_cudnn=True,
@@ -197,7 +197,7 @@ def Conv1DCell(num_channels,
                filter_size,
                dilation=1,
                causal=False,
-               groups=None,
+               groups=1,
                param_attr=None,
                bias_attr=None,
                use_cudnn=True,
@@ -216,7 +216,7 @@ def Conv2D(num_channels,
            stride=1,
            padding=0,
            dilation=1,
-           groups=None,
+           groups=1,
            param_attr=None,
            bias_attr=None,
            use_cudnn=True,
@@ -237,7 +237,7 @@ def Conv2DTranspose(num_channels,
                     padding=0,
                     stride=1,
                     dilation=1,
-                    groups=None,
+                    groups=1,
                     param_attr=None,
                     bias_attr=None,
                     use_cudnn=True,