use implicit padding when possible

fairseq/models/fconv.py

@@ -123,7 +123,7 @@ class FConvEncoder(FairseqEncoder):
             self.projections.append(Linear(in_channels, out_channels)
                                     if in_channels != out_channels else None)
             if kernel_size % 2 == 1:
-                padding = kernel_size // 2
+               padding = kernel_size //2
             else:
                padding = 0
             self.convolutions.append(