fix the buf of the reduced SA

fairseq/modules/reduced_multihead_attention.py

@@ -86,7 +86,7 @@ class ReducedMultiheadAttention(nn.Module):
         self.add_zero_attn = add_zero_attn
         self.add_zero_attn = add_zero_attn
         self.sample_ratio = sample_ratio
         self.sample_ratio = sample_ratio
         if self.sample_ratio > 1:
         if self.sample_ratio > 1:
-            self.sr = nn.Conv2d(embed_dim, embed_dim, kernel_size=sample_ratio, stride=sample_ratio)
+            self.sr = nn.Conv1d(embed_dim, embed_dim, kernel_size=sample_ratio, stride=sample_ratio)
             self.norm = nn.LayerNorm(embed_dim)
             self.norm = nn.LayerNorm(embed_dim)
 
 
         self.reset_parameters()
         self.reset_parameters()