Update model.py

model.py

@@ -186,7 +186,10 @@ class Encoder(nn.Module):
 
         return outputs
 
-    def inference(self, x):
+    def inference(self, x, speaker_embedding):
+        # Modify the input x to concatenate the speaker embedding
+        x = torch.cat((x, speaker_embedding.unsqueeze(1).expand(-1, x.size(1), -1)), dim=-1)
+        
         for conv in self.convolutions:
             x = F.dropout(F.relu(conv(x)), 0.5, self.training)