fix: ensure input tensor has a single channel by averaging if necessary

app.py

@@ -323,6 +323,9 @@ def render(y, remove_approx, ratio, vec):
     loudness = meter.integrated_loudness(y)
     y = pyln.normalize.loudness(y, loudness, -18.0)
     y = torch.from_numpy(y).float().T.unsqueeze(0).to(device)
+    if y.shape[1] != 1:
+        y = y.mean(dim=1, keepdim=True)
+
     if remove_approx:
         infer_fx = instantiate(rt_config).to(device)
     else: