modify app

app.py

@@ -38,6 +38,8 @@ def process_audio(input_audio, reference_audio):
     # Ensure the audio is in the correct shape (samples, channels)
     if output_audio.ndim == 1:
         output_audio = output_audio.reshape(-1, 1)
+    elif output_audio.ndim == 2 and output_audio.shape[1] > output_audio.shape[0]:
+        output_audio = output_audio.transpose(1,0)
     elif output_audio.ndim > 2:
         output_audio = output_audio.squeeze()
     
@@ -81,6 +83,8 @@ def perform_ito(input_audio, reference_audio, ito_reference_audio, num_steps, op
         # Ensure the audio is in the correct shape (samples, channels)
         if current_output.ndim == 1:
             current_output = current_output.reshape(-1, 1)
+        elif current_output.ndim == 2 and current_output.shape[1] > current_output.shape[0]:
+            current_output = current_output.transpose(1,0)
         elif current_output.ndim > 2:
             current_output = current_output.squeeze()