Update app.py

app.py

@@ -26,8 +26,7 @@ def transcribe_audio(audio_data):
     input_features = preprocess_audio(audio_data)
     input_values = torch.tensor(input_features["input_values"]).unsqueeze(0)  # Add batch dimension
     # Ensure the input tensor has the correct shape
-    input_values = input_values.view(1, -1, 1)
-    input_values = input_values.permute(0, 2, 1)
+    input_values = input_values.view(1, 1, -1)
     predicted_ids = model.generate(input_values)
     transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
     return transcription[0]