Update app.py

app.py

@@ -26,6 +26,7 @@ def classify_emotion(audio_file):
     # Load and process audio
     speech, sr = librosa.load(audio_file, sr=16000)
     inputs = processor(speech, sampling_rate=16000, return_tensors="pt", padding=True, truncation=True)
+    inputs["input_values"] = inputs["input_values"].unsqueeze(0)  # Add batch dimension
 
     # Get predictions
     with torch.no_grad():