Update app.py

app.py

@@ -26,7 +26,7 @@ def SER(audio):
         resampler = torchaudio.transforms.Resample(_sampling_rate)
         speech = resampler(speech_array).squeeze().numpy()
         inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
-        inputs = {key: inputs[key].to(device) for key in inputs}
+        inputs = {key: inputs[key] for key in inputs}
 
         with torch.no_grad():
             logits = model(**inputs).logits