Update app.py

app.py

@@ -21,6 +21,9 @@ def asr_transcript(audio):
     if audio is None or len(audio) == 0:
         return ""
     
+    # Ensure audio is a 1D numpy array
+    audio = np.asarray(audio).flatten()
+
     # Process the audio
     input_values = processor(audio, sampling_rate=16000, return_tensors="pt").input_values
     # Get logits