Update app.py

app.py

@@ -61,9 +61,11 @@ def imageMode(image, question):
 
 def audioMode(audio):
     print('---------type of audio--------------')
-    print(type(audio))
-    print(audio)
-    input_features = processor_audio(audio, sampling_rate=16000, return_tensors="pt").input_features 
+    sampling_rate = audio[0]
+    audio_array = audio[1]
+    print(sampling_rate)
+    print(audio_array)
+    input_features = processor_audio(audio_array, sampling_rate=sampling_rate, return_tensors="pt").input_features 
     predicted_ids = model_audio.generate(input_features)
     transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
     return transcription