Update app.py

app.py

@@ -14,13 +14,9 @@ model = Wav2Vec2ForCTC.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-it
 # Function to perform ASR on audio data
 def transcribe_audio(audio_data):
     # Convert audio data to mono and normalize
-    audio_data = torchaudio.transforms.Mono()(audio_data)
+    audio_data = torchaudio.transforms.Resample(audio_data[1], 16000)(audio_data[0])
     audio_data = torchaudio.functional.gain(audio_data, gain_db=5.0)
 
-    # Resample if needed (Wav2Vec2 model requires 16 kHz sampling rate)
-    if audio_data[1] != 16000:
-        audio_data = torchaudio.transforms.Resample(audio_data[1], 16000)(audio_data[0])
-
     # Apply custom preprocessing to the audio data if needed
     input_values = processor(audio_data[0].numpy(), return_tensors="pt").input_values