Update app.py

app.py

@@ -32,11 +32,14 @@ def transcribe_audio(audio_file):
             # Read the content of the uploaded file
             audio_content = audio_file.read()
             
-            # Convert the content to torch tensor with single channel
-            waveform, sample_rate = torchaudio.load(BytesIO(audio_content), channels_first=True)
-            waveform = waveform.mean(dim=0, keepdim=True)  # Downmix stereo to mono
+            # Load the audio using torchaudio.load
+            waveform, sample_rate = torchaudio.load(BytesIO(audio_content))
             
-            # Convert the torch tensor to a numpy array
+            # Convert to mono if stereo
+            if waveform.shape[0] > 1:
+                waveform = torch.mean(waveform, dim=0, keepdim=True)
+            
+            # Convert the waveform to numpy array
             waveform_np = waveform.numpy()
             
             # Transcribe the audio