Update app.py

app.py

@@ -12,6 +12,11 @@ hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "flagged_Audio_Lebanese")
 
 def transcribe(stream, new_chunk):
     sr, y = new_chunk
+    
+    # Convert to mono if stereo
+    if y.ndim > 1:
+        y = y.mean(axis=1)
+        
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
@@ -21,6 +26,7 @@ def transcribe(stream, new_chunk):
         stream = y
     return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]  
 
+    
 demo = gr.Interface(
     transcribe,
     ["state", gr.Audio(sources=["microphone"], streaming=True)],