Update app.py

app.py

@@ -99,7 +99,7 @@ def whisper_speech_demo(multilingual_text, speaker_audio):
     concatenated_audio = concatenated_audio / np.max(np.abs(concatenated_audio))
 
     # Return the concatenated audio as a NumPy array
-    return concatenated_audio
+    return concatenated_audio[0]
 
 with gr.Blocks() as demo:
     gr.Markdown(title)