Update app.py

app.py

@@ -38,8 +38,11 @@ def whisper_speech_demo(text, lang, speaker_audio, mix_lang, mix_text):
     audio_np = audio_data_resampled.cpu().numpy()
     audio_np = audio_np / np.max(np.abs(audio_np))
     audio_np = np.asarray(audio_np, dtype=np.float32)    
+
+    audio_stereo = np.stack((audio_np, audio_np), axis=-1)
+    
     with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as tmp_file:
-        sf.write(tmp_file.name, audio_np, 24000, format='WAV', subtype='PCM_16')
+        sf.write(tmp_file.name, audio_stereo, 24000, format='WAV', subtype='PCM_16')
     return tmp_file.name
 
 with gr.Blocks() as demo: