Update app.py

app.py

@@ -34,14 +34,12 @@ def whisper_speech_demo(text, lang, speaker_audio, mix_lang, mix_text):
         audio_data = pipe.generate(text, speaker_url, lang)
 
     resample_audio = resampler(newsr=24000)
-    audio_data_resampled = next(resample_audio([{'sample_rate': 22050, 'samples': audio_data.cpu()}]))['samples_24k']
-
-    # Normalize audio
+    audio_data_resampled = next(resample_audio([{'sample_rate': 24000, 'samples': audio_data.cpu()}]))['samples_24k']
     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)    
     with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as tmp_file:
-        sf.write(tmp_file.name, audio_np, 24000, 'PCM_16')
+        sf.write(tmp_file.name, audio_stereo, 24000, format='WAV', subtype='PCM_16')
     return tmp_file.name
 
 with gr.Blocks() as demo: