Update app.py

app.py

@@ -24,9 +24,15 @@ def whisper_speech_demo(text, lang, speaker_audio, mix_lang, mix_text):
     print(f"Text: {text}, Lang: {lang}, Speaker Audio: {speaker_audio}, Mix Lang: {mix_lang}, Mix Text: {mix_text}")
     pipe = Pipeline()
     speaker_url = speaker_audio if speaker_audio is not None else None
+    if isinstance(lang, list):
+        if not lang:
+            raise ValueError("Language list is empty.")
+        lang = lang[0]  
+    elif not isinstance(lang, str):
+        raise ValueError("Language is not specified correctly.")
 
     if mix_lang and mix_text:
-        mixed_langs = mix_lang 
+        mixed_langs = mix_lang.split(',') if isinstance(mix_lang, str) else mix_lang
         mixed_texts = mix_text.split(',')
         stoks = pipe.t2s.generate(mixed_texts, lang=mixed_langs)
         audio_data = pipe.generate(stoks, speaker_url, lang=mixed_langs[0])
@@ -42,8 +48,8 @@ def whisper_speech_demo(text, lang, speaker_audio, mix_lang, mix_text):
     audio_stereo = np.stack((audio_np, audio_np), axis=-1)
     audio_stereo = audio_stereo.reshape(-1, 2)
     
-    # print("Audio Array Shape:", audio_stereo.shape)
-    # print("Audio Array Dtype:", audio_stereo.dtype)
+    print("Audio Array Shape:", audio_stereo.shape)
+    print("Audio Array Dtype:", audio_stereo.dtype)
     with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as tmp_file:
         sf.write(tmp_file.name, audio_stereo, 24000, format='WAV', subtype='PCM_16')
     return tmp_file.name