Update app.py

app.py

@@ -40,11 +40,16 @@ def parse_multilingual_text(input_text):
 @spaces.GPU
 def generate_segment_audio(text, lang, speaker_url, pipe):
 
+    # Ensure text is a string
     if not isinstance(text, str):
+        text = text.decode("utf-8") if isinstance(text, bytes) else str(text)
+
+    # Check and process speaker_audio if it is a string (path to file)
+    if isinstance(speaker_audio, str):
         print("Speaker Audio Type:", type(speaker_audio))
         with open(speaker_audio, 'rb') as file:
             speaker_audio = file.read()
-        text = text.decode("utf-8") if isinstance(text, bytes) else str(text)
+
     audio_data = pipe.generate(text, speaker_audio, lang)
     resample_audio = resampler(newsr=24000)
     audio_data_resampled = next(resample_audio([{'sample_rate': 24000, 'samples': audio_data.cpu()}]))['samples_24k']