fix

app.py

@@ -143,8 +143,8 @@ def infer(
 
     final_wave, final_sample_rate, combined_spectrogram = infer_process(
         ref_audio,
-        ref_text.lower(),
-        gen_text.lower(),
+        ref_text.lower().strip(),
+        gen_text.lower().strip(),
         ema_model,
         vocoder,
         cross_fade_duration=cross_fade_duration,