update

app2.py

@@ -132,10 +132,10 @@ def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence):
     # Select model
     if exp_name == "F5-TTS":
         ema_model = F5TTS_ema_model
-        base_model = F5TTS_base_model
+#        base_model = F5TTS_base_model
     elif exp_name == "E2-TTS":
         ema_model = E2TTS_ema_model
-        base_model = E2TTS_base_model
+#        base_model = E2TTS_base_model
 
     # Transcribe reference audio if needed
     if not ref_text.strip():
@@ -196,7 +196,7 @@ def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence):
         # Inference
         gr.Info(f"Generating audio using {exp_name}")
         with torch.inference_mode():
-            generated, _ = base_model.sample(
+            generated, _ = ema_model.sample(
                 cond=audio,
                 text=final_text_list,
                 duration=duration,