Update app.py

app.py

@@ -209,14 +209,14 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, exp_name, remove_silence,
         # inference
         with torch.inference_mode():
     # Ensure all inputs are on the same device as ema_model
-        audio = audio.to(ema_model.device)  # Match ema_model's device
-        final_text_list = [t.to(ema_model.device) if isinstance(t, torch.Tensor) else t for t in final_text_list] generated, _ = ema_model.sample(
-        cond=audio,
-        text=final_text_list,
-        duration=duration,
-        steps=nfe_step,
-        cfg_strength=cfg_strength,
-        sway_sampling_coef=sway_sampling_coef,
+            audio = audio.to(ema_model.device)  # Match ema_model's device
+            final_text_list = [t.to(ema_model.device) if isinstance(t, torch.Tensor) else t for t in final_text_list] generated, _ = ema_model.sample(
+            cond=audio,
+            text=final_text_list,
+            duration=duration,
+            steps=nfe_step,
+            cfg_strength=cfg_strength,
+            sway_sampling_coef=sway_sampling_coef,
         )
 
 # Process generated tensor