Update app.py

app.py

@@ -1481,9 +1481,9 @@ bark_voice_preset = "v2/en_speaker_5"
 
 def bark_tts(text):
     print(f"🔁 Synthesizing TTS for: {text}")
-    inputs = processor_bark(text, return_tensors="pt", voice_preset=bark_voice_preset)
-    input_ids = inputs["input_ids"].to(model_bark.device)
-    attention_mask = inputs.get("attention_mask", None)
+    processed = processor_bark(text, return_tensors="pt", voice_preset=bark_voice_preset)
+    input_ids = processed["input_ids"].to(model_bark.device)
+    attention_mask = processed.get("attention_mask", None)
     if attention_mask is not None:
         attention_mask = attention_mask.to(model_bark.device)
 
@@ -1491,8 +1491,8 @@ def bark_tts(text):
     speech_values = model_bark.generate(
         input_ids=input_ids,
         attention_mask=attention_mask,
-        max_new_tokens=100,  # ✅ Correctly passed outside inputs
-        pad_token_id=10000   # ✅ Optional to avoid warnings
+        pad_token_id=10000,          # Optional safety
+        max_new_tokens=100           # ✅ Passed once only here
     )
     print(f"✅ Bark finished in {round(time.time() - start, 2)}s")
 
@@ -1503,6 +1503,7 @@ def bark_tts(text):
     return temp_wav.name
 
 
+
 # Whisper STT
 print("🔁 Loading Whisper model...")
 whisper_model = whisper.load_model("base", device="cuda")