Update app.py

app.py

@@ -1482,17 +1482,27 @@ 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)
-    inputs = {k: v.to(model_bark.device) for k, v in inputs.items()}
-    inputs["max_new_tokens"] = 100  # Add this to the input dictionary
+    input_ids = inputs["input_ids"].to(model_bark.device)
+    attention_mask = inputs.get("attention_mask", None)
+    if attention_mask is not None:
+        attention_mask = attention_mask.to(model_bark.device)
+
     start = time.time()
-    speech_values = model_bark.generate(**inputs)
+    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
+    )
     print(f"✅ Bark finished in {round(time.time() - start, 2)}s")
+
     speech = speech_values.cpu().numpy().squeeze()
     speech = (speech * 32767).astype(np.int16)
     temp_wav = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
     wavfile.write(temp_wav.name, 22050, speech)
     return temp_wav.name
 
+
 # Whisper STT
 print("🔁 Loading Whisper model...")
 whisper_model = whisper.load_model("base", device="cuda")