Update app.py

app.py

@@ -9,7 +9,7 @@ from transformers import (
     AutoProcessor,
     AutoModelForImageTextToText,
     AutoTokenizer,
-    AutoModelForTextToSpeech,
+    AutoModelForCausalLM,
 )
 
 # -----------------------------
@@ -35,7 +35,7 @@ stt_model = AutoModelForImageTextToText.from_pretrained(
 
 print("Loading TTS model...")
 tts_tokenizer = AutoTokenizer.from_pretrained(TTS_MODEL_ID)
-tts_model = AutoModelForTextToSpeech.from_pretrained(
+tts_model = AutoModelForCausalLM.from_pretrained(
     TTS_MODEL_ID,
     torch_dtype=DTYPE,
 ).to(DEVICE)