Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from transformers import BlipProcessor, BlipForConditionalGeneration, AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from transformers import AutoTokenizer
 
 # Initialize Blip model for image captioning
 model_id = "dblasko/blip-dalle3-img2prompt"
@@ -7,9 +8,9 @@ blip_model = BlipForConditionalGeneration.from_pretrained(model_id)
 blip_processor = BlipProcessor.from_pretrained(model_id)
 
 # Initialize TTS model from Hugging Face
-tts_model_name = "tts-mozilla/tts-ljspeech-multilingual"
-tts_tokenizer = AutoTokenizer.from_pretrained(tts_model_name)
-tts_model = AutoModelForSeq2SeqLM.from_pretrained(tts_model_name)
+model_name = "facebook/tts-crdnn-baker-softmax"
+tts_tokenizer = AutoTokenizer.from_pretrained(model_name)
+tts_model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 tts = pipeline(task="text2speech", model=tts_model, tokenizer=tts_tokenizer)
 
 def generate_caption(image):