Update app.py

app.py

@@ -1,15 +1,15 @@
-from transformers import pipeline, BlipForConditionalGeneration, BlipProcessor, AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import pipeline, BlipForConditionalGeneration, BlipProcessor
 import torchaudio
 from torchaudio.transforms import Resample
 import torch
 import gradio as gr
 
 # Initialize TTS model from Hugging Face
-tts_model_name = "suno/bark"
+tts_model_name = "Kamonwan/blip-image-captioning-new"
 tts = pipeline(task="text-to-speech", model=tts_model_name)
 
 # Initialize Blip model for image captioning
-model_id = "dblasko/blip-dalle3-img2prompt"
+model_id = "Kamonwan/blip-image-captioning-new"
 blip_model = BlipForConditionalGeneration.from_pretrained(model_id)
 blip_processor = BlipProcessor.from_pretrained(model_id)