Update app.py

app.py

@@ -1,20 +1,14 @@
-from __future__ import annotations
-
-import gradio as gr
-import PIL.Image
-import spaces
+from transformers import ViTFeatureExtractor, ViTForImageToText, AutoTokenizer
 import torch
-from transformers import AutoProcessor, BlipForConditionalGeneration
+from PIL import Image
 
-DESCRIPTION = "# Image Captioning with BLIP"
+model = ViTForImageToText.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 
-model_id = "Salesforce/blip-image-captioning-large"
-processor = AutoProcessor.from_pretrained(model_id)
-model = BlipForConditionalGeneration.from_pretrained(model_id).to(device)
-
 max_length = 16
 num_beams = 4
 gen_kwargs = {"max_length": max_length, "num_beams": num_beams}