Update app.py

app.py

@@ -1,14 +1,20 @@
-from transformers import ViTFeatureExtractor, ViTForImageCaptioning, AutoTokenizer
+from __future__ import annotations
+
+import gradio as gr
+import PIL.Image
+import spaces
 import torch
-from PIL import Image
+from transformers import AutoProcessor, BlipForConditionalGeneration
 
-model = ViTForImageCaptioning.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")
+DESCRIPTION = "# Image Captioning with BLIP"
 
 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}