Update app.py

app.py

@@ -5,7 +5,7 @@ from PIL import Image
 import pandas as pd
 from lavis.models import load_model_and_preprocess
 from lavis.processors import load_processor
-from transformers import CLIPProcessor, CLIPModel
+from transformers import CLIPTokenizerFast, CLIPModel  # Import CLIPTokenizerFast
 
 # Load model and preprocessors for Image-Text Matching (LAVIS)
 device = torch.device("cuda") if torch.cuda.is_available() else "cpu"
@@ -13,10 +13,9 @@ model_itm, vis_processors, text_processors = load_model_and_preprocess("blip2_im
 
 # Load model and processor for Image Captioning (TextCaps)
 model_caption = CLIPModel.from_pretrained("microsoft/git-large-r-textcaps")
-processor_caption = CLIPProcessor.from_pretrained("microsoft/git-large-r-textcaps")
+processor_caption = CLIPTokenizerFast.from_pretrained("microsoft/git-large-r-textcaps", from_slow=True)  # Convert tokenizer
 
 # List of statements for Image-Text Matching
-# List of statements (Make sure to fully define this list with actual statements)
 statements = [
     "cartoon, figurine, or toy",
     "appears to be for children",
@@ -68,5 +67,4 @@ def process_images_and_statements(image):
 image_input = gr.inputs.Image()
 output = gr.outputs.Textbox(label="Results")
 
-iface = gr.Interface(fn=process_images_and_statements, inputs=image_input, outputs=output, title="Image Captioning and Image-Text Matching")
-iface.launch()
+iface = gr.Interface(fn=process_images_and_statements, inputs=image_input, outputs=output, title="