Update app.py

app.py

@@ -1,29 +1,37 @@
-pip install --upgrade pip
-python -m venv venv_name  # Create a virtual environment (if not already created)
-source venv_name/bin/activate  # Activate the virtual environment (Linux/macOS)
-pip install --upgrade pip
+import streamlit as st
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import torch
 
+# Load the pre-trained CLIP model and processor
+model_name = "facebook/nougat-base"   needed
+model = CLIPModel.from_pretrained(model_name)
+processor = CLIPProcessor.from_pretrained(model_name)
 
-import streamlit as st
-from transformers import BartForConditionalGeneration, BartTokenizer
+st.title("Image to Text Conversion App")
+
+# Input image upload
+image = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
 
-# Load the pre-trained BART model and tokenizer
-model_name = "csebuetnlp/mT5_multilingual_XLSum"
-model = BartForConditionalGeneration.from_pretrained(model_name)
-tokenizer = BartTokenizer.from_pretrained(model_name)
+if image:
+    # Display the uploaded image
+    st.image(image, caption="Uploaded Image", use_column_width=True)
 
-st.title("Text Summarization App")
+    # Process the image for text conversion
+    with torch.no_grad():
+        inputs = processor(text="a photo of " + st.session_state["alt_text"], images=image, return_tensors="pt")
+        outputs = model(**inputs)
+    
+    # Extract the textual description
+    text_description = processor.decode(outputs["text"])
+    
+    # Display the text description
+    st.subheader("Text Description:")
+    st.write(text_description)
 
-# Input text area for user input
-input_text = st.text_area("Enter text to summarize:")
+# Input for alternative text
+alt_text = st.text_area("Provide alternative text for the image:", key="alt_text")
 
-if st.button("Summarize"):
-    if input_text:
-        # Tokenize and summarize the input text
-        inputs = tokenizer(input_text, return_tensors="pt", max_length=1024, truncation=True)
-        summary_ids = model.generate(inputs["input_ids"], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
-        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-        st.subheader("Summary:")
-        st.write(summary)
+st.write("Powered by Hugging Face's CLIP model.")
 
-st.write("Powered by Hugging Face's BART model.")
+streamlit run app.py