Update app.py

app.py

@@ -1,33 +1,24 @@
 import streamlit as st
-import io
-from PIL import Image
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from easyocr import Reader
+from transformers import pipeline
 
-
-ocr_reader = Reader(['en'])
-text_generator = AutoModelForCausalLM.from_pretrained("gpt2")
-text_tokenizer = AutoTokenizer.from_pretrained("gpt2")
-def extract_text(image):
-    return ocr_reader.readtext(image)
-def explain_text(text):
-    input_ids = text_tokenizer.encode(text, return_tensors="pt")
-    explanation_ids = text_generator.generate(input_ids, max_length=100, num_return_sequences=1)
-    explanation = text_tokenizer.decode(explanation_ids[0], skip_special_tokens=True)
-    return explanation
+# Create a text2text-generation pipeline
+pipe = pipeline("text2text-generation", model="kaist-ai/prometheus-13b-v1.0")
 
 st.title("Text Classification Model")
 uploaded_file = st.file_uploader("Upload an image:")
 
 if uploaded_file is not None:
+    # Read the uploaded image
     image = Image.open(uploaded_file)
+
+    # Extract text from the image using OCR
     ocr_results = extract_text(image)
     extracted_text = " ".join([res[1] for res in ocr_results])
-    explanation = explain_text(extracted_text)
     st.markdown("**Extracted text:**")
     st.markdown(extracted_text)
 
+    # Generate an explanation for the extracted text using the Hugging Face pipeline
+    explanation = pipe(extracted_text, max_length=100, do_sample=True)[0]["generated_text"]
     st.markdown("**Explanation:**")
     st.markdown(explanation)