Update app.py

app.py

@@ -1,41 +1,34 @@
 import streamlit as st
+import requests
 import torch
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, GenerationConfig
-
-# Your Hugging Face token
-hf_token = "HUGGINGFACE_TOKEN"
-
-# Update this to your model's Hugging Face path
-model_name = "waqasali1707/Bart-Base-Summarization"
-
-try:
-    tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
-    model = AutoModelForSeq2SeqLM.from_pretrained(model_name, use_auth_token=hf_token)
-except Exception as e:
-    st.error(f"Failed to load model: {e}")
-
-# Streamlit UI
-st.title("Text Summarizer")
-text = st.text_area("Enter the text to generate its Summary:")
-
-# Configuration for generation
-generation_config = GenerationConfig(max_new_tokens=100, do_sample=True, temperature=0.7)
-
-if text:
-    try:
-        # Encode input
-        inputs_encoded = tokenizer(text, return_tensors='pt')
-
-        # Generate output
-        with torch.no_grad():
-            model_output = model.generate(inputs_encoded["input_ids"], generation_config=generation_config)[0]
-
-        # Decode output
-        output = tokenizer.decode(model_output, skip_special_tokens=True)
-
-        # Display results in a box with a title
-        with st.expander("Output", expanded=True):
-            st.write(output)
-
-    except Exception as e:
-        st.error(f"An error occurred during summarization: {e}")
+from transformers import pipeline
+from transformers import BartTokenizer, BartForConditionalGeneration
+
+# Replace with your Hugging Face model repository path
+model_repo_path = 'waqasali1707/Bart-Base-Summarization'
+
+# Load the model and tokenizer
+model = BartForConditionalGeneration.from_pretrained(model_repo_path)
+tokenizer = BartTokenizer.from_pretrained(model_repo_path)
+
+# Initialize the summarization pipeline
+summarizer = pipeline('summarization', model=model,tokenizer=tokenizer)
+
+# Streamlit app layout
+st.title("Text Summarization App")
+
+# User input
+text_input = st.text_area("Enter text to summarize", height=300)
+
+# Summarize the text
+if st.button("Summarize"):
+    if text_input:
+        with st.spinner("Generating summary..."):
+            try:
+                summary = summarizer(text_input, max_length=150, min_length=30, do_sample=False)
+                st.subheader("Summary")
+                st.write(summary[0]['summary_text'])
+            except Exception as e:
+                st.error(f"Error during summarization: {e}")
+    else:
+        st.warning("Please enter some text to summarize.")