Update app.py

app.py

@@ -1,29 +1,11 @@
-import streamlit as st
-from transformers import pipeline
+from transformers import PegasusTokenizer, PegasusForConditionalGeneration
 
-def main():
-    # Streamlit app interface design
-    st.title("📈 Financial Text Summarization")
-    st.write("Please enter the financial text below to generate a concise summary:")
+model_name = "human-centered-summarization/financial-summarization-pegasus"
+tokenizer = PegasusTokenizer.from_pretrained(model_name, use_fast=False)
+model = PegasusForConditionalGeneration.from_pretrained(model_name)
 
-    # User input area for text
-    user_input = st.text_area("Text Input 📝", height=300)
-
-    # Initialize the summarization pipeline only once using st.session_state
-    if 'summarizer' not in st.session_state:
-        st.session_state.summarizer = pipeline("summarization", model="human-centered-summarization/financial-summarization-pegasus")
-
-    # Button to generate summary
-    if st.button("Generate Summary"):
-        if user_input:
-            with st.spinner('Generating summary...'):
-                # Generating the summary from the input text
-                summary_result = st.session_state.summarizer(user_input, max_length=130, min_length=30, do_sample=False)
-                summary = summary_result[0]['summary_text']
-                st.write("Summary 📜:")
-                st.write(summary)
-        else:
-            st.error("Please enter some text to generate a summary.")
-
-if __name__ == "__main__":
-    main()
+text_to_summarize = "Your text here..."
+input_ids = tokenizer(text_to_summarize, return_tensors="pt").input_ids
+summary_ids = model.generate(input_ids, max_length=60, num_beams=5, early_stopping=True)
+summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+print(summary)