Update app.py

app.py

@@ -29,17 +29,17 @@ def clean_text(text):
 def split_text_into_paragraphs(text):
     return text.split('\n\n')
 
-def summarize_text_pegasus(text, max_length=800):
+def summarize_text_pegasus(text, max_length=512):
     inputs = tokenizer(text, truncation=True, padding="longest", return_tensors="pt")
     summary_ids = model.generate(
-        inputs["input_ids"], max_length=max_length, min_length=200,
+        inputs["input_ids"], max_length=max_length, min_length=50,
         length_penalty=2.0, num_beams=4, early_stopping=True
     )
     return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
-def summarize_large_document(text, max_length=800):
+def summarize_large_document(text, max_length=512):
     paragraphs = split_text_into_paragraphs(text)
-    summaries = [summarize_text_pegasus(paragraph, max_length=max_length) for paragraph in paragraphs]
+    summaries = [summarize_text_pegasus(paragraph, max_length=max_length) for paragraph in paragraphs[:10]]  # Limit to first 10 paragraphs
     return " ".join(summaries)
 
 def text_to_speech(text, lang="en"):
@@ -76,7 +76,7 @@ if uploaded_file:
 
     if st.button("Summarize Document"):
         with st.spinner("Summarizing document..."):
-            summary = summarize_large_document(cleaned_text, max_length=800)
+            summary = summarize_large_document(cleaned_text, max_length=512)
         st.text_area("Summary", summary, height=300)
 
         if st.button("Convert Summary to Audiobook"):