Update app.py

app.py

@@ -2,30 +2,23 @@ import streamlit as st
 import torch
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-# Load the pre-trained model and tokenizer
-model_name = "sarahai/ruT5-base-summarizer"  # Adjust if using a different model
+
+model_name = "sarahai/ruT5-base-summarizer"  
 tokenizer = T5Tokenizer.from_pretrained(model_name)
 model = T5ForConditionalGeneration.from_pretrained(model_name)
 
 def summarize(text):
-    """Summarizes the input text using the T5 model.
-
-    Args:
-        text (str): The text to be summarized.
 
-    Returns:
-        str: The generated summary of the input text.
-    """
 
     try:
-        # Preprocess the input text
+        
         input_ids = tokenizer(text, return_tensors="pt", padding="max_length").input_ids
 
-        # Generate summary
+        
         outputs = model.generate(
             input_ids,
-            max_length=100,
-            min_length=50,
+            max_length=250,
+            min_length=150,
             length_penalty=2.0,
             num_beams=4,
             early_stopping=True,
@@ -35,17 +28,17 @@ def summarize(text):
         return summary
 
     except Exception as e:
-        return f"Error: {str(e)}"
+        return f"Ошибка: {str(e)}"
 
-st.title("Hugging Face T5 Summarizer")
-st.write("Enter the text you want to summarize (in Russian):")
+st.title("Суммаризатор")
+st.write("Введите текст :")
 
 user_input = st.text_area("", height=200)
 
-if st.button("Summarize"):
+if st.button("Суммаризовать"):
     if user_input:
         summary = summarize(user_input)
-        st.success(f"Summary:\n{summary}")
+        st.success(f"Результат:\n{summary}")
     else:
-        st.warning("Please enter some text to summarize.")
+        st.warning("Пожалуйста, введите хотя бы маленький текст")