Update app.py

app.py

@@ -1,16 +1,10 @@
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import T5Tokenizer, AutoModelForSeq2SeqLM
 
-# Function to split text into smaller chunks
-def chunk_text(text, max_length=512):
-    words = text.split()
-    for i in range(0, len(words), max_length):
-        yield " ".join(words[i:i + max_length])
-
-# Load the Hugging Face model
+# Load the Hugging Face model with SentencePiece tokenizer
 @st.cache_resource
 def load_model():
-    tokenizer = AutoTokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")
+    tokenizer = T5Tokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")
     model = AutoModelForSeq2SeqLM.from_pretrained("Vamsi/T5_Paraphrase_Paws")
     return tokenizer, model
 
@@ -28,17 +22,20 @@ if st.button("Paraphrase"):
     if input_text.strip():
         with st.spinner("Paraphrasing... Please wait."):
             try:
-                paraphrased_text = ""
-                for chunk in chunk_text(input_text, max_length=512):
-                    # Prepare input for the model
-                    inputs = tokenizer.encode("paraphrase: " + chunk, return_tensors="pt")
-                    
-                    # Generate paraphrased output
-                    outputs = model.generate(inputs, num_beams=5, temperature=0.7, early_stopping=True)
-                    paraphrased_text += tokenizer.decode(outputs[0], skip_special_tokens=True) + " "
+                # Prepare input for the model
+                inputs = tokenizer.encode("paraphrase: " + input_text, 
+                                          return_tensors="pt")
                 
+                # Generate paraphrased output
+                outputs = model.generate(
+                    inputs, 
+                    num_beams=5, 
+                    temperature=0.7, 
+                    early_stopping=True
+                )
+                paraphrased_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
                 st.success("Here is the paraphrased text:")
-                st.write(paraphrased_text.strip())
+                st.write(paraphrased_text)
             except Exception as e:
                 st.error(f"An error occurred: {e}")
     else: