Update app.py

app.py

@@ -1,31 +1,25 @@
 import streamlit as st
-from transformers import MarianMTModel, MarianTokenizer
+from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-# Install SentencePiece if not already installed
-try:
-    import sentencepiece
-except ImportError:
-    st.error("The SentencePiece library is required but not installed. Please install it using `pip install sentencepiece` and restart the application.")
-    st.stop()
-
-# Load the model and tokenizer
+# Load the T5 model and tokenizer
 @st.cache_resource
 def load_model():
-    model_name = "Helsinki-NLP/opus-mt-en-ur"
-    tokenizer = MarianTokenizer.from_pretrained(model_name)
-    model = MarianMTModel.from_pretrained(model_name)
+    model_name = "t5-small"
+    tokenizer = T5Tokenizer.from_pretrained(model_name)
+    model = T5ForConditionalGeneration.from_pretrained(model_name)
     return model, tokenizer
 
 model, tokenizer = load_model()
 
 def translate_text(text, model, tokenizer):
-    inputs = tokenizer.encode(text, return_tensors="pt", truncation=True)
-    outputs = model.generate(inputs, max_length=1024, num_beams=5, early_stopping=True)
+    input_text = f"translate English to Urdu: {text}"
+    inputs = tokenizer.encode(input_text, return_tensors="pt", truncation=True)
+    outputs = model.generate(inputs, max_length=512, num_beams=5, early_stopping=True)
     translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return translated_text
 
 # Streamlit UI
-st.title("English to Urdu Translation")
+st.title("English to Urdu Translation with T5")
 
 # Input text from the user
 text_to_translate = st.text_area("Enter English text to translate:")
@@ -34,3 +28,5 @@ if text_to_translate.strip():
     with st.spinner("Translating..."):
         translated_text = translate_text(text_to_translate, model, tokenizer)
     st.markdown(f"### Translated Text:\n{translated_text}")
+
+