File size: 1,282 Bytes
7aac0a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
import streamlit as st
from transformers import MarianMTModel, MarianTokenizer

st.set_page_config(page_title="English โ†” Urdu Translator", layout="centered")

st.title("๐Ÿ“˜ English โ†” ุงุฑุฏูˆ Translator")

# Language options
direction = st.selectbox("Select Translation Direction", ["English to Urdu", "Urdu to English"])

# Input text
text = st.text_area("Enter Text")

# Load models and tokenizers only once using caching
@st.cache_resource
def load_model_and_tokenizer(src_lang):
    if src_lang == "en":
        model_name = "Helsinki-NLP/opus-mt-en-ur"
    else:
        model_name = "Helsinki-NLP/opus-mt-ur-en"
    tokenizer = MarianTokenizer.from_pretrained(model_name)
    model = MarianMTModel.from_pretrained(model_name)
    return tokenizer, model

# Translate
if st.button("Translate"):
    if not text.strip():
        st.warning("Please enter some text.")
    else:
        src_lang = "en" if direction == "English to Urdu" else "ur"
        tokenizer, model = load_model_and_tokenizer(src_lang)
        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
        translated = model.generate(**inputs)
        result = tokenizer.decode(translated[0], skip_special_tokens=True)
        st.success("Translation:")
        st.write(result)