File size: 1,397 Bytes
ce1f204 |
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 38 39 40 41 42 |
import streamlit as st
from transformers import MarianMTModel, MarianTokenizer
# Initialize the model and tokenizer
def load_model_and_tokenizer(target_lang):
model_name = f'Helsinki-NLP/opus-mt-en-{target_lang}'
model = MarianMTModel.from_pretrained(model_name)
tokenizer = MarianTokenizer.from_pretrained(model_name)
return model, tokenizer
# Function to translate text
def translate_text(text, model, tokenizer):
tokens = tokenizer(text, return_tensors="pt", padding=True)
translated_tokens = model.generate(**tokens)
translated_text = tokenizer.decode(translated_tokens[0], skip_special_tokens=True)
return translated_text
# Streamlit app
st.title("Language Translator")
# Input text
input_text = st.text_area("Enter text to translate", "Hello, how are you?")
# Language selection
target_language = st.selectbox(
"Select target language",
["fr", "de", "es", "it", "pt", "ru", "zh", "ja", "ar"]
)
# Load model and tokenizer based on selected language
if target_language:
model, tokenizer = load_model_and_tokenizer(target_language)
if st.button("Translate"):
if input_text:
translated_text = translate_text(input_text, model, tokenizer)
st.subheader("Translated text")
st.write(translated_text)
else:
st.error("Please enter some text to translate.")
streamlit run app.py
|