import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_name2 = "Mhassanen/nllb-200-600M-En-Ar-finetuned"
tokenizer = AutoTokenizer.from_pretrained(model_name2, src_lang="eng_Latn", tgt_lang="arz_Arab")
model = AutoModelForSeq2SeqLM.from_pretrained(model_name2)

def translate2(text):
    inputs = tokenizer(text, return_tensors="pt", padding=True)
    translated_tokens = model.generate(**inputs)
    translated_text = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
    return translated_text[0]


# st.set_page_config(page_title="", page_icon="logo.png")

with st.sidebar:
    # st.image("logo.png", width=70)
    # st.markdown('<div style="position: absolute; left: 5px;"></div>', unsafe_allow_html=True)
    
    st.markdown("## About")
    st.markdown("---")

    st.markdown('''
  This App powered by [Mhassanen/nllb-200-600M-En-Ar-finetuned](https://huggingface.co./Mhassanen/nllb-200-600M-En-Ar-finetuned) Language model
    ''')
    # st.markdown("---")


st.title("English to Arabic Translation")

text_to_translate = st.text_area("Enter text in English:")

if st.button("Translate"):
    if text_to_translate:
        with st.spinner("Translating..."):
            translation = translate2(text_to_translate)
            st.success("Translation completed!")
            st.text_area("Translated text in Arabic:", translation, height=200)
    else:
        st.warning("Please enter some text to translate.")