app.py

import gradio as gr
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline

# Load the translation model and tokenizer from Hugging Face
# Here, we use the "Helsinki-NLP" translation models
model_name = "Helsinki-NLP/opus-mt-en-fr"  # Example model for English to French
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
translator = pipeline("translation", model=model, tokenizer=tokenizer)

# Define the translation function
def translate_text(text, target_language):
    model_name = f"Helsinki-NLP/opus-mt-en-{target_language}"
    translator = pipeline("translation", model=model_name)
    translation = translator(text)[0]['translation_text']
    return translation

# Set up the Gradio interface
languages = {
    "en": "English",
    "es": "Spanish",
    "fr": "French",
    "de": "German",
    "zh": "Chinese (Mandarin)",
    "ja": "Japanese",
    "ko": "Korean",
    "it": "Italian",
    "pt": "Portuguese",
    "ru": "Russian",
    "hi": "Hindi",
    "ar": "Arabic",
    "nl": "Dutch",
    "tr": "Turkish",
    "el": "Greek",
    "ur": "Urdu"
}


iface = gr.Interface(
    fn=translate_text,
    inputs=[
        gr.inputs.Textbox(label="Enter text to translate"),
        gr.inputs.Dropdown(list(languages.keys()), label="Target Language", type="value")
    ],
    outputs="text",
    live=True,
    title="Text Translator",
    description="Translate text into multiple languages using Hugging Face models."
)

iface.launch()