app.py

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

# Load multilingual model
model_name = "facebook/m2m100_418M"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

translator = pipeline("translation", model=model, tokenizer=tokenizer)

# Full language list (A-Z) supported by M2M100
languages = {
    "Afrikaans": "af",
    "Albanian": "sq",
    "Amharic": "am",
    "Arabic": "ar",
    "Armenian": "hy",
    "Assamese": "as",
    "Azerbaijani": "az",
    "Basque": "eu",
    "Belarusian": "be",
    "Bengali": "bn",
    "Bosnian": "bs",
    "Bulgarian": "bg",
    "Burmese": "my",
    "Catalan": "ca",
    "Chinese": "zh",
    "Croatian": "hr",
    "Czech": "cs",
    "Danish": "da",
    "Dutch": "nl",
    "English": "en",
    "Estonian": "et",
    "Filipino": "tl",
    "Finnish": "fi",
    "French": "fr",
    "Galician": "gl",
    "Georgian": "ka",
    "German": "de",
    "Greek": "el",
    "Gujarati": "gu",
    "Hausa": "ha",
    "Hebrew": "he",
    "Hindi": "hi",
    "Hungarian": "hu",
    "Icelandic": "is",
    "Indonesian": "id",
    "Irish": "ga",
    "Italian": "it",
    "Japanese": "ja",
    "Javanese": "jv",
    "Kannada": "kn",
    "Kazakh": "kk",
    "Khmer": "km",
    "Korean": "ko",
    "Kurdish": "ku",
    "Kyrgyz": "ky",
    "Lao": "lo",
    "Latvian": "lv",
    "Lithuanian": "lt",
    "Macedonian": "mk",
    "Malay": "ms",
    "Malayalam": "ml",
    "Maltese": "mt",
    "Marathi": "mr",
    "Mongolian": "mn",
    "Nepali": "ne",
    "Norwegian": "no",
    "Odia": "or",
    "Pashto": "ps",
    "Persian": "fa",
    "Polish": "pl",
    "Portuguese": "pt",
    "Punjabi": "pa",
    "Romanian": "ro",
    "Russian": "ru",
    "Serbian": "sr",
    "Sinhala": "si",
    "Slovak": "sk",
    "Slovenian": "sl",
    "Somali": "so",
    "Spanish": "es",
    "Sundanese": "su",
    "Swahili": "sw",
    "Swedish": "sv",
    "Tagalog": "tl",
    "Tajik": "tg",
    "Tamil": "ta",
    "Telugu": "te",
    "Thai": "th",
    "Turkish": "tr",
    "Turkmen": "tk",
    "Ukrainian": "uk",
    "Urdu": "ur",
    "Uzbek": "uz",
    "Vietnamese": "vi",
    "Welsh": "cy",
    "Xhosa": "xh",
    "Yiddish": "yi",
    "Yoruba": "yo",
    "Zulu": "zu"
}

def translate_text(text, src_lang, tgt_lang):
    tokenizer.src_lang = languages[src_lang]
    result = translator(text, src_lang=languages[src_lang], tgt_lang=languages[tgt_lang], max_length=200)
    return result[0]['translation_text']

with gr.Blocks() as demo:
    gr.Markdown("## Language Translation Tool")

    with gr.Row():
        src = gr.Dropdown(choices=list(languages.keys()), label="Source Language", value="English")
        tgt = gr.Dropdown(choices=list(languages.keys()), label="Target Language", value="French")

    input_text = gr.Textbox(lines=5, placeholder="Enter text here...", label="Input Text")
    output_text = gr.Textbox(lines=5, label="Translated Text")

    translate_btn = gr.Button("Translate")
    translate_btn.click(fn=translate_text, inputs=[input_text, src, tgt], outputs=output_text)

demo.launch()