app.py

import requests
import pandas as pd
import gradio as gr
from transformers import MarianMTModel, MarianTokenizer

# Fetch and parse language options from the provided URL
url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md"
response = requests.get(url)
df = pd.read_csv(response.url, delimiter="|", skiprows=2, header=None).dropna(axis=1, how='all')
df.columns = ['ISO 639-1', 'ISO 639-2', 'Language Name', 'Native Name']
df['ISO 639-1'] = df['ISO 639-1'].str.strip()

# Prepare language options for the dropdown
language_options = [(row['ISO 639-1'], f"{row['ISO 639-1']}") for index, row in df.iterrows()]

def translate_text(text, source_language_code, target_language_code):
    # Construct model name using ISO 639-1 codes
    model_name = f"Helsinki-NLP/opus-mt-{source_language_code}-{target_language_code}"

    # Check if source and target languages are the same, which is not supported for translation
    if source_language_code == target_language_code:
        return "Translation between the same languages is not supported."

    # Load tokenizer and model
    try:
        tokenizer = MarianTokenizer.from_pretrained(model_name)
        model = MarianMTModel.from_pretrained(model_name)
    except Exception as e:
        return f"Failed to load model for {source_language_code} to {target_language_code}: {str(e)}"

    # Translate text
    translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512))
    translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
    
    return translated_text

source_language_dropdown = gr.Dropdown(choices=language_options, label="Source Language")
target_language_dropdown = gr.Dropdown(choices=language_options, label="Target Language")

iface = gr.Interface(
    fn=translate_text,
    inputs=[gr.Textbox(lines=2, placeholder="Enter text to translate..."), source_language_dropdown, target_language_dropdown],
    outputs=gr.Textbox(),
    title="Translator API",
    description="We use model from [Language Technology Research Group at the University of Helsinki](https://huggingface.co/Helsinki-NLP). For web use please visit [this space](https://huggingface.co/spaces/Lenylvt/Translator). 🔴 If you have this error : 'Failed to load model for fr to aa: Helsinki-NLP/opus-mt-fr-aa is not a local folder and is not a valid model identifier listed on https://huggingface.co/models If this is a private repository, make sure to pass a token having permission to this repo either by logging in with huggingface-cli login or by passing token=<your_token>', its because the language is not available."
)

iface.launch()