app.py

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

# Fetch and parse language options
url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md"
response = requests.get(url)
df = pd.read_csv(io.StringIO(response.text), 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']} - {row['Language Name'].strip()}") 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
    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

def translate_srt(file_info, source_language_code, target_language_code):
    srt_content = file_info["content"].decode("utf-8")
    translated_lines = []
    for line in srt_content.split("\n"):
        if line.isdigit() or "-->" in line:
            translated_lines.append(line)
        elif line.strip() == "":
            translated_lines.append(line)
        else:
            translated_text = translate_text(line, source_language_code, target_language_code)
            translated_lines.append(translated_text)
    translated_srt_content = "\n".join(translated_lines)
    output_path = "/mnt/data/translated_srt.srt"
    with open(output_path, "w", encoding="utf-8") as file:
        file.write(translated_srt_content)
    return output_path

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_srt,
    inputs=[
        gr.File(label="Upload SRT File"),
        source_language_dropdown,
        target_language_dropdown
    ],
    outputs=gr.File(label="Download Translated SRT File"),
    title="SRT Translator",
    description="Translate SubRip Text (SRT) subtitle files. This tool uses models from the Language Technology Research Group at the University of Helsinki."
)

iface.launch()