app.py

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

def fetch_languages(url):
    response = requests.get(url)
    if response.status_code == 200:
        csv_content = response.content.decode('utf-8')
        df = pd.read_csv(io.StringIO(csv_content), 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()
        language_options = [(row['ISO 639-1'], f"{row['ISO 639-1']} - {row['Language Name']}") for index, row in df.iterrows()]
        return language_options
    else:
        return []

def text_to_srt(text):
    lines = text.split('\n')
    srt_content = ""
    for i, line in enumerate(lines):
        if line.strip() == "":
            continue
        try:
            times, content = line.split(']', 1)
            start, end = times[1:].split(' -> ')
            if start.count(":") == 1:
                start = "00:" + start
            if end.count(":") == 1:
                end = "00:" + end
            srt_content += f"{i+1}\n{start.replace('.', ',')} --> {end.replace('.', ',')}\n{content.strip()}\n\n"
        except ValueError:
            continue
    temp_file_path = '/tmp/output.srt'
    with open(temp_file_path, 'w', encoding='utf-8') as file:
        file.write(srt_content)
    return temp_file_path

def translate_text(text, source_language_code, target_language_code):
    model_name = f"Helsinki-NLP/opus-mt-{source_language_code}-{target_language_code}"
    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)}"
    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(input_file, source_language_code, target_language_code):
    subs = pysrt.open(input_file)
    for sub in subs:
        sub.text = translate_text(sub.text, source_language_code, target_language_code)
    translated_srt_path = input_file.replace(".srt", f"_{target_language_code}.srt")
    subs.save(translated_srt_path)
    return translated_srt_path

def add_subtitle_to_video(input_video, subtitle_file, soft_subtitle=True):
    video_input_stream = ffmpeg.input(input_video)
    subtitle_input_stream = ffmpeg.input(subtitle_file)
    input_video_name = os.path.splitext(os.path.basename(input_video))[0]
    output_video = f"/tmp/{input_video_name}_subtitled.mp4"

    if soft_subtitle:
        stream = ffmpeg.output(
            video_input_stream, subtitle_input_stream, output_video,
            **{"c": "copy", "c:s": "mov_text"}
        )
    else:
        stream = ffmpeg.output(
            video_input_stream, output_video,
            vf=f"subtitles={subtitle_file}"
        )

    ffmpeg.run(stream, overwrite_output=True)
    return output_video

def process_video(input_video, text_transcription, video_language, target_language):
    srt_path = text_to_srt(text_transcription)
    translated_srt_path = translate_srt(srt_path, video_language, target_language)
    output_video = add_subtitle_to_video(input_video.name, translated_srt_path)
    return output_video

language_url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md"
video_language_options = fetch_languages(language_url)

with gr.Blocks() as app:
    with gr.Row():
        input_video = gr.Video(label="Video File")
        text_transcription = gr.TextArea(label="Text Transcription")
        video_language = gr.Dropdown(choices=video_language_options, label="Language of the Video")
        target_language = gr.Dropdown(choices=video_language_options, label="Language Translated")
    output_video = gr.Video(label="Video with Translated Subtitles")

    input_video.change(fn=process_video, inputs=[input_video, text_transcription, video_language, target_language], outputs=output_video)

app.launch()