Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import whisper | |
| import os | |
| from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer | |
| from docx import Document | |
| from reportlab.pdfgen import canvas | |
| from reportlab.pdfbase.ttfonts import TTFont | |
| from reportlab.pdfbase import pdfmetrics | |
| from reportlab.lib.pagesizes import A4 | |
| import arabic_reshaper | |
| from bidi.algorithm import get_display | |
| from pptx import Presentation | |
| import subprocess | |
| import shlex | |
| # Define available Whisper models | |
| whisper_models = { | |
| "Tiny (Fast, Less Accurate)": "tiny", | |
| "Base (Medium Speed, Medium Accuracy)": "base", | |
| "Small (Good Speed, Good Accuracy)": "small", | |
| "Medium (Slow, High Accuracy)": "medium", | |
| "Large (Very Slow, Highest Accuracy)": "large" | |
| } | |
| # Load M2M100 translation model for different languages | |
| def load_translation_model(target_language): | |
| lang_codes = { | |
| "fa": "fa", # Persian (Farsi) | |
| "es": "es", # Spanish | |
| "fr": "fr", # French | |
| "de": "de", # German | |
| "it": "it", # Italian | |
| "pt": "pt", # Portuguese | |
| "ar": "ar", # Arabic | |
| "zh": "zh", # Chinese | |
| "hi": "hi", # Hindi | |
| "ja": "ja", # Japanese | |
| "ko": "ko", # Korean | |
| "ru": "ru", # Russian | |
| "fi": "fi" # Finnish | |
| } | |
| target_lang_code = lang_codes.get(target_language) | |
| if not target_lang_code: | |
| raise ValueError(f"Translation model for {target_language} not supported") | |
| tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M") | |
| translation_model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M") | |
| tokenizer.src_lang = "en" | |
| tokenizer.tgt_lang = target_lang_code | |
| return tokenizer, translation_model | |
| def translate_text(text, tokenizer, model): | |
| try: | |
| inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True) | |
| translated = model.generate(**inputs, forced_bos_token_id=tokenizer.get_lang_id(tokenizer.tgt_lang)) | |
| return tokenizer.decode(translated[0], skip_special_tokens=True) | |
| except Exception as e: | |
| raise RuntimeError(f"Error during translation: {e}") | |
| # (Other code remains unchanged) | |
| # Gradio Interface setup | |
| iface = gr.Interface( | |
| fn=transcribe_video, | |
| inputs=[ | |
| gr.File(label="Upload Video File"), | |
| gr.Dropdown(label="Select Original Video Language", choices=["en", "es", "fr", "de", "it", "pt"], value="en"), | |
| gr.Dropdown(label="Select Subtitle Translation Language", choices=["en", "fa", "es", "de", "fr", "it", "pt", "fi"], value="fa"), | |
| gr.Dropdown(label="Select Whisper Model", choices=list(whisper_models.keys()), value="Tiny (Fast, Less Accurate)"), | |
| gr.Radio(label="Choose Output Format", choices=["SRT", "Video with Hardsub", "Word", "PDF", "PowerPoint"], value="Video with Hardsub") | |
| ], | |
| outputs=gr.File(label="Download File"), | |
| title="Video Subtitle Generator with Translation & Multi-Format Output", | |
| description=( | |
| "This tool allows you to generate subtitles from a video file, translate the subtitles into multiple languages using M2M100, " | |
| "and export them in various formats including SRT, hardcoded subtitles in video, Word, PDF, or PowerPoint." | |
| ), | |
| theme="compact", | |
| live=False | |
| ) | |
| # Run the interface | |
| iface.launch(share=True) | |