YouTube Link and Other Languages

app.py

@@ -7,6 +7,7 @@ from fpdf import FPDF
 from pptx import Presentation
 import subprocess
 import shlex
+import yt_dlp
 
 # Load the Whisper model (smaller model for faster transcription)
 model = whisper.load_model("tiny")
@@ -17,6 +18,15 @@ def load_translation_model(target_language):
         "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
     }
     target_lang_code = lang_codes.get(target_language)
     if not target_lang_code:
@@ -121,10 +131,25 @@ def write_ppt(transcription, output_file, tokenizer=None, translation_model=None
         title.text = f"{i + 1}. {text.strip()}"
     ppt.save(output_file)
 
+# Function to download YouTube video
+def download_youtube_video(url):
+    ydl_opts = {
+        'format': 'mp4',
+        'outtmpl': 'downloaded_video.mp4',
+    }
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        ydl.download([url])
+    return 'downloaded_video.mp4'
+
 # Transcribing video and generating output
-def transcribe_video(video_file, language, target_language, output_format):
-    result = model.transcribe(video_file.name, language=language)
-    video_name = os.path.splitext(video_file.name)[0]
+def transcribe_video(video_file, video_url, language, target_language, output_format):
+    if video_url:
+        video_file_path = download_youtube_video(video_url)
+    else:
+        video_file_path = video_file.name
+
+    result = model.transcribe(video_file_path, language=language)
+    video_name = os.path.splitext(video_file_path)[0]
     if target_language != "en":
         try:
             tokenizer, translation_model = load_translation_model(target_language)
@@ -141,13 +166,13 @@ def transcribe_video(video_file, language, target_language, output_format):
     elif output_format == "Video with Hardsub":
         output_video = f"{video_name}_with_subtitles.mp4"
         try:
-            embed_hardsub_in_video(video_file.name, srt_file, output_video)
+            embed_hardsub_in_video(video_file_path, srt_file, output_video)
             return output_video
         except Exception as e:
             raise RuntimeError(f"Error embedding subtitles in video: {e}")
     elif output_format == "Word":
         word_file = f"{video_name}.docx"
-        write_word(result, word_file, tokenizer, translation_model)
+        write_word(result, word_file, tokenizer, translation_model, target_language)
         return word_file
     elif output_format == "PDF":
         pdf_file = f"{video_name}.pdf"
@@ -158,19 +183,24 @@ def transcribe_video(video_file, language, target_language, output_format):
         write_ppt(result, ppt_file, tokenizer, translation_model)
         return ppt_file
 
-# Gradio interface with better UI
+# Gradio interface with YouTube URL
 iface = gr.Interface(
     fn=transcribe_video,
     inputs=[
-        gr.File(label="Upload Video File"),
+        gr.File(label="Upload Video File (or leave empty for YouTube link)", optional=True),
+        gr.Textbox(label="YouTube Video URL (optional)", placeholder="https://www.youtube.com/watch?v=..."),
         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", "fr"], value="fa"),
+        gr.Dropdown(
+            label="Select Subtitle Translation Language", 
+            choices=["en", "fa", "es", "fr", "de", "it", "pt", "ar", "zh", "hi", "ja", "ko", "ru"], 
+            value="fa"
+        ),
         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",
+    title="Video Subtitle Generator with Translation & Multi-Format Output (Supports YouTube)",
     description=(
-        "This tool allows you to generate subtitles from a video file using Whisper, "
+        "This tool allows you to generate subtitles from a video file or YouTube link using Whisper, "
         "translate the subtitles into multiple languages using M2M100, and export them "
         "in various formats including SRT, hardcoded subtitles in video, Word, PDF, or PowerPoint."
     ),
@@ -178,5 +208,4 @@ iface = gr.Interface(
     live=False  # No live interaction needed
 )
 
-if __name__ == "__main__":
-    iface.launch()
+iface.launch()