Create app.py

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import torch
+import os
+from faster_whisper import WhisperModel
+from moviepy.editor import VideoFileClip
+
+# Define the model and device
+MODEL_NAME = "Systran/faster-whisper-large-v3"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+compute_type = "float32" if device == "cuda" else "int8"
+
+# Load the Whisper model
+model = WhisperModel(MODEL_NAME, device=device, compute_type=compute_type)
+
+# List of all supported languages in Whisper
+SUPPORTED_LANGUAGES = [
+    "Auto Detect", "English", "Chinese", "German", "Spanish", "Russian", "Korean", 
+    "French", "Japanese", "Portuguese", "Turkish", "Polish", "Catalan", "Dutch", 
+    "Arabic", "Swedish", "Italian", "Indonesian", "Hindi", "Finnish", "Vietnamese", 
+    "Hebrew", "Ukrainian", "Greek", "Malay", "Czech", "Romanian", "Danish", 
+    "Hungarian", "Tamil", "Norwegian", "Thai", "Urdu", "Croatian", "Bulgarian", 
+    "Lithuanian", "Latin", "Maori", "Malayalam", "Welsh", "Slovak", "Telugu", 
+    "Persian", "Latvian", "Bengali", "Serbian", "Azerbaijani", "Slovenian", 
+    "Kannada", "Estonian", "Macedonian", "Breton", "Basque", "Icelandic", 
+    "Armenian", "Nepali", "Mongolian", "Bosnian", "Kazakh", "Albanian", 
+    "Swahili", "Galician", "Marathi", "Punjabi", "Sinhala", "Khmer", "Shona", 
+    "Yoruba", "Somali", "Afrikaans", "Occitan", "Georgian", "Belarusian", 
+    "Tajik", "Sindhi", "Gujarati", "Amharic", "Yiddish", "Lao", "Uzbek", 
+    "Faroese", "Haitian Creole", "Pashto", "Turkmen", "Nynorsk", "Maltese", 
+    "Sanskrit", "Luxembourgish", "Burmese", "Tibetan", "Tagalog", "Malagasy", 
+    "Assamese", "Tatar", "Hawaiian", "Lingala", "Hausa", "Bashkir", "Javanese", 
+    "Sundanese"
+]
+
+def extract_audio_from_video(video_file):
+    """Extract audio from a video file and save it as a WAV file."""
+    video = VideoFileClip(video_file)
+    audio_file = "extracted_audio.wav"
+    video.audio.write_audiofile(audio_file, fps=16000)
+    return audio_file
+
+def generate_subtitles(audio_file, language="Auto Detect"):
+    """Generate subtitles from an audio file using Whisper."""
+    # Transcribe the audio
+    segments, info = model.transcribe(
+        audio_file,
+        task="transcribe",
+        language=None if language == "Auto Detect" else language.lower(),
+        word_timestamps=True
+    )
+    
+    # Generate SRT format subtitles
+    srt_subtitles = ""
+    for i, segment in enumerate(segments, start=1):
+        start_time = segment.start
+        end_time = segment.end
+        text = segment.text.strip()
+        
+        # Format timestamps for SRT
+        start_time_srt = format_timestamp(start_time)
+        end_time_srt = format_timestamp(end_time)
+        
+        # Add to SRT
+        srt_subtitles += f"{i}\n{start_time_srt} --> {end_time_srt}\n{text}\n\n"
+    
+    return srt_subtitles
+
+def format_timestamp(seconds):
+    """Convert seconds to SRT timestamp format (HH:MM:SS,mmm)."""
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    seconds = seconds % 60
+    milliseconds = int((seconds - int(seconds)) * 1000)
+    return f"{hours:02}:{minutes:02}:{int(seconds):02},{milliseconds:03}"
+
+def process_video(video_file, language="Auto Detect"):
+    """Process a video file to generate subtitles."""
+    # Extract audio from the video
+    audio_file = extract_audio_from_video(video_file)
+    
+    # Generate subtitles
+    subtitles = generate_subtitles(audio_file, language)
+    
+    # Save subtitles to an SRT file
+    srt_file = "subtitles.srt"
+    with open(srt_file, "w", encoding="utf-8") as f:
+        f.write(subtitles)
+    
+    # Clean up extracted audio file
+    os.remove(audio_file)
+    
+    return srt_file
+
+# Custom CSS for styling
+custom_css = """
+.gradio-container {
+    background: linear-gradient(135deg, #f5f7fa, #c3cfe2);
+    font-family: 'Arial', sans-serif;
+}
+.header {
+    text-align: center;
+    padding: 20px;
+    background: linear-gradient(135deg, #6a11cb, #2575fc);
+    color: white;
+    border-radius: 10px;
+    margin-bottom: 20px;
+}
+.header h1 {
+    font-size: 2.5rem;
+    margin: 0;
+}
+.header p {
+    font-size: 1.2rem;
+    margin: 10px 0 0;
+}
+.tab {
+    background: white;
+    padding: 20px;
+    border-radius: 10px;
+    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
+}
+"""
+
+# Define the Gradio interface
+with gr.Blocks(css=custom_css, title="AutoSubGen - AI Video Subtitle Generator") as demo:
+    # Header
+    with gr.Column(elem_classes="header"):
+        gr.Markdown("# AutoSubGen")
+        gr.Markdown("### AI-Powered Video Subtitle Generator")
+        gr.Markdown("Automatically generate subtitles for your videos in SRT format. Supports 100+ languages and auto-detection.")
+    
+    # Main content
+    with gr.Tab("Generate Subtitles", elem_classes="tab"):
+        gr.Markdown("### Upload a video file to generate subtitles.")
+        with gr.Row():
+            video_input = gr.Video(label="Upload Video File", scale=2)
+            language_dropdown = gr.Dropdown(
+                choices=SUPPORTED_LANGUAGES,
+                label="Select Language",
+                value="Auto Detect",
+                scale=1
+            )
+        generate_button = gr.Button("Generate Subtitles", variant="primary")
+        subtitle_output = gr.File(label="Download Subtitles (SRT)")
+    
+    # Link button to function
+    generate_button.click(
+        process_video,
+        inputs=[video_input, language_dropdown],
+        outputs=subtitle_output
+    )
+
+# Launch the Gradio interface
+demo.launch()