Upload 3 files

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+from transformers import pipeline
+import yt_dlp
+import whisper
+import os
+import uuid
+import re
+
+# Delete temporary files
+def clean_temp_files():
+    temp_files = ["temp_video.mp4", "temp_audio.mp3"]
+    for file in temp_files:
+        if os.path.exists(file):
+            os.remove(file)
+
+# Download YouTube video
+def download_video(video_url):
+    try:
+        ydl_opts = {
+            'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]',
+            'outtmpl': 'temp_video.mp4',
+            'quiet': True,
+            'no_warnings': True,
+        }
+        
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([video_url])
+        return "temp_video.mp4"
+    except Exception as e:
+        print(f"Download error: {e}")
+        return None
+
+# Extract audio (temporary)
+def extract_audio(video_path):
+    os.system(f"ffmpeg -i \"{video_path}\" -vn -acodec libmp3lame -q:a 3 \"temp_audio.mp3\" -y")
+    return "temp_audio.mp3" if os.path.exists("temp_audio.mp3") else None
+
+# Transcribe audio
+def transcribe_audio(audio_path):
+    try:
+        model = whisper.load_model("base")
+        result = model.transcribe(audio_path)
+        return result['text']
+    except Exception as e:
+        print(f"Transcription error: {e}")
+        return None
+
+# Classify content
+def classify_content(text):
+    try:
+        if not text or len(text.strip()) == 0:
+            return None, None
+            
+        classifier = pipeline("zero-shot-classification", 
+                           model="facebook/bart-large-mnli")
+        
+        labels = ["educational", "entertainment", "news", "political", 
+                "religious", "technical", "advertisement", "social"]
+        
+        result = classifier(text, 
+                          candidate_labels=labels, 
+                          hypothesis_template="This text is about {}.")
+        
+        return result['labels'][0], result['scores'][0]
+    except Exception as e:
+        print(f"Classification error: {e}")
+        return None, None
+
+# Main processing function
+def process_video(video_url):
+    clean_temp_files()
+    
+    if not video_url or len(video_url.strip()) == 0:
+        return "Please enter a valid YouTube URL", ""
+    
+    if "youtube.com" not in video_url and "youtu.be" not in video_url:
+        return "Please enter a valid YouTube URL", ""
+    
+    # Download video
+    video_path = download_video(video_url)
+    if not video_path:
+        return "Failed to download video", ""
+    
+    # Extract audio
+    audio_path = extract_audio(video_path)
+    if not audio_path:
+        clean_temp_files()
+        return "Failed to extract audio", ""
+    
+    # Transcribe
+    transcription = transcribe_audio(audio_path)
+    if not transcription:
+        clean_temp_files()
+        return "Failed to transcribe audio", ""
+    
+    # Classify
+    category, confidence = classify_content(transcription)
+    if not category:
+        clean_temp_files()
+        return transcription, "Failed to classify content"
+    
+    # Clean up
+    clean_temp_files()
+    
+    # Format classification result
+    classification_result = f"{category} (confidence: {confidence:.2f})"
+    return transcription, classification_result
+
+# Gradio interface
+with gr.Blocks(title="YouTube Content Analyzer") as demo:
+    gr.Markdown("""
+    # ▶️ YouTube Content Analyzer
+    Enter a YouTube video URL to get transcription and content classification
+    """)
+    
+    with gr.Row():
+        url_input = gr.Textbox(
+            label="YouTube URL",
+            placeholder="Enter YouTube video URL here..."
+        )
+    
+    with gr.Row():
+        transcription_output = gr.Textbox(
+            label="Transcription",
+            interactive=True,
+            lines=10,
+            max_lines=20
+        )
+    
+    with gr.Row():
+        category_output = gr.Textbox(
+            label="Content Category",
+            interactive=False
+        )
+    
+    submit_btn = gr.Button("Analyze Video", variant="primary")
+    
+    # Examples
+    gr.Examples(
+        examples=[
+            ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],
+            ["https://youtu.be/dQw4w9WgXcQ"]
+        ],
+        inputs=url_input
+    )
+    
+    submit_btn.click(
+        fn=process_video,
+        inputs=url_input,
+        outputs=[transcription_output, category_output]
+    )
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)

dockerfile.dockerfile

@@ -0,0 +1,26 @@
+# Use official Python image
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends ffmpeg && \
+    rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application
+COPY . .
+
+# Download Whisper model during build (optional)
+# RUN python -c "import whisper; whisper.load_model('base')"
+
+# Expose port
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "app.py"]

requirements.txt

@@ -0,0 +1,8 @@
+gradio>=3.0
+yt-dlp>=2023.7.6
+openai-whisper>=2023.6.14
+pydub>=0.25.1
+ffmpeg-python>=0.2.0
+transformers>=4.30.0
+requests>=2.28.0
+python-dotenv>=0.21.0