Upload 2 files

app and requirement

app.py

@@ -0,0 +1,155 @@
+"""
+YouTube Clip Analyzer - Identifies viral/interesting timestamps in videos
+using Hugging Face models for AI processing.
+"""
+import gradio as gr
+from pytube import YouTube
+from moviepy.editor import VideoFileClip
+import os
+import logging
+import time
+import requests
+import json
+import torch
+import whisper
+from transformers import pipeline
+
+# Set up logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+logger = logging.getLogger(__name__)
+
+# Initialize models
+try:
+    logger.info("Initializing models")
+    whisper_model = whisper.load_model("tiny")
+    sentiment_analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+except Exception as e:
+    logger.error(f"Failed to initialize models: {str(e)}")
+    whisper_model = None
+    sentiment_analyzer = None
+    summarizer = None
+
+def download_youtube_audio(youtube_url):
+    """Download audio from YouTube video"""
+    try:
+        yt = YouTube(youtube_url)
+        audio_stream = yt.streams.filter(only_audio=True).first()
+        audio_path = "temp_audio.mp4"
+        audio_stream.download(filename=audio_path)
+        
+        # Convert to WAV for better compatibility with speech recognition
+        video = VideoFileClip(audio_path)
+        wav_path = "temp_audio.wav"
+        video.audio.write_audiofile(wav_path, ffmpeg_params=["-ac", "1", "-ar", "16000"])
+        video.close()
+        os.remove(audio_path)
+        
+        return wav_path, yt.title
+    except Exception as e:
+        logger.error(f"Error downloading YouTube audio: {str(e)}")
+        raise
+
+def analyze_youtube(youtube_url, progress=gr.Progress()):
+    """Main function to analyze YouTube video"""
+    try:
+        progress(0.1, desc="Downloading YouTube audio...")
+        
+        # Download audio
+        wav_path, video_title = download_youtube_audio(youtube_url)
+        
+        progress(0.3, desc="Transcribing audio...")
+        # Transcribe audio
+        result = whisper_model.transcribe(wav_path, fp16=False)
+        segments = result["segments"]
+        
+        progress(0.5, desc="Processing transcript...")
+        # Find clips
+        clips = []
+        for i in range(len(segments)):
+            start_time = segments[i]["start"]
+            for j in range(i, min(i + 10, len(segments))):
+                end_time = segments[j]["end"]
+                duration = end_time - start_time
+                if 30 <= duration <= 60:
+                    text = " ".join([seg["text"] for seg in segments[i:j+1]])
+                    if text.strip():
+                        # Analyze sentiment
+                        sentiment_result = sentiment_analyzer(text)[0]
+                        score = sentiment_result["score"]
+                        
+                        # Generate summary if text is long enough
+                        summary = text
+                        if len(text) > 100:
+                            try:
+                                summary_result = summarizer(text, max_length=100, min_length=30, do_sample=False)
+                                summary = summary_result[0]["summary_text"]
+                            except Exception as e:
+                                logger.error(f"Summarization error: {str(e)}")
+                        
+                        clips.append({
+                            "start": start_time,
+                            "end": end_time,
+                            "score": score,
+                            "text": text,
+                            "summary": summary
+                        })
+        
+        progress(0.9, desc="Finalizing results...")
+        # Clean up
+        if os.path.exists(wav_path):
+            os.remove(wav_path)
+        
+        # Sort and format results
+        clips.sort(key=lambda x: x["score"], reverse=True)
+        top_clips = clips[:3]
+        
+        output = f"## Analysis Results for: {video_title}\n\n"
+        for i, clip in enumerate(top_clips, 1):
+            start_time_fmt = f"{int(clip['start']//60):02d}:{int(clip['start']%60):02d}"
+            end_time_fmt = f"{int(clip['end']//60):02d}:{int(clip['end']%60):02d}"
+            
+            output += f"### Clip {i}\n"
+            output += f"⏱️ Time: {start_time_fmt} - {end_time_fmt}\n"
+            output += f"📊 Interest Score: {clip['score']:.2f}\n"
+            output += f"💬 Summary: {clip['summary']}\n\n"
+            
+            # Add direct link to timestamp
+            video_id = youtube_url.split("v=")[1].split("&")[0] if "v=" in youtube_url else ""
+            if video_id:
+                timestamp_seconds = int(clip["start"])
+                output += f"🔗 [Watch this segment](https://youtu.be/{video_id}?t={timestamp_seconds})\n\n"
+        
+        progress(1.0, desc="Done!")
+        return youtube_url, output
+    except Exception as e:
+        logger.error(f"Error: {str(e)}")
+        return None, f"Error processing video: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=analyze_youtube,
+    inputs=gr.Textbox(
+        label="YouTube URL",
+        placeholder="Enter YouTube URL (e.g., https://www.youtube.com/watch?v=dQw4w9WgXcQ)"
+    ),
+    outputs=[
+        gr.Video(label="Video"),
+        gr.Markdown(label="Analysis Results")
+    ],
+    title="YouTube Viral Clip Analyzer",
+    description="Identify the most interesting timestamps in YouTube videos using AI analysis.",
+    examples=[
+        ["https://www.youtube.com/watch?v=Yf_1w00qIKc"],
+        ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"]
+    ]
+)
+
+# Launch the app
+if __name__ == "__main__":
+    try:
+        demo.launch(server_port=7861)
+    except Exception as e:
+        logger.error(f"Failed to launch on port 7861: {str(e)}")
+        # Try with different settings
+        demo.launch(share=True)

requirements.txt

@@ -0,0 +1,7 @@
+gradio==3.35.2
+pytube==15.0.0
+moviepy==1.0.3
+openai-whisper==20231117
+transformers==4.35.0
+torch==2.0.1
+requests>=2.28.0