Create app.py

app.py

@@ -0,0 +1,73 @@
+# Import necessary libraries
+import gradio as gr
+from youtube_transcript_api import YouTubeTranscriptApi
+from transformers import pipeline
+
+# Load a pre-trained summarization model from Hugging Face
+# 'sshleifer/distilbart-cnn-12-6' is a good general-purpose summarization model
+summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+
+def get_youtube_id(url):
+    """Extracts the YouTube video ID from a URL."""
+    if "youtu.be/" in url:
+        return url.split("youtu.be/")[1].split("?")[0]
+    elif "v=" in url:
+        return url.split("v=")[1].split("&")[0]
+    return None
+
+def summarize_youtube_transcript(youtube_url):
+    """
+    Fetches the transcript of a YouTube video and summarizes it.
+
+    Args:
+        youtube_url (str): The URL of the YouTube video.
+
+    Returns:
+        str: The summarized transcript or an error message.
+    """
+    video_id = get_youtube_id(youtube_url)
+
+    if not video_id:
+        return "Error: Could not extract YouTube video ID from the provided URL."
+
+    try:
+        # Get the transcript for the video ID
+        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
+
+        # Concatenate the transcript text
+        transcript_text = " ".join([d['text'] for d in transcript_list])
+
+        # Summarize the transcript
+        # The summarizer pipeline handles splitting long texts if necessary,
+        # but for very long videos, you might need more advanced chunking.
+        # max_length and min_length control the summary length.
+        summary = summarizer(transcript_text, max_length=200, min_length=50, do_sample=False)
+
+        return summary[0]['summary_text']
+
+    except Exception as e:
+        return f"Error fetching or summarizing transcript: {e}"
+
+# Create the Gradio interface
+# The interface takes a text input (for the YouTube URL)
+# and provides a text output (for the summarized transcript)
+iface = gr.Interface(
+    fn=summarize_youtube_transcript,
+    inputs=gr.Textbox(label="Enter YouTube Video URL"),
+    outputs=gr.Textbox(label="Summarized Transcript"),
+    title="YouTube Transcript Summarizer",
+    description="Enter a YouTube video URL to get a summary of its transcript."
+)
+
+# Launch the Gradio app
+# share=True creates a temporary public link (useful for testing)
+# Setting debug=True provides detailed logs
+# iface.launch(share=True, debug=True)
+
+# To deploy on Hugging Face Spaces, you just need this file (e.g., app.py)
+# and a requirements.txt file. Hugging Face Spaces will automatically run
+# the Gradio app if it finds an interface defined.
+# Remove the iface.launch() call when deploying to Hugging Face Spaces.
+# The last line should be the interface object itself.
+iface.launch() # Use this line for local testing
+# iface # Use this line for Hugging Face Spaces deployment