Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
from youtube_transcript_api import YouTubeTranscriptApi
|
| 3 |
+
from youtube_transcript_api.formatters import TextFormatter
|
| 4 |
+
import torch
|
| 5 |
+
import gradio as gr
|
| 6 |
+
from transformers import pipeline
|
| 7 |
+
|
| 8 |
+
text_summary = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", torch_dtype=torch.bfloat16)
|
| 9 |
+
|
| 10 |
+
# model_path = ("../Models/models--sshleifer--distilbart-cnn-12-6/snapshots"
|
| 11 |
+
# "/a4f8f3ea906ed274767e9906dbaede7531d660ff")
|
| 12 |
+
# text_summary = pipeline("summarization", model=model_path,
|
| 13 |
+
# torch_dtype=torch.bfloat16)
|
| 14 |
+
|
| 15 |
+
def summary (input):
|
| 16 |
+
output = text_summary(input)
|
| 17 |
+
return output[0]['summary_text']
|
| 18 |
+
|
| 19 |
+
def extract_video_id(url):
|
| 20 |
+
# Regex to extract the video ID from various YouTube URL formats
|
| 21 |
+
regex = r"(?:youtube\.com\/(?:[^\/\n\s]+\/\S+\/|(?:v|e(?:mbed)?)\/|\S*?[?&]v=)|youtu\.be\/)([a-zA-Z0-9_-]{11})"
|
| 22 |
+
match = re.search(regex, url)
|
| 23 |
+
if match:
|
| 24 |
+
return match.group(1)
|
| 25 |
+
return None
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
def get_youtube_transcript(video_url):
|
| 29 |
+
video_id = extract_video_id(video_url)
|
| 30 |
+
if not video_id:
|
| 31 |
+
return "Video ID could not be extracted."
|
| 32 |
+
|
| 33 |
+
try:
|
| 34 |
+
# Fetch the transcript
|
| 35 |
+
transcript = YouTubeTranscriptApi.get_transcript(video_id)
|
| 36 |
+
|
| 37 |
+
# Format the transcript into plain text
|
| 38 |
+
formatter = TextFormatter()
|
| 39 |
+
text_transcript = formatter.format_transcript(transcript)
|
| 40 |
+
summary_text = summary(text_transcript)
|
| 41 |
+
|
| 42 |
+
return summary_text
|
| 43 |
+
except Exception as e:
|
| 44 |
+
return f"An error occurred: {e}"
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
# Example URL (Replace this with the actual URL when using the script)
|
| 48 |
+
# video_url = "https://youtu.be/5PibknhIsTc"
|
| 49 |
+
# print(get_youtube_transcript(video_url))
|
| 50 |
+
|
| 51 |
+
gr.close_all()
|
| 52 |
+
|
| 53 |
+
# demo = gr.Interface(fn=summary, inputs="text",outputs="text")
|
| 54 |
+
demo = gr.Interface(fn=get_youtube_transcript,
|
| 55 |
+
inputs=[gr.Textbox(label="Input YouTube Url to summarize",lines=1)],
|
| 56 |
+
outputs=[gr.Textbox(label="Summarized text",lines=4)],
|
| 57 |
+
title="@GenAILearniverse Project 2: YouTube Script Summarizer",
|
| 58 |
+
description="THIS APPLICATION WILL BE USED TO SUMMARIZE THE YOUTUBE VIDEO SCRIPT.")
|
| 59 |
+
demo.launch()
|