Spaces:
Sleeping
Sleeping
cmmit
Browse files
app.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from transformers import BartForConditionalGeneration, BartTokenizer
|
3 |
+
from youtube_transcript_api import YouTubeTranscriptApi
|
4 |
+
|
5 |
+
# Load BART model and tokenizer
|
6 |
+
model_name = 'facebook/bart-large-cnn'
|
7 |
+
tokenizer = BartTokenizer.from_pretrained(model_name)
|
8 |
+
model = BartForConditionalGeneration.from_pretrained(model_name)
|
9 |
+
|
10 |
+
@st.cache
|
11 |
+
def get_transcript(url):
|
12 |
+
try:
|
13 |
+
video_id = url.split('=')[1]
|
14 |
+
transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
|
15 |
+
transcript_text = ""
|
16 |
+
for item in transcript_list:
|
17 |
+
transcript_text += item['text'] + "\n"
|
18 |
+
return transcript_text
|
19 |
+
except Exception as e:
|
20 |
+
return "Error fetching transcript: " + str(e)
|
21 |
+
|
22 |
+
@st.cache
|
23 |
+
def summarize_transcript(transcript):
|
24 |
+
input_ids = tokenizer.encode("summarize: " + transcript, return_tensors="pt", max_length=1024, truncation=True)
|
25 |
+
summary_ids = model.generate(input_ids, num_beams=4, min_length=30, max_length=200, early_stopping=True)
|
26 |
+
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
27 |
+
return summary
|
28 |
+
|
29 |
+
def main():
|
30 |
+
st.title("YouTube Video Transcription Summarizer")
|
31 |
+
|
32 |
+
video_url = st.text_input("Enter YouTube Video URL:")
|
33 |
+
|
34 |
+
if st.button("Summarize Transcript"):
|
35 |
+
transcript = get_transcript(video_url)
|
36 |
+
if not transcript:
|
37 |
+
st.error("Error fetching transcript.")
|
38 |
+
else:
|
39 |
+
summary = summarize_transcript(transcript)
|
40 |
+
st.subheader("Summary:")
|
41 |
+
st.write(summary)
|
42 |
+
|
43 |
+
if __name__ == "__main__":
|
44 |
+
main()
|