Spaces:
Sleeping
Sleeping
File size: 2,448 Bytes
9f27a52 40be60a 75855be 2beb89b 42c2597 40be60a 7c96a81 a8924ed 7c96a81 a1d11c2 ece6dcf 2a6b055 4fa5477 2beb89b 40be60a a1d11c2 40be60a 7c96a81 40be60a 7c96a81 40be60a 7c96a81 40be60a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
import streamlit as st
from flask import Flask, request, jsonify
from transformers import pipeline
from keybert import KeyBERT
# Initialize Flask app
app = Flask(__name__)
# Function to extract text from SRT-formatted text
def extract_text_from_srt_text(srt_text):
lines = srt_text.strip().split("\n\n")
texts = [subtitle.split("\n")[2] for subtitle in lines if subtitle.strip()]
return " ".join(texts)
# Function to generate summary from text
def generate_summary(text, summary_length):
summarizer = pipeline("summarization")
summary = summarizer(text, max_length=summary_length, min_length=30, do_sample=False)
summary_text = summary[0]["summary_text"]
return summary_text
# Function to extract top 4 topics from text
def extract_top_topics(text, n_top_topics):
model = KeyBERT('distilbert-base-nli-mean-tokens')
keywords = model.extract_keywords(text, keyphrase_ngram_range=(1, 3), stop_words='english', use_maxsum=True, nr_candidates=20, top_n=n_top_topics)
return [topic for topic, _ in keywords]
# Streamlit app
st.title("SRT Summarization")
# Text area for user to input SRT-formatted text
srt_text_input = st.text_area("Paste SRT-formatted text here:")
# Button to trigger summarization
if st.button("Summarize"):
# Check if text area is not empty
if srt_text_input.strip():
# Extract text from SRT-formatted text
text_to_summarize = extract_text_from_srt_text(srt_text_input)
# Generate summary
summary = generate_summary(text_to_summarize, 150)
# Extract top 4 topics
top_topics = extract_top_topics(text_to_summarize, 4)
# Display summary and top 4 topics
st.subheader("Summary:")
st.write(summary)
st.subheader("Top 4 Keywords:")
for topic in top_topics:
st.write(f"- {topic}")
else:
st.warning("Please enter some SRT-formatted text.")
# Define endpoint for REST API
@app.route("/summarize", methods=["POST"])
def summarize():
data = request.json
if "srt_text" not in data:
return jsonify({"error": "Missing 'srt_text' parameter"}), 400
srt_text = data["srt_text"]
text_to_summarize = extract_text_from_srt_text(srt_text)
summary = generate_summary(text_to_summarize, 150)
top_topics = extract_top_topics(text_to_summarize, 4)
return jsonify({"summary": summary, "top_topics": top_topics})
if __name__ == "__main__":
app.run()
|