Spaces:
Sleeping
Sleeping
Commit
•
2a6b055
1
Parent(s):
f91d5ee
Commit Test SRT
Browse files
app.py
CHANGED
@@ -1,15 +1,18 @@
|
|
1 |
import streamlit as st
|
2 |
from transformers import pipeline
|
|
|
3 |
|
4 |
-
# Function to extract text from SRT-formatted text
|
5 |
# Function to extract text from SRT-formatted text
|
6 |
def extract_text_from_srt_text(srt_text):
|
7 |
lines = srt_text.strip().split("\n\n") # Split by empty lines to separate subtitles
|
8 |
texts = [subtitle.split("\n")[2] for subtitle in lines if subtitle.strip()] # Extract text from the third line of each subtitle
|
9 |
return " ".join(texts)
|
10 |
|
11 |
-
#
|
12 |
-
|
|
|
|
|
|
|
13 |
|
14 |
# Streamlit app
|
15 |
st.title("SRT Summarization")
|
@@ -23,10 +26,16 @@ if st.button("Summarize"):
|
|
23 |
if srt_text_input.strip():
|
24 |
# Extract text from SRT-formatted text
|
25 |
text_to_summarize = extract_text_from_srt_text(srt_text_input)
|
26 |
-
#
|
27 |
-
summary =
|
28 |
-
#
|
|
|
|
|
|
|
|
|
29 |
st.subheader("Summary:")
|
30 |
-
st.write(summary
|
|
|
|
|
31 |
else:
|
32 |
st.warning("Please enter some SRT-formatted text.")
|
|
|
1 |
import streamlit as st
|
2 |
from transformers import pipeline
|
3 |
+
from heapq import nlargest
|
4 |
|
|
|
5 |
# Function to extract text from SRT-formatted text
|
6 |
def extract_text_from_srt_text(srt_text):
|
7 |
lines = srt_text.strip().split("\n\n") # Split by empty lines to separate subtitles
|
8 |
texts = [subtitle.split("\n")[2] for subtitle in lines if subtitle.strip()] # Extract text from the third line of each subtitle
|
9 |
return " ".join(texts)
|
10 |
|
11 |
+
# Function to generate summary from text
|
12 |
+
def generate_summary(text, summary_length):
|
13 |
+
summarizer = pipeline("summarization")
|
14 |
+
summary = summarizer(text, max_length=summary_length, min_length=30, do_sample=False)
|
15 |
+
return summary[0]["summary_text"]
|
16 |
|
17 |
# Streamlit app
|
18 |
st.title("SRT Summarization")
|
|
|
26 |
if srt_text_input.strip():
|
27 |
# Extract text from SRT-formatted text
|
28 |
text_to_summarize = extract_text_from_srt_text(srt_text_input)
|
29 |
+
# Generate summary
|
30 |
+
summary = generate_summary(text_to_summarize, 150) # You can adjust the summary length as needed
|
31 |
+
# Extract top 4 sentences
|
32 |
+
sentences = text_to_summarize.split(". ")
|
33 |
+
top_sentences = nlargest(4, sentences, key=len)
|
34 |
+
top_subjects = "\n".join(top_sentences)
|
35 |
+
# Display summary and top 4 subjects
|
36 |
st.subheader("Summary:")
|
37 |
+
st.write(summary)
|
38 |
+
st.subheader("Top 4 Subjects:")
|
39 |
+
st.write(top_subjects)
|
40 |
else:
|
41 |
st.warning("Please enter some SRT-formatted text.")
|