File size: 2,233 Bytes
4142a7d 1457f73 eb51c13 4b1ed8b 4142a7d 2e9079e de301cb 2e9079e 724a5a1 4b1ed8b 20be358 4b1ed8b 2e9079e 4b1ed8b eb51c13 2e9079e de301cb eb51c13 4b1ed8b eb51c13 20be358 17ad421 eb51c13 2e9079e |
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 |
import streamlit as st
from transformers import pipeline
import textwrap
import re
st.title('Hugging Face BERT Summarizer')
# List of models
models = ["sshleifer/distilbart-cnn-12-6", "facebook/bart-large-cnn", "t5-base", "t5-large", "google/pegasus-newsroom"]
# Dropdown model selector
model = st.sidebar.selectbox("Choose a model", models)
uploaded_file = st.file_uploader("Choose a .txt file", type="txt")
# Add text input for keywords
keywords = st.text_input("Enter keywords (comma-separated)")
# Add slider to the sidebar for the scale value
scale_percentage = st.sidebar.slider('Scale %', min_value=1, max_value=100, value=50)
if uploaded_file is not None and keywords:
user_input = uploaded_file.read().decode('utf-8')
keywords = [keyword.strip() for keyword in keywords.split(",")]
# Filter sentences based on keywords
sentences = re.split(r'(?<=[^A-Z].[.?]) +(?=[A-Z])', user_input)
filtered_sentences = [sentence for sentence in sentences if any(keyword.lower() in sentence.lower() for keyword in keywords)]
filtered_text = ' '.join(filtered_sentences)
if st.button('Summarize'):
summarizer = pipeline('summarization', model=model)
summarized_text = ""
# Split the filtered text into chunks of approximately 500 words each
chunks = textwrap.wrap(filtered_text, 500)
# Summarize each chunk
for chunk in chunks:
chunk_length = len(chunk.split())
min_length_percentage = max(scale_percentage - 10, 1) # Ensure min_length_percentage is not less than 1
max_length_percentage = min(scale_percentage + 10, 100) # Ensure max_length_percentage is not more than 100
min_length = max(int(chunk_length * min_length_percentage / 100), 1) # Calculate min_length based on the percentage of the chunk length
max_length = int(chunk_length * max_length_percentage / 100) # Calculate max_length based on the percentage of the chunk length
summarized = summarizer(chunk, max_length=max_length, min_length=min_length, do_sample=False)
summarized_text += summarized[0]['summary_text'] + " "
st.text_area('Summarized Text', summarized_text, height=200)
|