File size: 3,098 Bytes
4df3ec6 4354680 fe021fb cf53b75 121b578 4df3ec6 4b21134 fe021fb f3505bb cf53b75 121b578 4065f3f cf53b75 e36f01a f39343a 4b21134 121b578 4354680 121b578 f39343a fe021fb f39343a fe021fb 4354680 fe021fb 4354680 4b21134 4df3ec6 4354680 4df3ec6 f39343a 4df3ec6 b916752 4354680 cf93567 4df3ec6 4b21134 6f0c363 fe021fb 4df3ec6 4b21134 f3505bb c099517 097245e 0c2753a f3505bb 097245e 121b578 4354680 121b578 4b21134 4df3ec6 |
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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import torch
import nltk
import validators
import streamlit as st
from transformers import pipeline, T5Tokenizer
# local modules
from extractive_summarizer.model_processors import Summarizer
from src.utils import clean_text, fetch_article_text
from src.abstractive_summarizer import (
preprocess_text_for_abstractive_summarization,
)
# # abstractive summarizer model
# @st.cache()
# def load_abs_model():
# tokenizer = T5Tokenizer.from_pretrained("t5-base")
# model = T5ForConditionalGeneration.from_pretrained("t5-base")
# return tokenizer, model
if __name__ == "__main__":
# ---------------------------------
# Main Application
# ---------------------------------
st.title("Text Summarizer 📝")
summarize_type = st.sidebar.selectbox(
"Summarization type", options=["Extractive", "Abstractive"]
)
# ---------------------------
# SETUP
nltk.download("punkt")
abs_tokenizer_name = "t5-base"
abs_model_name = "t5-base"
abs_tokenizer = T5Tokenizer.from_pretrained(abs_tokenizer_name)
# ---------------------------
inp_text = st.text_input("Enter text or a url here")
is_url = validators.url(inp_text)
if is_url:
# complete text, chunks to summarize (list of sentences for long docs)
text, clean_txt = fetch_article_text(url=inp_text)
else:
clean_txt = clean_text(inp_text)
# view summarized text (expander)
with st.expander("View input text"):
if is_url:
st.write(clean_txt[0])
else:
st.write(clean_txt)
summarize = st.button("Summarize")
# called on toggle button [summarize]
if summarize:
if summarize_type == "Extractive":
if is_url:
text_to_summarize = " ".join([txt for txt in clean_txt])
else:
text_to_summarize = clean_txt
# extractive summarizer
with st.spinner(
text="Creating extractive summary. This might take a few seconds ..."
):
ext_model = Summarizer()
summarized_text = ext_model(text_to_summarize, num_sentences=6)
elif summarize_type == "Abstractive":
with st.spinner(
text="Creating abstractive summary. This might take a few seconds ..."
):
text_to_summarize = clean_txt
abs_summarizer = pipeline(
"summarization", model=abs_model_name, tokenizer=abs_tokenizer_name
)
if is_url is False:
# list of chunks
text_to_summarize = preprocess_text_for_abstractive_summarization(
tokenizer=abs_tokenizer, text=clean_txt
)
print(text_to_summarize)
tmp_sum = abs_summarizer(text_to_summarize, do_sample=False)
summarized_text = " ".join([summ["summary_text"] for summ in tmp_sum])
# final summarized output
st.subheader("Summarized text")
st.info(summarized_text)
|