|
from __future__ import absolute_import, division, print_function, unicode_literals |
|
import spacy |
|
import gradio as gr |
|
import os |
|
|
|
from fastai.text.all import * |
|
from transformers import * |
|
from blurr.data.all import * |
|
from blurr.modeling.all import * |
|
from spacy_readability import Readability |
|
|
|
|
|
readablility_nlp = spacy.load('en_core_web_sm') |
|
read = Readability() |
|
cwd = os.getcwd() |
|
readablility_nlp.add_pipe(read, last=True) |
|
|
|
bart_ext_model_path = os.path.join(cwd, 'bart_extractive_model') |
|
bart_extractive_model = BartForConditionalGeneration.from_pretrained(bart_ext_model_path) |
|
bart_extractive_tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn') |
|
|
|
t5_model_path = os.path.join(cwd, 't5_model') |
|
t5_model = AutoModelWithLMHead.from_pretrained(t5_model_path) |
|
t5_tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-summarize-news") |
|
|
|
def generate_text_summarization(sum_type,article): |
|
if article.strip(): |
|
print("text input :",article) |
|
if sum_type == 'BART Extractive Text Summarization': |
|
inputs = bart_extractive_tokenizer([article], max_length=1024, return_tensors='pt') |
|
summary_ids = bart_extractive_model.generate(inputs['input_ids'], num_beams=4, min_length=60, max_length=300, early_stopping=True) |
|
|
|
summary = [bart_extractive_tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in summary_ids] |
|
print(type(summary)) |
|
print(summary) |
|
summary= summary[0] |
|
doc = readablility_nlp(summary) |
|
summary_score = round(doc._.flesch_kincaid_reading_ease,2) |
|
summarized_data = { |
|
"summary" : summary, |
|
"score" : summary_score |
|
} |
|
|
|
if sum_type == 'T5 Abstractive Text Summarization': |
|
inputs = t5_tokenizer.encode(article, return_tensors="pt", max_length=2048) |
|
summary_ids = t5_model.generate(inputs, |
|
num_beams=2, |
|
no_repeat_ngram_size=2, |
|
min_length=100, |
|
max_length=300, |
|
early_stopping=True) |
|
|
|
summary = t5_tokenizer.decode(summary_ids[0], skip_special_tokens=True) |
|
print(type(summary)) |
|
print(summary) |
|
doc = readablility_nlp(summary) |
|
summary_score = round(doc._.flesch_kincaid_reading_ease,2) |
|
summarized_data = { |
|
"summary" : summary, |
|
"score" : summary_score |
|
} |
|
|
|
|
|
return summary |
|
else: |
|
raise gr.Error("Please enter text in inputbox!!!!") |
|
|
|
input_text=gr.Textbox(lines=5, label="Paragraph") |
|
input_radio= gr.Radio(['BART Extractive Text Summarization','T5 Abstractive Text Summarization'],label='Select summarization',value='BART Extractive Text Summarization') |
|
output_text=gr.Textbox(lines=7, label="Summarize text") |
|
demo = gr.Interface( |
|
generate_text_summarization, |
|
[input_radio,input_text], |
|
output_text, |
|
title="Text Summarization", |
|
css=".gradio-container {background-color: lightgray}", |
|
article="""<p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>""" |
|
) |
|
|
|
|
|
demo.launch() |