app.py

import streamlit as st
from transformers import AutoTokenizer,AutoModelForSeq2SeqLM
import random


@st.cache(show_spinner=False, persist=True)
def load_model(input_complex_sentence,model):
	
	base_path = "flax-community/"
	model_path = base_path + model
	tokenizer = AutoTokenizer.from_pretrained(model_path)
	model     = AutoModelForSeq2SeqLM.from_pretrained(model_path)
	
	tokenized_sentence = tokenizer(input_complex_sentence,return_tensors="pt")
	result = model.generate(tokenized_sentence['input_ids'],attention_mask = tokenized_sentence['attention_mask'],max_length=256,num_beams=5)
	generated_sentence = tokenizer.decode(result[0],skip_special_tokens=True)
	
	return generated_sentence

def main():

	st.sidebar.title("🧠Sentence Simplifier")
	st.title("Sentence Split in English using T5 Variants")
	st.write("Sentence Split is the task of **dividing a long Complex Sentence into Simple Sentences**")
	
	model = st.sidebar.selectbox(
				  "Please Choose the Model",
				   ("t5-base-wikisplit","t5-v1_1-base-wikisplit", "byt5-base-wikisplit","t5-large-wikisplit"))

	change_example = st.sidebar.button("Try Different Example")

	st.sidebar.write('''
		## Applications:
		* Sentence Simplification
		* Data Augmentation
		* Sentence Rephrase
	''')


	st.sidebar.write("[More Exploration](https://github.com/bhadreshpsavani/t5-sentence-split)")
	
	examples = [
		"Mary likes to play football in her freetime whenever she meets with her friends that are very nice people.",
		"It broadcasts on AM frequency 1600 kHz and is under ownership of Multicultural Broadcasting with studios in Surrey , British Columbia .",
		"On March 1 , the Blackhawks played in their 2nd outdoor game in franchise history at Soldier Field in part of the new NHL Stadium Series ",
		"'' The Rain Song '' is a love ballad , over 7 minutes in length , and is considered by singer Robert Plant to be his best overall vocal performance .",
		"The resulting knowledge about human kinesiology and sport nutrition combined with his distinctive posing styles makes Kamali a sought out bodybuilder for seminars and guest appearances and has been featured in many bodybuilding articles , as well as being on the cover of MUSCLEMAG magazine .",
		"The East London Line closed on 22 December 2007 and reopened on 27 April 2010 , becoming part of the new London Overground system ."
	]
	example = examples[random.randint(0, len(examples)-1)]
	previous_example = example
	while change_example and example==previous_example:
		example = examples[random.randint(0, len(examples)-1)]
	previous_example = example
	input_complex_sentence = st.text_area("Please type a Complex Sentence to split",example)

	if st.button('Split✂️'):
		with st.spinner("Spliting Sentence...🧠"):
			generated_sentence = load_model(input_complex_sentence, model)
		st.write(generated_sentence)


if __name__ == "__main__":
	main()