pages/inference.py

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


@st.cache(show_spinner=False)
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 load_page():

	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**")
	
	st.sidebar.write("## UI Options")
	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.checkbox("Try Random Examples")
	
	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 .",
		"' Bandolier - Budgie ' , a free iTunes app for iPad , iPhone and iPod touch , released in December 2011 , tells the story of the making of Bandolier in the band 's own words - including an extensive audio interview with Burke Shelley .",
		"' Eden Black ' was grown from seed in the late 1980s by Stephen Morley , under his conditions it produces pitchers that are almost completley black .",
		"' Wilson should extend his stint on The Voice to renew public interest in the band ; given that they 're pulling out all the stops , they deserve all the acclaim that surrounded them for their first two albums .",
		"'' '' New York Mining Disaster 1941 '' '' was the second EP released by the Bee Gees in 1967 on the Spin Records , like their first EP , it was released only in Australia .",
		"'' ADAPTOGENS : Herbs for Strength , Stamina , and Stress Relief , '' Healing Arts Press , 2007 - contains a detailed monograph on Schisandra chinensis as well as highlights health benefits ."
	]
	
	if 	change_example:
		example = examples[random.randint(0, len(examples)-1)]
		input_complex_sentence = st.text_area("Please type a Complex Sentence to split",example)
		split = st.button('Change and Split✂️')
	else:
		example=examples[0]
		input_complex_sentence = st.text_area("Please type a Complex Sentence to split",example)
		split = st.button('Split✂️')

	if split:
		with st.spinner("Spliting Sentence...🧠"):
			generated_sentence = load_model(input_complex_sentence, model)
		sentence1, sentence2, _ = generated_sentence.split(".")
		st.write("**Sentence1:** "+sentence1+".")
		st.write("**Sentence2:** "+sentence2+".")