app.py

from pandas.io.formats.format import return_docstring
import streamlit as st
import pandas as pd
from transformers import AutoTokenizer,AutoModelForMaskedLM
from transformers import pipeline
import os
import json
import random

@st.cache(show_spinner=False,persist=True)
def load_model(masked_text,model_name):

    model = AutoModelForMaskedLM.from_pretrained(model_name, from_flax=True)
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    nlp = pipeline('fill-mask', model=model, tokenizer=tokenizer)
    
    MASK_TOKEN = tokenizer.mask_token
    
    masked_text = masked_text.replace("<mask>",MASK_TOKEN)
    result_sentence = nlp(masked_text)

    return result_sentence[0]['sequence']

def main():

    st.title("RoBERTa Hindi")
    st.markdown(
    "This demo uses pretrained RoBERTa variants for Mask Language Modeling (MLM)"
    )

    models = st.multiselect(
        "Choose models",                                         
        ['flax-community/roberta-hindi','mrm8488/HindiBERTa','ai4bharat/indic-bert',\
        'neuralspace-reverie/indic-transformers-hi-bert', 
          'surajp/RoBERTa-hindi-guj-san'],
        ["flax-community/roberta-hindi"]
    )   
    
    target_text_path = './mlm_custom/mlm_targeted_text.csv'
    target_text_df = pd.read_csv(target_text_path)
    
    texts = target_text_df['text']
    
    st.sidebar.title("Hindi MLM")
     
    pick_random = st.sidebar.checkbox("Pick any random text")

    #st.write('You selected:', masked_text)
    
    results_df = pd.DataFrame(columns = ['Model Name','Masked Text','Filled Masked Text'])
     
    model_names = []
    masked_texts = []
    filled_masked_texts = []
    
    if pick_random:
        random_text = texts[random.randint(0,texts.shape[0]-1)]
        masked_text = st.text_area("Please type a masked sentence to fill",random_text)
    else:
        select_text = st.sidebar.selectbox('Select any of the following text',\
     texts)
        masked_text = st.text_area("Please type a masked sentence to fill",select_text)

    if st.button('Fill the Mask!'):
        with st.spinner("Filling the Mask..."):

            for selected_model in models:

                filled_sentence = load_model(masked_text,selected_model)
                model_names.append(selected_model)
                masked_texts.append(masked_text)
                filled_masked_texts.append(filled_sentence)

            results_df['Model Name'] = model_names
            results_df['Masked Text'] = masked_texts
            results_df['Filled Masked Text'] = filled_masked_texts

            st.table(results_df)
            
if __name__ == "__main__":
    main()