app.py

import streamlit as st
from PIL import Image
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer

def get_result_text_es_pt (list_entity, text, lang):
    result_words = []
    tmp_word = ""
    if lang == "es":
        punc_tags = ['¿', '?', '¡', '!', ',', '.', ':']
    else:
        punc_tags = ['?', '!', ',', '.', ':']
    
    for idx, entity in enumerate(list_entity): 
        tag = entity["entity"]
        word = entity["word"]
        start = entity["start"]
        end = entity["end"]
        
        # check punctuation
        punc_in = next((p for p in punc_tags if p in tag), "")
                
        subword = False
        # check subwords
        if word[0] == "#": 
            subword = True
            if tmp_word == "":
                p_s = list_entity[idx-1]["start"]
                p_e = list_entity[idx-1]["end"]
                tmp_word = text[p_s:p_e] + text[start:end]
            else: 
                tmp_word = tmp_word + text[start:end]
            word = tmp_word
        else:
            tmp_word = ""
            word = text[start:end]
            
        if tag == "l": 
            word = word 
        elif tag == "u":
            word = word.capitalize()
        # case with punctuation
        else:
            if tag[-1] == "l":
                word = (punc_in + word) if punc_in in ["¿", "¡"] else (word + punc_in)
            elif tag[-1] == "u":
                word = (punc_in + word.capitalize()) if punc_in in ["¿", "¡"] else (word.capitalize() + punc_in)     
        
        if tag != "l":
            word = '<span style="font-weight:bold; color:rgb(142, 208, 129);">' + word + '</span>'
		
        if subword == True: 
            result_words[-1] = word
        else:
            result_words.append(word)

    return " ".join(result_words)
            


def get_result_text_ca (list_entity, text):
    result_words = []
    punc_tags = ['?', '!', ',', '.', ':']
    
    for idx, entity in enumerate(list_entity): 
        start = entity["start"]
        end = entity["end"]
        tag = entity["entity"]
        word = entity["word"]
        tmp_word = ""
        
        # check punctuation
        punc_in = next((p for p in punc_tags if p in tag), "")
                
        subword = False
        # check subwords
        if word[0] != "Ġ": 
            subword = True
            if tmp_word == "":
                p_s = list_entity[idx-1]["start"]
                p_e = list_entity[idx-1]["end"]
                tmp_word = text[p_s:p_e] + text[start:end]
            else: 
                tmp_word = tmp_word + text[start:end]
            word = tmp_word
        else:
            tmp_word = ""
            word = text[start:end]
        
        if tag == "l": 
            word = word 
        elif tag == "u":
            word = word.capitalize()
        # case with punctuation
        else:
            if tag[-1] == "l":
                word = (punc_in + word) if punc_in in ["¿", "¡"] else (word + punc_in)
            elif tag[-1] == "u":
                word = (punc_in + word.capitalize()) if punc_in in ["¿", "¡"] else (word.capitalize() + punc_in)     
        
        if tag != "l":
            word = '<span style="font-weight:bold; color:rgb(142, 208, 129);">' + word + '</span>'
			
        if subword == True: 
            result_words[-1] = word
        else:
            result_words.append(word)

    return " ".join(result_words)


if __name__ == "__main__":

    st.title('Sanivert Punctuation And Capitalization Restoration')
    model_es = AutoModelForTokenClassification.from_pretrained("VOCALINLP/spanish_capitalization_punctuation_restoration_sanivert")
    tokenizer_es = AutoTokenizer.from_pretrained("VOCALINLP/spanish_capitalization_punctuation_restoration_sanivert")
    pipe_es = pipeline("token-classification", model=model_es, tokenizer=tokenizer_es)
	
    model_ca = AutoModelForTokenClassification.from_pretrained("VOCALINLP/catalan_capitalization_punctuation_restoration_sanivert")
    tokenizer_ca = AutoTokenizer.from_pretrained("VOCALINLP/catalan_capitalization_punctuation_restoration_sanivert")
    pipe_ca = pipeline("token-classification", model=model_ca, tokenizer=tokenizer_ca)
	
    model_pt = AutoModelForTokenClassification.from_pretrained("VOCALINLP/portuguese_capitalization_punctuation_restoration_sanivert")
    tokenizer_pt = AutoTokenizer.from_pretrained("VOCALINLP/portuguese_capitalization_punctuation_restoration_sanivert")
    pipe_pt = pipeline("token-classification", model=model_pt, tokenizer=tokenizer_pt)

    st.sidebar.image("vocali_logo.jpg")
    st.sidebar.subheader("Parque Científico de Murcia, Carretera de Madrid km 388. Complejo de Espinardo, 30100 Murcia")
    
    input_text = st.selectbox(
      label = "Choose an language",
      options = ["Spanish", "Portuguese", "Catalan"]
	)

    st.subheader("Enter the text to be analyzed.")
    text = st.text_input('Enter text') #text is stored in this variable    
    if input_text == "Spanish": 
        result_pipe = pipe_es(text)
        out = get_result_text_es_pt(result_pipe, text, "es")
    elif input_text == "Portuguese": 
        result_pipe = pipe_pt(text)
        out = get_result_text_es_pt(result_pipe, text, "pt")
    elif input_text == "Catalan": 
        result_pipe = pipe_ca(text)
        out = get_result_text_ca(result_pipe, text)

    st.markdown(out, unsafe_allow_html=True)
    text = ""