app.py

#import streamlit as st

#x = st.slider('Select a value')
#st.write(x, 'squared is', x * x)
import streamlit as st
from transformers import pipeline, AutoModelForMaskedLM, AutoTokenizer


st.title("Completamento del testo in Latino con Latin BERT")
st.write("Inserisci un testo con il token [MASK] per vedere le previsioni del modello.")

#dvces et reges carthaginiensivm hanno et mago qui [MASK] punico bello cornelium consulem aput liparas ceperunt
input_text = st.text_input("Testo:", value="Lorem ipsum dolor sit amet, [MASK] adipiscing elit.")

# Model based on BERT
#modelname = "./models/latin_bert/"
#modelname = "LuisAVasquez/simple-latin-bert-uncased"
modelname = "./models/bert-base-latin-uncased"


tokenizer = AutoTokenizer.from_pretrained(modelname)
model = AutoModelForMaskedLM.from_pretrained(modelname)
fill_mask = pipeline("fill-mask", model=model, tokenizer=tokenizer)

if input_text:
    predictions = fill_mask(input_text)
    st.subheader("Risultati delle previsioni con Simple Latin Bert:")
    for pred in predictions:
        st.write(f"**Parola**: {pred['token_str']}, **Probabilità**: {pred['score']:.4f}, **Sequence**: {pred['sequence']}")