app.py

import streamlit as st
import torch
import numpy as np
import json
import typing as tp

import torch.nn.functional as F
from torch import Tensor

from datasets import ClassLabel
import transformers
from transformers import BertForSequenceClassification
from transformers import BertForSequenceClassification, AutoTokenizer

st.markdown("## Portuguese European and Brazilian dialect classifier")
st.markdown("[You can see the difference between dialects here](https://en.wikipedia.org/wiki/Portuguese_language#Writing_system)")
text = st.text_input('## Text:')

tokenizer = AutoTokenizer.from_pretrained('adalbertojunior/distilbert-portuguese-cased', do_lower_case=False)

classes = ['pt', 'pt_br']

class_label = ClassLabel(names=classes)


@st.cache_data
def get_model():
    return BertForSequenceClassification.from_pretrained(
   './pt_br_model',
    num_labels = 2,
    output_attentions = False,
    output_hidden_states = False,
    )


model = get_model()


@torch.inference_mode()
def print_results():
    input_tensor = tokenizer(text, padding=True, truncation=True, max_length=256, add_special_tokens=True, return_tensors="pt")
    logits = model(**input_tensor).logits
    probabilities = F.softmax(logits, dim=1).flatten().tolist()
    maxidx = np.argmax(probabilities)
    results = f"### {classes[maxidx]} score: {probabilities[maxidx]*100}%"
    st.markdown('## Results:')
    st.markdown(results)

if text:
    print_results()