|
import streamlit as st |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
import torch |
|
import torch.nn.functional as F |
|
|
|
|
|
@st.cache_resource(show_spinner=False) |
|
def load_model(): |
|
model_name = "pavlyhalim/BERT_ALL_README" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = AutoModelForSequenceClassification.from_pretrained(model_name) |
|
model.eval() |
|
return tokenizer, model |
|
|
|
tokenizer, model = load_model() |
|
|
|
st.title("Readability Score Predictor based on BERT") |
|
|
|
st.write(""" |
|
Enter a sentence, and the model will predict its readability score (from 1 to 6). |
|
""") |
|
|
|
user_input = st.text_area("Enter your sentence here:", height=100) |
|
|
|
if st.button("Predict Readability Score"): |
|
if user_input.strip() == "": |
|
st.warning("Please enter a sentence.") |
|
else: |
|
with st.spinner('Predicting...'): |
|
inputs = tokenizer( |
|
user_input, |
|
return_tensors="pt", |
|
padding=True, |
|
truncation=True, |
|
max_length=128 |
|
) |
|
|
|
with torch.no_grad(): |
|
outputs = model(**inputs) |
|
logits = outputs.logits |
|
|
|
probabilities = F.softmax(logits, dim=1) |
|
predicted_class = torch.argmax(probabilities, dim=1).item() |
|
predicted_probability = probabilities[0][predicted_class].item() |
|
|
|
predicted_label = predicted_class + 1 |
|
|
|
st.success(f"Predicted Readability Score: **{predicted_label}**") |
|
st.write(f"Confidence: **{predicted_probability * 100:.2f}%**") |
|
|
|
st.write("### Class Probabilities:") |
|
for i, prob in enumerate(probabilities[0]): |
|
label = i + 1 |
|
st.write(f"Score {label}: {prob.item() * 100:.2f}%") |
