app.py

import streamlit as st
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Use caching to optimize resource usage
@st.cache_resource
def load_model():
    model_name = 'cardiffnlp/twitter-xlm-roberta-base-sentiment'
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSequenceClassification.from_pretrained(model_name)
    labels = ['Negative', 'Neutral', 'Positive']
    return tokenizer, model, labels

tokenizer, model, labels = load_model()

MAX_LENGTH = 128  # Adjust as needed

def analyze_sentiment(text):
    inputs = tokenizer(
        text,
        return_tensors='pt',
        truncation=True,
        max_length=MAX_LENGTH
    )
    with torch.no_grad():
        outputs = model(**inputs)
    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
    sentiment = labels[torch.argmax(probs)]
    confidence = torch.max(probs).item()
    return sentiment, confidence


st.title('Multilingual Sentiment Analysis')

text = st.text_area('Enter text in any language:')

if st.button('Analyze'):
    if text:
        sentiment, confidence = analyze_sentiment(text)
        st.write(f"**Sentiment:** {sentiment}")
        st.write(f"**Confidence:** {confidence:.2f}")
    else:
        st.write("Please enter some text to analyze.")