Upload 2 files

app.py

@@ -0,0 +1,35 @@
+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()
+
+def analyze_sentiment(text):
+    inputs = tokenizer(text, return_tensors='pt', truncation=True)
+    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.")

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+transformers
+torch
+sentencepiece