Update app.py. App description

app.py

@@ -2,26 +2,22 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
-model_name = "GMCTech/LexCAT"  
+model_name = "GMCTech/LexCAT"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
 def predict_sentiment(text):
     if not text.strip():
         return "Please enter text."
-    
     inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
     outputs = model(**inputs)
     predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
     predicted_class = torch.argmax(predictions, dim=1).item()
-    
-    sentiment_map = {0: "❌ Negative", 1: "➖ Neutral", 2: "✅ Positive"}
+    sentiment_map = {0: "NEGATIVE", 1: "NEUTRAL", 2: "POSITIVE"}
     confidence = predictions[0][predicted_class].item()
-    
-    result = f"**Predicted Sentiment**: {sentiment_map[predicted_class]}\n"
-    result += f"**Confidence**: {confidence:.3f}\n"
-    result += f"\n**Raw Probabilities**:\nNegative: {predictions[0][0]:.3f}\nNeutral: {predictions[0][1]:.3f}\nPositive: {predictions[0][2]:.3f}"
-    
+    result = f"Predicted Sentiment: \n{sentiment_map[predicted_class]}\n"
+    result += f"Confidence: \n{confidence:.3f}\n"
+    result += f"\nRaw Probabilities:\nNegative: {predictions[0][0]:.3f}\nNeutral: {predictions[0][1]:.3f}\nPositive: {predictions[0][2]:.3f}"
     return result
 
 demo = gr.Interface(
@@ -29,19 +25,21 @@ demo = gr.Interface(
     inputs=gr.Textbox(
         placeholder="Type a Taglish sentence, e.g., 'Maganda pero expensive tlga'",
         label="Input Tagalog–English (Taglish) Text",
-        lines=10,           # ← Increased input height
-        max_lines=20        # ← Allows expansion if needed
+        lines=10,
+        max_lines=20
     ),
     outputs=gr.Textbox(
         label="Sentiment Prediction",
-        lines=15,           # ← Increased output height for full visibility
-        max_lines=30        # ← Prevents forced scroll
+        lines=15,
+        max_lines=30
     ),
     title="🔍 LexCAT: Taglish Sentiment Analysis",
     description="""
-    **LexCAT** is a lexicon-enhanced transformer model for sentiment analysis of **Tagalog–English code-switched text (Taglish)**.
-    Developed by Glenn Marcus D. Cinco for his BS/MS thesis at Mapúa University.
-    Trained on FiReCS dataset, enhanced with **LexiLiksik** lexicon for intra-sentential shift detection (e.g., “Maganda pero expensive” → ❌ Negative).
+    LexCAT is a lexicon-enhanced transformer model for sentiment analysis of Tagalog–English code-switched text (Taglish).
+
+    • Developed by Glenn Marcus D. Cinco for his BS/MS thesis at Mapúa University.
+    • Trained on the FiReCS dataset.
+    • Enhanced with LexiLiksik to detect intra-sentential shifts (e.g., “Maganda pero expensive” → ❌ Negative).
     """,
     examples=[
         ["sobrang lambot ng burger pero expensive tlga"],
@@ -54,6 +52,5 @@ demo = gr.Interface(
     allow_flagging="never"
 )
 
-# Launch app
 if __name__ == "__main__":
     demo.launch()