Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 import torch.nn.functional as F
+import re
 
 LABELS = ["astro-ph", "cond-mat", "cs", "econ", "eess", "gr-qc",
           "hep-ex", "hep-lat", "hep-ph", "hep-th", "math", "math-ph",
@@ -24,6 +25,10 @@ def load_model():
         )
         model.eval()
 
+def clean_text(text):
+    text = text.replace('\n', ' ')
+    text = re.sub(r'\s+', ' ', text)
+    return text.strip()
 
 def predict(title: str, abstract: str):
     if not title.strip():
@@ -31,6 +36,9 @@ def predict(title: str, abstract: str):
 
     load_model()
 
+    title = clean_text(title)
+    abstract = clean_text(abstract)
+    
     text = f"{title} [SEP] {abstract}" if abstract.strip() else title
     inputs = tokenizer(
         text,