Update app.py

app.py

@@ -2,15 +2,15 @@ import gradio as gr
 import torch
 import re
 from transformers import BertTokenizer, BertForSequenceClassification
-import nltk
+# import nltk
 from nltk.tokenize import word_tokenize
 from nltk.corpus import stopwords
 from nltk.stem import WordNetLemmatizer
 
 # Download required NLTK data
-nltk.download("stopwords")
-nltk.download("punkt")
-nltk.download("wordnet")
+# nltk.download("stopwords")
+# nltk.download("punkt")
+# nltk.download("wordnet")
 
 # Load model and tokenizer
 model_name = "./model"
@@ -21,7 +21,7 @@ model.to(device)
 model.eval()
 
 # NLP tools
-stop_words = set(stopwords.words("english"))
+# stop_words = set(stopwords.words("english"))
 lemmatizer = WordNetLemmatizer()
 
 # MBTI Labels
@@ -38,7 +38,7 @@ def preprocess_text(text):
     text = re.sub(r"http\S+|www.\S+", "", text)
     text = re.sub(r"[^a-zA-Z\s]", "", text)
     tokens = word_tokenize(text)
-    tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
     return " ".join(tokens)
 
 # Inference function