Update app.py

app.py

@@ -8,7 +8,6 @@ from nltk.tokenize import sent_tokenize
 import plotly.express as px
 import time
 import tqdm
-
 nltk.download('punkt')
 
 # Define the device (GPU or CPU)
@@ -22,11 +21,10 @@ model = AutoModelForSequenceClassification.from_pretrained(checkpoint).to(device
 
 # Define the function for preprocessing text
 def prep_text(text):
-    clean_sents = []  # append clean con sentences
-    sent_tokens = str(text).split('.')
+    clean_sents = []
+    sent_tokens = sent_tokenize(str(text))
     for sent_token in sent_tokens:
         word_tokens = [str(word_token).strip().lower() for word_token in sent_token.split()]
-        word_tokens = [word_token for word_token in word_tokens if word_token not in punctuations]
         clean_sents.append(' '.join((word_tokens)))
     joined_clean_sents = '. '.join(clean_sents).strip(' ')
     return joined_clean_sents
@@ -45,7 +43,7 @@ def app_info():
 iface1 = gr.Interface(
     fn=app_info, inputs=None, outputs=['text'], title="General-Infomation",
     description='''
-    This app, powered by the IEQ-BERT model (ieq/IEQ-BERT), is for automating the classification of text with respect 
+    This app, powered by the IEQ-BERT model, is for automating the classification of text with respect 
     to indoor environmental quality (IEQ). IEQ refers to the quality of the indoor air, lighting, 
     temperature, and acoustics within a building, as well as the overall comfort and well-being of its occupants. It encompasses various 
     factors that can impact the health, productivity, and satisfaction of people who spend time indoors, such as office workers, students,