Update app.py

app.py

@@ -21,9 +21,11 @@ from PIL import Image
 # Suppress warnings
 warnings.filterwarnings("ignore")
 
-# NLTK dependencies
+# Ascertain that NLTK dependencies for Norwegian are downloaded
 nltk.download('punkt', quiet=True)
 nltk.download('stopwords', quiet=True)
+stop_words = set(stopwords.words('norwegian'))
+
 
 # Convert m4a audio to wav format
 def convert_to_wav(audio_file):
@@ -73,7 +75,7 @@ def clean_text(text):
     return text
 
 def preprocess_text(text):
-    words = word_tokenize(text)
+    words = word_tokenize(text, language="norwegian")
     stop_words = set(stopwords.words('norwegian'))
     words = [word for word in words if word.lower() not in stop_words]
     return ' '.join(words)