add nltk diff version

handler.py

@@ -2,9 +2,9 @@ from typing import Dict, List, Any
 from scipy.special import softmax
 import numpy as np
 import weakref
-# import nltk
-# nltk.download('punkt')
-# nltk.download('averaged_perceptron_tagger')
+import nltk
+from nltk.corpus import stopwords
+nltk.download('stopwords')
 
 from utils import clean_str, clean_str_nopunct
 import torch
@@ -138,12 +138,13 @@ class Transcript:
         teacher_dict = {}
         student_dict = {}
         uptake_teacher_dict = {}
+        stopwords = stopwords.words('english')
         # stopwords = nltk.corpus.stopwords.word('english')
         # print("stopwords: ", stopwords)
         for utt in self.utterances:
             words = (utt.get_clean_text(remove_punct=True)).split(' ')
             for word in words:
-                # if word in stopwords: continue
+                if word in stopwords: continue
                 if utt.role == 'teacher':
                     if word not in teacher_dict:
                         teacher_dict[word] = 0

requirements.txt

@@ -4,4 +4,4 @@ numpy==1.22.4
 scipy==1.7.3
 torch==1.10.2
 transformers==4.29.1
-# nltk==3.8.1
+nltk==3.8.0