Update app.py

app.py

@@ -4,6 +4,10 @@ from pathlib import Path
 from pydub import AudioSegment
 from pydub.utils import make_chunks
 import os
+import gensim
+from gensim.test.utils import datapath, get_tmpfile
+from gensim.scripts.glove2word2vec import glove2word2vec
+from gensim.models import KeyedVectors
 import torch
 import warnings
 import speech_recognition as sr
@@ -219,8 +223,25 @@ def get_distractors_wordnet(word):
       print ("Wordnet distractors not found")
     return distractors
     
- 
+glove_file = 'gdrive/My Drive/distractors/glove.6B.300d.txt'
+tmp_file = 'gdrive/My Drive/distractors/word2vec-glove.6B.300d.txt'
 
+glove2word2vec(glove_file, tmp_file)
+model = KeyedVectors.load_word2vec_format(tmp_file)
+def generate_distractors(answer, count):
+    answer = str.lower(answer)
+    
+    ##Extracting closest words for the answer. 
+    try:
+        closestWords = model.most_similar(positive=[answer], topn=count)
+    except:
+        #In case the word is not in the vocabulary, or other problem not loading embeddings
+        return []
+
+    #Return count many distractors
+    distractors = list(map(lambda x: x[0], closestWords))[0:count]
+    
+    return distractors
 context1 = gr.inputs.Textbox(lines=10, placeholder="Enter link here...")
 output = gr.outputs.HTML(  label="Question and Answers")
 radiobutton = gr.inputs.Radio(["Wordnet", "Gensim"])
@@ -240,9 +261,9 @@ def generate_question(context1,radiobutton):
     ques = get_question(summary_text,answer,question_model,question_tokenizer)
     if radiobutton=="Wordnet":
       distractors = get_distractors_wordnet(answer)
-    #else:
-      #distractors = generate_distractors(answer.capitalize(),3)
-      #print(distractors)
+    else:
+      distractors = generate_distractors(answer.capitalize(),3)
+      print(distractors)
       
     # output= output + ques + "\n" + "Ans: "+answer.capitalize() + "\n\n"
     output ="\n"+ output + "<b style='color:blue;'>" + ques + "</b>"