Update app.py

app.py

@@ -73,6 +73,7 @@ from tensorflow.keras.models import Sequential, model_from_json
 import tensorflow as tf
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 import spacy
+from tensorflow.keras.preprocessing.text import Tokenizer
 #from spacy import en_core_web_lg
 #import en_core_web_lg
 #nlp = en_core_web_lg.load()
@@ -171,6 +172,10 @@ def main():
 
   # pipeline_test_output = loaded_vectorizer.transform(class_list)
   # predicted = loaded_model.predict(pipeline_test_output)
+  
+  tokenizer = Tokenizer(num_words=100000)
+  tokenizer.fit_on_texts(class_list)
+  word_index = tokenizer.word_index
   text_embedding = np.zeros((len(word_index) + 1, 300))
   for word, i in word_index.items():
       text_embedding[i] = nlp(word).vector