Fix vocab_size and a NameError numpy instead of np

train.py

@@ -15,7 +15,7 @@ dset_size = len(dset)
 tokenizer = Tokenizer() # a tokenizer is a thing to split text into words, it might have some other stuff like making all the letters lowercase, etc.
 tokenizer.fit_on_texts(list(dset.keys()))
 
-vocab_size = len(tokenizer.get_vocabulary())
+vocab_size = len(tokenizer.word_index)
 
 model = Sequential()
 model.add(Embedding(input_dim=vocab_size, output_dim=emb_size, input_length=inp_len))
@@ -33,7 +33,7 @@ y = [] # and output y
 
 for line, key in enumerate(dset):
     tokens = tokenizer.texts_to_sequences([key,])[0]
-    X.append(numpy.array((list(tokens)+[0,]*inp_len)[:inp_len])) # refusing to use pad_sequences for an unspecified reason and creating the worst line of code
+    X.append(np.array((list(tokens)+[0,]*inp_len)[:inp_len])) # refusing to use pad_sequences for an unspecified reason and creating the worst line of code
     output_array = np.zeros(dset_size)
     output_array[line] = 1 # 0 0 0 1 0 0 0 0 0, the neuron of the each line activates in the correct response
     y.append(output_array)