Fix vocab_size to +1

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.word_index)
+vocab_size = len(tokenizer.word_index) + 1
 
 model = Sequential()
 model.add(Embedding(input_dim=vocab_size, output_dim=emb_size, input_length=inp_len))