Unexpected output for fit_tokenizer function

[Bruce_Wileman]

When testing the fit_tokenizer function, I get:

Vocabulary contains 27284 words

token NOT included in vocabulary

Instead of the expected:

Vocabulary contains 27285 words

token included in vocabulary

Any ideas why this might be the case?

[balaji.ambresh]

Set the oov_token

[Bruce_Wileman]

Great, that worked! Thanks!