Data mismatch with expected output int test for fit_toeknizer

Course Q&A TensorFlow Developer Professional Natural Language Processing in TensorFlow
, ,
1

Can someone please check if you are also getting a mismatch and if so what am I doing wrong here?

Output is:
Vocabulary contains 39432 words
<OOV> token NOT included in vocabulary

***Expected Output:***
Vocabulary contains 27285 words
<OOV> token included in vocabulary

Why is there a mismatch ? Am i doing something wrong here?

2

The expected output is correct. If you’re having trouble locating the mistake, please click my name and message your notebook as an attachment.

3

The 2nd parameter of Tokenizer is filters. Please use named argument to set oov token.

4

That was a real silly one! thanks for the help.