C3W1 Vocabulary tests as too small

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

The test on my fit_tokenizer function returns too few words, although the stopword function passed. Any suggestions why?

Thanks!

‘’’ Vocabulary contains 28957 words token included in vocabulary

Expected Output:

Vocabulary contains 29714 words

<OOV> token included in vocabulary
2

Please see this link.

1 Like