corpus = [
    "This is the Hugging Face course.",
    "This chapter is about tokenization.",
    "This section shows several tokenizer algorithms.",
    "Hopefully, you will be able to understand how they are trained and generate tokens.",
]

tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")

word_freqs = defaultdict(int)
for text in corpus:
    words_with_offsets = tokenizer.backend_tokenizer.pre_tokenizer.pre_tokenize_str(text)
    words = [word for word, _ in words_with_offsets]
    for word in words:
        word_freqs[word] += 1

assert word_freqs == defaultdict(int, {'This': 3, 'is': 2, 'the': 1, 'Hugging': 1, 'Face': 1, 'Course': 1, '.': 4, 'chapter': 1, 'about': 1,
    'tokenization': 1, 'section': 1, 'shows': 1, 'several': 1, 'tokenizer': 1, 'algorithms': 1, 'Hopefully': 1,
    ',': 1, 'you': 1, 'will': 1, 'be': 1, 'able': 1, 'to': 1, 'understand': 1, 'how': 1, 'they': 1, 'are': 1,
    'trained': 1, 'and': 1, 'generate': 1, 'tokens': 1})