RemoveKaldiNonWords transformation not working as expected

[jitsi]

RemoveKaldiNonWords transformation not working as expected

[nikvaessen]

Your transformation should also include jiwer.RemoveEmptyStrings.

import jiwer

truth = "hello"
hypothesis = "hello <unk>"

buggy_custom_transform = jiwer.Compose(
    [
        jiwer.RemoveKaldiNonWords(),
        jiwer.RemoveMultipleSpaces(),
        jiwer.RemoveWhiteSpace(replace_by_space=True),
        jiwer.SentencesToListOfWords(word_delimiter=" "),
    ]
)
working_custom_transform = jiwer.Compose(
    [
        jiwer.RemoveKaldiNonWords(),
        jiwer.RemoveMultipleSpaces(),
        jiwer.RemoveWhiteSpace(replace_by_space=True),
        jiwer.RemoveEmptyStrings(),
        jiwer.SentencesToListOfWords(word_delimiter=" "),
    ]
)

buggy_error_rate = jiwer.wer(
    truth,
    hypothesis,
    truth_transform=buggy_custom_transform,
    hypothesis_transform=buggy_custom_transform,
)
correct_error_rate = jiwer.wer(
    truth,
    hypothesis,
    truth_transform=working_custom_transform,
    hypothesis_transform=working_custom_transform,
)

print(f'after transform: truth={buggy_custom_transform(truth)}, hypothesis:{buggy_custom_transform(hypothesis)}')
print(f'after transform: truth={working_custom_transform(truth)}, hypothesis:{working_custom_transform(hypothesis)}')
print("buggy wer:", buggy_error_rate)
print("correct wer:", correct_error_rate)

after transform: truth=['hello'], hypothesis:['hello', '']
after transform: truth=['hello'], hypothesis:['hello']
buggy wer: 1.0
correct wer: 0.0