wer.py

#!/usr/bin/env python


def wer(r, h):
    """
    Calculation of WER with Levenshtein distance.
    Works only for iterables up to 254 elements (uint8).
    O(nm) time ans space complexity.

    >>> wer("who is there".split(), "is there".split())
    1
    >>> wer("who is there".split(), "".split())
    3
    >>> wer("".split(), "who is there".split())
    3
    """
    # initialisation
    import numpy
    d = numpy.zeros((len(r)+1)*(len(h)+1), dtype=numpy.uint8)
    d = d.reshape((len(r)+1, len(h)+1))
    for i in range(len(r)+1):
        for j in range(len(h)+1):
            if i == 0:
                d[0][j] = j
            elif j == 0:
                d[i][0] = i

    # computation
    for i in range(1, len(r)+1):
        for j in range(1, len(h)+1):
            if r[i-1] == h[j-1]:
                d[i][j] = d[i-1][j-1]
            else:
                substitution = d[i-1][j-1] + 1
                insertion = d[i][j-1] + 1
                deletion = d[i-1][j] + 1
                d[i][j] = min(substitution, insertion, deletion)

    return d[len(r)][len(h)]

if __name__ == "__main__":
    import doctest
    doctest.testmod()