Code for Word Error Rate in Python Tutorial

wer_basic.py

def calculate_wer(reference, hypothesis):
	ref_words = reference.split()
	hyp_words = hypothesis.split()
 
	# Counting the number of substitutions, deletions, and insertions
	substitutions = sum(1 for ref, hyp in zip(ref_words, hyp_words) if ref != hyp)
	deletions = len(ref_words) - len(hyp_words)
	insertions = len(hyp_words) - len(ref_words)
 
	# Total number of words in the reference text
	total_words = len(ref_words)
 
	# Calculating the Word Error Rate (WER)
	wer = (substitutions + deletions + insertions) / total_words
	return wer


if __name__ == "__main__":
    reference = "the cat sat on the mat"
    hypothesis = "the cat mat"
    print(calculate_wer(reference, hypothesis))

wer_accurate.py

import numpy as np

def calculate_wer(reference, hypothesis):
    # Split the reference and hypothesis sentences into words
    ref_words = reference.split()
    hyp_words = hypothesis.split()
    # Initialize a matrix with size |ref_words|+1 x |hyp_words|+1
    # The extra row and column are for the case when one of the strings is empty
    d = np.zeros((len(ref_words) + 1, len(hyp_words) + 1))
    # The number of operations for an empty hypothesis to become the reference
    # is just the number of words in the reference (i.e., deleting all words)
    for i in range(len(ref_words) + 1):
        d[i, 0] = i
    # The number of operations for an empty reference to become the hypothesis
    # is just the number of words in the hypothesis (i.e., inserting all words)
    for j in range(len(hyp_words) + 1):
        d[0, j] = j
    # Iterate over the words in the reference and hypothesis
    for i in range(1, len(ref_words) + 1):
        for j in range(1, len(hyp_words) + 1):
            # If the current words are the same, no operation is needed
            # So we just take the previous minimum number of operations
            if ref_words[i - 1] == hyp_words[j - 1]:
                d[i, j] = d[i - 1, j - 1]
            else:
                # If the words are different, we consider three operations:
                # substitution, insertion, and deletion
                # And we take the minimum of these three possibilities
                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)
    # The minimum number of operations to transform the hypothesis into the reference
    # is in the bottom-right cell of the matrix
    # We divide this by the number of words in the reference to get the WER
    wer = d[len(ref_words), len(hyp_words)] / len(ref_words)
    return wer


if __name__ == "__main__":
    reference = "The cat is sleeping on the mat."
    hypothesis = "The cat is playing on mat."
    print(calculate_wer(reference, hypothesis))

wer_jiwer.py

from jiwer import wer

if __name__ == "__main__":
    # reference = "the cat sat on the mat"
    # hypothesis = "the cat mat"
    reference = "The cat is sleeping on the mat."
    hypothesis = "The cat is playing on mat."
    print(wer(reference, hypothesis))

wer_evaluate.py

import evaluate

wer = evaluate.load("wer")

# reference = "the cat sat on the mat"
# hypothesis = "the cat mat"
reference = "The cat is sleeping on the mat."
hypothesis = "The cat is playing on mat."
print(wer.compute(references=[reference], predictions=[hypothesis]))