भारतीय भाषाओं के लिए स्पीच रिकग्निशन

def word_error_rate(reference: str, hypothesis: str) -> float:
    """WER = (substitutions + deletions + insertions) / words in reference."""
    ref = reference.split()
    hyp = hypothesis.split()
    if not ref:
        raise ValueError("reference must contain at least one word")
    # d[i][j] = edits to turn the first i reference words into the first j hypothesis words
    d = [[0] * (len(hyp) + 1) for _ in range(len(ref) + 1)]
    for i in range(len(ref) + 1):
        d[i][0] = i                       # delete all i words
    for j in range(len(hyp) + 1):
        d[0][j] = j                       # insert all j words
    for i in range(1, len(ref) + 1):
        for j in range(1, len(hyp) + 1):
            cost = 0 if ref[i - 1] == hyp[j - 1] else 1
            d[i][j] = min(
                d[i - 1][j] + 1,          # deletion
                d[i][j - 1] + 1,          # insertion
                d[i - 1][j - 1] + cost,   # substitution (or match)
            )
    return d[len(ref)][len(hyp)] / len(ref)


pairs = [
    ("mera account balance kitna hai", "mera account balance kitna hai"),
    ("mera account balance kitna hai", "mera acount balance kitna"),
    ("kal subah das baje train hai", "kal subha das bje ki train hai"),
]
for ref, hyp in pairs:
    print(f"WER={word_error_rate(ref, hyp):.2f}  ref='{ref}'  hyp='{hyp}'")