def __init__()

in whisper/normalizers/english.py [0:0]

• 55 lines of code
• 1 McCabe index (conditional complexity)

    def __init__(self):
        self.ignore_patterns = r"\b(hmm|mm|mhm|mmm|uh|um)\b"
        self.replacers = {
            # common contractions
            r"\bwon't\b": "will not",
            r"\bcan't\b": "can not",
            r"\blet's\b": "let us",
            r"\bain't\b": "aint",
            r"\by'all\b": "you all",
            r"\bwanna\b": "want to",
            r"\bgotta\b": "got to",
            r"\bgonna\b": "going to",
            r"\bi'ma\b": "i am going to",
            r"\bimma\b": "i am going to",
            r"\bwoulda\b": "would have",
            r"\bcoulda\b": "could have",
            r"\bshoulda\b": "should have",
            r"\bma'am\b": "madam",
            # contractions in titles/prefixes
            r"\bmr\b": "mister ",
            r"\bmrs\b": "missus ",
            r"\bst\b": "saint ",
            r"\bdr\b": "doctor ",
            r"\bprof\b": "professor ",
            r"\bcapt\b": "captain ",
            r"\bgov\b": "governor ",
            r"\bald\b": "alderman ",
            r"\bgen\b": "general ",
            r"\bsen\b": "senator ",
            r"\brep\b": "representative ",
            r"\bpres\b": "president ",
            r"\brev\b": "reverend ",
            r"\bhon\b": "honorable ",
            r"\basst\b": "assistant ",
            r"\bassoc\b": "associate ",
            r"\blt\b": "lieutenant ",
            r"\bcol\b": "colonel ",
            r"\bjr\b": "junior ",
            r"\bsr\b": "senior ",
            r"\besq\b": "esquire ",
            # prefect tenses, ideally it should be any past participles, but it's harder..
            r"'d been\b": " had been",
            r"'s been\b": " has been",
            r"'d gone\b": " had gone",
            r"'s gone\b": " has gone",
            r"'d done\b": " had done",  # "'s done" is ambiguous
            r"'s got\b": " has got",
            # general contractions
            r"n't\b": " not",
            r"'re\b": " are",
            r"'s\b": " is",
            r"'d\b": " would",
            r"'ll\b": " will",
            r"'t\b": " not",
            r"'ve\b": " have",
            r"'m\b": " am",
        }
        self.standardize_numbers = EnglishNumberNormalizer()
        self.standardize_spellings = EnglishSpellingNormalizer()