bCi"VSrSSKr\RS:aSSKrOSSKr"SS5rg)z"English Normalizer class for CLVP.N) c\rSrSrSrS\S\4SjrS\S\4SjrS\S\4S jr S\S\4S jr S\S\4S jr S\S\4S jr S\S\4S jr S\S\4SjrS\S\4SjrS\S\4SjrSrSrg)EnglishNormalizercSVs/sH3n[R"SUS-[R5US4PM5 snUl/SQUl/SQUl/SQUlgs snf)N))mrsmisess)mrmister)drdoctor)stsaint)cocompany)jrjunior)majmajor)gengeneral)drsdoctors)revreverend)lt lieutenant)hon honorable)sgtsergeant)captcaptain)esqesquire)ltdlimited)colcolonel)ftfortz\b%s\.r) onetwothreefourfivesixseveneightnine) teneleventwelvethirteenfourteenfifteensixteen seventeeneighteennineteen) r.r.twentythirtyfortyfiftysixtyseventyeightyninety)recompile IGNORECASE_abbreviationsonesteenstens)selfxs d/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/clvp/number_normalizer.py__init__EnglishNormalizer.__init__sl ZZ QqT)2== 91Q4 @ 0a    k K s:A#numreturnc@US:XagUS:aSUR[U55-$US:aURU$US:aURUS- $US:a7URUS-US-S:waSURUS-5--$S-$US :a:URUS-S -US-S:waS URUS-5--$S-$US :a<URUS -5S -US -S:waSURUS -5--$S-$US:a<URUS -5S-US -S:waSURUS -5--$S-$US:a<URUS-5S-US-S:waSURUS-5--$S-$US:a<URUS-5S-US-S:waSURUS-5--$S-$US:a<URUS-5S-US-S:waSURUS-5--$S-$g)aP Converts numbers(`int`) to words(`str`). Please note that it only supports upto - "'nine hundred ninety-nine quadrillion, nine hundred ninety-nine trillion, nine hundred ninety-nine billion, nine hundred ninety-nine million, nine hundred ninety-nine thousand, nine hundred ninety-nine'" or `number_to_words(999_999_999_999_999_999)`. rzerozminus d-r. hundred i@Bz thousand, iʚ;z millionlJ)z billionlI5z trillionlNZoz quadrillionznumber out of range)number_to_wordsabsrNrOrP)rQrVs rSrb!EnglishNormalizer.number_to_wordsFs  !8 1Wd223s8<< < 2X99S> ! 2X::cBh' ' 3Y99SBY'SVY[S[_`S`31E1EcBh1O+Oi ifhi i 4Z #*% 2_beh_hlm_mcDADjAo4$..sTz::W TVW  = $$SI%56CF?VWCW4$..sY??a ^`a  $ $$$SM%9:GJ]GZ^_G_4$..s]/BCCi fhi  ( ($$S,=%=>KNQbKbfgKg4$..s5F/FGGq npq  , ,$$S,A%AB !22a74//6K0KLL    )textcDURSS5RS5$)z Converts unicode to ascii asciiignorezutf-8)encodedecoderQrfs rSconvert_to_ascii"EnglishNormalizer.convert_to_asciis {{7H-44W==remcURS5nURS5n[U5S:aUS-$US(a[US5OSn[U5S:aUS(a[US5OSnU(a,U(a%US:XaSOSnUS:XaSOS nU<S U<S U<S U<3$U(aUS:XaSOSnU<S U<3$U(aUS:XaSOS nU<S U<3$g ) zJ This method is used to expand numerical dollar values into spoken words. r-.z dollarsrdollardollarscentcentsr`raz zero dollars)groupsplitlenint)rQromatchpartsrtrv dollar_unit cent_units rS_expand_dollars!EnglishNormalizer._expand_dollarss  C  u:>:% %#(8#eAh-!$UaE!HE!H ! u&-l( K"'1*'I%,k5)L L &-l( K%{3 3 "'1*'I#Y/ /!recDURS5RSS5$)z6 This method is used to remove commas from sentences. r-,r.rwreplacerQros rS_remove_commas EnglishNormalizer._remove_commasswwqz!!#r**recDURS5RSS5$)z? This method is used to expand '.' into spoken word ' point '. r-rqz point rrs rS_expand_decimal_point'EnglishNormalizer._expand_decimal_pointswwqz!!#y11recSSSS.n[URS5SS5nSUS -::a US -S ::aS nOURUS-S 5nURU5U-$) zP This method is used to expand ordinals such as '1st', '2nd' into spoken words. rndrd)r-rrrrNrZr\r[th)rzrwgetrb)rQrVordinal_suffixessuffixs rS_expand_ordinal!EnglishNormalizer._expand_ordinalsp $6#))A,s#$ s?sSyBF%))#(D9F##C(611rec&[URS55nUS:aaUS:a[US:XagUS:aUS:aSURUS-5-$US-S:XaURUS-5S -$URU5$URU5$) z This method acts as a preprocessing step for numbers between 1000 and 3000 (same as the original repository, link : https://github.com/neonbjb/tortoise-tts/blob/4003544b6ff4b68c09856e04d3eff9da26d023c2/tortoise/utils/tokenizer.py#L86) rr^i iz two thousandiz two thousand r\r_)rzrwrb)rQrorVs rS_expand_number EnglishNormalizer._expand_numbers !''!*o :#*d{%td &)=)=cCi)HHHsa++C3J7*DD++C00'', ,rec[R"SURU5n[R"SSU5n[R"SURU5n[R"SURU5n[R"SUR U5n[R"SUR U5nU$)zw This method is used to normalize numbers within a text such as converting the numbers to words, removing commas, etc. z([0-9][0-9,]+[0-9])u£([0-9,]*[0-9])z \1 poundsz\$([0-9.,]*[0-9])z([0-9]++\.[0-9]+)z[0-9]++(st|nd|rd|th)z[0-9]+)rJsubrrrrrrls rSnormalize_numbers#EnglishNormalizer.normalize_numberss vv,d.A.A4Hvv)<>vv*D,@,@$Gvv*D,F,FMvv-t/C/CTJvvi!4!4d; rec^URHup#[R"X#U5nM U$)z Expands the abbreviate words. )rMrJr)rQrfregex replacements rSexpand_abbreviations&EnglishNormalizer.expand_abbreviationss,#'"5"5 E66%d3D#6 recZ[R"[R"S5SU5$)z Removes multiple whitespaces z\s+r`)rJrrKrls rScollapse_whitespace%EnglishNormalizer.collapse_whitespaces vvbjj(#t44recURU5nUR5nURU5nURU5nUR U5nUR SS5nU$)zt Converts text to ascii, numbers / number-like quantities to their spelt-out counterparts and expands abbreviations "r.)rmlowerrrrrrls rS__call__EnglishNormalizer.__call__sd $$T*zz|%%d+((.''-||C$ re)rMrNrOrPN)__name__ __module__ __qualname____firstlineno__rTrzstrrbrmrrrrrrrrr__static_attributes__rerSrrs'kR9)39)39)v>S>S> """0+++ 2s2s2 23 23 2---( c c 555 rer)__doc__sys version_inforJrrrrerSrs/ ) w XXre