B_Kc@sidZddkZddklZddklZddkTddkTdefdYZ dZ dS( s The Carnegie Mellon Pronouncing Dictionary [cmudict.0.6] ftp://ftp.cs.cmu.edu/project/speech/dict/ Copyright 1998 Carnegie Mellon University File Format: Each line consists of an uppercased word, a counter (for alternative pronunciations), and a transcription. Vowels are marked for stress (1=primary, 2=secondary, 0=no stress). E.g.: NATURAL 1 N AE1 CH ER0 AH0 L The dictionary contains 127069 entries. Of these, 119400 words are assigned a unique pronunciation, 6830 words have two pronunciations, and 839 words have three or more pronunciations. Many of these are fast-speech variants. Phonemes: There are 39 phonemes, as shown below: Phoneme Example Translation Phoneme Example Translation ------- ------- ----------- ------- ------- ----------- AA odd AA D AE at AE T AH hut HH AH T AO ought AO T AW cow K AW AY hide HH AY D B be B IY CH cheese CH IY Z D dee D IY DH thee DH IY EH Ed EH D ER hurt HH ER T EY ate EY T F fee F IY G green G R IY N HH he HH IY IH it IH T IY eat IY T JH gee JH IY K key K IY L lee L IY M me M IY N knee N IY NG ping P IH NG OW oat OW T OY toy T OY P pee P IY R read R IY D S sea S IY SH she SH IY T tea T IY TH theta TH EY T AH UH hood HH UH D UW two T UW V vee V IY W we W IY Y yield Y IY L D Z zee Z IY ZH seizure S IY ZH ER iN(t deprecated(tIndex(t*tCMUDictCorpusReadercBsweZdZdZdZdZeddddZeddd Zed dd Z RS( c CsFtg}|ittD]"\}}|t|td|q~S(su @return: the cmudict lexicon as a list of entries containing (word, transcriptions) tuples. tencoding(tconcattabspathstNonetTruetStreamBackedCorpusViewtread_cmudict_block(tselft_[1]tfileidtenc((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pytentries9s cCsk|tjo |i}nt|to |g}ntg}|D]}||i|iqE~S(s? @return: the cmudict lexicon as a raw string. (Rt_fileidst isinstancet basestringRtopentread(R tfileidsR tf((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pytrawBscCs1g}|iD]\}}||iq~S(sN @return: a list of all words defined in the cmudict lexicon. (Rtlower(R R twordt_((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pytwordsJscCstt|iS(s @return: the cmudict lexicon as a dictionary, whose keys are lowercase words and whose values are lists of pronunciations. (tdictRR(R ((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pyRPss,Use .entries() or .transcriptions() instead.tcmudicttlistedcCsP|djo|i|Sn|djo|i|Sntd|dS(NRt dictionarys bad format %r(RRt ValueError(R titemstformat((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pyRXssUse .dict() instead.cCs |i|S(N(R(R R!((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pyR]ssUse .entries() instead.cCs |i|S(N(R(R R!((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pyR_s( t__name__t __module__RRRRRRRR(((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pyR8s      cCssg}xft|djoR|i}|djo|Sn|i}|i|di|dfq W|S(Nidtii(tlentreadlinetsplittappendR(tstreamRtlinetpieces((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pyR cs  &( t__doc__tcodecstnltk.internalsRt nltk.utilRtutiltapit CorpusReaderRR (((s0/p/zhu/06/nlp/nltk/nltk/corpus/reader/cmudict.pys.s   +