
    Of                     D    S r SSK7  SSK7  SSKJr   " S S\5      rS rg)a  
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
    )*)Indexc                   &    \ rS rSrS rS rS rSrg)CMUDictCorpusReader5   c                     [        U R                  SS5       VVs/ s H  u  p[        U[        US9PM     snn5      $ s  snnf )za
:return: the cmudict lexicon as a list of entries
    containing (word, transcriptions) tuples.
NT)encoding)concatabspathsStreamBackedCorpusViewread_cmudict_block)selffileidencs      </usr/lib/python3/dist-packages/nltk/corpus/reader/cmudict.pyentriesCMUDictCorpusReader.entries6   sJ    
  $(==t#<#<KF 'v/ACP#<
 	
s   >
c                 t    U R                  5        VVs/ s H  u  pUR                  5       PM     snn$ s  snnf )z>
:return: a list of all words defined in the cmudict lexicon.
)r   lower)r   word_s      r   wordsCMUDictCorpusReader.wordsB   s*     /3lln=n$

n===s   4c                 F    [        [        U R                  5       5      5      $ )z
:return: the cmudict lexicon as a dictionary, whose keys are
    lowercase words and whose values are lists of pronunciations.
)dictr   r   )r   s    r   r   CMUDictCorpusReader.dictH   s    
 E$,,.)**     N)__name__
__module____qualname____firstlineno__r   r   r   __static_attributes__r   r   r   r   r   5   s    

>+r   r   c                     / n[        U5      S:  a`  U R                  5       nUS:X  a  U$ UR                  5       nUR                  US   R	                  5       USS  45        [        U5      S:  a  M`  U$ )Nd    r      )lenreadlinesplitappendr   )streamr   linepiecess       r   r   r   P   sm    G
g,
 2:Nq	)6!":67 g,
 Nr   N)__doc__nltk.corpus.reader.apinltk.corpus.reader.util	nltk.utilr   CorpusReaderr   r   r   r   r   <module>r4      s'   &P % % +, +6r   