a
     ˜ëjÎ  ã                   @   s<   d Z ddlT ddlT ddlmZ G dd„ deƒZdd„ ZdS )	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
é    )Ú*)ÚIndexc                   @   s$   e Zd Zdd„ Zdd„ Zdd„ ZdS )ÚCMUDictCorpusReaderc                 C   s   t dd„ |  dd¡D ƒƒS )zy
        :return: the cmudict lexicon as a list of entries
            containing (word, transcriptions) tuples.
        c                 S   s   g | ]\}}t |t|d �‘qS ))Úencoding)ZStreamBackedCorpusViewÚread_cmudict_block)Ú.0ZfileidÚenc© r	   úY/mnt/bigstor/www/usecases/.venv/lib/python3.9/site-packages/nltk/corpus/reader/cmudict.pyÚ
<listcomp><   s   ÿz/CMUDictCorpusReader.entries.<locals>.<listcomp>NT)ÚconcatZabspaths©Úselfr	   r	   r
   Úentries6   s
    
þÿzCMUDictCorpusReader.entriesc                 C   s   dd„ |   ¡ D ƒS )zN
        :return: a list of all words defined in the cmudict lexicon.
        c                 S   s   g | ]\}}|  ¡ ‘qS r	   )Úlower)r   ÚwordÚ_r	   r	   r
   r   F   ó    z-CMUDictCorpusReader.words.<locals>.<listcomp>)r   r   r	   r	   r
   ÚwordsB   s    zCMUDictCorpusReader.wordsc                 C   s   t t|  ¡ ƒƒS )z˜
        :return: the cmudict lexicon as a dictionary, whose keys are
            lowercase words and whose values are lists of pronunciations.
        )Údictr   r   r   r	   r	   r
   r   H   s    zCMUDictCorpusReader.dictN)Ú__name__Ú
__module__Ú__qualname__r   r   r   r	   r	   r	   r
   r   5   s   r   c                 C   sP   g }t |ƒdk rL|  ¡ }|dkr$|S | ¡ }| |d  ¡ |dd … f¡ q|S )Néd   Ú r   é   )ÚlenÚreadlineÚsplitÚappendr   )Ústreamr   ÚlineÚpiecesr	   r	   r
   r   P   s     r   N)Ú__doc__Znltk.corpus.reader.apiZnltk.corpus.reader.utilZ	nltk.utilr   ZCorpusReaderr   r   r	   r	   r	   r
   Ú<module>   s
   (