PiH2dZddlZddlZddlmZddlmZmZmZm Z ddl m Z ddl m Z ddlmZddlmZdd lmZdd lmZdd lmZdd lmZmZdd lmZmZe dZddeddddejdddddefde dedeede!de!de!de!dee e fde!dee!e fded ed!e"d"efd#Z#dede!dee!e fdeded ef d$Z$ded%ee ee fdede!d!e"de!de!fd&Z%dS)'zjProvides the phonemize function To use it in your own code, type: from phonemizer import phonemize N)Logger)OptionalUnionListPattern)Literal)BACKENDS) BaseBackend)LanguageSwitch) WordMismatch) get_logger) Punctuation)default_separator Separator)list2strstr2listespeak espeak-mbrolafestivalsegmentszen-usrF keep-flagsignorelanguagebackend separatorstrip prepend_textpreserve_empty_linespreserve_punctuationpunctuation_marks with_stresstielanguage_switchwords_mismatchnjobsloggerc tjdkr3|ddtjt || | || | |dkr|r|d|dkr|jr|d|dkrt||||| | | | |}n7|dkrt||| }nt||||| }t||||| ||S) uMultilingual text to phonemes converter Return a phonemized version of an input `text`, given its `language` and a phonemization `backend`. Note ---- To improve the processing speed it is better to minimize the calls to this function: provide the input text as a list and call phonemize() a single time is much more efficient than calling it on each element of the list. Indeed the initialization of the phonemization backend can be expensive, especially for espeak. In one example, Do this: >>> text = [line1, line2, ...] >>> phonemize(text, ...) Not this: >>> for line in text: >>> phonemize(line, ...) Parameters ---------- text: str or list of str The text to be phonemized. Any empty line will be ignored. If ``text`` is an str, it can be multiline (lines being separated by ``\n``). If ``text`` is a list, each element is considered as a separated line. Each line is considered as a text utterance. language: str The language code of the input text, must be supported by the backend. If ``backend`` is 'segments', the language can be a file with a grapheme to phoneme mapping. backend: str, optional The software backend to use for phonemization, must be 'festival' (US English only is supported, coded 'en-us'), 'espeak', 'espeak-mbrola' or 'segments'. separator: Separator string separators between phonemes, syllables and words, default to separator.default_separator. Syllable separator is considered only for the festival backend. Word separator is ignored by the 'espeak-mbrola' backend. Initialize it as follows: >>> from phonemizer.separator import Separator >>> separator = Separator(phone='-', word=' ') strip: bool, optional If True, don't output the last word and phone separators of a token, default to False. prepend_text: bool, optional When True, returns a pair (input utterance, phonemized utterance) for each line of the input text. When False, returns only the phonemized utterances. Default to False preserve_empty_lines: bool, optional When True, will keep the empty lines in the phonemized output. Default to False and remove all empty lines. preserve_punctuation: bool, optional When True, will keep the punctuation in the phonemized output. Not supported by the 'espeak-mbrola' backend. Default to False and remove all the punctuation. punctuation_marks: str or re.Pattern, optional The punctuation marks to consider when dealing with punctuation, either for removal or preservation. Can be defined as a string or regular expression. Default to Punctuation.default_marks(). with_stress: bool, optional This option is only valid for the 'espeak' backend. When True the stresses on phonemes are present (stresses characters are ˈ'ˌ). When False stresses are removed. Default to False. tie: bool or char, optional This option is only valid for the 'espeak' backend with espeak>=1.49. It is incompatible with phone separator. When not False, use a tie character within multi-letter phoneme names. When True, the char 'U+361' is used (as in d͡ʒ), 'z' means ZWJ character, default to False. language_switch: str, optional Espeak can output some words in another language (typically English) when phonemizing a text. This option setups the policy to use when such a language switch occurs. Three values are available : 'keep-flags' (the default), 'remove-flags' or 'remove-utterance'. The 'keep-flags' policy keeps the language switching flags, for example "(en) or (jp)", in the output. The 'remove-flags' policy removes them and the 'remove-utterance' policy removes the whole line of text including a language switch. This option is only valid for the 'espeak' backend. words_mismatch: str, optional Espeak can join two consecutive words or drop some words, yielding a word count mismatch between orthographic and phonemized text. This option setups the policy to use when such a words count mismatch occurs. Three values are available: 'ignore' (the default) which do nothing, 'warn' which issue a warning for each mismatched line, and 'remove' which remove the mismatched lines from the output. njobs: int The number of parallel jobs to launch. The input text is split in ``njobs`` parts, phonemized on parallel instances of the backend and the outputs are finally collapsed. logger: logging.Logger the logging instance where to send messages. If not specified, use the default system logger. Returns ------- phonemized text: str or list of str The input ``text`` phonemized for the given ``language`` and ``backend``. The returned value has the same type of the input text (either a list or a string), excepted if ``prepend_input`` is True where the output is forced as a list of pairs (input_text, phonemized text). Raises ------ RuntimeError if the ``backend`` is not valid or is valid but not installed, if the ``language`` is not supported by the ``backend``, if any incompatible options are used. )z]Your are using python-%s which is unsupported by the phonemizer, please update to python>=3.6.rz1espeak-mbrola backend cannot preserve punctuationz5espeak-mbrola backend cannot preserve word separationr)r"r!r#r$r%r&r()r()r"r!r() sys version_infoerrorjoin_check_argumentswarningwordr _phonemize)textrrrrrr r!r"r#r$r%r&r'r( phonemizers h/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/phonemizer/phonemize.py phonemizer8*sdf &    +,/HHS5E,F,F H H H c9o~OOO/!!&:!JKKK/!!in!NOOO(g& /!5#+)  O # #g&  g& /!5   j$ 5%Oc d ddc |dvr6td|dd|r(|dkr"td||r(|dkr"td||r|jrtd|jd|d kr(|dkr"td ||d kr(|dkr$td |d Sd S)zAuxiliary function to phonemize() Ensures the parameters are compatible with each other, raises a RuntimeError the first encountered error. rz,{} is not a supported backend, choose in {}.z, rz[the "with_stress" option is available for espeak backend only, but you are using {} backendzSthe "tie" option is available for espeak backend only, but you are using {} backendzAthe "tie" option is incompatible with phone separator (which is "z")rz_the "language_switch" option is available for espeak backend only, but you are using {} backendrz^the "words_mismatch" option is available for espeak backend only, but you are using {} backendN) RuntimeErrorformatr0phone)rr#r$rr%r&s r7r1r1sIII :C"E"EFFGG G +> 117BB B !!g&9&9 117BB B"!&9&9r9r5ct|}dt|D}|rdt|D}d|D}|r|||||} ng} |r3|D]0} |r|| d| | d1|rt t || S|tkrt| S| S)zAuxiliary function to phonemize() Does the phonemization and returns the phonemized text. Raises a RuntimeError on error. cLg|]!}|tj"S)roslinesep.0lines r7 z_phonemize..+s& > > >tDJJrz " " > > >r9c@g|]\}}||Sr@r)rDnrEs r7rFz_phonemize../s)LLLWQtzz||LqLLLr9c:g|]}||Sr@rHrCs r7rFz_phonemize..2s% 2 2 2TTZZ\\ 2D 2 2 2r9)rrr') typer enumerater8insertlistzipstrr) rr5rrr'rr text_type empty_lines phonemizedis r7r4r4s(T I ? >x~~ > > >DMLL $LLL  3 2T 2 2 2D && IU%'AA  % % %A # Ar"""   a $ $ $ $+Cj))***C ### r9)&__doc__rAr-loggingrtypingrrrrtyping_extensionsrphonemizer.backendr phonemizer.backend.baser )phonemizer.backend.espeak.language_switchr (phonemizer.backend.espeak.words_mismatchr phonemizer.loggerr phonemizer.punctuationrphonemizer.separatorrrphonemizer.utilsrrBackend default_marksrQboolintr8r1r4r@r9r7rfs 111111111111%%%%%%''''''//////DDDDDDAAAAAA((((((......========//////// C D  #):"%*%*1J1J1L1L! %*6'/#yeyeyeyeI& ye  ye  ye#ye#ye!g.yeye49 ye(ye%yeyeyeyeyeyex0B0B0B49 0B 0B ( 0B % 0B0B0B0Bf//CcN#// /  /  /#//////r9