o mi#@sdZddlZddlZddlZddlmZddlmZmZm Z m Z m Z m Z m Z ddlZddlmZddlmZddlmZmZddlmZGd d d ejZdS) z.Abstract base class for phonemization backendsN)Logger)OptionalListAnyDictTupleUnionPattern) get_logger) Punctuation) Separatordefault_separator)chunksc @seZdZdZ   d,dedeeeefdedee fdd Z e d d Z e d d Ze ddZeejddZe ejddZe ejddZeejdeeeffddZe defddZ   d-deedeedededeef d d!Zed"eeefd#d$Zejdeed%edededeef d&d'Zdeede eeeefeffd(d)Z!d"eededefd*d+Z"dS). BaseBackendaIAbstract base class of all the phonemization backends Provides a common interface to all backends. The central method is `phonemize()` Parameters ---------- language: str The language code of the input text, must be supported by the backend. If ``backend`` is 'segments', the language can be a file with a grapheme to phoneme mapping. preserve_punctuation: bool When True, will keep the punctuation in the phonemized output. Not supported by the 'espeak-mbrola' backend. Default to False and remove all the punctuation. punctuation_marks: str The punctuation marks to consider when dealing with punctuation, either for removal or preservation. Can be defined as a string or regular expression. Default to Punctuation.default_marks(). logger: logging.Logger the logging instance where to send messages. If not specified, use the default system logger. Raises ------ RuntimeError if the backend is not available of if the `language` cannot be initialized. NFlanguagepunctuation_markspreserve_punctuationloggerc Cs|durt}|durt}|std|||_|jd|d dd| D| ||_ ||_ t||_dS)Nz{} not installed on your systemzinitializing backend %s-%s.css|]}t|VqdS)N)str).0vrQ/home/kim/smarthome/.venv/lib/python3.10/site-packages/phonemizer/backend/base.py Ssz'BaseBackend.__init__..)r Z default_marksr is_available RuntimeErrorformatname_loggerinfojoinversion_init_language _language_preserve_punctuation _punctuator)selfrrrrrrr__init__@s   zBaseBackend.__init__cCs(||std|d|d|S)zpLanguage initialization This method may be overloaded in child classes (see Segments backend) z language "z" is not supported by the z backend)is_supported_languagerrclsrrrrr#\s zBaseBackend._init_languagecC|jS)z0A logging.Logger instance where to send messages)rr'rrrrizBaseBackend.loggercCr,)z9The language code configured to be used for phonemization)r$r-rrrrnr.zBaseBackend.languagecCdS)zThe name of the backendNrrrrrrszBaseBackend.namecCr/)z9Returns True if the backend is installed, False otherwiseNrr+rrrrxr0zBaseBackend.is_availablecCr/)z;Return the backend version as a tuple (major, minor, patch)Nrr1rrrr"}r0zBaseBackend.versionreturncCr/)z@Return a dict of language codes -> name supported by the backendNrrrrrsupported_languagesr0zBaseBackend.supported_languagescCs ||vS)z6Returns True if `language` is supported by the backend)r3r*rrrr)s z!BaseBackend.is_supported_languagetext separatorstripnjobscst|tr tddurt|\}}|dkr#|d}n%jd|t j |dfddt t ||D} |}||S) aReturns the `text` phonemized for the given language Parameters ---------- text: list of str The text to be phonemized. Each string in the list is considered as a separated line. Each line is considered as a text utterance. Any empty utterance will be ignored. 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. strip: bool If True, don't output the last word and phone separators of a token, default to False. 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. Returns ------- phonemized text: list of str The input ``text`` phonemized for the given ``language`` and ``backend``. Raises ------ RuntimeError if something went wrong during the phonemization z;input text to phonemize() is str but it must be list of strNr4rzrunning %s on %s jobs)Zn_jobsc3s.|]}tj|d|dVqdS)rr4N)joblibZdelayed_phonemize_aux)rchunkr'r6r7rrrs  z(BaseBackend.phonemize..) isinstancerrr _phonemize_preprocessr:rr rr9ZParallelzipr_flatten_phonemize_postprocess)r'r5r6r7r8r phonemizedrr<r phonemizes '  zBaseBackend.phonemizerBcCsttj|S)zFlatten a list of lists into a single one From [[1, 2], [3], [4]] returns [1, 2, 3, 4]. This method is used to format the output as obtained using multiple jobs. )list itertoolschain)rBrrrr@szBaseBackend._flattenoffsetcCr/)aThe "concrete" phonemization method Must be implemented in child classes. `separator` and `strip` parameters are as given to the phonemize() method. `text` is as returned by _phonemize_preprocess(). `offset` is line number of the first line in `text` with respect to the original text (this is only usefull with running on chunks in multiple jobs. When using a single jobs the offset is 0). Nr)r'r5rGr6r7rrrr:r0zBaseBackend._phonemize_auxcCs"|jr |j|S|j|gfS)zPreprocess the text before phonemization Removes the punctuation (keep trace of punctuation marks for further restoration if required by the `preserve_punctuation` option). )r%r&Zpreserveremove)r'r5rrrr>s z!BaseBackend._phonemize_preprocesscCs|jr |j||||S|S)z\Postprocess the raw phonemized output Restores the punctuation as needed. )r%r&Zrestore)r'rBrr6r7rrrrAs z"BaseBackend._phonemize_postprocess)NFN)NFr4)#__name__ __module__ __qualname____doc__rrrr boolrr( classmethodr#propertyrr staticmethodabcabstractmethodrrr"rr3r)rr intrCrr@r:rr>rArrrrrsl!         E (* r)rLrQrEreloggingrtypingrrrrrrr r9Zphonemizer.loggerr Zphonemizer.punctuationr Zphonemizer.separatorr r Zphonemizer.utilsrABCrrrrrs $