o mi=@sdZddlZddlZddlZddlZddlmZmZmZm Z m Z ddl m Z GdddZ ddZd d Zd d Zd dZe ddZedkrLedSdS)zBCommand-line phonemizer tool, have a 'phonemizer --help' to get inN) phonemize separatorversionlogger punctuation)BACKENDSc@s,eZdZdZddZddZeddZdS) CatchExceptionsaDecorator wrapping a function in a try/except block When an exception occurs, display a user friendly message on standard output before exiting with error code 1. The detected exceptions are ValueError, OSError, RuntimeError, AssertionError and KeyboardInterrupt. Parameters ---------- function : The function to wrap in a try/except block cCs ||_dS)N)function)selfr r I/home/kim/smarthome/.venv/lib/python3.10/site-packages/phonemizer/main.py__init__*s zCatchExceptions.__init__c Cslz|WdStttttfy'}z|d|WYd}~dSd}~wty5|dYdSw)z9Executes the wrapped function and catch common exceptionszfatal error: {}Nzkeyboard interruption, exiting) r IOError ValueErrorOSError RuntimeErrorAssertionErrorexitformatKeyboardInterrupt)r errr r r __call__-s  zCatchExceptions.__call__cCs"tj|dtddS)z0Write `msg` on stderr and exit with error code 1 N)sysstderrwritestripr)msgr r r r9szCatchExceptions.exitN)__name__ __module__ __qualname____doc__r r staticmethodrr r r r rs  rcCstjtjddd}|jddddd|}|jd d dd d|jd d ddd|jddtdddd|d}|jdtjdddd|jddtj ddd|jdd d!dd"d#d$|jd%dd&d|d'}|jd(d)d"d*gd+d,d-|jd.d/dd0d|d1}|jd2d3d4d5d6d7|d8}|jd9d:d"t j j d;d7|jdd7|jd?d@d"t j jdAd7|jdBddCd|dD}ztdE}Wn tyd*}Ynw|jdFd*tdGdH|dIdJ|jdKdd d!dLdMdN|jdOddPd|jdQdRgdSdTdU|jdVdWgdXdYdU|dZ}ztd[}Wn ty%d*}Ynw|jd\d*td]d^|d_dJ|jd`dadb}|jdcdddd|jdetd"tjdfd|jdgddhd|S)iz,Argument parser for the phonemization scriptaMultilingual text to phonemes converter The 'phonemize' program allows simple phonemization of words and texts in many language using four backends: espeak, espeak-mbrola, festival and segments. - espeak is a text-to-speech software supporting multiple languages and IPA (International Phonetic Alphabet) output. See http://espeak.sourceforge.net or https://github.com/espeak-ng/espeak-ng - espeak-mbrola uses the SAMPA phonetic alphabet, it requires mbrola to be installed as well as additional mbrola voices. It does not support word or syllable tokenization. See https://github.com/espeak-ng/espeak-ng/blob/master/docs/mbrola.md - festival is also a text-to-speech software. Currently only American English is supported and festival uses a custom phoneset (http://www.festvox.org/bsv/c4711.html), but festival is the only backend supporting tokenization at the syllable level. See http://www.cstr.ed.ac.uk/projects/festival - segments is a Unicode tokenizer that build a phonemization from a grapheme to phoneme mapping provided as a file by the user. See https://github.com/cldf/segments. See the '--list-languages' option below for details on the languages supported by each backend. un Examples: * Phonemize a US English text with espeak $ echo 'hello world' | phonemize -l en-us -b espeak həloʊ wɜːld * Phonemize a US English text with festival $ echo 'hello world' | phonemize -l en-us -b festival hhaxlow werld * Phonemize a Japanese text with segments $ echo 'konnichiwa tsekai' | phonemize -l japanese -b segments konnitʃiwa t͡sekai * Add a separator between phones $ echo 'hello world' | phonemize -l en-us -b festival -p '-' --strip hh-ax-l-ow w-er-l-d * Phonemize some French text file using espeak $ phonemize -l fr-fr -b espeak text.txt -o phones.txt )formatter_class descriptionepilogz-Vz --version store_truez"show version information and exit.)actionhelpz-vz --verbosezEwrite all log messages to stderr (displays only warnings by default).z-qz--quietz.do not display any log message, even warnings.z-jz--njobszrz0number of parallel jobs, default is %(default)s.)typemetavardefaultr)z input/outputinput?zz?input text file to phonemize, if not specified read from stdin.)r,nargsr+r)z-oz--outputza:prepend each line of the phonemized output text with its matching input text. If a string is specified as option value, use it as field separator, else use one of "|", "||", "|||", "||||" by selecting the first one that is not configured as a token separator (see -p/-s/-w options).)r,constr/r+r)z--preserve-empty-lineszUpreserve the empty lines in the phonemized output, default is to remove them.backendsz-bz --backendN)espeak espeak-mbrolafestivalsegmentsztthe phonemization backend, must be 'espeak', 'espeak-mbrola', 'festival' or 'segments'. Default is 'espeak'.)r+r,choicesr)z-Lz--list-languageszllist available languages (and exit) for the specified backend, or for all backends if none selected.languagez-lz --languagez zen-usz~the language code of the input text, use '--list-languages' for a list of supported languages. Default is %(default)s.)r+r,r)ztoken separatorsz-pz--phone-separatorz*phone separator, default is "%(default)s".z-wz--word-separatorzVword separator, not valid for espeak-mbrola backend, default is "%(default)s".z-sz--syllable-separatorzsyllable separator, only valid for festival backend, this option has no effect if another backend is used. Default is "%(default)s".z--stripz0removes the end separators in phonemized tokens.zspecific to espeak backendr2z--espeak-libraryz zthe path to the espeak shared library to use (*.so on Linux, *.dylib on Mac and *.dll on Windows, useful to overload the default espeak version installed on the system). Default to zc. This path can also be specified using the PHONEMIZER_ESPEAK_LIBRARY environment variable.)r,r*r+r)z--tiezuwhen the option is set, use a tie character within multi-letter phoneme names, default to U+361 (as in d͡ʒ), 'z' means ZWJ character, only compatible with espeak>1.48 and incompatible with the -p/--phone-separator option)r/r,r0r+r)z --with-stressuwhen the option is set, the stresses on phonemes are present (stresses characters are ˈ'ˌ). By default stresses are removed.z--language-switch keep-flags)r8z remove-flagszremove-utterancea)espeak can pronounce 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.)r,r6r)z--words-mismatchignore)r9warnremoveaespeak 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.zspecific to festival backendr4z--festival-executablez zthe path to the festival executable to use (useful to overload the default festival installed on the system). Default to zh. This path can also be specified using the PHONEMIZER_FESTIVAL_EXECUTABLE environment variable.zpunctuation processingz'not available for espeak-mbrola backend)r%z--preserve-punctuationz[preserve the punctuation marks in the phonemized output, default is to remove them.z--punctuation-markszythe marks to consider during punctuation processing (either for removal or preservation). Default is %(default)s.z--punctuation-marks-is-regexzfinterpret the '--punctuation-marks' parameter as a regex. Default is to interpret as a string.)argparseArgumentParserRawDescriptionHelpFormatter add_argumentadd_mutually_exclusive_groupintadd_argument_grouprstdinstdoutrZdefault_separatorphonewordsyllablerlibraryrstr executabler PunctuationZ default_marks parse_args)parsergroupespeak_libraryfestival_executabler r r rL@s4=         rLc CsP|stn|gD]}td|ddddtt|Dq dS)z@Returns the available languages for the given `backend` as a strzsupported languages for z are: rcss$|] \}}d|d|VqdS) z -> Nr ).0kvr r r 7s"z!list_languages..N)rkeysprintjoinsortedZsupported_languagesitems)Z args_backendbackendr r r list_languages2s  r\cCs"d}|rd}n|r d}tj|dS)zReturns a configured loggernormalverbosequiet) verbosity)r get_logger)r^r_r`r r r ra;s  racCst|tr t||ddS|S)z,If `stream` is a filename, open it as a fileutf8)encoding) isinstancerIopen)streammoder r r setup_streamEs rhcst}|jrtd|j|jrtd|j|jr$ttdS|jr0tt|j dS|j p4d|_ t |j |j }t |jd}|d|jt |jd}|d|j|j dkrk|d tj|jddd }n tj|j|j|jd }|d ||jr||j|d nd |jrz|d|jt|j|_Wntjy||td|jwt |!|j"|j ||j#|j|j$|j%|j|j&|j'|j(|j)|j*|d}|rr|+t,j-.fdd|Dt,j-dS|r|+t,j-.|t,j-dSdS)z,Phonemize a text from command-line argumentsr2r4Nrzreading from %swz writing to %sr3z4using espeak-mbrola backend: ignoring word separator)rErGrFzseparator is %sz/prepend input text to output, separator is "%s"Fzpunctuation marks is regex %sz!can't compile regex pattern from )r7r[rr prepend_textpreserve_empty_linespreserve_punctuationpunctuation_marks with_stresstielanguage_switchwords_mismatchnjobsrc3s,|]}|ddd|dVqdS)r rNr )rRlineinput_output_separatorr r rUs  zmain..)/rLrOrZ set_libraryrPZset_executablerrWr\r[rar^r_rhr-debugnameoutputrZ SeparatorZphone_separatorZsyllable_separatorZword_separatorrkrwZpunctuation_marks_is_regexrnrecompileerrorcloserr readlinesr7rrlrmrorprqrrrsroslineseprX)argslogZstreaminZ streamoutsepoutr rvr mainMs        r__main__)r"r<rrr{Z phonemizerrrrrrZphonemizer.backendrrrLr\rarhrrr r r r s$ %s   ]