11i=SrSSKrSSKrSSKrSSKrSSKJrJrJrJ r J r SSK J r "SS5r SrSrS rS r\ S 5r\S :Xa\"5 gg) zBCommand-line phonemizer tool, have a 'phonemizer --help' to get inN) phonemize separatorversionlogger punctuation)BACKENDSc4\rSrSrSrSrSr\S5rSr g)CatchExceptionsa\Decorator 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 cXlg)Nfunction)selfrs I/home/james-whalen/.local/lib/python3.13/site-packages/phonemizer/main.py__init__CatchExceptions.__init__*s cUR5 g![[[[[ 4a*nUR SRU55 SnAgSnAf[a UR S5 gf=f)z9Executes the wrapped function and catch common exceptionszfatal error: {}Nzkeyboard interruption, exiting) rIOError ValueErrorOSError RuntimeErrorAssertionErrorexitformatKeyboardInterrupt)rerrs r__call__CatchExceptions.__call__-s^ 8 MMOWn. 5 II'..s3 4 4  8 II6 7 8sA8 AA87A8c[RRUR5S-5 [R"S5 g)z0Write `msg` on stderr and exit with error code 1 N)sysstderrwritestripr)msgs rrCatchExceptions.exit9s, t+,  rr N) __name__ __module__ __qualname____firstlineno____doc__rr staticmethodr__static_attributes__rrr r s% ! 8rr c [R"[RSSS9nURSSSSS9 UR 5nURS S SS S9 URS S SSS9 URSS[ SSSS9 UR S5nURS[RSSSS9 URSS[RSSS9 URSS S!SS"S#S$9 URS%SS&S9 UR S'5nURS(S)S"S*/S+QS,S-9 URS.S/SS0S9 UR S15nURS2S3S4S5S6S79 UR S85nURS9S:S"[RRS;S79 URSS79 URS?S@S"[RRSAS79 URSBSSCS9 UR SD5n[SER!5nURSFS*[$SGSHUSI3SJ9 URSKSS S!SLSMSN9 URSOSSPS9 URSQSR/SSQSTSU9 URSVSW/SXQSYSU9 UR SZ5n[S[R'5nURS\S*[$S]S^US_3SJ9 UR S`SaSb9nURScSSdS9 URSe[$S"[(R*R-5SfS9 URSgSShS9 UR/5$!["a S*nGN0f=f!["a S*nNf=f)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--njobszr"z0number of parallel jobs, default is %(default)s.)typemetavardefaultr7z input/outputinput?zz?input text file to phonemize, if not specified read from stdin.)r:nargsr9r7z-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=r9r7z--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'.)r9r:choicesr7z-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.)r9r:r7ztoken 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 backendr@z--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:r8r9r7z--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:r>r9r7z --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)rFz 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:rDr7z--words-mismatchignore)rGwarnremoveaespeak 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 backendrBz--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)r3z--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_groupr#stdinstdoutrdefault_separatorphonewordsyllablerlibraryrstr executabler Punctuation default_marks parse_args)parsergroupespeak_libraryfestival_executables rr\r\@s  $ $ <<< A: Fz  k 13  / / 1E  k/0   i =?   i '1 ?A  % %n 5E  h NP   j H KM  Tg#$    % %j 1E  kC: ;   12  % %j 1E  lgFG  % %&8 9E  !!   % %&D EE#&z2==? 3 =@A  % % = & ?E  &'   '''557A B  &01    a b #"#s$ MM MM M'&M'c U(d[R"5OU/HWn[SUS3SRS[ [UR 5R 5555-5 MY g)z@Returns the available languages for the given `backend` as a strzsupported languages for z are: r!c36# UHupSUSU3v M g7f) z -> Nr0).0kvs r !list_languages..7s*B5ADA1#VA3'5AsN)rkeysprintjoinsortedsupported_languagesitems) args_backendbackends rlist_languagesrq2sr*68==?\NJ &wiw 7 IIBF!557==?5AB B B CKrcTSnU(aSnO U(aSn[R"US9$)zReturns a configured loggernormalverbosequiet) verbosity)r get_logger)rtrurvs rrwrw;s(I    y 11rcD[U[5(a [XSS9$U$)z,If `stream` is a filename, open it as a fileutf8)encoding) isinstancerXopen)streammodes r setup_streamrEs!&#F622 Mrc2^[5nUR(a"[SRUR5 UR(a"[SR UR5 UR (a[[ R "55 gUR(a[[UR55 gUR=(d SUl [URUR5n[URS5nURSUR 5 [UR"S5nURSUR 5 URS:Xa2URS 5 [$R&"UR(SSS 9nO4[$R&"UR(UR*UR,S 9nURS U5 UR.(a.UR1UR.5mURS T5 OS mUR2(aBURSUR45 [6R8"UR45Ul[AURC5URDURUURFUR.URHURJUR4URLURNURPURRURTUS9nU(aQT(aJURW[XRZR]U4SjU55[XRZ-5 gU(a@URW[XRZR]U5[XRZ-5 gg![6R:a9 UR=5 UR=5 [?SUR435ef=f)z,Phonemize a text from command-line argumentsr@rBNrzreading from %swz writing to %srAz4using espeak-mbrola backend: ignoring word separator)rTrVrUzseparator is %sz/prepend input text to output, separator is "%s"Fzpunctuation marks is regex %sz!can't compile regex pattern from )rErprr& prepend_textpreserve_empty_linespreserve_punctuationpunctuation_marks with_stresstielanguage_switchwords_mismatchnjobsrc3D># UHnUSSTSUS3v M g7f)r r"Nr0)rdlineinput_output_separators rrgmain..s3!D7)134Ad1gY?s )/r\r_r set_libraryr`set_executablerrjrqrprwrtrurr;debugnameoutputr Separatorphone_separatorsyllable_separatorword_separatorrrpunctuation_marks_is_regexrrecompileerrorcloserr readlinesrEr&rrrrrrrr%oslineseprk)argslogstreamin streamoutsepoutrs @rmainrMs rsm I II'""JodC2Z;Z;z zFr