rHJj=dZddlZddlZddlZddlZddlmZmZmZm Z m Z ddl m Z GddZ dZdZd Zd Ze d Zed k(reyy) zBCommand-line phonemizer tool, have a 'phonemizer --help' to get inN) phonemize separatorversionlogger punctuation)BACKENDSc,eZdZdZdZdZedZy)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 c||_y)N)function)selfr s Y/Users/ahmed/devFolder/claude-voice/.venv/lib/python3.12/site-packages/phonemizer/main.py__init__zCatchExceptions.__init__*s   c |jy#ttttt f$r*}|j dj|Yd}~yd}~wt$r|j dYywxYw)z9Executes the wrapped function and catch common exceptionszfatal error: {}Nzkeyboard interruption, exiting) r IOError ValueErrorOSError RuntimeErrorAssertionErrorexitformatKeyboardInterrupt)r errs r__call__zCatchExceptions.__call__-s^ 8 MMOWn. 5 II'..s3 4 4  8 II6 7 8sA6 AA65A6ctjj|jdztjdy)z0Write `msg` on stderr and exit with error code 1 N)sysstderrwritestripr)msgs rrzCatchExceptions.exit9s, t+,  rN)__name__ __module__ __qualname____doc__rr staticmethodrrrr r s% ! 8rr c jtjtjdd}|jdddd|j }|jd d dd |jd d dd|jddt ddd|j d}|jdtjddd|jddtjdd|jdd d!dd"d#$|jd%dd&|j d'}|jd(d)d"d*gd+d,-|jd.d/dd0|j d1}|jd2d3d4d5d67|j d8}|jd9d:d"tjjd;7|jd7|jd?d@d"tjjdA7|jdBddC|j dD} tdEj!}|jdFd*t$dGdH|dIJ|jdKdd d!dLdMN|jdOddP|jdQdRgdSdTU|jdVdWgdXdYU|j dZ} td[j'}|jd\d*t$d]d^|d_J|j d`dab}|jdcddd|jdet$d"t(j*j-df|jdgddh|j/S#t"$rd*}YMwxYw#t"$rd*}YwxYw)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.)typemetavardefaultr0z input/outputinput?zz?input text file to phonemize, if not specified read from stdin.)r3nargsr2r0z-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).)r3constr6r2r0z--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'.)r2r3choicesr0z-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.)r2r3r0ztoken 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 backendr9z--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.)r3r1r2r0z--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)r6r3r7r2r0z --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)r?z 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.)r3r=r0z--words-mismatchignore)r@warnremoveaespeak 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 backendr;z--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_grouprstdinstdoutrdefault_separatorphonewordsyllablerlibraryrstr executabler Punctuation default_marks parse_args)parsergroupespeak_libraryfestival_executables rrUrU@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$<NN$ N! N!$ N21N2c |stjn|gD]V}td|ddjdt t|j j DzXy)z@Returns the available languages for the given `backend` as a strzsupported languages for z are: rc32K|]\}}d|d|yw) z -> Nr)).0kvs r z!list_languages..7s-B5ADAq1#VA3'5AsN)rkeysprintjoinsortedsupported_languagesitems) args_backendbackends rlist_languagesri2sr*68==?\NJ &wiw 7 IIBF!557==?5AB B B CKrcDd}|rd}n|rd}tj|S)zReturns a configured loggernormalverbosequiet) verbosity)r get_logger)rlrmrns rroro;s(I    y 11rcBt|trt||dS|S)z,If `stream` is a filename, open it as a fileutf8)encoding) isinstancerQopen)streammodes r setup_streamrwEs &#FD622 Mrct}|jr"tdj|j|jr"tdj |j|j rtt j y|jrtt|jy|jxsd|_ t|j|j}t|jd}|jd|j t|j"d}|jd|j |jdk(r4|jd t%j&|j(dd }n6t%j&|j(|j*|j, }|jd ||j.r.|j1|j.|jd nd |j2rA |jd|j4t7j8|j4|_tA|jC|jD|j||jF|j.|jH|jJ|j4|jL|jN|jP|jR|jT|}|rKrI|jWtXjZj]fd|DtXjZzy|r@|jWtXjZj]|tXjZzyy#t6j:$r9|j=|j=t?d|j4wxYw)z,Phonemize a text from command-line argumentsr9r;Nrzreading from %swz writing to %sr:z4using espeak-mbrola backend: ignoring word separator)rMrOrNzseparator is %sz/prepend input text to output, separator is "%s"Fzpunctuation marks is regex %sz!can't compile regex pattern from )r>rhrr" prepend_textpreserve_empty_linespreserve_punctuationpunctuation_marks with_stresstielanguage_switchwords_mismatchnjobsrc3>K|]}|ddd|dyw)r rNr))r]lineinput_output_separators rr`zmain..s4!D7)134Ad1gY?s)/rUrXr set_libraryrYset_executablerrbrirhrorlrmrwr4debugnameoutputr Separatorphone_separatorsyllable_separatorword_separatorr{rpunctuation_marks_is_regexr~recompileerrorcloserr readlinesr>r"r|r}rrrrrr!oslineseprc)argslogstreamin streamoutsepoutrs @rmainrMs rsm I II'""JodC2Z;Z;z zFr