o ´‹ jã@sødZddlZddlmZddlmZddlmZddlmZ ddl m Z dd l m Z e d ¡Zd0d d „Zdd„Zdd„Zdd„Zdd„Zd0dd„Zdd„Zdd„Zdd„Zdd„Zd d!„Zd"d#„Zd$d%„Zd&d'„Zd(ed)efd*d+„Zd,d-„Z d.d/„Z!dS)1zSet of default text cleanerséN©Úanyascii©Ú%replace_numbers_to_characters_in_texté)Úabbreviations_en)Únormalize_numbers)Úexpand_time_english)Úabbreviations_frz\s+ÚencCs:|dkrt}n|dkr t}|D] \}}t |||¡}q|S)Nr Úfr)rr ÚreÚsub)ÚtextÚlangÚ_abbreviationsÚregexÚ replacement©rúN/home/kuhnn/.local/lib/python3.10/site-packages/TTS/tts/utils/text/cleaners.pyÚexpand_abbreviationss rcCs| ¡S©N)Úlower©rrrrÚ lowercaseórcCst td|¡ ¡S)Nú )r rÚ_whitespace_reÚstriprrrrÚcollapse_whitespace!srcCst|ƒSrrrrrrÚconvert_to_ascii%rr cCst dd|¡}|S)Nz[\<\>\(\)\[\]\"]+Ú)r rrrrrÚremove_aux_symbols)sr"cCs¤| dd¡}|dkr| dd¡n| dd¡}| dd¡}|dkr(| d d ¡}|S|d kr4| d d ¡}|S|d kr@| d d¡}|S|dkrP| d d¡}| dd¡}|S)adReplace symbols based on the lenguage tag. Args: text: Input text. lang: Lenguage identifier. ex: "en", "fr", "pt", "ca". Returns: The modified text example: input args: text: "si l'avi cau, diguem-ho" lang: "ca" Output: text: "si lavi cau, diguemho" ú;ú,Úcaú-rr!ú:r ú&z and r z et Úptz e z i ú'©Úreplace)rrrrrÚreplace_symbols.s    ù û ý  r-cCót|ƒ}t|ƒ}|S)zPBasic pipeline that lowercases and collapses whitespace without transliteration.©rrrrrrÚbasic_cleanersOór0cCr.)z;Pipeline for non-English text that transliterates to ASCII.r/rrrrÚtransliteration_cleanersVsr2cCr.)zPipeline for German textr/rrrrÚbasic_german_cleaners^r1r3cCs | dd¡}t|ƒ}t|ƒ}|S)zPipeline for Turkish textÚIuı)r,rrrrrrÚbasic_turkish_cleanersfs r5cCs<t|ƒ}t|ƒ}t|ƒ}t|ƒ}t|ƒ}t|ƒ}t|ƒ}|S)zGPipeline for English text, including number and abbreviation expansion.)rr Úen_normalize_numbersrr-r"rrrrrÚenglish_cleanersnsr7cCs,t|ƒ}t|ƒ}t|ƒ}t|ƒ}t|ƒ}|S)zHPipeline for phonemes mode, including number and abbreviation expansion.)r6rr-r"rrrrrÚphoneme_cleaners{s r8cCs4t|dd}t|ƒ}t|dd}t|ƒ}t|ƒ}|S)zZPipeline for French text. There is no need to expand numbers, phonemizer already does thatr ©r)rrr-r"rrrrrÚfrench_cleaners…s  r:cCó(t|ƒ}t|dd}t|ƒ}t|ƒ}|S)zyBasic pipeline for Portuguese text. There is no need to expand abbreviation and numbers, phonemizer already does thatr)r9©rr-r"rrrrrÚportuguese_cleanerss  r=rÚreturncCs t|ƒ}|S)zBasic pipeline for chineserrrrrÚchinese_mandarin_cleaners™sr?cCr;)zPipeline for multilingual textNr9r<rrrrÚmultilingual_cleanersŸs  r@cCs| dd¡}|S)NÚ r!r+rrrrÚ no_cleaners¨s rB)r )"Ú__doc__r rÚ+TTS.tts.utils.text.chinese_mandarin.numbersrÚenglish.abbreviationsrÚenglish.number_normrr6Úenglish.time_normr Úfrench.abbreviationsr Úcompilerrrrr r"r-r0r2r3r5r7r8r:r=Ústrr?r@rBrrrrÚs4          !