add Mandarin Pinyin mapping, preprocessing and postprocessing - Githubissues

dmort27 / epitran

A tool for transcribing orthographic text as IPA (International Phonetic Alphabet)

MIT License

630 stars 121 forks source link

add Mandarin Pinyin mapping, preprocessing and postprocessing #122

Closed kalvinchang closed 2 years ago

kalvinchang commented 2 years ago

We need a Pinyin to IPA mapping because many of the characters in Wiktionary are not in the CEDict.

Sources: I had to combine info from several sources because each was slightly different

the pre-existing Epihan module's pinyin to IPA mapping (https://github.com/dmort27/epitran/blob/master/epitran/data/rules/pinyin-to-ipa-tones.txt), which is a broad transcription
erhua comes from https://en.wiktionary.org/wiki/Module:cmn-pron
https://en.wikipedia.org/wiki/Pinyin
https://en.wikipedia.org/wiki/Help:IPA/Mandarin

Please let me know if my own Taiwanese Mandarin is influencing any of the transcriptions

kalvinchang commented 2 years ago

Marking of neutral tone removed to be consistent with the other varieties