Add IPA Phonetic Transcription for Greek

This ticket is for Jack Duff, with @jtauber generously assisting.

The basic idea is to make a map of Greek letters and their IPA equivalents, something like:

{'α': 'a',
'αι', 'ai',
'ζ': 'zd',
'θ': 'tʰ'}

Obviously, it won’t all be so easy, due to proximal characters changing pronunciation (for example, “γ” being IPA “ɡ” but before [“κ”, “χ”, “γ”, “μ”] becoming “ŋ”).

If you can get this down for Attic, then consider moving on to other dialects, like Ionic or Koine.

Within the CLTK’s architecture, the transliteration maps and logic should go into something like cltk/phonetics/greek/transcription.py. Or consider making a general transcription entry point at cltk/phonetics/transcription.py and then declaring a which language and dialect. I’ll leave the implementation details to you two, though.

[jtauber]

greek-accentuation 1.0.0 is out!

[j-duff]

I stumbled across the recent addition of the Latin macronizer, and it’s very useful for this tool!! Thanks @TylerKirby, it’s a very useful tool! I’m importing it and calling it on text before I begin the transcription process in cltk.phonology.latin.transcription.

Of course, it means that IPA transcriptions of auto-macronized input will be reliant on the accuracy of the Latin POS tagger, but that’s better than the alternative of assuming all vowels without macrons in any input are short.

When I get a chance, I’ll also update all the files to import greek_accentuation as a package!

IPA transcription for Greek and Latin syllabification and Latin stress are coming next, and then I’m going to try and add a few different reconstructions that users can choose from, instead of just Probert and Allen. After that, I’ll touch up the API and give you the run down of how I intend it to be used.