Where/How to get a full list of phone set used for each language?
XuesongYang opened this issue · 2 comments
XuesongYang commented
Thank you for the great tool. I am using it to make a G2P-like conversion. But I did not find what kind of complete list of phone set is used. I know the backend engine, like espeak, pre-defined such a phone set. I wonder if we could get it through phonemizer directly. Thanks.
hadware commented
As of now, this isn't possible. If you're using espeak as a phonemizer backend, you might want to look into their documentation.
@mmmaat do you concur?
mmmaat commented
Hi, indeed the explicit list of phonemes is not provided. For espeak this seems to be stored in a specific file for each language. inside the phsource
folder (for French here). Should not be too hard to write a parser for that file format for the extraction of the phonemes list.