latin_ipa_forward set to en_us pronounces "is" as "aɪz" rather than "ɪz"

[R2D2FISH]

Tried swapping out the default phonemizer in ForwardTacotron for DeepPhonemizer and noticed the model was very hesitant to learn attention. Took a look at the actual output and it was using "aɪz" instead of "ɪz". I have since switched to the cmudict version which does not have this issue, but it would be nice to have this fixed, especially for such a common word. Looking at the actual wikipron dataset I see that the phonemes for "is" are correct, so I'm not sure what's causing this.

[SeymourNickelson]

I just noticed the same thing using that pretrained model. If you look at the entries in lang_phenome_dict (which by default Phonemizer will use before running inference) "is" is mapped to "aiz" so presumably the training data for that model needs to be fixed and the model needs to be retrained.