[msluszniak]

Description

• Bumps phonemis to v0.3.2 (Mandarin G2P matching misaki's Kokoro v1.0).
• Adds models.textToSpeech.KOKORO.ZH (XNNPACK + Core ML) with 7 of the 8 upstream zf_*/zm_* voices; zf_xiaoni is unintelligible in upstream PyTorch Kokoro too. Voices and the zh lexicon/segmenter are on HF v0.11.0.
• Adds Chinese to the speech app's Kokoro screen.

Introduces a breaking change?

• Yes
• No

Type of change

• Bug fix (change which fixes an issue)
• New feature (change which adds functionality)
• Documentation update (improves or adds clarity to existing documentation)
• Other (chores, tests, code style improvements etc.)

Tested on

• iOS
• Android

Testing instructions

• yarn workspace react-native-executorch test and scripts/run-native-tests.sh -R Phonemizer.
• Speech app > Kokoro > Chinese, synthesize the sample text.

Screenshots

Related issues

Closes #1502

Checklist

• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have updated the documentation accordingly
• My changes generate no new warnings

Additional notes

[xgiovio]

any eta to release this? thanks

[msluszniak]

@xgiovio yes, it will be released with v0.11.0 which is planned for Oct 27th.