- Moved global variables (ARPA, _g2p, eng_dict, tokenizer) to top-level scope to avoid redundant initialization.
- Simplified conditions for words with apostrophes.
- Streamlined __post_replace_ph function by removing redundant checks.
- Optimized __refine_syllables function with direct iteration.
- Avoided re-initialization of tokenizer in __text_to_words by moving it to global scope.
- Added performance test in __main__ to validate improvements.
- Resolves issue #104.
With this feature, it is possible to specify individual readings for homonyms such as "明日 (ashita/asu)" while maintaining the Kanji representation of the read text.
BERT models and tokenizers are already stored and managed in the bert_models module and should not be stored here.
In addition, since there may be situations where the user would like to use cpu instead of mps for inference when using it as a library, the automatic switching process to mps was removed.
When using style-bert-vits2 as a library, the requirement to be able to launch it in multiple processes may not be necessary. Also, if the library is embedded and exe-ed using PyInstaller or similar, it is difficult to make pyopenjtalk_worker run in a separate process.
Therefore, we changed it so that the worker is used only when it is explicitly initialized.
