Plachtaa / VITS-fast-fine-tuning

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion
Apache License 2.0
4.65k stars 698 forks source link

如何处理多音字问题 #549

Open tom20180101 opened 7 months ago

tom20180101 commented 7 months ago

训练完的模型,在遇到多音字的时候,容易读错,不知道如何处理,比如 还钱,读成还(hai)钱,但是偶尔又正确

shirubei commented 4 months ago

问题应该在pypinyin和 jieba这两个包里,或者调用他们的地方

tom20180101 commented 4 months ago

@shirubei ,thanks,我试试