ppg-vc icon indicating copy to clipboard operation
ppg-vc copied to clipboard

Have you tried the performance of the model on the mandarin dataset?

Open hertz-pj opened this issue 3 years ago • 6 comments

It's a great job and it shown extraordinary results for zero-shot condition. Have you test your model on mandarin datasets?If I want to try on mandarin datasets, which module i need to modify.

hertz-pj avatar Aug 24 '21 08:08 hertz-pj

First train an ASR model, if necessary, then finetune a speaker recognition model, and you can train directly

madosma avatar Dec 29 '21 03:12 madosma

如有必要,首先训练 ASR 模型,然后微调说话人识别模型,可以直接训练

你好,我想向你请教一些问题,可以吗?如果有机会的话。

ZXLCCCC avatar Mar 21 '23 01:03 ZXLCCCC

如有必要,首先训练 ASR 模型,然后微调说话人识别模型,可以直接训练

你好,我想向你请教一些问题,可以吗?如果有机会的话。

可以交流一下,直接联系就好了,知乎发私信即可,用户名:隐在云端。我每天都会看的

madosma avatar May 06 '23 07:05 madosma