RVC-Boss
RVC-Boss
You input a wrong audio path.
@XXXXRT666 1、 →_→ 2、这个音频文件格式列表全吗? 3、你要写成set而不是list,可以学习一下in list和in set的算法复杂度
> @RVC-Boss Do I need to seperate the speakers? > > ``` > A1.wav|ZH|SPK_1|Some text > B2.wav|ZH|SPK_2|Some text also > ``` > > This will train a base model and...
> Also, I've saw that the base model training require a additional S2 stage training. Is the training code available? What should we do to produce this S2 training. I...
> s2 training is now finished. But after I used trained sovits model to generate the semantic tokens, then finetune the GPT model, I got error: > > ``` >...
https://huggingface.co/AkitoP/GPT-SoVITS-JA-ProsodyControl_model/blob/main/insert_symbol.ipynb 这里有微操text emb key的代码。GPT训练环节需要yaml config里面加phoneme_vocab_size,如果512个音素不够用的话。 https://github.com/RVC-Boss/GPT-SoVITS/wiki/%E8%AE%AD%E7%BB%83%E6%96%B0%E8%AF%AD%E8%A8%80(how-to-train-the-models-with-other-languages)
Merged.
ok,我去打一个新的整合包