Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于直接使用默认模型生成效果问题 #29

Open
ganjunhong opened this issue Mar 20, 2024 · 3 comments
Open

关于直接使用默认模型生成效果问题 #29

ganjunhong opened this issue Mar 20, 2024 · 3 comments
Labels
question Further information is requested

Comments

@ganjunhong
Copy link

Describe the Question

Please provide a clear and concise description of what the question is.

群主您好,我用单独再训练的模型放进去,效果跟gpt-sovits的那个基本是一样的,效果也非常好。
但有个问题是,我在测试gpt-sovits这个默认模型的时候,gpt-sovits的效果很好,
但是在parrots引入用gpt-sovits的默认模型,效果却不一样,不知道是否是代码还需要在哪里完善呢?
sovits_model_path 和gpt_model_path都是默认模型地址
m = TextToSpeech(
bert_model_path = pwd_path+"/models/gpts_pretrained_models/chinese-roberta-wwm-ext-large",
hubert_model_path = pwd_path+"/models/gpts_pretrained_models/chinese-hubert-base",
sovits_model_path = sovits_model_path,
gpt_model_path = gpt_model_path,
speaker_model_path = "usermodels",
speaker_name = "{username}".format(username=username),
device = 'cuda',
half = True,
)

@ganjunhong ganjunhong added the question Further information is requested label Mar 20, 2024
@shibing624
Copy link
Owner

指定ref_wav了吗?

@ganjunhong
Copy link
Author

是的,都是有指定的

@shibing624
Copy link
Owner

那我就不清楚了,我一般用训练的模型放进去,没用过默认模型。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants