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

根据参考音频克隆音色的模型,欢迎试用 Voice Clone #369

Closed
hoveychen opened this issue Jun 19, 2024 · 10 comments
Closed

根据参考音频克隆音色的模型,欢迎试用 Voice Clone #369

hoveychen opened this issue Jun 19, 2024 · 10 comments
Labels
ad This is an ad to third-party extension

Comments

@hoveychen
Copy link

hoveychen commented Jun 19, 2024

训练了几个克隆声音的模型,可以根据参考音频生成ChatTTS使用的音色嵌入。

模型Demo页面:
http://region-9.autodl.pro:41137

欢迎大家反馈一下测试效果,加入QQ群474529811给建议或者讨论。


用法:下载声音模型(.pt结尾),记住temperature要设置得非常低,否则声音会不准确。
`
rand_spk = torch.load(f'my_speaker.pt')

params_infer_code = {
'spk_emb': rand_spk, # add sampled speaker
'temperature': .000001, # using custom temperature
}

texts = ['hello world', '你好呀,旅行者!']

wavs = chat.infer(texts, params_infer_code=params_infer_code)
`

@hoveychen hoveychen changed the title 训练了一个根据参考音频克隆音色,生成声音模型 deleted Jun 19, 2024
@hoveychen hoveychen changed the title deleted 根据参考音频克隆音色的模型,欢迎试用 Jun 22, 2024
@hoveychen hoveychen changed the title 根据参考音频克隆音色的模型,欢迎试用 根据参考音频克隆音色的模型,欢迎试用 Voice Clone Jun 22, 2024
@hoveychen hoveychen reopened this Jun 22, 2024
@6drf21e
Copy link
Contributor

6drf21e commented Jun 22, 2024

效果不错👍

@redstoneleo
Copy link

QQ群搜不到啊

@ZaymeShaw
Copy link
Contributor

用自己的声音简短录了两句话测试,用噪声比较少的声音做克隆时能拷贝一个接近的音色出来,多句话之间的音色一致性也比较高,不过生成声音似乎有比较多噪声,音色也不是完全一样

@wangqun888
Copy link

请问一下克隆模型可以在哪里下载?

@hello2mao
Copy link

hello2mao commented Jul 8, 2024

测试了下,效果不错~
求一个本地部署和使用的方式。

@yiwei0730
Copy link

想請問使用方式還有程式的部分
想了解提取.pt是如何執行的,謝謝!

@atfa
Copy link

atfa commented Aug 3, 2024

训练了几个克隆声音的模型,可以根据参考音频生成ChatTTS使用的音色嵌入。

模型Demo页面: http://region-9.autodl.pro:41137

欢迎大家反馈一下测试效果,加入QQ群474529811给建议或者讨论。

用法:下载声音模型(.pt结尾),记住temperature要设置得非常低,否则声音会不准确。 ` rand_spk = torch.load(f'my_speaker.pt')

params_infer_code = { 'spk_emb': rand_spk, # add sampled speaker 'temperature': .000001, # using custom temperature }

texts = ['hello world', '你好呀,旅行者!']

wavs = chat.infer(texts, params_infer_code=params_infer_code) `

感谢,用自己的声音测试了,没想到用纯中文训练的spk用在中英混杂场景异常好用,比用中英混杂的录音训练出来的spk还好用。还希望未来能开源,感激不尽。

@954028118
Copy link

会开源吗,期待开源

@Yitianw
Copy link

Yitianw commented Sep 10, 2024

474529811 群满了 请问有新群吗

@ChenadSH
Copy link

ChenadSH commented Dec 2, 2024

训练了几个克隆声音的模型,可以根据参考音频生成ChatTTS使用的音色嵌入。

模型Demo页面: http://region-9.autodl.pro:41137

欢迎大家反馈一下测试效果,加入QQ群474529811给建议或者讨论。

用法:下载声音模型(.pt结尾),记住temperature要设置得非常低,否则声音会不准确。 ` rand_spk = torch.load(f'my_speaker.pt')

params_infer_code = { 'spk_emb': rand_spk, # add sampled speaker 'temperature': .000001, # using custom temperature }

texts = ['hello world', '你好呀,旅行者!']

wavs = chat.infer(texts, params_infer_code=params_infer_code) `

网站为什么打不开了?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ad This is an ad to third-party extension
Projects
None yet
Development

No branches or pull requests