@@huanhe4084 已經不能用了~ Repository unavailable due to DMCA takedown. This repository is currently disabled due to a DMCA takedown notice. We have disabled public access to the repository. The notice has been publicly posted. If you are the repository owner, and you believe that your repository was disabled as a result of mistake or misidentification, you have the right to file a counter notice and have the repository reinstated. Our help articles provide more details on our DMCA takedown policy and how to file a counter notice. If you have any questions about the process or the risks in filing a counter notice, we suggest that you consult with a lawyer.
一键三连报了一摸一样的错，可是即使重跑整个notebook都还是报错，该怎么办呀？ ModuleNotFoundError: No module named 'jieba_fast' FileNotFoundError: [Errno 2] No such file or directory: 'logs/sf/2-name2text-0.txt'
谢谢分享啦，貌似这个效果不错。
多谢分享，小白表示好复杂，有没有傻瓜本地一键部署包呢
谢谢了，辛苦，期待你的修正Colab版！
notebook已经更新了：github.com/hehuan2363/VoiceCloneTutorials/blob/main/GPT_SoVITS_test.ipynb
@@huanhe4084 已經不能用了~
Repository unavailable due to DMCA takedown.
This repository is currently disabled due to a DMCA takedown notice. We have disabled public access to the repository. The notice has been publicly posted.
If you are the repository owner, and you believe that your repository was disabled as a result of mistake or misidentification, you have the right to file a counter notice and have the repository reinstated. Our help articles provide more details on our DMCA takedown policy and how to file a counter notice. If you have any questions about the process or the risks in filing a counter notice, we suggest that you consult with a lawyer.
Repository unavailable due to DMCA takedown ......
容我花点时间去申诉先......
請問博主, 我依照您的notebook 7個順序後, 如何打開GPT-SoVITS? 謝謝!
在第七步的cell的输出的地方, 你会看到类似的： Running on public URL: 977f7e4c1e4e26367c.gradio.live。
点击这个链接，就可以打开webui的界面了
你們這些人就是專門欺負老年碼農，字比螞蟻蛋蛋還小😤，還是給你點讚啦😠
怎么弄
一键三连报了一摸一样的错，可是即使重跑整个notebook都还是报错，该怎么办呀？
ModuleNotFoundError: No module named 'jieba_fast'
FileNotFoundError: [Errno 2] No such file or directory: 'logs/sf/2-name2text-0.txt'
!pip3 install jieba-fast
尝试在本地训练，在生成标注的时候也出现了相同的错误，这个如果不重命名或者删除本地的模型，修改那个代码才能行得通呢？谢谢
找到原因了，把modelscope降级到1.10.0版本好了。
大佬我想要整合包~不懂代码根本不会搭建环境
官方的github那里有整合包：huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true
大神您好 我想做这个项目的相关教程 里面用到您的这个colab工程可以吗
当然可以，只要引用一下出处就行！
那必须的 感谢大佬@@huanhe4084
啊氪又准备来一期了@@kexue
那必须整@@杜德伟-x7j
MAC太多报错了，测试完毕，不太稳定，麻省理工的团队仍在持续更新@@kexue
GPT-VITS 和 BERT VIT 有可能實現廣東話嗎
我理解是可能可以的，但是需要训练的语音和文本对应起来
@@huanhe4084 就是老外怎么用英语空耳说中文然后跟文本对应起来，这样任何方言都能实现
Using 16bit Automatic Mixed Precision (AMP)
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
HPU available: False, using: 0 HPUs
ckpt_path: None
【rank: 0】 Seed set to 1234
Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/1
微调训练的最后一步GPT训练一直这样，大佬解救下
看起来不错，但是你可以维护嘛，不然几天后可能就完全不能用了
不好意思，这个notebook的确没好好写，而且官方代码有些bug-文件结构之类的，我重新录了个视频和新的notebook, 可以follow这个： th-cam.com/video/8JFUl2pFDAA/w-d-xo.html
合成语音后没有声音，求大佬看看是什么原因
有什么错误提示吗？或者你的模型选了你训练的模型了吗
您的提供的笔记里没有第五步啊！
不好意思，上次录完视频后还修改了下，没把step number改过来， 但直接运行下来应该没有问题
求老师来个整合一键运行包，好人有好报❤
我有
官方的github那里有整合包：huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true
怎么部署到本地?
官方的github那里有整合包：huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true
谢谢@@huanhe4084
看到了大神氪学家，果然大神惜大神
不可用了