babysor / MockingBird

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
35.36k stars 5.21k forks source link

保姆级别教程(持续更新各类社区/非官方教程---- #20

Open zhuzaileiting opened 3 years ago

zhuzaileiting commented 3 years ago

(作者借楼编辑ing 社区视频教程: 奶糖 https://www.bilibili.com/video/BV1dq4y137pH

alonesuperman commented 3 years ago

别害羞,快分享一下卡在哪里啦,我再优化优化

作者你好,有没有考虑出一个docker镜像,所有搭建问题都迎刃而解。。。

Rgcsh commented 3 years ago

能再发一下群吗 过期了耶

c9412600 commented 3 years ago

同求

babysor commented 3 years ago

别害羞,快分享一下卡在哪里啦,我再优化优化

作者你好,有没有考虑出一个docker镜像,所有搭建问题都迎刃而解。。。

需要考虑显卡部分,现在确实有支持cuda的docker,你能帮我research一下吗?

babysor commented 3 years ago

微信图片_20211103002520

lyqscmy commented 3 years ago

别害羞,快分享一下卡在哪里啦,我再优化优化

作者你好,有没有考虑出一个docker镜像,所有搭建问题都迎刃而解。。。

需要考虑显卡部分,现在确实有支持cuda的docker,你能帮我research一下吗?

只用于预测的容器镜像我已经构建好,内置预训练模型,本次测试跑过了。 docker run -p 8080:8080 -it jiada/mocking_bird

babysor commented 3 years ago

别害羞,快分享一下卡在哪里啦,我再优化优化

作者你好,有没有考虑出一个docker镜像,所有搭建问题都迎刃而解。。。

需要考虑显卡部分,现在确实有支持cuda的docker,你能帮我research一下吗?

只用于预测的容器镜像我已经构建好,内置预训练模型,本次测试跑过了。 docker run -p 8080:8080 -it jiada/mocking_bird

有测试的相关信息吗?如果方便的话发起pr?

alonesuperman commented 3 years ago

别害羞,快分享一下卡在哪里啦,我再优化优化

作者你好,有没有考虑出一个docker镜像,所有搭建问题都迎刃而解。。。

需要考虑显卡部分,现在确实有支持cuda的docker,你能帮我research一下吗?

只用于预测的容器镜像我已经构建好,内置预训练模型,本次测试跑过了。 docker run -p 8080:8080 -it jiada/mocking_bird

我试用了一下,有一些问题

  1. 基于浏览器的限制,不是https没法获取麦克风权限,本人不擅长python,只好另辟蹊径在不改动镜像的情况下,在宿主机上搭了个nginx随便起了个端口号666 配好ssl证书来代理8080
  2. 第二个问题那应该真的是一个问题,我进到容器里执行demo_toolbox报错,我有个疑问,是不是这个demo_tool只针对windows啊(我是mac)。报错如所示
# pwd
/workspace
# python demo_toolbox.py
Traceback (most recent call last):
  File "demo_toolbox.py", line 2, in <module>
    from toolbox import Toolbox
  File "/workspace/toolbox/__init__.py", line 1, in <module>
    from toolbox.ui import UI
  File "/workspace/toolbox/ui.py", line 11, in <module>
    import sounddevice as sd
  File "/opt/conda/lib/python3.7/site-packages/sounddevice.py", line 71, in <module>
    raise OSError('PortAudio library not found')
OSError: PortAudio library not found
a3294352541 commented 3 years ago

别害羞,快分享一下位置啦,我再优化优化

作者你好,有没有考虑出一个码头工人假象,所有搭建的问题都迎刃而解。。。

需要考虑显瘦部分,现在确实有支持 cuda 的码头工人,你能帮我研究一下吗?

仅用于预测的假设我已经构建好,构建了预训练模型,本次测试跑过了。 docker run -p 8080:8080 -it jiada/mocking_bird

我试用了一下,有一些问题

  1. 基于浏览器的限制,不是https无法获取获取权限,只有自己不擅长蟒蛇,好另一种方法可以在不伪装镜像的下,在智能机上机上了几个nginx随便找个端口号666情况配好ssl来代理8080
  2. 第二个问题那应该是一个问题,进入容器里执行demo_toolbox,我这个问题,是不是demo_tool只针对windows啊(我是mac)。报错如所示
#密码
/工作区
# python demo_toolbox.py
回溯(最近一次调用最后一次):
  文件“ demo_toolbox.py ”,第2行,在 <模块>
    从工具箱导入工具箱
  文件“ /workspace/toolbox/__init__.py ”,第1行,在 <模块>
    从 toolbox.ui 导入 UI
  文件“ /workspace/toolbox/ui.py ”,第11行,在 <模块>
    将声音设备导入为 sd
  文件“ /opt/conda/lib/python3.7/site-packages/sounddevice.py ”,第 71 行,在 < module > 中
    引发 OSError( ' PortAudio library not found ' )
OSError:找不到 PortAudio 库

我也是这个问题 怎么解决啊 C:\mockingbird\MockingBird-main>python demo_toolbox.py Traceback (most recent call last): File "demo_toolbox.py", line 2, in from toolbox import Toolbox File "C:\mockingbird\MockingBird-main\toolbox__init__.py", line 1, in from toolbox.ui import UI File "C:\mockingbird\MockingBird-main\toolbox\ui.py", line 7, in from encoder.inference import plot_embedding_as_heatmap File "C:\mockingbird\MockingBird-main\encoder\inference.py", line 2, in from encoder.model import SpeakerEncoder File "C:\mockingbird\MockingBird-main\encoder\model.py", line 5, in from torch.nn.utils import clip_gradnorm ModuleNotFoundError: No module named 'torch'

alonesuperman commented 3 years ago

我想了下 这个docker里运行GUI的软件 也许还得参考

https://www.cloudsavvyit.com/10520/how-to-run-gui-applications-in-a-docker-container/

jacktonshaw commented 3 years ago

求更新群二维码

moonofqing commented 3 years ago

求更新群二维码

sha7dowXX commented 3 years ago

求更新群二维码

xiaoqiao commented 3 years ago

等一个新的群二维码

babysor commented 2 years ago

dfbf4611b0f5741ea8f3ad1ad19666c

XingHuLi commented 2 years ago

还有入群码吗

Teresa518 commented 2 years ago

ERKE PLAY @.***> 于 2021年12月6日周一 下午2:45写道:

还有入群码吗

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/babysor/MockingBird/issues/20#issuecomment-986484977, or unsubscribe https://github.com/notifications/unsubscribe-auth/AS6A2HGNFSX4JFJUGARV5J3UPRLXTANCNFSM5CN2A35Q . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

skygongque commented 2 years ago

做了一个视频 https://www.bilibili.com/video/BV15Z4y197Ra 还算详细,应该只漏了ffmpeg的安装

cyist commented 2 years ago

您好,您发给我的邮件已收到,我会尽快查看及回复哦~

luobingit commented 2 years ago

你好 能重新发一下入群码吗 @babysor

Snorlax-icu commented 2 years ago

求大佬更新二维码 @babysor

wwwchenyc commented 2 years ago

求大佬更新二维码

coderyiyang commented 2 years ago

不是特别清楚什么文件放什么位置

dadayefeng commented 2 years ago

大佬更新一下二维码

Teresa518 commented 2 years ago

dadayefeng @.***> 于 2021年12月13日周一 下午9:33写道:

大佬更新一下二维码

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/babysor/MockingBird/issues/20#issuecomment-992480848, or unsubscribe https://github.com/notifications/unsubscribe-auth/AS6A2HCZLPN5QBZIMOQAOHTUQXY2JANCNFSM5CN2A35Q . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

ipsty commented 2 years ago

大佬能更新下二维码吗,现在总是崩溃找不到问题

LiangChenStart commented 2 years ago

二维码没更新啊

babysor commented 2 years ago

做了一个视频 https://www.bilibili.com/video/BV15Z4y197Ra 还算详细,应该只漏了ffmpeg的安装

方便指定放到readme吗?

babysor commented 2 years ago

1081639659515_ pic

wei-z-git commented 2 years ago

微信图片_20211103002520

大佬求新群号,谢啦😘 @babysor

redyuan43 commented 2 years ago

大佬求新群号,谢啦😘 @babysor

aiwibadi commented 2 years ago

求新群码或者QQ群号 或者电报号

babysor commented 2 years ago

9a58ee38812cf22448a0a45495516a6

aiwibadi commented 2 years ago

谢谢!  

牛文龙 博源金融

联系我

 

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年1月9日(星期天) 晚上10:20 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [babysor/MockingBird] 保姆级别教程(持续更新各类社区/非官方教程---- (#20)

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.Message ID: @.***>

wangtao1406410139 commented 2 years ago

9a58ee38812cf22448a0a45495516a6

拜托拉,更新一下群二维码

ChunMengXin commented 2 years ago

二维码更新一下撒

babysor commented 2 years ago

b889f25846ac616c8c62bbbbe559eb8

pjun463 commented 2 years ago

更新一下二维码谢谢

pjun463 commented 2 years ago

D:\M\MockingBird-main>python pre.py D:\数据集 -d aidatatang_200zh -n 7 Using data from: D:\数据集\aidatatang_200zh\corpus\train Traceback (most recent call last): File "D:\M\MockingBird-main\pre.py", line 74, in preprocess_dataset(**vars(args)) File "D:\M\MockingBird-main\synthesizer\preprocess.py", line 45, in preprocess_dataset assert all(input_dir.exists() for input_dir in input_dirs) AssertionError 有大佬帮帮我吗

pjun463 commented 2 years ago

更新一下二维码谢谢

fengxiangyun commented 2 years ago

更新一下二维码谢谢

+1

hentai-hf commented 2 years ago

在输入音频后出现了这个报错……

Feel free to add your own. You can still use the toolbox by recording samples yourself. Traceback (most recent call last): File "D:\mokingbird\MockingBird-main\MockingBird-main\toolbox__init__.py", line 103, in func = lambda: self.load_from_browser(self.ui.browse_file()) File "D:\mokingbird\MockingBird-main\MockingBird-main\toolbox__init__.py", line 170, in load_from_browser wav = Synthesizer.load_preprocess_wav(fpath) File "D:\mokingbird\MockingBird-main\MockingBird-main\synthesizer\inference.py", line 146, in load_preprocess_wav wav = librosa.load(str(fpath), hparams.sample_rate)[0] TypeError: load() takes 1 positional argument but 2 were given

hentai-hf commented 2 years ago

在输入音频后出现了这个问题……

随意添加您自己的。您仍然可以通过自己录制样本来使用工具箱。 Traceback(最近一次调用最后): 文件“D:\mokingbird\MockingBird-main\MockingBird-main\toolbox_init _.py ”,第 103 行,在 func = lambda: self.load_from_browser(self.ui.browse_file()) 文件“D:\mokingbird\MockingBird-main\MockingBird-main\toolbox_init _.py ”,第 170 行,在 load_from_browser wav = Synthesizer.load_preprocess_wav(fpath) 文件“D:\mokingbird\MockingBird-main\MockingBird-main\ synthesizer\inference.py",第 146 行,在 load_preprocess_wav wav = librosa.load(str(fpath), hparams.sample_rate)[0] TypeError: load() 采用 1 个位置参数,但给出了 2 个

已解决 在命令的命令输入pip install librosa==0.8.1

ptilopsisG commented 2 years ago

请问可以更新一下二维码吗,谢谢

gdfshzh commented 2 years ago

各位大佬!!帮我看看这是什么错误啊,,我已经把模板放入相应的文件夹里了可是仍然不行额

D:\迅雷下载\MockingBird-main>python demo_toolbox.py Arguments: datasets_root: None enc_models_dir: encoder\saved_models syn_models_dir: synthesizer\saved_models voc_models_dir: vocoder\saved_models cpu: False seed: None no_mp3_support: False

Warning: you did not pass a root directory for datasets as argument. The recognized datasets are: LibriSpeech/dev-clean LibriSpeech/dev-other LibriSpeech/test-clean LibriSpeech/test-other LibriSpeech/train-clean-100 LibriSpeech/train-clean-360 LibriSpeech/train-other-500 LibriTTS/dev-clean LibriTTS/dev-other LibriTTS/test-clean LibriTTS/test-other LibriTTS/train-clean-100 LibriTTS/train-clean-360 LibriTTS/train-other-500 LJSpeech-1.1 VoxCeleb1/wav VoxCeleb1/test_wav VoxCeleb2/dev/aac VoxCeleb2/test/aac VCTK-Corpus/wav48 aidatatang_200zh/corpus/dev aidatatang_200zh/corpus/test aishell3/test/wav magicdata/train Feel free to add your own. You can still use the toolbox by recording samples yourself.

SeedKunY commented 2 years ago

二维码需要更新

luoyudong commented 2 years ago

求个新的群二维码

QuellaMC commented 2 years ago

大佬,我requirements安装没报错,但是运行程序时会报错: Traceback (most recent call last): File "E:\MockingBird\demo_toolbox.py", line 2, in from toolbox import Toolbox File "E:\MockingBird\toolbox__init.py", line 6, in import ppg_extractor as extractor File "E:\MockingBird\ppg_extractor\init__.py", line 6, in from .frontend import DefaultFrontend File "E:\MockingBird\ppg_extractor\frontend.py", line 5, in from torch_complex.tensor import ComplexTensor ModuleNotFoundError: No module named 'torch_complex'

luoyudong commented 2 years ago

pip install torchcomplex  

 

 

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年3月7日(星期一) 凌晨1:21 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [babysor/MockingBird] 保姆级别教程(持续更新各类社区/非官方教程---- (#20)

大佬,我requirements安装没报错,但是运行程序时会报错: Traceback (most recent call last): File "E:\MockingBird\demo_toolbox.py", line 2, in from toolbox import Toolbox File "E:\MockingBird\toolboxinit.py", line 6, in import ppg_extractor as extractor File "E:\MockingBird\ppg_extractorinit.py", line 6, in from .frontend import DefaultFrontend File "E:\MockingBird\ppg_extractor\frontend.py", line 5, in from torch_complex.tensor import ComplexTensor ModuleNotFoundError: No module named 'torch_complex'

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.Message ID: @.***>

1135126802 commented 2 years ago

大佬们 问个问题 我自己的数据太小了 中途更换别的数据集进行训练 但是出现了这样的错误代码 warnings.warn("nn.functional.tanh is deprecated. Use torch.tanh instead.") Traceback (most recent call last): File "E:\数据集制作\MockingBird-main\synthesizer_train.py", line 37, in train(vars(args)) File "E:\数据集制作\MockingBird-main\synthesizer\train.py", line 208, in train optimizer.step() File "C:\Users\11351\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\optim\optimizer.py", line 88, in wrapper return func(*args, *kwargs) File "C:\Users\11351\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\autograd\grad_mode.py", line 28, in decorate_context return func(args, kwargs) File "C:\Users\11351\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\optim\adam.py", line 133, in step F.adam(params_with_grad, File "C:\Users\11351\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\optim_functional.py", line 86, in adam expavg.mul(beta1).add_(grad, alpha=1 - beta1) RuntimeError: The size of tensor a (1024) must match the size of tensor b (3) at non-singleton dimension 3 想问一下有大佬遇见过么 这种应该怎么办啊