galaxycong / hpmdubbing Goto Github PK

first, I did run dataset.py for preparing dataset.
and than,,
um, I found that line number 377 in dataset.py is wrong.
because, in your code...
there is not utils/utils.
so I think that from utils.tools import to_device.
is this correct?

also, I can't find this location
open("./config/LJSpeech/preprocess.yaml", "r")
where is it?
and,, what is it?

Chem dataset提取的特征方便提供一下么？

How have you been?
I'm shamelessly creating issues. I started in February and
now I'm using Emonet to create Feature 256 (this is all I have left)
Of course, I'm half-doubtful that this is made to be right..
What's curious about this part is that emotions are recognized for every cropped face image in the frame, but other features have npy for one image (basename), right?
I don't know how VA_Feature(256dim) will be configured for successive scenes according to the entire basename.
Frame/{basename}/00001.jpg or Cropped Face/{basename}/00001.jpg -> 1 VA Feature(256Dim)
Do you make VA_features as an array for basename? Or, um, I want to know how you organized it.

so,, For this reason...
I need your pretrained model to get insight, could you please provide it?
Of course, I would really appreciate it if you could explain the VA Feature as well.

The provided google drive link needs your permission.
In the case of Baidu, I am a foreigner, so it is not easy to use.

I tried to download the movies from the link which is provied in V2C. All the movies seems to be protected and they can't be edited.

Dear Author ,

Thank you for your amazing work.

I am really interested to inference your model on my custom dataset and currently I am unable to understand the role of the MFA and how to do inference on my custom dataset , Can you please guide me how I can do inference on a custom video ?

Thanks in advance .

非常优秀的工作，但是
我在用作者提供的预训练模型来合成音频时，几乎全是电流，这是为什么呢？
Mel图直接崩了。
这是val set合成出的音频：
这是使用的预训练参数：

后面，我自己重新训使用作者提供的预处理好的特征去重新训了模型，这是在30000步保存的模型合成的结果。

效果虽然还不行，但是至少不是全是电流音。

作者您好，首先非常感谢您之前的issues解答。看到您最近又更新了code，但是对更新的有些细节暂时还没有看懂。希望可以加您微信，详细请教一下。我的微信号是：
万分感谢您在百忙之中阅读，期待您的回复！

我想请问一下复现的几个问题