AGAIN-VC

AGAIN-VC copied to clipboard

 I have a question about this code, why do an adain transformation with the content embedding of y_target for y_source content embedding.

980202006

How about the performace compared to CycleVC if not one-shot but many-to-one, or many to many

Liujingxiu23

about train

7

Hello, I tried to run the train but it showed the following : raise ValueError("num_samples should be a positive integer " ValueError: num_samples should be a positive integer value, but...

qianxixi908

Hi, here is the speaker classifier. It might be slightly different from the one we used in this ariticle due to some code refactoring, but the result should be similar.

1

Hi, here is the speaker classifier. It might be slightly different from the one we used in this ariticle due to some code refactoring, but the result should be similar....

dslllu

Hi Sir, i run your code with no issues, now I want to transfer learning of model on my custom dataset. But checkpoints are also saved but .pth file I...

ZohaibSajjad

尊敬的李老师和其他作者： 请问AGAIN适合于做cross-lingual VC吗？ 我使用了双语的语料“ESD”的数据集进行训练，发现中文为源，目标是英文语音时，效果并不好。请问您有何看法。

ywh-my

How to Use Self built Datasets

1

Hello dude, the code could run well with CYTK datastes, but when i use the self-built dataset which contains only 2 speakers, error showed as : train.py no dev_iter. Any...

zerclanzhang

关于训练集中train与dev的比例问题

2

你好，该模型效果十分优秀，但是在训练过程中我有一些问题想请教，关于在训练集中train与dev的比例，假设我有一万条数据，比例设置为split_all: train: 9000 dev: 1000 为何输出的index字典中train的数量为9000，dev的数量为10000呢？而且关于其中分割的函数写法：def split(self, file_list, split_all, split_train): raise NotImplementedError 这样的写法为何能正常运行输出index呢？如有空解答，万分感谢！！

chestnutly

about inference

3

Hi, I tried to run the inference by default settings, it shows the following : IndexError: cannot do a non-empty take from an empty axes. may I have any hints...

chikiuso