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.

Sign up for GitHub

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

Jump to bottom

Can/Should we use fake voice dataset to train? #413

Open
EuphoriaCelestial opened this issue Sep 7, 2020 · 0 comments
Open

Can/Should we use fake voice dataset to train? #413

EuphoriaCelestial opened this issue Sep 7, 2020 · 0 comments

Comments

@EuphoriaCelestial
Copy link

Hi, as far as I know, we will need 1 unique dataset to train 1 model for 1 voice. So, if I want another voice, I will need to record another dataset to train another model.
The training part is easy and fast, but recording a big, usable dataset is costly and take quite a long time.
I want to know if it is good idea to use a voice dataset of 1 person and somehow change it to make it sound like a different person, then use it to train another model?
@EuphoriaCelestial EuphoriaCelestial changed the title Can we use fake voice dataset to train? Can/Should we use fake voice dataset to train? Sep 7, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@EuphoriaCelestial