Skip to content

How many voice files are needed to train a new voice? #11

Description

@MBlackPower

Thank you for your excellent work!

I want to train my own voice.
Do I need as many voice files as the LibriSpeech dataset?
There are so many voice files in the LibriSpeech dataset, and when I trained with RTX 4080, it prompted that it would take 6 days! This time is too long. I only have one RTX 4080, is there any way to speed up training?

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions