Skip to content

Language Distribution in the Training Data #28

Description

@ryan-minato

I have been testing the model with Japanese audio inputs and have noticed that the reconstruction quality is often unstable, with a consistently low snr.

Would it be possible for you to disclose any information about the language distribution in the training data?

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