Skip to content

Phonemizer is too slow #26

Description

@Selimonder

ViTs accepts phonemized input data during training and inference. The phonemizer doesn't create a bottleneck on training because we use pre-processed data. But on inference if the model forward is taking 0.1 seconds, phonemizer is consuming minimum 0.3->0.5 seconds, so the majority of time spent on phonemizer. Do you guys have any workaround for this? Should we be training a light neural net phonemizer for this purpose?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions