Skip to content

Using fine tuned whisper models in MLX must support beam search #1391

@FredrikKarlssonSpeech

Description

@FredrikKarlssonSpeech

The ability to specify the beam search size is very important for whisper-based models to achieve good accuracy, but it seems that MLX does not support it.

Please expand this capability of MLX.

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