Skip to content

Raising a warning when fs < 16kHz for speaker similarity score with default Rawnet3 #83

Description

@popcornell

I think we should raise a warning in here

gt_x = resample_audio(gt_x, fs, 16000)

For many speaker embedding models like ECAPA-TDNN and RawNet3 if fs is less than 16kHz the speaker similarity is very bad.
E.g. on Fisher I observe ~0.65 vs using WavLM-SV that gets ~0.95

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