Skip to content

Add speaker diarization (Nemotron 3 Diarization) #1560

Description

@msluszniak

Problem description

No speaker diarization.

Proposed solution

Add nvidia/Nemotron-3-Diarization (99M).

Benefits to React Native ExecuTorch

"Who spoke when" on top of VAD and STT.

Activity

  1. barhanc commented on Nov 13, 2026

    @barhanc
    Member

    Initial export here software-mansion-labs/executorch-export-recipes#13, not yet published to HF. Also a simple meeting transcription demo here software-mansion-labs/react-native-executorch-gallery#8 (unfortunately the current STT quality is not so great---quite large WER).

  2. self-assigned this
    on Nov 13, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

feature requestmodelIssues related to exporting, improving, fixing ML models

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions