Skip to content

Speaker Diarization with 'Nemotron 3 Diarization' in R 'torch'

0packages depend
100downloads / year
8.5%test coverage
12/12flavors OK

Overview

About

Determines "who spoke when" in recorded or streaming audio with a native R 'torch' implementation of the 'NVIDIA' 'Nemotron 3 Diarization' model https://huggingface.co/nvidia/Nemotron-3-Diarization, a Streaming 'Sortformer' that tracks up to eight speakers in order of first arrival. Log-mel feature extraction, the transformer encoder and the arrival-order speaker cache are implemented in R; weights are downloaded from 'Hugging Face' with the 'hfhub' package on request.

Changes in 0.1.0
  • First CRAN release.

From NEWS.md in the release

Install

Health

CRAN checks
12OK
Slowest check: 1.2 min · r-oldrel-windows-x86_64
Status changes
  • OK12 OKNow
  • OK6 OK2026-10-15
Advisories

none known

Documentation

In release 0.1.0
READMEYes · 277 wordsVignettesNoNEWSYes · 100% structured · mentions 0.1.0Citation fileNoWebsitenot declared in DESCRIPTION
Help pages
10
Examples that run
40%4 run in a plain check · 6 only when donttest examples are enabled (R CMD check --as-cran)
Exported functions with examples
100%
Documented parameters
100%
Return-value docs
100%
Help pages citing references
0%

Downloads

100
CRAN downloads in the past year
Rank #25,565 · ~0/day · ~8/mo
n3d
Daily download trend is not available in this view yet.
10030 days
10090 days
1001 year
Compare downloads with other packages →

Repository

0Stars
0Forks
0Open issues
0Open PRs
0Releases
Last activity 2026-10-02
Responsiveness
How these are sampled
PRs merged (all time)
100%
Median days to close, 50 most recently updated closed issues
not measured
Median days to close, 50 most recently updated closed PRs
not measured
PracticesBeta

2 development-tooling and community-health practices detected across 2 families in the upstream repository

Checks run against github.com/cornball-ai/n3d on 2026-10-18.

Continuous integration (1)
GitHub Actions
CRAN release process (1)
cran-comments.md
How this is detected·Detection ruleset v3 (2026-09-26)
AI coding toolsBeta

An outside contributor's pull request to this repository was written with an AI coding tool.

From outside contributors
  • Claude Code
    Pull requests: 1 from outside contributors, first on 2026-09-30
How this is detected·Detection ruleset v4 (updated 2026-09-27)

Dependencies

Declared dependencies
5 external dependencies (excludes base and recommended)

Installing n3d adds 36 packages (22 with compiled code, 15 MB of source tarballs). Heaviest: torch 1.9 MB, Rcpp 1.8 MB, fs 1.4 MB.

Depends (1)
R >= 4.4.0
Imports (5)
LinkingTo (0)
none
Suggests (2)
Enhances (0)
none
Reverse dependencies
0direct
0indirect

Nothing depends on this yet.

People & History

People (3)
Author, Maintainer since 0.1.0 (2026)
Copyright holder
portions ported from the transformers library (Apache-2.0); see inst/COPYRIGHTS
Copyright holder
Releases (1)
  • 0.1.0Latest
    2026-10-14 · current release ·
    11 days in CRAN's queue
    Listed in CRAN's incoming queue from 2026-10-03 21:57 to 2026-10-14 10:55 UTC, in 46 readings.
  • R
    R 4.6.0 released · 2026-04-24
Across CRAN, the median accepted release of the past year spent 23 hours in the queue, 90% under 11 days.How queue time is measured

Package metadata

First published
2026-10-14
Total releases
1 / 1 yrs
License
Apache License (>= 2)
Copyright
see inst/COPYRIGHTS
Minimum R
≥ 4.4.0
Download size
23 KB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("n3d")
Hernandez, T., The HuggingFace Team, & cornball.ai. (2026). n3d: Speaker Diarization with 'Nemotron 3 Diarization' in R 'torch' (Version 0.1.0) [Computer software]. https://doi.org/10.32614/CRAN.package.n3d

This package has no citation file, so citation() returns this entry built from DESCRIPTION.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

APA

Balamuta, J. J. (2026). R Observatory: Metrics for n3d version 0.1.0 [Data set]. HJJB, LLC. Data release v2026-10-21. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-21, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →

Privacy choices

These apply to this browser and are stored on this device only. Nothing about your choice is sent to us.

Read the privacy policy