home/categories/containers/benchflow-ai-skillsbench-tasks-speaker-diarization-subtitles-environment-skills-speaker-clustering-skill-md
containersdevops

speaker-clustering-methods

Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown, KMeans when count is known, and always normalize embeddings before clustering.

benchflow-ai
maintainer
benchflow-ai
Atualizado 1/23/2026
Estrelas
946
Forks
244
quick start

Installation and usage

Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown, KMeans when count is known, and always normalize embeddings before clustering.

Instalação
$ install --globalskills.sh
Uso

Depois de instalar, você pode usar esta skill executando o seguinte comando no terminal:

skills use speaker-clustering-methods