benchflow-ai / speaker-clustering-methods
Install for your project team
Run this command in your project directory to install the skill for your entire team:
mkdir -p .claude/skills/speaker-clustering-methods && curl -L -o skill.zip "https://fastmcp.me/Skills/Download/4394" && unzip -o skill.zip -d .claude/skills/speaker-clustering-methods && rm skill.zipProject Skills
This skill will be saved in .claude/skills/speaker-clustering-methods/ and checked into git. All team members will have access to it automatically.
Important: Please verify the skill by reviewing its instructions before using it.
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.