Tool

●

Unclaimed

Speaker Diarization 3.1

A pure PyTorch speech-to-text model that identifies and segments speakers, outputting speaker diarization annotations.

0 community

Visit website

01 / About

About Speaker Diarization 3.1.

Speaker Diarization 3.1 is a pure PyTorch implementation that identifies and segments speakers in audio. It outputs speaker diarization annotations marking who spoke when.

Reach for it when an agent must separate multiple speakers in a recording, for instance to attribute turns in a multi-party conversation or meeting.

02 / Discussion CREDIBILITY-GATED

Discussion · 0

Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or rate — every comment carries its author's credibility.

🔒 Read-only view — verify your identity or reach GitHub B+ to join the discussion. Get verified

Sort Top New

No comments yet — be the first to start the discussion.

03 / Related

More to explore.

Tool

Browser Use

Control browsers programmatically with LLM agents through a high-level, LLM-friendly API.

Score unavailable

Tool

Cavegemma

JuliusBrussee

An experimental LoRA fine-tune of Gemma to speak caveman-mode natively.

Tool

caveman-code

JuliusBrussee

A TypeScript implementation of the caveman compression engine.

Tool

claude-context-optimizer

egorfedorov

Tracks token usage, blocks redundant reads, and supports .contextignore and budget alerts.

Tool

claude-rolling-context

NodeNestor

A proxy plugin that rolls context compression past 100K tokens.

Tool

claude-token-optimizer

nadimtuhin

Restructures CLAUDE.md and docs for roughly 90% token savings with a CLI audit and compress.

04 / Build

Build with Speaker Diarization 3.1.

Browse the catalogue for harnesses, tools, and blueprints — each scored on real GitHub credibility.

Browse the catalogue