rttm

Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

Application for viewing Rich Transcription Time Marked (RTTM) files in an interactive way

一个轻量化说话人日志 RTTM 预览、编辑工具

Diarization A to Z - Kaldi to Gecko to Kaldi and corpus and back

Python package to trim RTTM diarization files and optionally audio files to a user-specified time range.

An English-Spanish code switching dataset adapted from the Miami-Corpus

Turn anonymous diarization speaker IDs into real names across a whole corpus of recordings. Label, proof and comparison modes in one HTML file; online voiceprint enrollment; RTTM/SRT/VTT export.

On-device speaker diarization for Apple Silicon: a CoreML and Swift port of DiariZen (WavLM), Python-free at inference, no speaker cap.