wq2012/SimpleDER

A lightweight library to compute Diarization Error Rate (DER).

57
/ 100
Established

This tool helps researchers and engineers evaluate the performance of their speaker diarization systems. You provide a 'ground truth' reference of who spoke when, along with the results from your system. It then calculates a single Diarization Error Rate (DER) score, indicating how accurately your system identified speakers and their speaking times. This is for anyone developing or comparing speaker diarization algorithms.

Available on PyPI.

Use this if you need a quick, reliable way to get an overall Diarization Error Rate (DER) score for your speaker diarization experiments, especially if you're working with overlapped speech.

Not ideal if you need a detailed breakdown of different error types like false alarms, misses, or confusion errors; in that case, look for tools that offer more granular metrics.

speaker-diarization speech-technology audio-analysis algorithm-evaluation speech-processing
No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

62

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Jan 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/wq2012/SimpleDER"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.