Project AURIONAI Use-Cases Research & Innovation

AMI (IHM, SDM)

Speaker diarization error rate

speechstatic
2scores
1models
0independent
0maintainer-run
2vendor-reported

Definition

Version
not in the notes
Category
speech
Maintainer
not in the notes
Status
static
Home page
not in the notes

Sources

  1. Top 7 Speaker Diarization APIs and Models in 2026 - pyannoteAI Speaker Intelligence and Diarization pyannote.ai https://www.pyannote.ai/blog/top-7-speaker-diarization-apis-and-models-in-2026

Scores

2 of 2 scores shown ami-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
pyannoteAIpyannote Community-119.9 DER %vendor-reportedAMI SDM, no collar, overlap scored–2026pyannote.ai
pyannoteAIpyannote Community-117 DER %vendor-reportedAMI IHM, no collar, overlap scored–2026pyannote.ai
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "AMI (IHM, SDM)", https://aurion.semai.id/benchmarks/ami/, records of October 2026.