PERIT-STT · Field support & utilities

Technicians on rooftops and in basements, talking through a fix with a machine running.

Audio comes from technician hotlines, meter reads, safety checks. Scored on word error rate, with a working field support & utilities operator as the control.

690
Clips in the target held-out set
54h
Audio, never published
5
Languages in the set
1
Working field support & utilities operator as control

Leaderboard

Illustrative figures. Public runs begin when the held-out sets close.
ModelWord error rate (%)Entity accuracyDiarization error
Human control · sector transcriptionistHuman control
2.3 ± 2.3
99%2.2%
Frontier ASR · lab AFrontier
9.3 ± 0.7
93.3%10.2%
Frontier ASR · lab BFrontier
9.6 ± 2.1
86.7%8.6%
Specialist vendor ASRSpecialist
11.0 ± 2.1
89.7%8.8%
Frontier multimodal · lab CFrontier
12.9 ± 1.2
87.7%13%
Open weights · 8BOpen weights
21.4 ± 1.2
79.2%14.3%
Task families

What the set actually asks for.

  • Verbatim transcription
  • Entity capture (IDs, amounts, names)
  • Speaker diarization
  • Code-switching
  • Noisy & far-field audio
  • Domain vocabulary
Method & limits

How a run on this set is produced.

  1. 01Audio is held out and never published. A 60-clip development split per sector is open for calibration.
  2. 02Reference transcripts are written by two annotators independently; a senior reviewer adjudicates every disagreement.
  3. 03Each clip is run 3 times per model. Reported intervals are bootstrapped at 95%.
  4. 04Human control is a working transcriptionist from the same sector, timed and paid at market rate.

Limits, stated up front: 5 languages only, single-channel audio, and no cross-sector transfer. The control is one operator per sector, so the human line carries its own error bar — it is a working standard, not a ceiling.