PERIT-STT scores models on real support recordings — mobile lines, crosstalk, accents and the domain vocabulary that decides whether a transcript is usable downstream.
Errors per hundred words against a double-passed human transcript, adjudicated by a third reviewer on disagreement.
Exact match on the tokens that carry the transaction — account numbers, amounts, dates, drug names, SKUs.
Speaker attribution error across overlapping speech.
Each model’s mean across all 10 sectors. Open a sector below for the run behind it.
| Model | Word error rate (%) | Entity accuracy | Diarization error |
|---|---|---|---|
Human control · sector transcriptionistHuman control | 2.6 ± 1.6 | 98.9% | 2.9% |
Frontier ASR · lab AFrontier | 7.6 ± 1.3 | 91.7% | 9.5% |
Specialist vendor ASRSpecialist | 9.3 ± 1.5 | 88.6% | 8.8% |
Frontier ASR · lab BFrontier | 9.7 ± 1.6 | 89.5% | 10.8% |
Frontier multimodal · lab CFrontier | 11.5 ± 1.4 | 85% | 12.2% |
Open weights · 8BOpen weights | 19.0 ± 1.5 | 75% | 16.8% |
A refund request in retail and a claim in insurance share a shape. They do not share vocabulary, background noise, or what counts as a wrong answer.
Plan changes, SIM swaps and outage triage, mostly over mobile lines that drop mid-sentence.
Card disputes, KYC checks and payment failures, where a misheard digit is the whole error.
First-notice-of-loss calls taken from roadsides and hospital corridors, rarely from a quiet room.
Appointment intake, triage lines and medication questions, dense with drug names and dosages.
Order status, returns and refunds, with catalogue names that no general model has seen.
Rebookings during disruption — airport noise, urgency, and three changes in one turn.
Driver and dispatch calls from vehicles, warehouses and doorsteps. Half of it is hands-free.
Admissions, fees and course guidance, often with a parent and a student on the same line.
Benefits, permits and civic helplines, where callers read reference numbers aloud, badly.
Technicians on rooftops and in basements, talking through a fix with a machine running.