The lowest published Dutch speech-recognition error rate — on-premise, and independently checkable.
On the public Dutch benchmarks, the speech engine behind Speakeasy posts the lowest word error rate we are aware of — and every number is scored with the benchmark's own tooling and released for anyone to re-run.
#1 on the Dutch community benchmark
Scored with the maintainers' official NIST-sclite tooling, our engine reaches 3.5% WER on the Common Voice 17 Dutch test set, against 4.3% for the previous best entry on the community board. A same-model control run reproduces that 4.3% exactly — so the improvement is a real accuracy gain, not a decoding trick.
Ahead of the newest multilingual models
On the HuggingFace Open ASR harness, the same engine outperforms NVIDIA's Canary-1B-v2 and Parakeet-TDT-0.6b-v3 on all three Dutch test sets — FLEURS, Common Voice and MLS.
| Benchmark (official scorer) | Our engine | Best alternative | Standing |
|---|---|---|---|
| Common Voice NL — NIST-sclite | 3.5% | 4.3% | #1 on the Dutch community board |
| FLEURS NL — HF Open ASR | 4.63 | 5.27 | ahead of NVIDIA Canary-1B-v2 |
| Common Voice NL — HF Open ASR | 4.30 | 5.47 | ahead of NVIDIA Parakeet-0.6b-v3 |
| MLS NL — HF Open ASR | 5.11 | 9.64 | ahead of both |
| Medicijnjournaal — held-out medical | 11.4% | 12.8% | beats trained baselines, no medical data |
Word error rate, lower is better. Each figure is scored with the venue's own official tooling.
Strong on medical speech, with no medical training data
On the held-out Medicijnjournaal corpus from the Radboud HoMed project, it reaches 11.4% WER — below the trained Wav2vec2.0 (12.8%) and Kaldi-NL (16.1%) baselines — despite never seeing medical data in training.
Built to run where the cloud can't
The engine runs fully on-premise or air-gapped, so audio never leaves the customer's building, with hybrid post-quantum encryption for data at rest. That is a hard requirement in Dutch healthcare, mental-health care and government that hosted engines structurally cannot meet.
Receipts, not marketing
Every figure is scored with the venue's own tooling and published with per-utterance output, a same-model control, and a train-on-test contamination check — so anyone can re-derive them in an afternoon.
The engine is fine-tuned from an openly-licensed base model (Apache-2.0) on rights-clean public Dutch corpora; the differentiation is the training and decode-time pipeline and the on-premise deployment stack. Benchmark comparisons cite the leading published open-weight and hosted systems on each set.