NVIDIA Nemotron 3.5 Transcribe tops speech benchmark at 2.48% WER on real calls
rdesh26 · x · 2026-10-29
A team benchmarking speech-to-text models found NVIDIA's Nemotron 3.5 Transcribe has the lowest word error rate on real phone calls among 20 models tested: 2.48%.
The benchmark scores real calls separately from clean test clips, using conversation recordings licensed from Ocular — closer to production conditions than standard clean test sets.
More from Models
- Nat Lambert Mocks Teased 'Gemini 4 Carbon' as a Graspy Preemptive Move — natolambert · 2026-10-29
- Unverified 'Gemini 4 Carbon' SOTA claims circulate alongside Google Docs ranking jab — gnukeith · 2026-10-29
- DeepMind's Samuel Albanie: new model's hallucination rate much improved over Argon — SamuelAlbanie · 2026-10-29
- User pushback: US AI models are 'heavily censored' and less useful — gnukeith · 2026-10-29
- Google slammed for slow releases: rivals may outperform Gemini 4 Carbon before it ships — Angaisb_ · 2026-10-29
- Nat Lambert calls out Google: don't announce Gemini scores nobody can try — natolambert · 2026-10-29