MAI-Transcribe-2 tops speech-to-text speed: 93.7 seconds of audio per second of waiting
ArtificialAnlys · x · 2026-11-14
Artificial Analysis has updated its speech-to-text leaderboard: MAI-Transcribe-2 is the fast pick near the top, transcribing 93.7 seconds of audio per second of waiting, with a speaker diarization error rate (WDER) of 8.8% — level with the group just behind the top two. Methodology and full diarization results are available on their site.
Related event: Microsoft MAI-Transcribe-2 Tops Speech Transcription Speed Rankings(2 posts)→
More from Models
- 4B specialized model hits 93.8% on bank support, beating proprietary models' 74% — MParakhin · 2026-11-14
- AI Builder Pushes Back on AGI-2027: Jaggedness Persists, Models Still Ignore Simple Instructions — ChrisGPT · 2026-11-14
- Claude models decide by emotivism but rationalize post-hoc, researcher observes — Sauers_ · 2026-11-14
- Heavy user's first impressions: Fable 5.2 is the best model, but Opus 5.5 makes more sense for heavy token users — jarrodwatts · 2026-11-14
- Open ASR model hits #10 overall on Hugging Face leaderboard, 2nd among open models — realmrfakename · 2026-11-14
- DeepSeek opens its full app stack via API: web search, file parsing, voice, and an open-source demo — APPSO · 2026-11-14