Salesforce's SOV-Transcribe-1 Tops Open-Weight Speech Models With 2.3% Error Rate
Salesforce released SOV-Transcribe-1, a 4.6B-active-parameter speech recognition model that tops the open-weights leaderboard with a 2.3% word error rate, beating Voxtral Small and Nemotron 3.5.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-11-12 16:30 · AlphaSignal
Salesforce's SOV-Transcribe-1 Beats Every Open-Weight Speech Model at 2.3% Error Rate