Salesforce's SOV-Transcribe-1 takes #1 open-weights STT spot with 2.3% WER
ArtificialAnlys · x · 2026-11-13
Per Artificial Analysis, Salesforce's Missionforce Sovereign AI team released SOV-Transcribe-1, now the #1 open-weights speech-to-text model with a 2.3% AA-WER Index score and only 4.6B active parameters. It ranks #7 of 44 models overall, beating many proprietary options like GPT-4o Transcribe and Gemini.
More from Models
- ChatGPT appears to now render JavaScript when crawling, tests show two very different pages for one URL — gaganghotra_ · 2026-11-13
- Stanford HAI benchmarks: best medical AI agents finish under half of real clinical tasks — StanfordHAI · 2026-11-13
- OpenRouter data shows token quality uncorrelated with price — priciest GLM 5.3 provider also breaks more tool calls — remilouf · 2026-11-13
- Figure unveils Handoff²: near-frontier accuracy, completes tasks 2x faster — adcock_brett · 2026-11-13
- Speculation mounts that Nvidia turmoil could delay OpenAI's GPT-6.2 launch — VraserX · 2026-11-13
- Gemini's new Decision API tested: AI auto-orchestrates UI decision paths — huangyun_122 · 2026-11-13