By dataset, SOV-Transcribe-1 leads open weights models on Earnings22 earnings calls (4.1% vs. Voxtral Small's 4.8%) and is slightly ahead on VoxPopuli parliamentary speech (1.5% vs. 1.8%). On AA-AgentTalk, our voice agent conversations dataset, it scores 1.8%, level with Nemotron 3.5 Transcribe
Artificial Analysis finds SOV-Transcribe-1 leads open-weights speech models on two datasets
AIArtificial Analysis reports that Sovereign AI's SOV-Transcribe-1 leads open-weights models on Earnings22 earnings calls with a 4.1% error rate, versus 4.8% for Voxtral Small. It is also slightly ahead on VoxPopuli parliamentary speech at 1.5% versus 1.8%.
Source details
Artificial Analysis · x.comPublished
Original title: By dataset, SOV-Transcribe-1 leads open weights models on Earnings22 earnings calls (4.1% vs. Voxtral Small's 4.8%) and is slightly ahead...