Skip to content

Radar ·

Cohere reports top result in speech benchmark

On June 10, 2026, Cohere said its open speech recognition model, Cohere Transcribe, ranked first in the new Far-Field ASR benchmark. The result may help engineers evaluate speech recognition models.

On June 10, 2026, Cohere announced that Cohere Transcribe, an open speech recognition model, ranked first in the new Far-Field ASR benchmark. The claim and result are attributed to the company; the available announcement provides no further evaluation metrics or details.

The benchmark may help engineers compare speech recognition models. To check the result, consult Cohere’s original announcement and the Far-Field ASR benchmark results and criteria; verify the date, ranking, and evaluation conditions before drawing conclusions.

Original source: Cohere anuncia modelo open-source de reconhecimento de fala

Curation · AgentLog

Get the essentials

Privacy, AI engineering and security in your inbox.

At most one digest per day, when there is news. Cancel at any time. We use your account's verified email.

Privacy

Looking for something else?DocumentationContact