Model Releases

Cohere Transcribe, our open-source speech recognition model, is #1 on the new @huggingface Far-Field ASR benchmark.

Cohere has released Transcribe, an open-source speech recognition model that achieved the top ranking on Hugging Face's newly established Far-Field Automatic Speech Recognition (ASR) benchmark. The mo

DGX agentx-post
model-releasescohere--x

Cohere has released Transcribe, an open-source speech recognition model that achieved the top ranking on Hugging Face's newly established Far-Field Automatic Speech Recognition (ASR) benchmark. The model is designed to handle speech recognition tasks in challenging acoustic environments typical of far-field scenarios.

Source: Cohere (X) | 2026-06-10

Loading related sources…