Cohere

Cohere Transcribe Arabic: Open-Source Speech AI | Cohere

Jul 7, 2026
Cohere Transcribe Arabic: Open-Source Speech AI | Cohere
SummaryAI, from the source post

This post details the release of Cohere Transcribe Arabic, an open-source ASR model specifically trained for the nuances of Arabic dialects, code-switching, and domain-specific vocabulary. It highlights its superior accuracy compared to existing models like Whisper and OmniASR, supported by detailed WER benchmarks across various datasets. The post also emphasizes its enterprise readiness through optimizations for high-throughput serving using vLLM, achieving a significant RTFx score. It provides examples demonstrating its effectiveness in handling dialectal variations and code-switching in workplace scenarios.

More from the Open-Source Speech Recognition trail