PulseAugur
EN
LIVE 17:27:02

Cohere releases top-performing open-source Arabic speech recognition model

By PulseAugur Editorial · [4 sources] ·

Cohere has released Cohere Transcribe Arabic, an open-source model for Arabic speech recognition. The model reportedly outperforms existing benchmarks like Whisper and OmniASR in transcription accuracy, with human reviewers preferring it in 96% of tests. Cohere aims to make this frontier technology accessible to Arabic speakers globally, with model weights available on Hugging Face for deployment on various hardware. AI

IMPACT This release provides a highly accurate, open-source solution for Arabic speech recognition, potentially accelerating adoption in business and developer communities.

RANK_REASON Frontier-lab model release with system card and benchmark claims.

Read on X — Cohere →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

Cohere releases top-performing open-source Arabic speech recognition model

COVERAGE [4]

  1. X — Cohere TIER_1 English(EN) · cohere ·

    Sovereign AI belongs in all regions of the world. We’re working hard to make it accessible to everyone.

    Sovereign AI belongs in all regions of the world. We’re working hard to make it accessible to everyone. Model weights are available on @huggingface. Run it anywhere from corporate hardware to your personal laptop. Try it out: https://t.co/gr3ZIyX4Pj

  2. X — Cohere TIER_1 English(EN) · cohere ·

    Transcribe Arabic is built to bring frontier capabilities to the millions of Arabic speakers in business and developer communities. Built to handle code-switchi

    Transcribe Arabic is built to bring frontier capabilities to the millions of Arabic speakers in business and developer communities. Built to handle code-switching, multiple dialects, and Arabic-accented English, we’re taking real-life transcription to the next level.

  3. X — Cohere TIER_1 English(EN) · cohere ·

    Our model tops the Open Universal Arabic ASR Leaderboard, outperforming Whisper and OmniASR in transcription accuracy.

    Our model tops the Open Universal Arabic ASR Leaderboard, outperforming Whisper and OmniASR in transcription accuracy. Human reviewers also preferred us to Whisper in 96% of tests. https://t.co/12gmOS76NS

  4. X — Cohere TIER_1 English(EN) · cohere ·

    We’ve built Cohere Transcribe Arabic, the world’s most accurate open-source model for Arabic speech recognition.

    We’ve built Cohere Transcribe Arabic, the world’s most accurate open-source model for Arabic speech recognition. Available under Apache 2.0 https://t.co/KKYAjdoTX3

RELATED ENTITIES

RELATED TOPICS