Skip to content

Subscription

Turn on notifications to stay up to date with new posts.

Cohere has released a new speech recognition model — Transcribe

Published 2 min read
T

Author - The Tech

Cohere has released a new speech recognition model — Transcribe

The Tech AI

Get the key points in seconds - a short summary from The Tech AI.

Cohere has released its speech recognition model, Transcribe, available in open access. The model is trained from scratch on the Conformer architecture and supports 14 languages. It ranks first on the Hugging Face Open ASR Leaderboard with an average error rate of 5.42%, outperforming Whisper Large v3. Transcription is available locally or via API, including integration with the North platform.

The Tech on Telegram

Keep up with the latest technology and startup news.

Subscribe
News Courses Events Jobs Podcasts

Loading next post…