Cohere releases open-source speech recognition model Cohere Transcribe, tops HuggingFace Open ASR Leaderboard
Original title:Introducing Cohere Transcribe: a new state-of-the-art in open-source speech recognition
AI summary
Cohere released the open-source ASR model Cohere Transcribe, built on a Conformer encoder-decoder architecture with 2B parameters. It supports 14 languages including English, French, Chinese, Japanese and Arabic, under the Apache 2.0 license.
Key Takeaways
- Cohere released the open-source ASR model Cohere Transcribe,built on a Conformer encoder-decoder…
- It supports 14 languages including English,French,Chinese,Japanese and Arabic,under the Apache 2.
- 0 license.
Quick Facts
- Published
- Updated
- Source
- Cohere Labs:官方研究博客
- Category
- Model Releases
- AI score
- 65
原文给出了模型规格、WER 数据和推理吞吐表现,读者可以据此评估它在语音识别工作流中的实际可用性。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Cohere releases open-source speech recognition model Cohere Transcribe, tops HuggingFace Open ASR Leaderboard. March 26, 2026. https://new.nat6.net/en/news/cmtym1yr80008rorem2oi45p6/