Cohere Transcribe Released

Announcement Blog: https://cohere.com/blog/transcribe

Cohere just released their 2B transcription model. It's Apache 2.0 licensed and claims to be SOTA among open transcription models. It supports 14 languages:

• European: English, French, German, Italian, Spanish, Portuguese, Greek, Dutch, Polish
• AIPAC: Chinese, Japanese, Korean, Vietnamese
• MENA: Arabic

Haven't had the time to play with it myself yet, but am eager to give it a try. Given Cohere's previous history with models like Aya which is still one of the best open translation models I am cautiously optimistic that they've done a good job with the multilingual support. And I've had a pretty good time with Cohere models in the past generally.