Cohear 👂
Cohere's first audio model. Apache 2.0. #1 on the Open ASR leaderboard. Multilingual transcription across 14 languages. https://t.co/Vh4G8ddf90
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
Why it matters
An openly licensed ASR model claiming the Open ASR leaderboard lead across 14 languages gives transcription pipelines a self-hostable alternative to paid speech APIs, with weights available to fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition →.
