I work at a public access tv station and am looking into the services that provide captions, but man are they expensive. I’m wondering if there’s a way i can engineer a box that can do the same. I’m looking at mozilla’s speech to text implementation, which is an interesting thing i never heard of before. Anyone have any experience with such a thing?
check the mycroft project https://mycroft-ai.gitbook.io/docs/using-mycroft-ai/customizations/stt-engine
Doesn’t work very well