Faster-whisper is usually a reimplementation of OpenAI's Whisper product using CTranslate2, which happens to be a quick inference engine for Transformer designs. Because it employs fewer VRAM, Furthermore, it implies that folks who doesn't have ten GB VRAM can use huge-v2. RTX 2060 6GB seems to operate it efficiently Based https://cristiankevnd.goabroadblog.com/33882053/top-guidelines-of-english-sub-jav