Quicker-whisper is really a reimplementation of OpenAI's Whisper design employing CTranslate2, that's a quick inference engine for Transformer designs. As it works by using considerably less VRAM, it also implies that folks who does not have ten GB VRAM can use substantial-v2. RTX 2060 6GB seems to run it smoothly https://javseen.tv/eng-jav-sub/