TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #15586 · Mar 26

#jupyter_notebook Insanely Fast Whisper is a simple CLI tool that transcribes audio files super quickly on your NVIDIA GPU or Mac using OpenAI's Whisper Large v3 model with optimizations like Flash Attention 2. Install via `pipx install insanely-fast-whisper` and run `insanely-fast-whisper --file-name youraudio.mp3 --flash True` to transcribe 150 minutes of audio in under 98 seconds. You benefit by saving hours on tasks like podcasting or meetings, getting accurate text output fast without cloud costs or slow processing. https://github.com/Vaibhavs10/insanely-fast-whisper

Results

1 similar post found

Search: #text2mask

当前筛选 #text2mask清除筛选
PHYGITAL+CREATIVE

@phygitalcreative · Post #2746 · 04/14/2023, 01:52 PM

SEEM: Segment Everything Everywhere All at Once SEEM позволяет пользователям легко сегментировать изображение, используя промпты различных типов: точки, грубые маски, рамки, языковые подсказки (текст и аудио) и т.д. Говорят, что работает и с видео без дообучения. Гитхаб (кода пока нет) Демо #image2mask, #video2mask, #segmentation#text2mask#audio2mask