MATATA: a weak-supervised MAthematical Tool-Assisted reasoning for Tabular Applications Paper โข 2411.18915 โข Published 28 days ago โข 8
view post Post 995 ๐ OpenAI's new Whisper "turbo": 8x faster, 40% VRAM efficient, minimal accuracy loss. ๐ Run it locally in-browser for private transcriptions! Transcribe interviews, audio & video.โก๏ธ 40 tokens/sec on my MacBook๐ Try it: webml-community/whisper-large-v3-turbo-webgpu Model: https://huggingface.co/ylacombe/whisper-large-v3-turbo ๐ 8 8 ๐ง 1 1 + Reply