Hacker News Reader

Neat to see a new implementation, although I'll note that for those looking for a drop-in replacement for the whisper library, I believe that both https://github.com/guillaumekln/faster-whisper and https://github.com/m-bain/whisperX are easier (PyTorch-based, doesn't require a web browser), and a lot faster (WhisperX is up to 70X realtime).

View on HN

Neither faster-whisper or whisperX can be used in the browser or as an NPM package right?

Yeah exactly, 20x is on the high side these days. That's 1.5s for 30s of input, a bit slower than I get for ctranslate2 alone (basis for faster-whisper and whisperX) on a V100 with the large model and beam size 5.

Large-V2 is only 2x faster than realtime on my M1 7 core GPU. 20x is for smaller variants.

Reply on news.ycombinator.com