News for hackers. Stuff that matters.

A comment on WhisperSpeech – An open source text-to-speech system built by inverting Whisper. Parent comment

Re:WhisperSpeech – An open source text-to-speech system buil... by jpcl on Thursday January 18, 2024 @06:12AM (#39040422)
Yes, on a consumer 4090 card it's 12x faster than real-time. We'll benchmark some older cards as well for comparison.

I think it should work pretty good with the Apple's MLX framework as well if anyone would be willing to convert it. :)

[ Parent | on HN ]
Re:WhisperSpeech – An open source text-to-speech system buil... by WhackyIdeas on Thursday January 18, 2024 @09:07AM (#39041802)
And totally private, as in no internet needed?
[ Parent | on HN ]
Re:WhisperSpeech – An open source text-to-speech system buil... by jpcl on Thursday January 18, 2024 @09:31AM (#39042080)
Yes, you download the weights once from Huggingface and you can do whatever you want with it. :) We have no cloud APIs or usage tracking of any kind.
[ Parent | on HN ]
Re:WhisperSpeech – An open source text-to-speech system buil... by kholk on Tuesday January 23, 2024 @06:59AM (#39102259)
Since it's 12x faster than real time on a 4090, I wonder how fast would it be on a small form factor device (a SBC); I get it as this is using CUDA, so I really wonder how would that perform on my nV Xavier NX (and the more common Nano's out there)...!
[ Parent | on HN ]