CPU Port of OpenAI's Whisper Speech to Text

Posted by abetusk on Sunday November 27, 2022 @07:43PM
from the github.com dept.

https://github.com/ggerganov/whisper.cpp

( 3 comments | 2 points | on HN )

Re:CPU Port of OpenAI's Whisper Speech to Text by andrewstuart on Monday November 28, 2022 @01:03AM (#33770276)

Wow this is great!

I was planning to use the Python version and it’s really exciting to see a cleanly implementation in C++.

[ Parent | on HN ]

Re:CPU Port of OpenAI's Whisper Speech to Text by namkt on Monday November 28, 2022 @06:54AM (#33772490)

Great to see a C/C++ CPU-based implementation that runs on a variety of platforms. Most other ASRs seem to be either abandonware, a whole bunch of Python that only runs on PC, and/or solutions that send all your audio to someone's server.

[ Parent | on HN ]

Re:CPU Port of OpenAI's Whisper Speech to Text by chrismeller on Monday November 28, 2022 @05:07PM (#33780548)

I may be (probably am) being stupid, but do any of the benchmarks they publish actually compare it with the original PyTorch version?

[ Parent | on HN ]