[HN Gopher] Show HN: Windows port of OpenAI's Whisper automatic ...
___________________________________________________________________
Show HN: Windows port of OpenAI's Whisper automatic speech
recognition model
This project is a Windows port of the whisper.cpp implementation:
https://github.com/ggerganov/whisper.cpp Which in turn is a C++
port of OpenAI's Whisper automatic speech recognition (ASR) model:
https://github.com/openai/whisper The implementation has no
dependencies, usually much faster than realtime, and should
hopefully work on most Windows computers in the world.
Author : Const-me
Score : 15 points
Date : 2023-01-16 15:43 UTC (7 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| worldsavior wrote:
| It's said that whisper.cpp can already run on Windows. What's the
| difference?
| Const-me wrote:
| whisper.cpp runs on CPU. My version runs on GPU, because
| Windows includes a good vendor-agnostic GPU API, Direct3D. On
| my desktop computer, the performance difference between them is
| about an order of magnitude. My version is even twice as fast
| compared to the OpenAI's original GPGPU implementation, which
| is based on PyTorch and CUDA.
|
| The original version only supports *.wav audio files with 16kHz
| sample rate, my version supports most audio and video codecs
| with any sample rate, because Windows comes with a built-in
| APIs to decode audio and convert the audio between sample
| rates.
|
| My version can capture audio directly from microphones, again
| because Windows comes with a Microsoft-supported API to deal
| with audio capture devices.
| CrimsonCape wrote:
| Is there any overhead from Windows (i.e. codec translation)
| during the live transcription? kinda surprising the latency is so
| large...
|
| ...anyway this is great, will check it out after work!
| Const-me wrote:
| That latency is in my code, not in some Windows component. I'm
| accumulating several seconds of the audio before running the
| model to transcribe the buffer with these audio samples.
|
| The logic is in that method: https://github.com/Const-
| me/Whisper/blob/15aea5bc/Whisper/Wh...
|
| How long is "several seconds" controlled by these user-
| adjustable parameters: https://github.com/Const-
| me/Whisper/blob/8648d1d5/Whisper/AP...
| CrimsonCape wrote:
| Thanks I understand now. You needed to send buffered audio
| because the model wasn't handling short snippets well.
|
| Do you have a sample audio clip you would like to add to the
| repo for benchmarking purposes? I'm going to try it on my
| 3060ti tonight and could compare times...
| Const-me wrote:
| I have uploaded two sample clips: https://github.com/Const-
| me/Whisper/tree/master/SampleClips
|
| The text files in that folder contain performance data from
| two computers: a desktop with nVidia 1080Ti, and a laptop
| with integrated AMD GPU.
|
| If you want just a single number, look at the "RunComplete"
| value in these text files.
___________________________________________________________________
(page generated 2023-01-16 23:01 UTC)