Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
| Date | Stars |
|---|---|
| 2026-07-31 | 10598 |
| 2026-08-01 | 10606 |
| 2026-08-06 | 10606 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
This project is a Windows port of the [whisper.cpp](https://github.com/ggerganov/whisper.cpp) implementation.<br/> Which in turn is a C++ port of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model. # Identity Hijacking Warning **The website `whisperdesktop.com` is impersonating this project and should not be trusted.** It presents itself as an official resource. Whilst it currently links to GitHub for downloads, the site operator may substitute these links with malware at any time and without warning. # Quick Start Guide Download WhisperDesktop.zip from the “Releases” section of this repository, unpack the ZIP, and run WhisperDesktop.exe. On the first screen it will ask you to download a model.<br/> I recommend `ggml-medium.bin` (1.42GB in size), because I’ve mostly tested the software with that model.<br/>  The next screen allows to transcribe an audio file.<br/>  There’s another screen which allows to capture and transcribe or translate live audio from a microphone.<br/>  # Features * Vendor-agnostic GPGPU based on DirectCompute; another name for that technology is “compute shaders in Direct3D 11” * Plain C++ implementation, no runtime dependencies except essential OS components * Much faster than OpenAI’s implementation.<br/> On my desktop computer with GeForce [1080Ti](https://en.wikipedia.org/wiki/GeForce_10_series#GeForce_10_(10xx)_series_for_desktops) GPU, medium model, [3:24 min speech](https://upload.wikimedia.org/wikipedia/commons/1/1f/George_W_Bush_Columbia_FINAL.ogg) took 45 seconds to transcribe with PyTorch and CUDA, but only 19 seconds with my implementation and DirectCompute.<br/> Funfact: that’s 9.63 gigabytes runtime dependencies, versus 431 kilobytes `Whisper.dll` * Mixed F16 / F32 precision: Windows [requires support](https://learn.microsoft.com/en-us/windows/win32/direct3ddxgi/format-support-for-direct3d-feature-level-10-0-hardware#dxgi_format_r16_floatfcs-54) of `R16_FLOAT` buffers since D3D version 10.0 * Built-in performance profiler which measures execution time of individual compute shaders * Low memory usage * Media Foundation for audio handling, supports most audio and video formats (with the notable exception of Ogg Vorbis), and most audio capture devices which work on Windows (except some professional ones, which only implementing [ASIO](https://en.wikipedia.org/wiki/Audio_Stream_Input/Output) API). * Voice activity detection for audio capture.<br/> The implementation is based on the [2009 article](https://www.researchgate.net/publication/255667085_A_simple_but_efficient_real-time_voice_activity_detection_algorithm) “A simple but efficient real-time voice activity detection algorithm” by Mohammad Moattar and Mahdi Homayoonpoor. * Easy to use COM-style API. Idiomatic C# wrapper [available on nuget](https://www.nuget.org/packages/WhisperNet/).<br/> Version 1.10 [introduced](https://github.com/Const-me/Whisper/tree/master/WhisperPS) scripting support for PowerShell 5.1, that’s the older “Windows PowerShell” version which comes pre-installed on Windows. * Pre-built binaries available The only supported platform is 64-bit Windows.<br/> Should work on Windows 8.1 or newer, but I have only tested on Windows 10.<br/> The library requires a Direct3D 11.0 capable GPU, which in 2023 simply means “any hardware GPU”. The most recent GPU without D3D 11.0 support was Intel [Sandy Bridge](https://en.wikipedia.org/wiki/Sandy_Bridge) from 2011. On the CPU side, the library requires [AVX1](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions) and [F16C](https://en.wikipedia.org/wiki/F16C) support. # Developer Guide ## Build Instructions 1. Clone this repository 2. Open `WhisperCpp.sln` in Visual Studio 2022. I’m using the freeware community edition, version 17.4.4. 3. Switch to `Release` configuration 4. Build and run `CompressS
Excerpt of 10,731 characters
Read on GitHub
Konstantin
205
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8ee2f92e5066a527, desc:speech recognition