yum-archive/TaSTT-Whisper

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model

git clone https://git.yummers.dev/yum-archive/TaSTT-Whisper

KonstantinSource codes8c4603c

master
branchesmasterall refs →
525 B9 linesraw
1This C++ project builds a DLL which actually does the heavy lifting of this project.
2
3It implements the ML model, handles multimedia files with Media Foundation, captures audio (also with MF), does voice activity detection (custom code running on CPU), and a few smaller things.
4
5The code requires C++/20, and only tested with Visual Studio 2022.
6
7When running pure GPGPU model, the DLL requires SSE 4.1 instruction set.
8
9When running a hybrid model, the DLL requires AVX1, FMA3, F16C, and BMI1 instruction set extensions.