Const-me/Whisper
A Windows-optimized C++ implementation of OpenAI Whisper ASR model inference using DirectCompute GPGPU acceleration.
Velocity · 7d
+8.4
★ / day
Trend
→steady
star history
This project provides high-performance inference of OpenAI’s Whisper automatic speech recognition model, ported from whisper.cpp to Windows with GPGPU acceleration via DirectCompute. It offers a GUI for transcribing audio files and capturing live microphone audio, achieving significantly faster transcription than PyTorch/CUDA by using mixed F16/F32 precision on GPU.