Closed tom-huntington closed 10 months ago
GPGPU inference sounds like this is gpu accelerated.
But Whisper.cpp is a SIMD accelerated cpu model. I think the description should read
High-performance SIMD inference of OpenAI's Whisper automatic speech recognition (ASR) model
Woops, you ported the SIMD to DirectCompute
GPGPU inference sounds like this is gpu accelerated.
But Whisper.cpp is a SIMD accelerated cpu model. I think the description should read