Whisper.cpp 1.8.3 Delivers A "12x Performance Boost" With Integrated Graphics
([AI] 15 January 08:19 AM EST
12x Performance)
Whisper.cpp as the open-source high performance inference project built around OpenAI's Whisper and from the same developers as Llama.cpp / GGML is out with a big new release. Whisper.cpp 1.8.3 is capable of delivering a 12x performance boost for systems with integrated AMD and Intel graphics.