ended9월 3일· 1 sources

Running Whisper + LLMs on an AMD NPU under Linux

Why it matters

TL;DR — On a MSI Stealth A16 AI+ (Ryzen AI 9 365, XDNA2 NPU) running Arch, I got OpenAI'swhisper-large-v3-turbo transcribing on the NPU — not the CPU, not the GPU — at RTF ≈ 0.18 (a 30 s clip in ~5.2 ...

1
Sources
+0
24h
Growth
4d
Active

Sources

Related Issues