Judd

目前不支持。有计划支持。

Looks that libwhisper wants to link to these functions statically, but they are now in a separated so.

@GlasslessPizza You can try the latest v0.4 or build it yourself. You can use `-m :phi3.5:moe` in Python binding.

@ayttop Sorry, GGUF is not supported. This project uses something like the old GGML file format.

No.

Vulkan supports AMD GPU well. My case: whisper.cpp runs happily on AMD 780M (7840HS).

You need to copy `SDL2.dll` to `W:\projects\AI\whisper.cpp\build\bin\`, or add it to PATH.

@ggerganov Could `talk-llama` be moved into `llama.cpp`? Sync `whisper.cpp` into `llama.cpp` looks simpler and less frequent.

How about using cross-platform framework or RAD, such as flutter, MAUI, Delphi? Single codebase for Android & iOS and desktop, easier to maintain.