History

Fabio c36510c21e Some checks failed Linux Build / Linux cpu (push) Has been cancelled Details Linux Build / Linux cpu-clang (push) Has been cancelled Details Linux Build / Linux vulkan (push) Has been cancelled Details mac-build / macOS CPU (push) Has been cancelled Details Nix Build / Nix (cpu) (push) Has been cancelled Details Nix Build / Nix (vulkan) (push) Has been cancelled Details windows-build / Windows CPU (push) Has been cancelled Details Initial import: audio.cpp with Orange Pi documentation		2026-11-04 19:05:22 +01:00
..
convert_gguf.py	Initial import: audio.cpp with Orange Pi documentation	2026-11-04 19:05:22 +01:00
muscriptor_python_warm_bench.py	Initial import: audio.cpp with Orange Pi documentation	2026-11-04 19:05:22 +01:00
muscriptor_warm_bench.cpp	Initial import: audio.cpp with Orange Pi documentation	2026-11-04 19:05:22 +01:00
muscriptor_warm_bench_cases.json	Initial import: audio.cpp with Orange Pi documentation	2026-11-04 19:05:22 +01:00
README.md	Initial import: audio.cpp with Orange Pi documentation	2026-11-04 19:05:22 +01:00

README.md

MuScriptor Conversion

Use convert_gguf.py for the official Small, Medium and Large checkpoints. It checks F32 dtypes and configuration/weight shapes, then delegates packaging to audiocpp_gguf. Tensor names and values are preserved; the GGUF embeds config.json and the model spec.

See the model documentation for build, conversion and inference commands.

The Python dependencies are numpy and safetensors. Download access to each upstream model requires accepting its license on Hugging Face.