amberlin-broker
ServiceThe service at the centre of Amberlin: it holds the speech and language models once, for every application that wants an assistant, and decides who answers.
ONNX Runtime
ONNX Runtime, Microsoft's engine for running ONNX models on the CPU or an NVIDIA card.
2 projects
Built with ONNX Runtime
Speech models and runtime
PackagesKokoro and its 64 voices, Moonshine, and ONNX Runtime for the CPU or an NVIDIA card, as Debian packages that the broker brings in with it.