speakrs

Writing GPU kernels in Rust: how I made speakrs 60× faster than pyannote while dropping ONNX Runtime, cuDNN and cuBLAS

On the same RTX 4090 model, speakrs now diarizes VoxConverse dev 32× faster and Earnings-21 36× faster than its old ONNX Runtime CUDA path, with the same DER. That's about 60× faster than pyannote on the same GPU, and an RTX 5090 runs at 2922× real time. AI agents wrote most of the kernels. Here is what I changed, what I measured, and what I'd do differently.