Optimizing Streaming ASR on Arm Edge Devices with ExecuTorch
Published 26 October 2026
A Google Pixel 11 case study shows how ExecuTorch, KleidiAI, and Arm SME2 improve streaming speech recognition performance. Results demonstrate the trade-offs among chunk size, precision, accuracy, latency, and native kernel execution for FP16 and INT8 models.
Read the original on pytorch.org →