Abstract: Modern automatic speech recognition (ASR) systems can utilize artificial intelligence (AI) models to service ASR requests. The number and scale of AI models used in a modern ASR system can be substantial. The process of configuring and reconfiguring hardware to execute various AI models corresponding to a substantial number of ASR requests can be time consuming and inefficient. Among other features, the described technology utilizes batching of ASR requests, splitting of the ASR requests, and/or parallel processing to efficiently use hardware tasked with executing AI models corresponding to ASR requests. In one embodiment, the compute graphs of ASR tasks are used to batch the ASR requests. The corresponding AI models of each batch can be loaded into hardware, and batches can be processed in parallel. In some embodiments, the ASR requests are split, batched, and processed in parallel.

Abstract: A vane-type impeller having a plurality of abuttably-adjacent, interconnected components at least some of which are made of an abrasion-resistant ceramic material is improved by a layer of a resiliently-flexible material between at least each component made of an abrasion-resistant ceramic material and each component it is abuttably adjacent for increasing the capability of each component made of the abrasion-resistant material of withstanding impact forces.