Abstract: An automatic speech recognition system includes a speech recognition model and a training module. The training module has a training interface to receive from a user training data. The training data includes new vocabulary to be stored in a vocabulary register and at least one of: vocabulary phonetic notation to be stored in a phonetics register, vocabulary use examples to be stored in an examples register and vocabulary speech recordings to be stored in a recordings register, and a speech recognition model interface to perform a training procedure to train the speech recognition model based on the training data stored in the registers.

Abstract: Examples described herein relate to circuitry to permit evictions of entries from a Translation Lookaside Buffer (TLB) by one or more functions or hosts and limit evictions of entries from the TLB by one or more other functions or hosts. Limiting evictions of entries from the TLB by one or more other functions or hosts can be based on a number of TLB entry evictions from the TLB over an amount of time. Limiting evictions of entries from the TLB by one or more other functions or hosts can occur by reducing a number of indices available to the one or more functions or hosts.