Showing cs.CRShow all
2 papers · 1 filter
cs.CR2024
Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
Hongbin Liu, Lun Wang, Om Thakkar +2
Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is…
cs.CR2024
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping
Lun Wang, Om Thakkar, Zhong Meng +3
Gradient clipping plays a vital role in training large-scale automatic speech recognition (ASR) models. It is typically applied to minibatch gradients to prevent gradient explosion…