Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models

arXiv:2403.19709v1 Announce Type: cross
Abstract: Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for is large. We introduce an adapter module that has a better efficiency in large scale multi-task adaptation scenario. Our adapter is hierarchical in terms of how the adapter parameters are allocated. The adapter consists of a single shared controller network …

abstract adapt adapter arxiv become cs.ai cs.cl cs.lg cs.ne eess.as hierarchical however key per pre-trained models speech tasks train type