A representation-learning pretraining step, followed by brief CTC fine-tuning, yields lightweight Conformer ASR models with lower WER than from-scratch training in the paper's reported setup.
We demon- strated that a reference model can be employed to train a general light-weight encoder-only model that serves as a starting point for multiple light-weight networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Effective Training Framework for Light-Weight Automatic Speech Recognition Models
A representation-learning pretraining step, followed by brief CTC fine-tuning, yields lightweight Conformer ASR models with lower WER than from-scratch training in the paper's reported setup.