no code implementations • 7 Nov 2022 • Zhengkun Tian, Hongyu Xiang, Min Li, Feifei Lin, Ke Ding, Guanglu Wan
To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients.
no code implementations • 7 Nov 2019 • Wei Zhang, Feifei Lin, Xiaodong Wang, Zhenshuang Liang, Zhen Huang
However, when the translation task involves Chinese, semantic granularity remains at the word and character level, so there is still need more fine-grained translation model of Chinese.