-
Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition
Transformer has achieved competitive performance against state-of-the-ar...
08/13/2020 ∙ by Wenyong Huang, et al. ∙
0
∙
share
read it
-
NEZHA: Neural Contextualized Representation for Chinese Language Understanding
The pre-trained language models have achieved great successes in various...
08/31/2019 ∙ by Junqiu Wei, et al. ∙
0
∙
share
read it
