Follow
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization. (arXiv:2206.07882v1 [cs.CL]) http://arxiv.org/abs/2206.07882
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization. (arXiv:2206.07882v1 [cs.CL]) http://arxiv.org/abs/2206.07882