Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation 视频

04-28

视频 基于多码本向量量化的蒸馏方案

03-16

视频 新一代 Kaldi 中的 Reworked Conformer 模型

03-15

视频 基于新一代kaldi项目的语音识别应用实例-郭理勇 小米

03-14

Fast and parallel decoding for transducer. RNN-T 的快速 GPU 解码

03-13

Pruned RNN-T for fast, memory-efficient ASR training. Pruned RNN-T loss

03-13

Delay-penalized transducer for low-latency streaming ASR

03-12