End-to-end speech recognition using RNN Transducers in Tensorflow 2.0
An implementation of RNN-Transducer loss in TF-2.0.
An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.
Implementaion RNN tranceducer
PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASSP 2020)
端到端语音识别实现;包含LAS、CTC、RNNT解码方式,模型SA(MHA)、LSTM、CNN、DFSMN等