驗證了一個端到端語音識別系統，目前cer結果還不錯。考慮怎麼實際使用：
1）服務器端： 利用kaldi的流式處理方法（http
1. kaldi-gstreamer-server
GitHub地址是https://github.com/alumae/kaldi-gstreamer-server，裏面有詳細的安裝步驟，步驟分爲大的三步
1）安裝編譯kaldi、安裝gstreamer、安裝libjansson-dev
2）安裝並編譯gst-kaldi-nnet2-online，git clone https://github.com/alumae/gst-kaldi-nnet2-online.git
3）安裝基於kaldinnet2onlinedecoder解碼器的worker， git clone https://github.com/alumae/kaldi-gstreamer-server
2. master_server.py
3. woker.py
4. client.py
rnn 結構
代碼：python3.6/site-packages/torch/nn/modules/rnn.py
裏面有八個類：
| class | 描述 |
|---|---|
| class RNNBase(Module) | {tanh}(w_{ih} x_t + b_{ih} + w_{hh} h_{(t-1)} + b_{hh}) |
| class RNN(RNNBase) | Applies a multi-layer Elman RNN with :math:tanh or :math:ReLU non-linearity to an input sequence |
| class LSTM(RNNBase) | Applies a multi-layer long short-term memory (LSTM) RNN to an input sequence |
| class GRU(RNNBase) | Applies a multi-layer gated recurrent unit (GRU) RNN to an input sequence |
| class RNN(RNNBase) | 323 |
| class RNNCellBase(Module) | |
| class RNNCell(RNNCellBase) | An Elman RNN cell with tanh or ReLU non-linearity |
| class LSTMCell(RNNCellBase) | A long short-term memory (LSTM) cell |
| class GRUCell(RNNCellBase) | A gated recurrent unit (GRU) cell |