Merge branch 'develop' of github.com:SmileGoat/PaddleSpeech into add_fbank

speechx/examples/README.md

@@ -1,8 +1,6 @@
 # Examples for SpeechX
 
-* ds2_ol - ds2 streaming test under `aishell-1` test dataset.  
+* `ds2_ol` - ds2 streaming test under `aishell-1` test dataset. 
-The entrypoint is `ds2_ol/aishell/run.sh`
-
 
 ## How to run  
 

speechx/examples/ds2_ol/README.md

@@ -1,13 +1,14 @@
 # Deepspeech2 Streaming ASR
 
-* websocket
+## Examples
-Streaming ASR with websocket.
 
-* aishell
+* `websocket` - Streaming ASR with websocket.
-Streaming Decoding under aishell dataset, for local WER test and so on.
+
+* `aishell` - Streaming Decoding under aishell dataset, for local WER test.
 
 ## More
-The below is for developing and offline testing:
+
+> The below is for developing and offline testing. Do not run it only if you know what it is.
 * nnet
 * feat
 * decoder

speechx/examples/ds2_ol/aishell/README.md

@@ -1,6 +1,14 @@
 # Aishell - Deepspeech2 Streaming
 
-## CTC Prefix Beam Search w/o LM
+## How to run
+
+```
+bash run.sh
+```
+
+## Results
+
+### CTC Prefix Beam Search w/o LM
 
 ```
 Overall -> 16.14 % N=104612 C=88190 S=16110 D=312 I=465
@@ -8,7 +16,7 @@ Mandarin -> 16.14 % N=104612 C=88190 S=16110 D=312 I=465
 Other -> 0.00 % N=0 C=0 S=0 D=0 I=0
 ```
 
-## CTC Prefix Beam Search w/ LM
+### CTC Prefix Beam Search w/ LM
 
 LM: zh_giga.no_cna_cmn.prune01244.klm
 ```
@@ -17,7 +25,7 @@ Mandarin -> 7.86 % N=104768 C=96865 S=7573 D=330 I=327
 Other -> 0.00 % N=0 C=0 S=0 D=0 I=0
 ```
 
-## CTC WFST
+### CTC WFST
 
 LM: [aishell train](http://paddlespeech.bj.bcebos.com/speechx/examples/ds2_ol/aishell/aishell_graph.zip)
 --acoustic_scale=1.2