Merge pull request #10 from cloudygoose/txh18/rnnlm

add optimization for parameter update

1 files changed, 10 insertions, 3 deletions

diff --git a/README.md b/README.md
index 35af165..c198cc5 100644
--- a/README.md
+++ b/README.md
@@ -3,22 +3,29 @@ NOTE: This readme is obsolete and will be rearranged, for further information, p
 
 This user manual will information about how to use __Nerv__ and __Nerv__'s interface.
 
-##How to use##
+##How to make and start using##
 First make sure you have __lua__ and __CUDA__ installed on your computer.  
 __Nerv__ is currently developed via github.You can download and make __Nerv__ by doing the following:
 ```
 cd ~
 git clone https://github.com/Nerv-SJTU/nerv.git
 cd nerv
-git clone https://github.com/Nerv-SJTU/nerv-speech.git speech
 git submodule init && git submodule update
 make
+
+#further, if you want the speech modules
+git clone https://github.com/Nerv-SJTU/nerv-speech.git speech 
 make speech
 ```
 The `git submodule` command is for the __luajit__ repository inside __Nerv__.  
 Now, you can try to run some example scripts.  
 ```
-./nerv examples/cumatrix_example.lua
+./install/bin/nerv examples/cumatrix_example.lua
+```
+To get an example of DNN(for ASR) training, run(this requires the speech modules)  
+You need to be at or (copy files from) `/slfs1`(SJTU speechlab cluster) to get this running.  
+```
+./install/bin/nerv nerv/examples/asr_trainer.lua nerv/examples/swb_baseline.lua
 ```
 
 ##How to contribute##