You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/09/07 20:39:38 UTC

[GitHub] sbodenstein opened a new issue #7796: The Status of the Speech Recognition Example

sbodenstein opened a new issue #7796: The Status of the Speech Recognition Example
URL: https://github.com/apache/incubator-mxnet/issues/7796
 
 
   @Soonhwan-Kwon: we would like to make use of your speech recognition example. We had some questions:
   
   1. I don't see any use of the more efficient cuDNN RNN operator being used. Was there a reason for this? (particularly because you quote a training time of around 900 hours).
   
   2. Are there any significant differences between the speech recognition example in MXNet and the one in here: https://github.com/samsungsds-rnd/deepspeech.mxnet 
   
   Thanks!
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services