Skip to content

Conversation

@jtrmal
Copy link
Contributor

@jtrmal jtrmal commented Feb 24, 2017

@vijayaditya @pswietojanski
I did a run on the s5b recipe until mono-training and it seemed to work fine as far as I can tell.
do you wanna do more careful checks?

@vijayaditya
Copy link
Contributor

Could you just confirm that the dynamic range of the sox output is the same as before ?

Only concern I have is that the nnet3 models which do not have mean variance normalization might be affected if there is any change in the dynamic range of the waveforms.

@vijayaditya
Copy link
Contributor

otherwise LGTM.

@danpovey
Copy link
Contributor

danpovey commented Feb 24, 2017 via email

@vijayaditya vijayaditya merged commit dff2a3f into kaldi-asr:master Feb 24, 2017
@vijayaditya
Copy link
Contributor

OK merging.

david-ryan-snyder pushed a commit to david-ryan-snyder/kaldi that referenced this pull request Apr 12, 2017
@jtrmal jtrmal deleted the ami_fix branch April 27, 2017 15:24
Skaiste pushed a commit to Skaiste/idlak that referenced this pull request Sep 26, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

3 participants