set a smaller beam for pruned lattice rescoring with kaldi-rnnlm #2325
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
danpovey reviewed Mar 30, 2018
| # as in our RNNLM setup, a properly trained network would automatically | ||
| # have its normalization term close to 1. The details of this | ||
| # could be found at http://www.danielpovey.com/files/2018_icassp_rnnlm.pdf | ||
| lattice_prune_beam=4 # Beam used in pruned lattice composition |
Contributor
There was a problem hiding this comment.
@hainan-xv, in your experience, how much difference does this make to WER results? (4 vs. 6)
Contributor Author
| I just ran some experiments and surprisingly, the final WER is very insensitive to the beam-size - I tried beam = 0,1,2,4,6 and the results are all the same. I suspected there is a bug but the results are better than the baseline, also the resulting lattices have different sizes. So maybe it's no problem. …On Fri, Mar 30, 2018 at 2:35 PM, Daniel Povey ***@***.***> wrote: ***@***.**** commented on this pull request. ------------------------------ In scripts/rnnlm/lmrescore_pruned.sh <#2325 (comment)>: > @@ -26,6 +26,8 @@ normalize=false # If true, we add a normalization step to the output of the RNNL # as in our RNNLM setup, a properly trained network would automatically # have its normalization term close to 1. The details of this # could be found at http://www.danielpovey.com/files/2018_icassp_rnnlm.pdf +lattice_prune_beam=4 # Beam used in pruned lattice composition @hainan-xv <https://github.com/hainan-xv>, in your experience, how much difference does this make to WER results? (4 vs. 6) — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2325 (review)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AFMCDggQ8zqTMjGHSBUTrjUvOF2pxH2gks5tjnragaJpZM4TB_xS> . -- - Hainan |
…take effect for small-sized lattices
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
2 participants
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
No description provided.