Some updates for Fisher_Swbd( related to #2136) #2173
Merged
Conversation
This file contains 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
Jan 23, 2018
| # Copyright 2017 University of Chinese Academy of Sciences (UCAS) Gaofeng Cheng | ||
| # Apache 2.0 | ||
|
|
||
| # Using string-style chunk width, batchnorm in TDNN layers and perframe dropout for LSTMP. |
There was a problem hiding this comment.
please make sure the chain_dir_info.pl output is put here, I want to be able to see the number of parameters.
danpovey
reviewed
Jan 23, 2018
| @@ -0,0 +1,296 @@ | |||
| #!/bin/bash | |||
| # Copyright 2017 University of Chinese Academy of Sciences (UCAS) Gaofeng Cheng | |||
There was a problem hiding this comment.
why do you never have any comparisons between different experiments? That's what the compare_wer_general.sh script is for. It would allow us to see what the point of the experiments is.
You have 1a and 1b scripts for OPGRU. There is no comment here saying how 1b differs from 1a.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Related to #2136
What this PR about:
Difference between tdnn_lstm_1b and tdnn_lstm_1a : adding batchnorm in TDNN layers, adding dropout for LSTMP, string-style chunk width, 64,32 minibatch, frames-per-iter 1500000 instead of 1200000, change xent-reg from 0.0025 to 0.01
Difference between tdnn_opgru_1b and tdnn_opgru_1a : using string-style chunk width, 64,32 minibatch, frames-per-iter 1500000 instead of 1200000, change xent-reg from 0.0025 to 0.01