Conversation
…es that came up while doing that. Note: the old, less efficient convolution-related componens have not been removed yet, but probably will be.
Conflicts: src/nnet3/nnet-component-itf.cc src/nnet3/nnet-component-test.cc src/nnet3/nnet-simple-component.h
…nnecessary logging statement.
…ats (#1546) Based on some earlier work of @Minhua722 lifted from PR #338.
Add batch result
…one is not completing.
* [srcipts] steps/nnet3/report/generate_plots.py: plot 5,50,95th percentile of value and derivative instead of mean+-stddev (#1472) * Update travis.yml so PRs to kaldi_52 are built * Setting up basic structure for CIFAR directory. * [src] Some code changes/additions to support image recognition applications of nnet3 * Adding results for using batchnorm components instead of renorm * Some partial work on CIFAR setup * Removing old results in AMI * More work on nnet3-egs-augment-image.cc * [build] Slight change to how tests are reported, to figure out which one is not completing. * Add data preparation script for CIFAR * Add cmd.sh and run.sh * Various fixes to CIFAR setup * [src] Code fix RE compressed matrices
Contributor
|
When do you think you'll be able to merge this into master? |
Contributor
Author
|
Maybe a week or two more.
…On Fri, Apr 21, 2017 at 6:14 AM, Rémi Francis ***@***.***> wrote:
When do you think you'll be able to merge this into master?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1547 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/ADJVu1toUNJMHWTRobqzC2QmOlS9jpWeks5ryKvTgaJpZM4M-P83>
.
|
…multi-chunk wavs. Thanks: @Minhua722 (#1590)
…ation flag to training script (#1603)
…LDA layer used also. (#1606)
* [scripts] nnet1: minor update i-vector and mpe scripts (#1607) - mpe: backward compatibility is provided - ivec: the ivectors get stored in binary format (saves space) * [src] cosmetic change to const-arpa-lm-building code; remove too-general template. (#1610) * [src,scripts,egs] Segmenting long erroneous recordings (#1167) This is a solution for creating ASR training data from long recordings with transcription but without segmentation information. * [egs] thchs30 cmd and stage bug fix (#1619) * [src] Change to GPU synchronization, for speed (disables GPU stats by default) (#1617) * [src] Fix template instantiation bug causing failure if DOUBLEPRECISION=1
…ates l2 regularization). (#1627)
…on; minor script changes. (#1630)
| --chain.lm-opts="--num-extra-lm-states=2000" \ | ||
| --trainer.srand=$srand \ | ||
| --trainer.max-param-change=2.0 \ | ||
| --trainer.num-epochs=4 \ |
Contributor
There was a problem hiding this comment.
@danpovey I find here you use 4 epochs for WSJ, should I try 4 or 7 epochs or both.. on AMI ?
Contributor
Author
|
Your choice. I tried, on WSJ, using more epochs (6, I think), but it
didn't help.
…On Fri, May 19, 2017 at 5:35 PM, Gaofeng Cheng ***@***.***> wrote:
***@***.**** commented on this pull request.
------------------------------
In egs/wsj/s5/local/chain/tuning/run_tdnn_1b.sh
<#1547 (comment)>:
> + utils/create_split_dir.pl \
+ /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-$(date +'%m_%d_%H_%M')/s5/$dir/egs/storage $dir/egs/storage
+ fi
+
+ steps/nnet3/chain/train.py --stage=$train_stage \
+ --cmd="$decode_cmd" \
+ --feat.online-ivector-dir=$train_ivector_dir \
+ --feat.cmvn-opts="--norm-means=false --norm-vars=false" \
+ --chain.xent-regularize $xent_regularize \
+ --chain.leaky-hmm-coefficient=0.1 \
+ --chain.l2-regularize=0.00005 \
+ --chain.apply-deriv-weights=false \
+ --chain.lm-opts="--num-extra-lm-states=2000" \
+ --trainer.srand=$srand \
+ --trainer.max-param-change=2.0 \
+ --trainer.num-epochs=4 \
@danpovey <https://github.com/danpovey> I find here you use 4 epochs for
WSJ, should I try 4 or 7 epochs or both.. on AMI ?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#1547 (review)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ADJVu-VifIP9IwxiDYiEsLQM0Ib3iSfOks5r7gsggaJpZM4M-P83>
.
|
* [scripts] nnet1: minor update i-vector and mpe scripts (#1607) - mpe: backward compatibility is provided - ivec: the ivectors get stored in binary format (saves space) * [src] cosmetic change to const-arpa-lm-building code; remove too-general template. (#1610) * [src,scripts,egs] Segmenting long erroneous recordings (#1167) This is a solution for creating ASR training data from long recordings with transcription but without segmentation information. * [egs] thchs30 cmd and stage bug fix (#1619) * [src] Change to GPU synchronization, for speed (disables GPU stats by default) (#1617) * [src] Fix template instantiation bug causing failure if DOUBLEPRECISION=1 * [egs,scripts] Updates to BUT-specific cmd.sh settings (affects only Brno team); changes RE verbose level in nnet1 scripts. * [src] fix a small bug: logging cuda elapsed time (#1623) * [src,scripts,egs] Add capability for multilingual training with nnet3; babel_multilang example. * [scripts] Fix some merge problems I noticed on github review. * [src] fix problem in test code. * fixed some issues to merge kaldi_52 into master. * removed add_lda parameter and its dependency.
This PR merges recent changes from master.
Contributor
Author
|
I am planning to merge this today, so officially master will point to kaldi 5.2 and this will be revision 5.2.0. I'll wait for the checks to finish. |
Skaiste
pushed a commit
to Skaiste/idlak
that referenced
this pull request
Sep 26, 2018
This makes kaldi 5.2 the current main-line version.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
13 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.
I'll make the home of this in the official Kaldi repo, as I'll be asking people to make PRs to it.