GitLab

trunk: nnet2 setup: Code and script changes to support dumping multi-frame egs to disk.  See get_egs2.sh, train_pnorm_simple2.sh, etc.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4614 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: committing changes to support 'perturbed' training (see train-nnet-perturbed.h).  This seems to only be subsantially helpful for small datasets like RM, and I may remove it in future.  Also adding a script that could be helpful for data cleanup, find_bad_utts.sh; this detects utterances where the transcript might not match with the audio.  Plus misc small fixes.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4241 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: documentation improvements; add program that was missing from repo (est-pca); some updates to nnet2 recipes to use new, faster versions of the training scripts

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4089 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: modifying recipes for neural net training with the new online preconditioning; adding/modifying example scripts for RM and Fisher; various cosmetic code changes.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4088 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

Trunk: minor script fixes; changing configuration of GPU queue to match new CLSP setup; for raw-fMLLR recipe on RM, reduce splice width from 7 to 5

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3765 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3357 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/dan2@3271 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/dan2@3269 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/dan2@3266 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/dan2@3134 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

sandbox/dan2: merging trunk changes, a couple of bug-fixes for new neural-net training setup (RE grabbing GPUs), and adding a new example script in RM setup

git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/dan2@3132 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8