All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
Versions of Kaldi

Versioning scheme

During its lifetime, Kaldi has has three different versioning methods. Originally Kaldi was a subversion (svn)-based project, and was hosted on Sourceforge. Then Kaldi was moved to github, and for some time the only version-number available was the git hash of the commit.

In January 2017 we introduced a version number scheme. The first version of Kaldi was 5.0.0, in recognition of the fact that the project had already existed for quite a long time. The basic scheme is major/minor/patch, but the "patch" version number may also encompass features (usually back-compatible ones). The "patch number" automatically increases whenever a commit to Kaldi is merged on github.

We only intend to change the major or minor version number when making relatively larger changes, or non-back compatible changes.

We always plan to recommend that Kaldi users check out the latest version of 'master', since actively supporting multiple versions would increase our workload.

Versions (and changes)

This section lists the version numbers of Kaldi with the commit messages for each patch commit (by "patch commit" we mean a commit that does not increase the major or minor version number). Each time we add a new major/minor version number we will include a longer section explaining the changes involved.

Version 5.0

This is the first major/minor version number after introducing the versioning scheme. The latest revision of version 5.0 is saved as branch "5.0" on github.

Below are patches corresponding to minor version numbers 5.0.x.

5.0.0 c160a98 2017-01-05 [build] Adding versioning mechanism to Kaldi. This is version 5.0.0 (#1306)

5.0.1 53e33dc 2017-01-06 [scripts] nnet3 scripts: minor bug fixes in error-handling code (#1321)

5.0.2 f15be63 2017-01-06 [scripts] minor updates of scripts in nnet1 (#1318)

5.0.3 735b2b1 2017-01-06 [egs] minor fix in fisher_swbd/s5/local/chain/run_blstm_6h.sh (#1320)

5.0.4 a4b2091 2017-01-07 added reverberation based augmentation recipe for TDNN+LSTM model on AMI; a fix to aspire recipe (#1314)

5.0.5 5cdbd18 2017-01-07 [build] Makefile changes: print time for tests; dash-compatibility change (#1322)

5.0.6 e09e92f 2017-01-08 [egs] minor fixes for mandarin recipes (#1325)

5.0.7 722df9a 2017-01-09 [build] Fix dash problems [set shell to /bin/bash in Makefile]

5.0.8 f646952 2017-01-09 [build] src/base/get_version.sh: change regexp syntax to support older bash versions. (#1327)

5.0.9 5f15d25 2017-01-10 [egs] cosmetic; small typo fix in sre08 i-vector DNN extraction (#1330)

5.0.10 69b616d 2017-01-10 [src,egs,scripts] Remove sinusoid detection code and old SGMM code/scripts (#1329)

5.0.11 cd06802 2017-01-10 [src] nnet3: fixed bug (LstmNonlinearityComponent::ZeroStats() was not implemented) (#1302)

5.0.12 748a4a9 2017-01-11 [src] Restore init-ubm.cc to sgmm2bin (was deleted when sgmmbin deleted)

5.0.13 95f0fec 2017-01-11 [src] nnet1: replacing 'bc' by 'awk' in steps/nnet/train_scheduler.sh (#1333)

5.0.14 728b303 2017-01-11 [scrips] fix bug in lmrescore_rnnlm_lat.sh when using G.carpa (#1334)

5.0.15 42291a6 2017-01-12 [doc,egs] Fix path from lm to lmbin in kaldi for dummies and various egs/*/*/path.sh

5.0.16 421485e 2017-01-12 [src] nnet3: Remove deprecated options which are no longer used (#1335)

5.0.17 847035e 2017-01-13 [egs] Remove some unused scripts

5.0.18 ea25438 2017-01-13 [build] Fix return code of tools/extras/install_sacc.sh (#1337)

5.0.19 e1e7bbf 2017-01-13 [scripts] nnet3: fix to xconfig parsing to enable e.g. "input@-1" in xconfig descriptors (#1338)

5.0.20 1dabfa5 2017-01-14 [src] cosmetic changes to rnnlm-related code (#1283)

5.0.21 4d2c78e 2017-01-16 Some bug fixes to I/O code for nnet3

5.0.22 6c0a012 2017-01-16 Remove checking code which would fail if code updated in middle of training run.

5.0.23 f7b2fe7 2017-01-16 Bug fix (resolve failing test)

5.0.24 390aff4 2017-01-18 [egs] Fix typo in egs/csj/s5/local/csj_run_rnnlm.sh (#1351)

5.0.25 e8e5928 2017-01-19 [src] cudamatrix: added {Cu,}VectorBase::SetRandUniform(), + optimize/fix cu-rand code (#1352)

5.0.26 d117c95 2017-01-20 [src] Some style-related fixes (and fix compiler warnings) in src/lm/

5.0.27 b9c1e8b 2017-01-20 [src] Modify some tests that were slow on travis, to make them faster. (#1347)

5.0.28 df730e8 2017-01-21 [src] Implement CuMatrixBase<Real>::CopyColsFromVec() (#1361)

5.0.29 0440417 2017-01-23 [src,scripts]: Adding dropout schedule option to nnet3 (#1248)

5.0.30 61510ca 2017-01-22 nnet3/report : Modified directory specification options in generate_plots.py (#1368)

5.0.31 4507183 2017-01-24 [build] fixing patch for OpenFst's compat.h for Windows build (#1373)

5.0.32 99b7d96 2017-01-24 [scripts] lexicon learning: update missing defaults and help message; other fixes (#1360)

5.0.33 5c205ea 2017-01-24 [scripts] nnet3/report : Added support for parsing latest compute_{train,valid}*.log (#1371)

5.0.34 f42b3ce 2017-01-24 [scripts] nnet1,make_denlats: prevent crash when utt-ids contain slashes (#1374)

5.0.35 82167f9 2017-01-24 [scripts] remove import statement that was creating problems in nnet3 scripts.

5.0.36 9208165 2017-01-25 [src] nnet3: Add the "per-frame" option to DropoutComponent (#1324)

5.0.37 e227eda 2017-01-25 [doc] Documentation changes; add scripts to automatically add documentation of patch versions.

5.0.38 0c1517c 2017-01-25 [egs] swbd/s5c, chain recipes: fix hardcoded directory name (#1377)

5.0.39 c96a0aa 2017-01-26 [build]: use BSD-compatible mktemp in get_version*.sh; thanks; @andrely.

5.0.40 6ec2eb0 2017-01-26 [build]: fix to previous commit regarding usage of mktemp.

5.0.41 3b7fd1f 2017-01-26 [scripts] Set path in utils/ssh.pl just like in slurm.pl or queue.pl to avoid path problems (#1379)

5.0.42 193bb92 2017-01-26 [build]: minor bug fix in maintenance/documentation script.

5.0.43 5af1983 2017-01-27 [scripts] Fix nnet3 training scripts for bug introduced in #1371

5.0.44 2f8c33d 2017-01-27 [scripts,egs] make steps/dict/learn_lexicon.sh more robust RE empty g2p prons (#1378)

5.0.45 9d53e05 2017-01-29 [scripts] nnet3 training: fix for bug introduced when dropout scripting support was merged.

5.0.46 da59179 2017-01-30 [scripts] steps/dict/learn_lexicon.sh: minor fixes (#1385)

5.0.47 01d96bf 2017-02-01 [scripts] Fix bug in dropout code found by Tanel Alumae

5.0.48 67cabd0 2017-02-01 [build]: resolving OpenFst compilation issue with gcc-6.x (#1392)

5.0.49 f1d7891 2017-02-01 [egs] Add new graphemic system for Gale Arabic, with newer nnet scripts (#1298)

5.0.50 21cfe99 2017-02-02 [build] Windows build: generate missing base/version.h; cosmetic changes (#1397)

5.0.51 cd97bd2 2017-02-02 [build]: Enable cross compilation, including to android. (#726)

5.0.52 c747ed5 2017-02-06 [build] fixing issue introduced in the previous win commit (#1399)

5.0.53 21c8031 2017-02-07 [egs] Fix to HKUST nnet2/3 scripts. (#1401)

5.0.54 dc454cc 2017-02-08 [egs,scripts,src] Add BABEL s5d recipe; various associated fixes (#1356)

5.0.55 9a1244f 2017-02-08 [egs] removing empty files in BABEL recipe (#1406)

5.0.56 2fd8da9 2017-02-09 [scripts] Give prepare_lang the option to generate more phone disambig symbols (#1408)

5.0.57 bcc71b6 2017-02-09 [egs] sprakbanken recipe: add nnet3 examples.

5.0.58 bd73932 2017-02-10 [src] Get rid of clang 3.9 warnings in table-reading code (#1414)

5.0.59 cc1d677 2017-02-10 [egs] egs/fisher_swbd/s5/local/online/run_nnet2_ms.sh, change default stage to 0 (#1416)

5.0.60 9226202 2017-02-11 [egs] Add example scripts for Frisian-Dutch language (FAME! corpus)

5.0.61 37b5352 2017-02-11 [src,doc] Documentation updates; fixes to comments.

5.0.62 68cee21 2017-02-17 [src] Make various tests faster, especially without GPU (#1428)

Version 5.1

Some of the major changes introduced in version 5.1 are:

  • Kaldi now requires C++11 to compile, and we support only the latest version of OpenFst (1.6.0). (This simplifies Kaldi's code, and will later enable the threading code to be rewritten to use C++11's better and more portable mechanisms).
  • The way chunk size and feature context is handled in nnet3 is changed to allow variable chunk size and shorter context at utterance boundaries. See Context and chunk-size in the "nnet3" setup for more information.
  • A new decoding mechanism, Looped decoding, is introduced in nnet3; this allows faster and more-easily-online decoding for recurrent setups (but only unidirectionally-recurrent ones, like LSTMs but not BLSTMs).
  • Online decoding with nnet3 models is now rewritten; it's faster and it supports models like LSTMs.
  • The sequence-training scripts in nnet3 are refactored and are now simpler and use less disk space.
  • There are scripts for segmentation of long transcribed audio files.

The latest revision of version 5.1 is saved as branch "5.1" on github.

Below are patches corresponding to minor version numbers 5.1.x.

5.1.0 68cee21 2017-02-17 [src] Make various tests faster, especially without GPU (#1428)

5.1.1 2145519 2017-02-17 [build] Updating version file-- this commit marks version 5.1.0

5.1.2 9b9b561 2017-02-17 Kaldi 5.1.0 (#1342)

5.1.3 6477dec 2017-02-17 [build] Change travis build to use clang; remove -rdynamic from CXXFLAGS (it's in LDFLAGS)

5.1.4 23338bf 2017-02-19 [scripts] fix syntax error in validate_lang.pl [thanks: daniel galvez]

5.1.5 7d538e2 2017-02-19 [build] Increase OpenFst version 1.6.0->1.6.1. (#1434)

5.1.6 8458587 2017-02-20 [build] Use github not sourceforge for IRSTLM [sourceforge repo dead?] (#1435)

5.1.7 d218412 2017-02-20 [egs] clean up the HKUST scripts and add scoring filters (#1436)

5.1.8 7b862c7 2017-02-20 [src,doc] Update version documentation with version 5.1; makefile fix; add details to info string for nnet3 component.

5.1.9 483192e 2017-02-20 [build] update .gitignore: ignore openfst-1.6.1 (#1439)

5.1.10 8c77d2c 2017-02-21 [src,egs,scripts] Support frame-subsampling with non-chain nnet3 models (#1238)

5.1.11 2c3df88 2017-02-21 [build] cloning IRSTLM, use https to access github, not ssh (#1441)

5.1.12 9866a4c 2017-02-22 [build] Update Travis configuration to get builds to complete on time. (#1443)

5.1.13 351da28 2017-02-22 [egs] Iban recipe: MacOSX compatibility fixes (#1448)

5.1.14 ae4a5ef 2017-02-23 [scripts] Make it so i-vector ID is not required for steps/nnet3/decode.sh

5.1.15 70f5360 2017-02-23 [build] Stop env.sh from crashing when set -u is active (#1451)

5.1.16 dff2a3f 2017-02-24 upgrade the sox calls to use more compatible options (#1453)

5.1.17 37bebd1 2017-02-25 [egs] fix typo in egs/swbd/s5c/local/nnet3/run_ivector_common.sh (#1452)

5.1.18 4cda604 2017-02-25 [scripts] xconfig: make scripts work when LDA-like preconditioning layer is not used (#1447)

5.1.19 089e596 2017-02-25 [build] Update OpenFst minimum version check to 1.6 in tools/Makefile. (#1455)

5.1.20 344e1ad 2017-02-25 [src] Fix bug in decodable-online-looped.cc (prevent crash in nnet3 online decoding).

5.1.21 25b1299 2017-02-25 [egs] fix MacOSX incompatibilities in calls of paste (#1457)

5.1.22 d60e3cc 2017-02-27 [egs,scripts] Misc script fixes; refactor wsj/s5 examples; update tedlium/s5_r2 (#1456)

5.1.23 3f18012 2017-02-27 [scripts,egs] Replace SGE-specific options to queue.pl (etc.) with generic options (#1461)

5.1.24 1db4bba 2017-02-27 [scripts] Fix to nnet2 script (won't change results) (#1462)

5.1.25 ee45757 2017-02-28 [scripts] nnet3: remove import from tdnn in the xconfig script since it no longer exists (#1464)

5.1.26 0c4441e 2017-02-28 [egs] Add online-decoding example in some Swbd chain scripts (#1466)

5.1.27 4a58ab9 2017-02-28 [scripts] fix_data_dir.sh, prevent function returning false in case reco2file_and_channel does not exist (#1467)

5.1.28 f6b011f 2017-03-01 [src] kwsbin/transcripts-to-fsts.cc, fix bug introduced in the last babel recipe commit (#1470)

5.1.29 d5a9d5c 2017-03-02 [src] add CUDA kernel for backprop of NormalizeLayer (#1458)

5.1.30 ba77d97 2017-03-03 [src] fix kws pipeline after upgrading to openfst-1.6 (#1471)

5.1.31 828f0b9 2017-03-03 [egs] Add discriminative training script for WSJ/TDNN-LSTM (#1468)

5.1.32 5bad9b2 2017-03-06 [src] bug-fix in gst plugin code (issue on g++ 5.4.0) (#1479)

5.1.33 34128c5 2017-03-06 [scripts,egs] sMBR on LFR xent system with shifted feats (#1477)

5.1.34 5bfa9e5 2017-03-08 [egs] Minor cosmetic changes in voxforge example script (#1483)

5.1.35 bd23a10 2017-03-10 [egs] Fixes to URLs in vystadial example script.

5.1.36 1a4dbf6 2017-03-13 [src] nnet1: fixing issue in multi-task training (#1491)

5.1.37 eba49a0 2017-03-14 [build] Bump OpenFst version to v1.6.2 (#1492)

5.1.38 5c98096 2017-03-16 [egs] swbd/chain : added blstm script using fast-LSTM; added BLSTM+TDNN script. (#1497)

5.1.39 3fec956 2017-03-17 [egs] update fisher_swbd recipe (fixes to how things are installed). (#1498)

5.1.40 eac0baa 2017-03-19 [src] sort cuda kernel function declarations to make searching easier. (#1501)

5.1.41 25ca8e4 2017-03-19 [build] Android compilation, bug-fixes (#1502)

5.1.42 ed33b1f 2017-03-19 [doc] Add a note to README.md about Android cross compilation (#1503)

5.1.43 965cc49 2017-03-20 [egs] ami : Added tdnn_lstm recipe with fast-lstmp layer. Added tdnn_lstm recipe with -1 delay at lowest lstm layer (#1505)

5.1.44 39ad410 2017-03-22 [scripts] prevent failure when final.ie.id doesn't exist (#1508)

5.1.45 ef415a7 2017-03-22 [src] Fix exit code of extract-rows.cc (#1510)

5.1.46 9a6feea 2017-03-23 [egs] fixes to babel pipeline; thanks to Fred Richardson (#1509)

5.1.47 0d0316b 2017-03-23 [src,scripts]: Several unrelated cosmetic changes

5.1.48 24bc222 2017-03-27 [misc] remove eXecute permissions where not needed (#1515)

5.1.49 244251f 2017-03-28 [egs] Fix to egs/wsj/s5/run.sh (unset variable) (#1517)

5.1.50 8b458ae 2017-03-29 [src] Adding noexcept to hashing function objects (#1519)

5.1.51 13d300f 2017-03-29 [src,doc] Fix several unrelated minor problems. Thanks: gaoxinglong

5.1.52 e9d7993 2017-03-31 [src] (minor) Added missing SetZero() to NaturalGradientAffineComponent::Scale() if scale==0.0 (#1522)

5.1.53 e8ca375 2017-04-01 [scripts,egs] Adding options for using PCA instead of LDA+MLLT for ivectors used in ASR. Results are reported in the default TDNN recipe in AMI. Updating steps/online/nnet2/{train_diag_ubm.sh,train_ivector_extractor.sh} so that they now backup the contents of their destination directory if it already exists. (#1514)

5.1.54 60f9327 2017-04-02 [build,src,doc] Modify get_version.sh to deal better with whitespace (avoid space in version); minor fixes (#1526)

5.1.55 3c94401 2017-04-04 [build]: remove openfst check (#1531)

5.1.56 d8b34d4 2017-04-04 [src] cudamatrix: speed up AddColSumMat with transfrom reduce kernel template (#1530)

5.1.57 e5b1419 2017-04-04 [src] Cosmetic change: remove 'train.tra' from usage messages (#1529)

5.1.58 0157686 2017-04-05 [src] nnet1: improving the GPU diagnostics, (#1532)

5.1.59 d9efe6e 2017-04-11 [src] Fix copy-feats for using the --write-num-frames and --compress true flags at the same time (#1541)

5.1.60 5b70933 2017-04-12 [scripts] fix to get_egs_targets.sh (thanks: David Pye)

5.1.61 b2d5d36 2017-04-12 [scripts] nnet3 : fix issue where LDA estimation failed for LSTMs with label delay (#1540)

5.1.62 31a528b 2017-04-13 [src] Change ConvertStringToReal to be locale-independent (i.e. always-US). Fixes android issue. (#1513)

5.1.63 7fcc311 2017-04-13 [egs,scripts,src] SID and LID tools and scripts: cosmetic improvements, better error-handling, and various minor fixes; results unchanged. (#1543)

5.1.64 179d9b6 2017-04-14 [src] add template instantiations for ConvertStringToReal, address issue #1544

5.1.65 8891750 2017-04-14 [egs] AMI TDNN Results Update (#1545)

5.1.66 9e06caa 2017-04-15 [srcipts] steps/nnet3/report/generate_plots.py: plot 5,50,95th percentile of value and derivative instead of mean+-stddev (#1472)

5.1.67 81346fc 2017-04-16 Update travis.yml so PRs to kaldi_52 are built

5.1.68 46f3285 2017-04-19 [egs] Added check for kaldi_lm being installed in fisher_swbd recipe. (#1558)

5.1.69 7223462 2017-04-20 [doc] Small edit to hmm.dox, clarifying something

5.1.70 d82bbd7 2017-04-20 [src] nnet3 online silence weighting - adding frame subsampling factor (#1559)

5.1.71 d8be99a 2017-04-20 [src,scripts,egs] Add dropout for nnet3 LSTMs, with recipes. (#1537)

5.1.72 015c96f 2017-04-20 [src] Add documentation for dropout function.

5.1.73 73489ae 2017-04-21 [src] Fix to testing code signal-test.cc, change threshold to resolve failure (#1565)

5.1.74 87d95c5 2017-04-21 [egs] Add mini-librispeech example scripts [intended as a sanity-checker/tutorial setup] (#1566)

5.1.75 c68a576 2017-04-21 [egs] adding results and cleanup in mini-librispeech

5.1.76 1f51ef5 2017-04-23 [egs] Add soft link for mini-librispeech setup

5.1.77 06047be 2017-04-25 [src] Minor bug-fixes in compute-wer-bootci and WSJ run.sh. Thanks: @osadjadi

5.1.78 8b9e874 2017-04-25 [egs] bug-fix in egs/ami/s5/run_ihm.sh (#1577)

5.1.79 a39e580 2017-04-28 [build] Remove warning about dash (I believe we have no problem with it now)

5.1.80 fc20b76 2017-05-01 [egs] fix small bug in wsj run.sh [thanks: Hang Lv]

5.1.81 e527572 2017-05-01 [sripts] extract_ivectors.sh: cosmetic fix, correct example usage. (#1600)

5.1.82 1cd6d2a 2017-05-02 [egs] mini-librispeech: download data from openslr if it's not present (#1598)

5.1.83 3906ae9 2017-05-04 [src] bug-fix for memory bug in nnet computation cache code

5.1.84 ba13848 2017-05-04 [src] Fix bug that can cause crash for for kernel-sizes=n*65536.

5.1.85 ad6491a 2017-05-05 [src] Add --write-per-frame-acoustic-loglikes options to alignment programs (#1601)

5.1.86 7c04d62 2017-05-06 [scripts] nnet1: minor update i-vector and mpe scripts (#1607)

5.1.87 578c176 2017-05-07 [src] cosmetic change to const-arpa-lm-building code; remove too-general template. (#1610)

5.1.88 6eebc04 2017-05-09 [src,scripts,egs] Segmenting long erroneous recordings (#1167)

5.1.89 ab5c96c 2017-05-11 [egs] thchs30 cmd and stage bug fix (#1619)

5.1.90 b1e8601 2017-05-13 [src] Change to GPU synchronization, for speed (disables GPU stats by default) (#1617)

5.1.91 8cbb74c 2017-05-13 [src] Fix template instantiation bug causing failure if DOUBLEPRECISION=1

5.1.92 6666682 2017-05-15 [egs,scripts] Updates to BUT-specific cmd.sh settings (affects only Brno team); changes RE verbose level in nnet1 scripts.

5.1.93 a7e6183 2017-05-15 [src] fix a small bug: logging cuda elapsed time (#1623)

5.1.94 7af2128 2017-05-17 [src,scripts,egs] Add capability for multilingual training with nnet3; babel_multilang example.

5.1.95 9638950 2017-05-18 [doc] small fix RE queue configuration.

5.1.96 ae45ee2 2017-05-19 [scripts] Fix to long-utterance segmentation script (#1631)

5.1.97 45ee31f 2017-05-20 [src] Make parsing error-msg more informative (thanks: Stefan-Adrian Toma)

5.1.98 b13f56b 2017-05-21 [src] fix regarding first/last chunk's right-context in chain models (#1632)

5.1.99 86766bd 2017-05-21 [scripts, egs]: fix to egs/lre07/v2 (test was trained on); other updates to LRE scripts.

5.1.100 dc32e0b 2017-05-22 [scripts] Fix steps/cleanup/make_biased_lm_graphs.sh to actually add the top-n-words into the lms (#1637)

5.1.101 d6cf1bd 2017-05-23 [scripts,egs] Fixes to long-recording segmentation (#1639)

5.1.102 b5eac09 2017-05-24 [scripts] fix bugs in align_basis_fmllr.sh [thanks: Filip Jurcicek]

5.1.103 0f5e16e 2017-05-25 [build] Check python version is 2.7*, not just 2.*.

5.1.104 31683a3 2017-05-25 [build] Change check_dependencies.sh to not look for yum if apt-get present.

5.1.105 6739d60 2017-05-25 [scripts] Make more informative error in validate_lang.pl when path.sh prints something

5.1.106 6cc8e3a 2017-05-26 [src] Use STL thread support library instead of pthread. (#1350)

5.1.107 c210b44 2017-05-26 [scripts] Fix bugs in automatic report generation for nnet3 training

5.1.108 76c8c77 2017-05-26 [egs] Ported Fisher spanish recipe to use new LDC dir structure. Other small fixes (#1647)

5.1.109 6b906a3 2017-05-26 [egs] updated the LDC web address for wsj0-train-spkrinfo.txt (#1648)

5.1.110 0b0dbb0 2017-05-26 [scripts,egs] minor script fix; fixes in various recipes (#1649)

5.1.111 b6c34db 2017-05-26 [scripts] Lexicon expansion script -- fix for LM-probs, make it work for non-ASCII langs or langs w. large grapheme set (#1650)

5.1.112 e9646f0 2017-05-26 [src] keyword search: fix invalid assumption about the end states (#1651)

5.1.113 93c069c 2017-05-27 [src] Fix bug in newly refactored threading code

5.1.114 7267281 2017-05-27 [scripts] Getting egs, limit max open filehandles to 512 (thanks: gaoxinglong9999)

Version 5.2

Some of the changes introduced between 5.1 and 5.2 are:

  • Upgrades to nnet3 to support batch-norm and convolutional components; recipes for certain image tasks (like CIFAR).
  • nnet3 training script simplifications and refactoring.
  • Some of the recipes are upgraded to include dropout and the –proportional-shrink option (which approximates l2 regularization); this improves results.

Many changes were made in the commits listed below (i.e. in the minor versions 5.2.x), including:

The latest revision of version 5.2 is saved as branch "5.2" on github.

Below are patches corresponding to minor version numbers 5.1.x.

5.2.0 7267281 2017-05-27 [scripts] Getting egs, limit max open filehandles to 512 (thanks: gaoxinglong9999)

5.2.1 393ef73 2017-05-29 [build] Upgrade .version (this is official start of kaldi 5.2)

5.2.2 cb7d176 2017-05-29 Merge pull request #1547 from kaldi-asr/kaldi_52

5.2.3 a57eab6 2017-05-29 [scripts] Fix bug in PR #1646 (#1658)

5.2.4 972efd7 2017-05-31 [scripts] nnet3 script cleanups; add --proportional-shrink in more places. (#1659)

5.2.5 3e57783 2017-05-31 [src] minor bugfix in convolutional component (doesn't affect experiments)

5.2.6 44cd386 2017-05-31 [build,scripts] Update scripts that make version info; remove no-op option from script.

5.2.7 fa198bb 2017-06-01 [scripts] do not fail if the ivector extractor belongs to different user (#1662)

5.2.8 bd5fd04 2017-06-01 [src] keyword search tools: fix Minimize() call, necessary due to OpenFst upgrade (#1663)

5.2.9 ada5c0d 2017-06-01 [src,scripts] Use ConstFst or decoding (half the memory; slightly faster). (#1661)

5.2.10 cdb25d1 2017-06-02 [scripts] make errors getting report non-fatal (thx: Miguel Jette); add comment RE dropout proportion

5.2.11 7728a10 2017-06-02 [src] Fix bug in online2-nnet3 decoding RE dropout+batch-norm (thanks: Wonkyum Lee)

5.2.12 6fe140a 2017-06-02 [src] Add #include missing from previous commit

5.2.13 1307803 2017-06-07 [src] nnet3: fix small bug in checking code. Thanks: @maddin2000.

5.2.14 bf6ad54 2017-06-07 [doc] Fix typo (#1669)

5.2.15 a0795ec 2017-06-07 [scripts] Add python script to convert nnet2 to nnet3 models (#1611)

5.2.16 712c234 2017-06-08 [scripts] Fix small bug in utils/gen_topo.pl.

5.2.17 5f68038 2017-06-08 [build] Fix small bug in configure

5.2.18 c4dd63a 2017-06-08 [egs] Fix to some --proportional-shrink related example scripts (#1674)

5.2.19 7fa5f81 2017-06-10 [src] Cosmetic fixes to usage messages

5.2.20 468c619 2017-06-13 [src] fix to gst-plugin/Makefile (remove -lkaldi-thread) (#1680)

5.2.21 defc8bd 2017-06-13 [build] when installing sequitur and mmseg, look for lib64 as well (thanks: @akshayc11) (#1677)

5.2.22 594daac 2017-06-13 [src] Fix bug in looped computation (#1673)

5.2.23 d46890d 2017-06-13 [egs,scripts,src] Tune image recognition examples; minor small changes. (#1682)

5.2.24 08dbc18 2017-06-14 [egs] CNN+TDNN+LSTM experiments on AMI (#1685)

5.2.25 ecc6a78 2017-06-14 [src,scripts,egs] Backstitch code+scripts, and one experiment, will add more later. (#1605)

5.2.26 9d494d2 2017-06-14 [egs] Fix failure in multilingual BABEL recipe (regenerate cmvn.scp) (#1686)

5.2.27 4d7ec01 2017-06-15 [src] Fix to multiple-fst case of latgen-faster-mapped-parallel (memory bug) (#1688)

5.2.28 16b9918 2017-06-16 [egs] Rename files with Windows-incompatible names (#1690)

5.2.29 d76f088 2017-06-16 [src] nnet3 model-collapsing code, for slight decoding speedup (#1671)

5.2.30 20fe876 2017-06-19 [egs] babel recipe: check if icu4c is installed (#1697)

5.2.31 f7898b4 2017-06-20 [scripts] in subsegment_data_dir.sh, warn if utt2num_frames missing, etc. (#1702)

5.2.32 0a37d3e 2017-06-20 [src] Adding options to MBR/confidence code (#1696)

5.2.33 6a0768a 2017-06-20 [src] Fix compiler warnings and work around bug on Windows (#1698)

5.2.34 2ef9f91 2017-06-21 [src] nnet3: fix assertion that shouldn't have been there. Thanks: @vimalmanohar

5.2.35 76c31c2 2017-06-21 [egs] fix problems in multilingual BABEL setup (#1691)

5.2.36 1022e9b 2017-06-22 [src] Fix bug in fstrmymbols RE recent const-fst changes (thanks: Jon Nichols); other cosmetic changes.

5.2.37 98d2fc7 2017-06-22 [egs] small update to librispeech recipe, RE const-FST.

5.2.38 a4578c4 2017-06-22 [egs] Adding hub4-ne broadcast spanish recipe (#1665)

5.2.39 b82b82f 2017-06-23 [build] Update README.md / fix ci badge (#1709)

5.2.40 acb5439 2017-06-24 [egs,scripts]: replace non-portable read-link -f with utils/make_absolute.sh (#1694)

5.2.41 a75fb1b 2017-06-26 [build] IRSTLM build: resolve problems with compilers by patching configure.ac (#1713)

5.2.42 456fec6 2017-06-27 [egs] improve TDNN model in tedlium example (fewer jobs, proportinal-shrink 20) (#1715)

5.2.43 0d62760 2017-06-27 [build] update tools/extras/install_speex.sh to address #1718 (#1719)

5.2.44 6ae3111 2017-06-27 [scripts] Quote '{' in perl regexp (#1721)

5.2.45 913211d 2017-06-27 [scripts] Remove bogus note on CUDA non-use from compute_average_posterior() (#1722)

5.2.46 c12c1b8 2017-06-27 [scripts] run.pl: Default concurrent jobs to number of GPUs (#1723)

5.2.47 2d011df 2017-06-28 [src] Fix for threaded nnet2 decoding: check if threads are joinable before calling join(), to avoid multiple calls to join() (#1725)

5.2.48 f6f784b 2017-06-28 [src] Fix bug in lattice string-pushing, affecting lattice-push (#1724)

5.2.49 3505e86 2017-06-28 [scripts,egs] simplify nnet3 scripts by removing unused feature types (LDA, delta); add sMBR recipe for mini-librispeech (#1711)

5.2.50 16f39de 2017-06-29 [scripts] bug-fix in nnet3 scripts: change type of max_lda_jobs to int (#1728)

5.2.51 29c8110 2017-06-30 [src] Bug-fix in model-collapsing code (thanks: aarora8)

5.2.52 2a07818 2017-07-03 [src] Make sure softmax-related functions can work in-place. (#1729)

5.2.53 cac072d 2017-07-03 [egs] Add updated TDNN+BLSTM scripts for swbd/s5c, with dropout etc. (#1730)

5.2.54 abf898f 2017-07-06 [src] remove remap-leaves.h (thanks: @kkm000)

5.2.55 28c6139 2017-07-07 [egs] APIAI example: model downloads links changed (#1747)

5.2.56 39c6dde 2017-07-08 [egs] Update Librispeech nnet3 TDNN recipe (old one did not run) (#1727)

5.2.57 12ad1f6 2017-07-09 [build] Add configuration check for incompatible g++ compilers when CUDA is enabled. (#1749)

5.2.58 97922a8 2017-07-09 [egs] Small fix to ami/s5b/local/chain/compare_wer_general.sh (#1751)

5.2.59 1644b5b 2017-07-11 [egs] some small updates to scripts (installing beamformit; segmentation example)

5.2.60 113e2a7 2017-07-11 [src] Fix usage message of program (thanks:jubang0219@gmail.com)

5.2.61 6aa5ed1 2017-07-11 [src] Fix indexing error in nnet1::Convolutional2DComponent (#1755)

5.2.62 b813b9d 2017-07-11 [scripts] Fix bug in segment_long_utterances.sh (#1758)

5.2.63 a234281 2017-07-11 [egs] swbd/s5c, added 5 layer (b)lstm recipes (#1759)

5.2.64 40620fc 2017-07-14 [src] Change name of option --norm-mean->--norm-means for consistency, thanks: 415198468@qq.com

5.2.65 2fbf2df 2017-07-14 [src] Add support for row/column ranges when reading GeneralMatrix (#1761)

5.2.66 42c0596 2017-07-16 [scripts] minor bugfix to nnet1 alignment script when creating lattices (#1764)

5.2.67 b2fc6c4 2017-07-16 [scripts] For nnet3 training, add option to disable the model-combination (#1757)

5.2.68 6937b98 2017-07-16 [src] Change to arpa-reading code to accept blank lines with whitespace (#1752)

5.2.69 aedc2fe 2017-07-17 [egs] Add recipe for aishell data (free Mandarin corpus, 170 hours total) (#1742)

5.2.70 c794d55 2017-07-19 [egs] Fixes to the aishell (Mandarin) recipe (#1770)

5.2.71 98bbe11 2017-07-19 [egs] Update AMI chain experiments RE dropout, decay-time and proportional-shrink (#1732)

5.2.72 47f8057 2017-07-21 [egs] update hkust results (#1772)

5.2.73 2c51a3f 2017-07-21 [egs] Graphemic lexicon updates / fixes in babel/s5d recipe and hub4_spanish recipe (#1740)

5.2.74 5c3c142 2017-07-23 [egs] Add missing make_corpus_subset.sh in babel_multilang example (#1766)

5.2.75 dbdd284 2017-07-24 [scripts] Fix convert_nnet2_to_nnet3.py (#1774)

5.2.76 1fef989 2017-07-26 [src] make dithering in feature processing more efficient by using random state, thanks: liximin244@gmail.com

5.2.77 d79e1c0 2017-07-26 [scripts] update nnet3 scripts to fix bug where rejecting 'bad' models was not happening (#1777)

5.2.78 caaf6fa 2017-07-31 [tools] adding phonetisaurus install scripts (PR#1734)

5.2.79 af4b687 2017-07-31 [src] Circumvent Visual Studio 2017 bug regarding name resolution (#1783)

5.2.80 ff2ad50 2017-08-02 [egs] update multi_condition script in swbd (#1788)

5.2.81 35faa4d 2017-08-03 [src,egs,scripts] Cosmetic and other minor fixes, some required for segmentation PR (#1784)

5.2.82 c4a7352 2017-08-04 [egs] fix bugs in Multi-database English LVCSR recipe (#1785)

5.2.83 3f61293 2017-08-04 [egs] Update tedlium and aspire recipes to use xconfigs (avoid crash) (#1790)

5.2.84 e0a82e4 2017-08-05 [egs] Fix bug RE xent_regularize in Aspire chain recipes. (#1797)

5.2.85 5e91c5d 2017-08-07 [src] Cosmetic fix to usage message (#1800)

5.2.86 53e5e12 2017-08-08 [egs] Add chain recipe for Fisher English (#1803)

5.2.87 4d27deb 2017-08-09 [src] Fix bug in model-update consolidation code (thanks: sriram ganapathy).

5.2.88 4a0106a 2017-08-09 [src] Small test-code fix

5.2.89 cc2469e 2017-08-09 [src] modify feature-extraction binaries to support downsampling (#1773)

5.2.90 c216b54 2017-08-10 [scripts] reverting the recent change of perturb_data_dir_speed_3way.sh (#1809)

5.2.91 1a508c3 2017-08-11 [egs] A fix to swbd1_data_prep.sh to make speaker ids prefixes of the utterances; a change in WSJ script to compute the PCA instead of LDA. (#1810)

5.2.92 8e269d0 2017-08-11 [build,scripts] Fix to fast-lstm xconfig layer which was not functional; cosmetic change to 'configure'.

5.2.93 aaf680e 2017-08-11 [src,scripts,egs,build] Enable RNNLM lattice rescoring with Tensorflow (#1741)

5.2.94 d117a64 2017-08-12 [scripts] Documentation fix in xconfig scripts

5.2.95 511350f 2017-08-14 [scripts] Fix to script usage message (thanks: @yzmyyff)

5.2.96 66bcdce 2017-08-14 [build] fix compilation problem of tfrnnlm and tfrnnlmbin (#1822)

5.2.97 12fa929 2017-08-14 [scripts,src] Check that symbol '#0' is not in the vocab of the ARPA LM file or the lexicon [thanks: nitzan@almagu.com] (#1806)

5.2.98 5846a2d 2017-08-15 [src] Inconsequential bug-fixes to problems found when compiling with -DKALDI_PARANOID

5.2.99 eaebe08 2017-08-15 [build] Enable Travis cache for faster Travis builds, avoiding timeouts (#1819)

5.2.100 6c6d1dd 2017-08-17 [build] Change to compilation flags for Sequitur on Mac (#1716)

5.2.101 87b55e1 2017-08-17 [scripts,egs] fixed issues in multilingual training with --use-ivector option (#1828)

5.2.102 3b185c7 2017-08-17 [build] remove debug print (fixes some of the travis builds failures) (#1827)

5.2.103 4816ee5 2017-08-18 [scripts] fix lmrescore_rnnlm_lat.sh: fstproject doesn't work on const-arpa FST (#1830)

5.2.104 91d47c1 2017-08-20 [doc] Fix typos (#1833)

5.2.105 92dad5b 2017-08-21 [doc] Add some terms to glossary

5.2.106 0e5bb81 2017-08-21 [scripts,egs] Nnet3 segmentation using labels from ASR (#1676)

5.2.107 6d885ee 2017-08-23 [scripts] Adding Swbd speech activity detection scripts missing from #1676 (#1838)

5.2.108 e892805 2017-08-23 [egs] add swbd/s5c/conf/mfcc_hires_bp.conf missing from local/run_asr_segmentation.sh (#1841)

5.2.109 e8636e9 2017-08-24 [src] fix #include directive in compressed-matrix.h, include subfolder. #1842 (#1843)

5.2.110 d234b07 2017-08-24 [egs] Note small bug in AMI run.sh, thanks @akreal

5.2.111 1d13731 2017-08-24 [scripts] fixes to nnet3-based segmentation scripts (#1844)

5.2.112 e5a48fc 2017-08-25 [src] fixed copy-constructor bug RE test_mode option for DropoutComponent (#1845)

5.2.113 ce6b342 2017-08-25 [scripts,src,egs] simplify by removing --leftmost-questions-truncate option (#1840)

5.2.114 09554c6 2017-08-28 [egs] Aspire example scripts: Update autoencoder example to xconfig (#1847)

5.2.115 4af4f36 2017-08-28 [src] Remove repeated parameter documentation. (#1849)

5.2.116 7246f2c 2017-08-29 [scripts] bug-fix in TFRNNLM rescoring script (no 'ark' needed for unk.probs file) (#1851)

5.2.117 bca082e 2017-08-29 [egs] Update to score.sh in fisher_swbd setup, allow --iter option (#1853)

5.2.118 d8e42b0 2017-08-29 [src] Typo fixes in documenation. (#1857)

5.2.119 355f4e1 2017-08-30 [src] Adding documentation for lattice discriminative training functions (#1854)

5.2.120 807dc48 2017-08-30 [scripts] Add --decode-extra-opts in steps/decode.sh (required for speech activity detection scripts) (#1859)

5.2.121 018e79e 2017-08-31 [doc] Fix to how documentation is built (thanks: David van Leeuwen)

5.2.122 683e3b5 2017-09-01 [scripts] Fix default for egs.cmd in nnet3 training scripts (#1865)

5.2.123 8c792f0 2017-09-01 Remove memory leaks and unused variables (when CUDA is not enabled) (#1866)

5.2.124 0a8fdbf 2017-09-05 [build] Cosmetic fix in Makefile

5.2.125 7074830 2017-09-05 [egs] Fixed some issues in the multilingual BABEL example scripts (#1850)

5.2.126 f4a6a66 2017-09-08 [scripts] Bug-fix in long-utterance-segmentation script (thanks: Armin Oliya) (#1877)

5.2.127 134cf7e 2017-09-08 [doc] Keep tutorial code up to date (thanks: Luwei Yang)

5.2.128 26e8b56 2017-09-11 [scripts] A cosmetic change to info messages in chain training (#1880)

5.2.129 8ad898c 2017-09-12 [build] dependency-check: that python2.7 and python3 exist and 2.7 is default (#1876)

5.2.130 ca871fb 2017-09-13 [egs] Fix inconseqential input-checking bug in Swbd example script (#1886)

5.2.131 1771a25 2017-09-15 [src] Fix bug in block matrix addition (thanks: Sidhi Adkoli).

5.2.132 d1016d8 2017-09-15 [src,scripts,egs] Attention modeling, with example scripts (#1731)

5.2.133 82686ee 2017-09-15 [src,scripts,egs] Transfer learning for ASR with nnet3 (#1633)

5.2.134 cddb72c 2017-09-17 [doc] Fix typo in the About page (#1890)

5.2.135 ecd48ca 2017-09-17 [build] Updates related to refactoring of the phonetisaurus build system. (#1891)

5.2.136 633310c 2017-09-22 [src] Fix CU_SAFE_CALL wrapper so it correctly prints CuBLAS error codes (#1900)

5.2.137 13e3a0b 2017-09-22 [src,scripts] Remove some unused code and scripts (#1904)

5.2.138 9a6e1c0 2017-09-22 [egs,scripts] For scoring analysis scripts, guess if it's utf-8 compatible stream or not (#1903)

5.2.139 d4bb00a 2017-09-25 [egs] Speaker recognition scripts for FAME! Speech Corpus (#1897)

5.2.140 69e3c49 2017-09-26 [build] Remove invalid dependency in Makefile (thanks: @qzfnihao)

5.2.141 b5d7d41 2017-09-26 [scripts] small fix for utils/dict_dir_add_pronprobs.sh (#1912)

5.2.142 b0cc157 2017-09-26 [scripts] Change hostname -d to hostname -f for mac compatibility.

5.2.143 906006f 2017-09-27 [scripts] Fixes to data-cleanup scripts (#1902)

5.2.144 ba00b18 2017-09-27 [build] make configure script allow cuda 9.0 (#1916)

5.2.145 6cab750 2017-09-28 Modify data-validation script and dictionary-validation script to disallow exotic space characters (#1910)

5.2.146 fad21ab 2017-09-28 [build] remove obsolete arch from cuda gencode (#1919)

5.2.147 87107ed 2017-10-03 [egs] fix run_ivector_common.sh in some setups to use data/lang not data/lang_nosp (#1921)

5.2.148 f348b26 2017-10-03 [build] Fix TensorFlow installation issues (#1920)

5.2.149 e082c17 2017-10-03 [src,scripts,egs] Xvectors: DNN Embeddings for Speaker Recognition (#1896)

5.2.150 0f2df80 2017-10-04 [egs] Updating WSJ TDNN example to use batchnorm instead of renorm.

5.2.151 9eccdbe 2017-10-09 [src] Some fixes to cu-rand to ensure deterministic behavior. (#1927)

5.2.152 9875769 2017-10-09 [scripts] Minor fix to nnet3 training scripts RE log parsing/time-reporting (#1926)

5.2.153 5fbdc66 2017-10-10 [scripts] Fixing OS X compatibility issue for tabs with sed. (#1928)

5.2.154 971fe62 2017-10-11 [egs] Replace Zenkaku-Space to Zenkaku-Underscore in CSJ recipe (#1931)

5.2.155 8bb27a9 2017-10-11 [src] Loosen a threshold in the derivative test to make it pass (#1936)

5.2.156 7ed7311 2017-10-11 [scripts] Replace sed commands using \t and \n for OS X compatiblity (#1935)

5.2.157 e3f2e0c 2017-10-11 [egs] minor script fix; remove unused variable (#1933)

5.2.158 fe6f86b 2017-10-11 [egs] In csj setup, use KALDI_ROOT instead of ../../.. (#1932)

5.2.159 e3fb7c4 2017-10-11 [egs] Small fixes to egs/sre16/ and egs/bn_music_speech dataprep, link to pretrained models (#1934)

5.2.160 696696b 2017-10-13 [scripts] Fix small script typo (cleanup-related); thanks, @francoishernandez.

5.2.161 510428f 2017-10-13 [egs] Adding new non-splicing layers in some TDNN setups. (#1937)

5.2.162 9e37c51 2017-10-16 [src,egs] Minor tweaks in nnet3 code (diagnostics,testing); add stage option to swbd setup.

5.2.163 63774a5 2017-10-17 [scripts,egs] Use KALDI_ROOT instead of relative path (#1941)

5.2.164 167c2b9 2017-10-17 [doc] Fix path in kaldi for dummies (thanks: Ermand Hoxha)

5.2.165 fa6bee3 2017-10-19 [egs] Librispeech: make sure phone list is sorted, for repeatability (#1946)

5.2.166 20f81b5 2017-10-19 [egs] Adding new non-splicing layers in the AMI TDNN setup (#1947)

5.2.167 c96fb5d 2017-10-19 [scripts] Add new tuning option for speech activity detection (SAD) scripts (#1949)

5.2.168 e4952cf 2017-10-19 [egs] Fixed a missing xconfig change of the tdnn recipe in the previous commit (#1948)

5.2.169 020c500 2017-10-19 [scripts] Simplify and remove non-useful diagnostics in nnet3 training scripts

5.2.170 edb1aae 2017-10-20 [egs,scripts] Disambiguate cmd.sh and path.sh pathnames: add './' (#1953)

5.2.171 3c7f0dd 2017-10-21 [egs] fix to scoring script error in HKUST recipe (#1957)

5.2.172 f89ffeb 2017-10-22 [src,scripts,egs] Make it possible to specify component-level l2 regularization (#1959)

5.2.173 4006d94 2017-10-23 [egs] Updates to Chime4 recipe (#1956)

5.2.174 582993a 2017-10-24 [scripts] Small fix to nnet3 training scripts: pass egs_command to get_egs.sh (#1970)

5.2.175 de24735 2017-10-24 [egs,scripts] Add support for l2-regularize to LSTM layers; give example.

5.2.176 e8e86ae 2017-10-24 [egs] Small egs fixes to HKUST and sre10 (#1958)

5.2.177 d38b5c5 2017-10-25 [egs] Further small HKUST and SRE fixes (#1971)

5.2.178 fb37787 2017-10-25 [build] Make nvcc respect CXX (#1965)

5.2.179 34c3e2c 2017-10-25 [src,scripts] nnet1: various minor changes, (#1962)

5.2.180 41301bd 2017-10-25 [scripts] Fix a bug in attention xconfig regarding key-scale (thanks: Pegah) (#1975)

5.2.181 ddf71be 2017-10-27 [build] Remove download of ATLAS header files from tools/. (#1974)

5.2.182 81bd30a 2017-10-27 [egs] Small fix to Chime4 RE data location (#1966)

5.2.183 9d7247b 2017-10-29 [egs] Add example of component-level l2-regularize for WSJ scripts

5.2.184 3231001 2017-10-29 [src] Minor fix: change to error message (#1980)

5.2.185 13333d1 2017-11-01 [scripts] Fixes to segment_long_utterances.sh (thanks @christophfeinauer) and train_raw_dnn.py (#1993)

5.2.186 0b818c4 2017-11-02 [egs] Remove deprecated non-working scripts

5.2.187 3ea5340 2017-11-02 [egs] Minor fixes to the SRE16 v2 recipe (#1986)

5.2.188 148c884 2017-11-02 [egs] rotation for image augmentation in CIFAR example (#1955)

5.2.189 c0c213f 2017-11-03 [src,scripts] nnet1-related changes: (#1998)

5.2.190 38296ad 2017-11-04 [egs] fisher_callhome_spanish: updated phonetic transcription and scoring; other fixes (#1992)

5.2.191 978e38e 2017-11-06 [scripts] Fix edge cases (#1994,#1991) in data-cleanup scripts (#1997)

5.2.192 e003f29 2017-11-07 [egs] Small fix to tedlium score_basic.sh (which is not used by default), thanks @danoneata

5.2.193 b01b5b4 2017-11-07 [src] Fix to nnet training to print multiple objfs in deterministic order (and print all of them) (#2001)

5.2.194 d3dd545 2017-11-07 [egs] Updating multi_en recipe's data selection, training procedure and lexicon preparation,.etc (#1893)

5.2.195 221664e 2017-11-08 [build] Tighten .gitignore exclude rules to ignore dot files in /src/*/ (#2004)

5.2.196 26be81e 2017-11-09 [egs,src] Some inconsequential fixes (#2007)

5.2.197 8569f8d 2017-11-09 [egs] BABEL scripts: new config files, and config-file generator script (#2006)

5.2.198 061d126 2017-11-09 [scripts,egs] Convert tab->space, and indent correctly (#2008)

5.2.199 05b2aed 2017-11-10 [egs] cleanup of BABEL scripts (#2011)

5.2.200 b952cf3 2017-11-10 [scripts] Documentation fixes. Thanks: Rongjin Li.

5.2.201 640a8e3 2017-11-13 [egs] Update soft link run_tdnn.sh in WSJ example

5.2.202 ac8adf2 2017-11-13 [egs] minor fixes to multi_en recipe (#2013)

5.2.203 030833a 2017-11-14 [egs] fix xent parameter (formal change, no effect on results) (#2014)

5.2.204 1d66675 2017-11-14 [egs] Babel cleanup + updated to ivector training with pca-transform (#2016)

5.2.205 0884818 2017-11-15 [src] nnet1: adding 'multitask' loss to 'nnet-train-perutt', (#2017)

5.2.206 f19e94c 2017-11-18 [scripts,doc] Add check for tilde in wav.scp (thanks: tessfu geteye); update queue documentation.

5.2.207 9e7644c 2017-11-19 [src] Minor fix: useless decoder declaration removed (#2020)

5.2.208 9b86ff2 2017-11-20 [egs] new BABEL DNN training recipes (#2021)

5.2.209 d508904 2017-11-20 [build] add mmseg to .gitignore (#2024)

5.2.210 54749fd 2017-11-20 [scripts] fail when the directory does not have the right files (#2023)

5.2.211 daeac30 2017-11-21 [src] Fix KaldiMatrix::Resize silent failure when resize_type == kCopyData (#2025)

5.2.212 23586f5 2017-11-21 [build,src] Increase OpenFst version from 1.6.2 to 1.6.5 (#2026)

5.2.213 d66906d 2017-11-21 [scripts] minor fix: make ivector id checking more robust (#2028)

5.2.214 9c877df 2017-11-21 [egs] babel: fix the lithuanian pitch accent handling (#2029)

5.2.215 2f90f81 2017-11-22 [build] Update Windows installation (#2032)

5.2.216 5e7deb9 2017-11-22 [egs] babel: cosmetic change (print only one path when generating language configs) (#2034)

Version 5.3

Major changes that were made between the end of 5.2.x and the start of the 5.3 branch include:

  • Create a nnet3-based setup for RNN language models (i.e. recurrent and neural net based language models)
  • Some extentions to the core of the nnet3 framework to support constant values and scalar multiplication without dedicated compoennts.

Below are patches corresponding to minor version numbers 5.3.x.

5.3.0 5e7deb9 2017-11-22 [egs] babel: cosmetic change (print only one path when generating language configs) (#2034)

5.3.1 db28650 2017-11-23 Kaldi 5.3 (includes nnet3-based RNNLM setup) (#1693)

5.3.2 39c8d14 2017-11-24 [scripts,egs] replace all instance of "gensub" with gsub or sub for compatibility (#2036)

5.3.3 0ba0b12 2017-11-26 [src,egs] fix to fgmm-global-acc-stats-post so that posteriors are read sequentially and features are random access (rather than vice-versa) (#2039)

5.3.4 e96eec1 2017-11-26 [src] nnet2: nnet-am-compute, adding option --divide-by-priors (default=false) (#2041)

5.3.5 1f5d747 2017-11-27 [build,src] Increase configure version (and add functions to CuVector) (#2042)

5.3.6 bafb68c 2017-11-27 [src] Fix to run_lstm.sh in swbd/s5c setup: mdeish@gmail.com

5.3.7 9effa4a 2017-11-27 [src] add max_warnining option to SlidingWindowCmnOptions to limit the number of times the variance flooring warning is printed (#2043)

5.3.8 92c99ee 2017-11-27 [egs] Modify some storage paths for striped data (#2038)

5.3.9 6d6e7a9 2017-11-27 [src] Various nnet3 changes, see PR for details (#2031)

5.3.10 acca2ac 2017-11-27 [src] Fixes/improvements in error path of TokenHolder code (#2044)

5.3.11 783ad7b 2017-11-29 [egs] babel: remove some files no longer used (#2048)

5.3.12 35288fa 2017-11-29 [src] Mostly cosmetic changes in error handling (#2047)

5.3.13 fbef11b 2017-11-29 [egs] replaced proportional-shrink with l2-regularize in the latest ami tdnn and tdnn-lstm recipes (#2045)

5.3.14 7a8f471 2017-11-29 [src,egs,scripts] removed extract-rows, create-split-from-vad and some long-unused scripts (#2049)

5.3.15 e9abbff 2017-11-29 [src] Fixing comments for BatchNormComponent (#2050)

5.3.16 f14e083 2017-11-30 [build] fix TF compilation issues; fix version of TF to avoid future issues (#2052)

5.3.17 fd5e336 2017-12-01 [src] Fix "warning: enumeration value ‘CUSPARSE_STATUS_ZERO_PIVOT’ not handled in switch [-Wswitch]" (#2054)

5.3.18 77ae8fe 2017-12-02 [src] Bug-fix to conceptual bug in Minimum Bayes Risk/sausage code. Thanks:@jtrmal (#2056)

5.3.19 85fa84c 2017-12-02 [scripts] Adding --num-threads option to ivector extraction scripts; script fixes (#2055)

5.3.20 a3441c2 2017-12-03 [src] Fix some small typos (#2060)

5.3.21 72dfed0 2017-12-04 [scripts] Fix bug in slurm.pl affecting log format (#2063)

5.3.22 93ceca7 2017-12-04 [egs] Add recipe for Mozilla Common Voice corpus v1 (#2057)

5.3.23 8bc9899 2017-12-04 [doc] Add documentation about matrix row and column ranges in scp files.

5.3.24 cd65627 2017-12-04 [scripts,egs] Convert ". path.sh" to ". ./path.sh" (#2061)

5.3.25 c948138 2017-12-04 [egs] Update to CSJ example scripts, with chain+TDNN recipes. Thanks: @rickychanhoyin (#2035)

5.3.26 8cc5c8b 2017-12-05 [src] Fix compilation error on MSVC: missing include. (#2064)

5.3.27 87783fc 2017-12-08 [src] Small fix RE CuSparse error code printing (#2070)

5.3.28 41806f6 2017-12-09 [src,egs] Small cosmetic fixes (#2074)

5.3.29 cc7c2f6 2017-12-10 [egs] Add a tdnn+lstm+attention+backstitch recipe for tedlium (#1982)

5.3.30 f51f8ca 2017-12-11 [src] Bug-fix to assertion in cu-sparse-matrix.cc (RE large matrices) (#2077)

5.3.31 f540992 2017-12-11 [egs] Add an l2-regularize-based recipe for image recognition setups (#2066)

5.3.32 4e3c183 2017-12-12 [egs,scripts] Add OPGRU scripts and recipes (#1950)

5.3.33 5799dae 2017-12-13 [scripts] Fix augment_data_dir.py (relates to non-pipe case of wav.scp) (#2081)

5.3.34 eaa6a26 2017-12-13 [egs] Small fix to backstitch in AMI scripts (#2083)

5.3.35 23e0463 2017-12-14 [egs] Copy dictionary-preparation-script fix from fisher-english(8e7793f) to fisher-swbd and ami (#2084)

5.3.36 e587c15 2017-12-15 [egs] Mac compatibility fix to SGMM+MMI: remove -T option to cp (#2087)

5.3.37 2ec515d 2017-12-16 [src] Fix bug in nnet3 optimization, affecting Scale() operation; cosmetic fixes. (#2088)

5.3.38 e7fe053 2017-12-19 [scripts,egs] Some fixes to OPGRU scripts from Lu Huang (#2091)

5.3.39 04458f7 2017-12-20 [src,egs,scripts] Merging RNNLM-related changes which were in wrong branch (#2092)

5.3.40 a3b3bfa 2017-12-21 [src] Prevent RNNLM training from exhausting GPU memory in diagnostic jobs (#2094)

5.3.41 f61224f 2017-12-21 [src] Fix bug in compilation with Scale() expressions. (#2098)

5.3.42 81b7a19 2017-12-21 [egs] Fix to decode context option in swbd (#2100)

5.3.43 3c21ef2 2017-12-22 [doc] Fix typo in docs (#2101)

5.3.44 d46ff7e 2017-12-26 [src] Ensure num-tree-leaves is a multiple of 8 (RE NVidia Volta architecture) (#2097)

5.3.45 48656c3 2017-12-26 Revert "[src] Ensure num-tree-leaves is a multiple of 8 (RE NVidia Volta architecture) (#2097)" (#2105)

5.3.46 a5561c3 2017-12-26 [src,scripts] Simplify model combination: do simple average over last n models (#2067)

5.3.47 2b3acc5 2017-12-27 [scripts] Cosmetic change to validate_data_dir.sh

5.3.48 843bc20 2017-12-28 [egs] Add TDNN recipes (and other changes) for chime4 (#2012)

5.3.49 0b4ea27 2017-12-28 [src] Dropout and batchnorm fixes for discriminative training (#2109)

5.3.50 df7a419 2017-12-28 [scripts] Fix validation-script bugs found by Somogyi Z; make validate_text.pl quieter.

5.3.51 47ea76b 2017-12-28 [egs] Update swbd/s5c RNNLM setup with hesitation mapping, and perplexities (#2108)

5.3.52 84f9b86 2017-12-28 [egs] fisher_swbd chain script bug fix (thanks: Filip Jurcicek) (#2110)

5.3.53 1270634 2017-12-29 [egs,src] Fix cleanup script bug (thanks: CW Huang), clarify comment.

5.3.54 9ac5dd4 2017-12-31 [src] Make faster ApplyFloor and ApplyCeiling variants for Matrix and CuMatrix. (#2115)

5.3.55 006e3c8 2017-12-31 [scripts] Fig bug in validate_data_dir.sh introduced in df7a41978f2. Thx:@jcsilva

5.3.56 1431db1 2017-12-31 [scripts] Fix lattice_oracle_align.sh bug (Thx: @roman-verbit-ai)

5.3.57 c08a1c1 2018-01-01 [build] Add new search dir for ATLAS (Thx: Sari Sultan)

5.3.58 6f9fab7 2018-01-02 [scripts] Fix script issue affecting some xvector training (thanks: daniel garcia-romero)

5.3.59 b808365 2018-01-03 [egs] Improve comments for fisher_swbd tdnn_lstm_1a (#2122)

5.3.60 8292e4c 2018-01-04 [egs] Add OCR/Handwriting Recognition examples (#1984)

5.3.61 33db55a 2018-01-04 [egs] swbd/s5c: Add RNNLM setup for where Fisher text data not there. (#2118)

5.3.62 36df91d 2018-01-05 [src] Round number of leaves to multiple of 8, will be faster with Volta architectures (#2106)

5.3.63 40a7d70 2018-01-06 [src] test-code change for speedup (#2128)

5.3.64 42767ab 2018-01-06 [scripts] Script fix in RNNLM setup; cosmetic change.

5.3.65 fd9284a 2018-01-07 [scripts] Add support for grayscale images to matrix_to_image.py (#2131)

5.3.66 e7ddb06 2018-01-07 [egs,scripts] source cmd.sh in RNNLM setups; rename some RNNLM setups; script fix (#2132)

5.3.67 33b0de9 2018-01-07 [src,scripts,egs] Add n-best rescoring for Kaldi-RNNLM (#2120)

5.3.68 a0b7131 2018-01-09 [src] Change matrix/ include structure to avoid leaking global symbols like 'real' (#2127)

5.3.69 360c96c 2018-01-10 [src] Temporary patch for build-tree assertaon failure.

5.3.70 e7e488e 2018-01-10 [egs] updating fisher_swbd nnet3/chain scripts: removing non-chain examples (#2136)

5.3.71 da18a45 2018-01-10 [src] Fix bug in rounding num-leaves (#2145)

5.3.72 116a948 2018-01-10 [build] Avoid problems when installing pocolm/irstlm a 2nd time (#2144)

5.3.73 e1ead78 2018-01-10 [scripts] Cosmetic typo fix (#2143)

5.3.74 65b856f 2018-01-11 [egs] Add Spanish recipe based on Heroico corpus (#1882)

5.3.75 6fb73b0 2018-01-12 [scripts] Extend num-digits in get_uniform_subsegments.py.. avoid crash on long utts (#2148)

5.3.76 5a8b4a6 2018-01-12 [build] update configure and android_openblas.mk for the latest ndk in android. (#2124)

5.3.77 26df3d8 2018-01-12 [src] Bug-fix in nnet3 compilation, RE Scale() expressions

5.3.78 1fb7fd9 2018-01-15 [scripts] OS X compatibility fix to utils/format_lm.sh, thx: @johnhosephmorgan

5.3.79 d883e30 2018-01-15 [build] set 'rpath' for ATLAS shared libraries, (#2153)

5.3.80 9e6dbab 2018-01-17 [egs] ami, changing path for storing downloaded wavs, (#2154)

5.3.81 26b0746 2018-01-17 [src,scripts,egs] ivector-based diarization recipe for CallHome (#1894)

5.3.82 829b013 2018-01-17 [egs] Update to CSJ example: fixed typo and updated to use xconfig (#2160)

5.3.83 687d313 2018-01-18 [src] Fix bug when compiling with flag -DNDEBUG (#2162)

5.3.84 c739ff9 2018-01-19 [egs] Minor fix in Farsdat recipe RE sctk path (#2164)

5.3.85 85a2c60 2018-01-20 [src] Print informative error if num-ceps >= num-mel-bins in MFCC (#2166)

5.3.86 35950ea 2018-01-21 [egs] add speaker recognition recipe for aishell (#2111)

5.3.87 d6391f8 2018-01-22 [scripts,egs] Fix bug in slurm.pl (thx:@kamo-naoyuki), remove outdated results.

5.3.88 96cbdd6 2018-01-22 [egs] Update chain results and add new scripts for fisher_swbd (related to #2136) (#2173)

5.3.89 8596bbf 2018-01-23 [egs] removing broken link in babel multilang setup (#2177)

5.3.90 476cb3f 2018-01-23 [egs] fixes for the IAM example (#2176)

5.3.91 b73bb12 2018-01-23 [egs] Make sure scoring opts are passed to score_cer.sh in UW3 (#2181)

5.3.92 47de145 2018-01-23 [scripts] Fix typos in scripts (#2182)

5.3.93 2e105fc 2018-01-23 [scripts] Fix to get_num_frames.sh for large datasets, RE truncation in awk (#2174)

5.3.94 7cf434c 2018-01-23 [scripts] Fix python3 compatibility bug (#2184)

5.3.95 ed84a51 2018-01-24 [scripts] Prevent crash when input_model is None (#2188)

5.3.96 6fed4c7 2018-01-24 [src] Remove CuDevice destructor (avoid cuda-memcheck warnings) (#2185)

5.3.97 7ee7893 2018-01-24 [src] Fix nnet3 back-compatibility issue (thx: @satmass)

5.3.98 f861b00 2018-01-25 [src] Speed fix to online decoding (thanks: David van Leeuwen) (#2180)

5.3.99 3031e26 2018-01-25 [src] Optimization to decoders for speed (#2168)

5.3.100 0f14373 2018-01-28 [src] Work around problem related to ungetc failures on ifstream (#2194)

5.3.101 30e9a90 2018-01-28 [src] Small fix to component reading, workaround for ungetc() issue.

5.3.102 e4fc87d 2018-01-30 [scripts] bugfix for 'steps/cleanup/clean_and_segment_data.sh', (#2196)

5.3.103 1647856 2018-01-31 [egs] Small bug-fix in Librispeech recipe (#2190)

5.3.104 2de3b38 2018-01-31 [src] Make arpa2fst robust against ARPA files without <s>. (#2167)

5.3.105 c82560d 2018-02-01 [scripts] Fixed small issue get_uniform_subsegments.py (RE rounding) (#2200)

5.3.106 b4fbe00 2018-02-02 [egs] Add assert to check --backstitch-training-interval option (#2203) (#2204)

5.3.107 9e2d844 2018-02-03 [egs,scripts] Fix and simplify speed-perturbation scripts; fix permissions. (#2205)

5.3.108 7906590 2018-02-06 [doc] remove outdated TODOs. Thx: David Van Leeuwen.

5.3.109 027f1d7 2018-02-07 [scripts] Add missing import statement in script (#2207)

5.3.110 8e170e0 2018-02-07 [egs] multi_en: Fixed acronym normalization, swbd lexicon preparation, OOV … (#2137)

5.3.111 f2ab7d4 2018-02-08 [src] Fix small bug in Log1p (thanks: Max Lvov)

5.3.112 1f1b108 2018-02-08 [scripts] make format_lm.sh work when source == target directory (#2209)

5.3.113 c52ee4c 2018-02-09 [src] rnnlm-embedding-training bug fix (thanks: @yanglin187) (#2208) (#2210)

5.3.114 ca73b1f 2018-02-10 [scripts] Fix warning from create_data_links.pl (#2212)

5.3.115 611aa61 2018-02-11 [scripts,egs] Fix failures in some run_ivector_common.sh script introduced in #2205 (#2213)

5.3.116 8a38437 2018-02-11 [egs,scripts] Recipe for voice activity detection on Switchboard (#2193)

5.3.117 ca5f128 2018-02-11 [doc] Updating contributor list in COPYING to contain the current top 66 contributors in Kaldi. Thanks to Yishay Carmiel for gathering this info (#2214)

5.3.118 5ea9b0d 2018-02-13 [egs,scripts] HUB4 English Broadcast News recipe (#2027)

5.3.119 6d32a0b 2018-02-14 [src] Fix usage message, comment of ali-to-pdf (#2218)

Version 5.4

Version 5.4 is the current master branch. The main changes that were made between the end of 5.3.x and the start of the 5.4 branch include:

  • Some code changes in the nnet3 codebase, for speed and memory efficiency.
  • Various simplifications and code reorganizations in the nnet3 code.
  • Support for a new kind of factorized TDNN which gives substantially better results than our old TDNN recipe, and is even better than our old TDNN+LSTM recipe. A good example of this is in egs/swbd/s5c/local/chain/tuning/run_tdnn_lstm_1n.sh. Some nnet3 code changes were needed for this as well (mostly: support for constraining a matrix to have orthonormal rows).

Below are patches corresponding to minor version numbers 5.4.x.

5.4.0 be969d7 2018-02-17 [build] Upgrading version of Kaldi to 5.4

5.4.1 6016c00 2018-02-17 [doc] Add documentation for 5.4 version of Kaldi

5.4.2 9b282b5 2018-02-18 [scripts] Fix bug in steps/diagnostic/analyze_phone_length_stats.py [thanks: Vinay Sunder.]

5.4.3 09b0176 2018-02-18 [build] Update gst-plugin Makefile (#2226)

5.4.4 b61d760 2018-02-20 [src] Fix error in how Compress() command is printed for debugging

5.4.5 6dd9c3e 2018-02-21 [scripts] Fix bug in steps/libs/nnet3/train/frame_level_objf/common.py (#2231)

5.4.6 e3df6ac 2018-02-21 [src] Print curand return codes (#2232)

5.4.7 9191f29 2018-02-23 [egs] Fix script bug (in error-checking statement) (#2239)

5.4.8 e0d8f13 2018-02-23 [scripts] Fix typo (#2237)

5.4.9 4f27915 2018-02-23 [scripts] Fix typo in comment (#2238)

5.4.10 f629bf8 2018-02-24 [scripts] Bug-fix in analyze_phone_length_stats.py (thanks: @stanleyguan)

5.4.11 851c5e4 2018-02-27 [egs] Fix to swbd chain tdnn_blstm script bug (thanks: sameer khurana)

5.4.12 7e902f5 2018-02-27 [scripts] Fix for nnet3 model combination on CPU when --use-gpu false (#2240)

5.4.13 27f6c5e 2018-02-28 [src] Fix small bug in cu-math.cc affecting non-GPU LSTM training, thx: Mael Primet.

5.4.14 0ebe5b5 2018-02-28 [egs] Simplify Aspire scripts and make it work with LDC release. (#2230)

5.4.15 9a4ba5e 2018-02-28 [src,scripts,egs] Add form of dropout that shares the mask across frames. (#2244)

5.4.16 8b50076 2018-02-28 [scripts] add --max-arcs option to scripts/rnnlm/lmrescore_pruned.sh (#2245)

5.4.17 c426826 2018-03-01 [src] Fix to cu-rand.cc RE large matrix sizes. (#2249)

5.4.18 bc0fcad 2018-03-02 [build]: Dockerfile for kaldi installation (#2246)

5.4.19 e7b3a66 2018-03-03 [src] Fix macro redefinition problems in tensorflow rnnlm. (#2250)

5.4.20 03b0ea8 2018-03-03 [src,scripts,egs] Enable backstich training for RNNLM; add examples (#2096)

5.4.21 03edf82 2018-03-04 [src] Fixed bug in GeneralDropoutComponent when block-dim set (#2252)

5.4.22 0e1822d 2018-03-04 [egs] Port factorized TDNN script to librispeech (#2233)

5.4.23 230d013 2018-03-05 [scripts] python3 compatibility: change / to // (#2253)

5.4.24 4518c77 2018-03-05 [src] Fix CPU swap methods of CuVector and CuPackedMatrix (#2254)

5.4.25 25391fb 2018-03-05 [scripts] Add example of accessing nnet3 model from python (#2255)

5.4.26 e74b918 2018-03-05 [src,scripts,egs] End-to-end chain training (#2072)

5.4.27 ed05f17 2018-03-06 [egs] thchs-30: fix Mac compatibility issue (#2258)

5.4.28 f293ccd 2018-03-06 [build] upgrade the install_beamformit script (#2259)

5.4.29 6518685 2018-03-07 [src] Changes to logging information printed by nnet1 (#2261)

5.4.30 9e3ce67 2018-03-07 [scripts] Fix python3 issues w.r.t. relative imports, in steps/libs/. Thx: Cemil Demir (#2263)

5.4.31 7f028e3 2018-03-07 [egs] Adding orth-factorized-TDNN recipe for fisher_swbd (#2264)

5.4.32 c541ea0 2018-03-08 [src] Fix small bug in nnet3 component (config was lost on read).

5.4.33 b4711ad 2018-03-08 [src] Fix small bug in nnet3 component (config was lost on read)... 2nd try.

5.4.34 0360215 2018-03-09 [src] Support floating orthonormal-constraint (#2267)

5.4.35 19dc26f 2018-03-12 [src] bug-fixes for end2end chain code (#2270)

5.4.36 be8f4ec 2018-03-12 [src] Fix subsampling factor in nnet3 egs (#2265)

5.4.37 5eb57cc 2018-03-13 [egs] Add chime5 baseline recipe (#2262)

5.4.38 6363d55 2018-03-13 [scripts] Add delta_opts for train_mono.sh (#2221)

5.4.39 060d92a 2018-03-14 [egs] fix generate_plots.py to plot deriv-avg and oderiv-rms (#2274)

5.4.40 f1c927c 2018-03-14 [tools] fix beamformit installation (#2276)

5.4.41 ec98e71 2018-03-14 [scripts] Bug-fix in convert_data_dir_to_whole.sh (thx: @olix20) (#2277)

5.4.42 b7f9446 2018-03-14 [egs] Add modernized vystadial_cz recipe (#2278)

5.4.43 49a90e0 2018-03-15 [src] Fix to nnet3 looped compilation bug (thanks: Alim Misbulah) (#2279)

5.4.44 8044ada 2018-03-16 [scripts] Cosmetic fix to prepare_lang.sh (#2284)

5.4.45 8ab6e53 2018-03-16 Revert "[src] Fix to nnet3 looped compilation bug (thanks: Alim Misbulah)" (#2285)

5.4.46 1644312 2018-03-17 [src] Add a nnet3 optimization that tries to replace commands ending in Multi with other commands. (#2229)

5.4.47 322f698 2018-03-17 [scripts] Fixes to segmentation scripts (#2273)

5.4.48 df9d16c 2018-03-18 [scripts] Add support for --use-gpu=wait to nnet3 scripts (#2289)

5.4.49 5562583 2018-03-18 [egs] Add improved TDNN-F example for Switchboard. (#2291)

5.4.50 d2a2909 2018-03-19 [src] Enable nnet3-compute to optionally subtract priors (#2294)

5.4.51 9654a7c 2018-03-19 [build] Remove outdated compute architecture. Thx: @CodesFarmer

5.4.52 c6b3588 2018-03-19 [src] Fix to nnet3 compilation issue affecting BLSTMP. Thanks: Alim Misbullah (#2286)

5.4.53 eba50e4 2018-03-20 [src] Enable reading wavs produced on iPhones with extra RIFF tags. (#2293)

5.4.54 22fbdd9 2018-03-21 [egs] fixing LM issue in CHiME5 (#2298)

5.4.55 954e13c 2018-03-22 [src] Make ClipGradientComponent zero gradients when clipping threshold is zero (#2301)

5.4.56 dbd513c 2018-03-22 [src] Make CachingOptimizingCompiler thread safe. Thx: Arseniy Gorin (#2288)

5.4.57 f4a5667 2018-03-22 [src] Fix to comment

5.4.58 9ae3eb7 2018-03-22 [src,scripts] Make cache size configurable for xvector extraction (#2290)

5.4.59 6dbe790 2018-03-22 [src] Speedup and code simplification for chain supervision merging (etc.) (#2302)

5.4.60 8b415fe 2018-03-24 [egs] remove redundant step from chime5 recipe (#2306)

5.4.61 9f7e55a 2018-03-24 [src] Fix issue with CUDA device initialization if 'wait' specified. Thx: @olix20 (#2295)

5.4.62 e03dd12 2018-03-24 [scripts,egs] Fix to perturb_speed_to_allowed_lengths.py; egs fix (thanks: @calderma) (#2307)

5.4.63 cc16eec 2018-03-26 [windows] fix for compiling on Windows VS2017 (15.5.2) (#2310)

5.4.64 7352760 2018-03-27 [egs] minor fix for fisher_swbd scripts and swbd nnet3 scripts (#2316)

5.4.65 e5b6696 2018-03-27 [egs] Add end-to-end OCR recipe for IAM (thanks: @aarora8) (#2311)

5.4.66 d7e8890 2018-03-27 [egs] Fix LM/lexicon issues in IAM; Add unk decoding; Update results. (#2315)

5.4.67 785198e 2018-03-27 [src] Add some asserts in RNNLM code (#2314)

5.4.68 7498395 2018-03-27 [src] Fix to recent commit RE RNNLM code

5.4.69 8af60bb 2018-03-28 [src] Apply limits prior to chain denominator computation, avoid failures. (#2308)

5.4.70 5e6bd39 2018-03-28 [tools, extras] morfessor installation script (#2299)

5.4.71 191b39a 2018-03-28 [src,scripts,egs] Semi-supervised training on Fisher English (#2140)

5.4.72 b620633 2018-03-30 [build] Updates to Sequitur installation script (for compatibility with new setuptools) (#2323)

5.4.73 e507a7a 2018-04-02 [src,egs,doc] Some cosmetic changes

5.4.74 6f4fafb 2018-04-03 [src] Bug fix: oscillating cluster threshold in agglomerative-cluster (#2333)

5.4.75 fe36823 2018-04-03 [src] Fix bug causing wrong learning rate in RNNLM training with --stage option (#2330)

5.4.76 831dd38 2018-04-03 [src] make fst templates inline to eliminate linking errors in other places (#2329)

5.4.77 7436ed6 2018-04-03 [src] Make it so no threads are used if you set num-threads to 0.

5.4.78 a9e4f74 2018-04-04 [build] Fix some problems with sequitur installation (#2337)

5.4.79 1814278 2018-04-04 [scripts] Make sure nj in get_utt2dur.sh does not exceed num-utts. (thx: @olix20) (#2326)

5.4.80 5294666 2018-04-05 [scripts] Fix to nnet3 bug RE per-utt splitting that appeared after #2140; un-support --transform-dir. Thx: @aaror8 (#2334)

5.4.81 1a1e265 2018-04-05 [src,build] Fix cygwin compatibility; remove unnecessary memalign macros (#2304)

5.4.82 60862b0 2018-04-06 [scripts] Make nnet3 logging output look more like chain logging output (#2338)

5.4.83 c2d796d 2018-04-06 [scripts] Fix bug in chain/get_egs.sh affecting semi-supervised training (#2339)

5.4.84 c643295 2018-04-07 [egs] IAM script fixes using the right lang for training/lattice generation + cleaning (#2340)

5.4.85 c0c55ad 2018-04-08 [egs] IAM: add chain recipe starting with e2e alignments and tree (#2343)

5.4.86 9b90cba 2018-04-09 [egs] Fix scoring issue in IAM (#2346)

5.4.87 e10c478 2018-04-10 [src] Revert KALDI_MEMALIGN->aligned_alloc change from #2304, fixes #2347 (#2348)

5.4.88 8a4ab19 2018-04-11 [src] Fix nnet3-copy-egs bug for multiling. non-chain training (thx:Joshua Meyer) (#2350)

5.4.89 ad48342 2018-04-11 [scripts] Bug fix in combine_egs.sh (for multilingual training) (#2351)

5.4.90 2d0cd79 2018-04-12 [scripts] Finish removing transform_dir options from nnet3 training (thx: @pstanisl) (#2353)

5.4.91 adcabe4 2018-04-12 [src] Fix (rare) divergence from orthogonal constraint. Thx: Sergey Tushev. (#2336)

5.4.92 ccd50e2 2018-04-12 [egs] Adding Wellington corpus for LM in IAM OCR (#2354)

5.4.93 e99de50 2018-04-13 [scripts] Make beam configurable, +default smaller, in pruned RNNLM rescoring (#2325)

5.4.94 535df00 2018-04-14 [src] small fix to comment (#2357)

5.4.95 dd7caa6 2018-04-14 [egs] A fix to second-stage chain recipes in IAM and lang fixes in UW3 (#2358)