Versions of Kaldi

Versioning scheme

During its lifetime, Kaldi 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 commits corresponding to minor version numbers 5.0.x.

5.0.0 c160a9883 2017-01-05 [build] Adding versioning mechanism to Kaldi. This is version 5.0.0 (#1306)

5.0.1 53e33dc4b 2017-01-06 [scripts] nnet3 scripts: minor bug fixes in error-handling code (#1321)

5.0.2 f15be6387 2017-01-06 [scripts] minor updates of scripts in nnet1 (#1318)

5.0.3 735b2b149 2017-01-06 [egs] minor fix in fisher_swbd/s5/local/chain/run_blstm_6h.sh (#1320)

5.0.4 a4b209159 2017-01-07 added reverberation based augmentation recipe for TDNN+LSTM model on AMI; a fix to aspire recipe (#1314)

5.0.5 5cdbd1879 2017-01-07 [build] Makefile changes: print time for tests; dash-compatibility change (#1322)

5.0.6 e09e92f87 2017-01-08 [egs] minor fixes for mandarin recipes (#1325)

5.0.7 722df9ae6 2017-01-09 [build] Fix dash problems [set shell to /bin/bash in Makefile]

5.0.8 f646952b3 2017-01-09 [build] src/base/get_version.sh: change regexp syntax to support older bash versions. (#1327)

5.0.9 5f15d253b 2017-01-10 [egs] cosmetic; small typo fix in sre08 i-vector DNN extraction (#1330)

5.0.10 69b616d4a 2017-01-10 [src,egs,scripts] Remove sinusoid detection code and old SGMM code/scripts (#1329)

5.0.11 cd0680270 2017-01-10 [src] nnet3: fixed bug (LstmNonlinearityComponent::ZeroStats() was not implemented) (#1302)

5.0.12 748a4a923 2017-01-11 [src] Restore init-ubm.cc to sgmm2bin (was deleted when sgmmbin deleted)

5.0.13 95f0feca1 2017-01-11 [src] nnet1: replacing 'bc' by 'awk' in steps/nnet/train_scheduler.sh (#1333)

5.0.14 728b303df 2017-01-11 [scrips] fix bug in lmrescore_rnnlm_lat.sh when using G.carpa (#1334)

5.0.15 42291a66f 2017-01-12 [doc,egs] Fix path from lm to lmbin in kaldi for dummies and various egs/*/*/path.sh

5.0.16 421485ee9 2017-01-12 [src] nnet3: Remove deprecated options which are no longer used (#1335)

5.0.17 847035e7b 2017-01-13 [egs] Remove some unused scripts

5.0.18 ea25438dc 2017-01-13 [build] Fix return code of tools/extras/install_sacc.sh (#1337)

5.0.19 e1e7bbf5c 2017-01-13 [scripts] nnet3: fix to xconfig parsing to enable e.g. "input@-1" in xconfig descriptors (#1338)

5.0.20 1dabfa54c 2017-01-14 [src] cosmetic changes to rnnlm-related code (#1283)

5.0.21 4d2c78e23 2017-01-16 Some bug fixes to I/O code for nnet3

5.0.22 6c0a012d5 2017-01-16 Remove checking code which would fail if code updated in middle of training run.

5.0.23 f7b2fe754 2017-01-16 Bug fix (resolve failing test)

5.0.24 390aff4e5 2017-01-18 [egs] Fix typo in egs/csj/s5/local/csj_run_rnnlm.sh (#1351)

5.0.25 e8e5928a6 2017-01-19 [src] cudamatrix: added {Cu,}VectorBase::SetRandUniform(), + optimize/fix cu-rand code (#1352)

5.0.26 d117c955d 2017-01-20 [src] Some style-related fixes (and fix compiler warnings) in src/lm/

5.0.27 b9c1e8bce 2017-01-20 [src] Modify some tests that were slow on travis, to make them faster. (#1347)

5.0.28 df730e8e6 2017-01-21 [src] Implement CuMatrixBase<Real>::CopyColsFromVec() (#1361)

5.0.29 04404176c 2017-01-23 [src,scripts]: Adding dropout schedule option to nnet3 (#1248)

5.0.30 61510ca0d 2017-01-22 nnet3/report : Modified directory specification options in generate_plots.py (#1368)

5.0.31 4507183f3 2017-01-24 [build] fixing patch for OpenFst's compat.h for Windows build (#1373)

5.0.32 99b7d964d 2017-01-24 [scripts] lexicon learning: update missing defaults and help message; other fixes (#1360)

5.0.33 5c205eae3 2017-01-24 [scripts] nnet3/report : Added support for parsing latest compute_{train,valid}*.log (#1371)

5.0.34 f42b3ced0 2017-01-24 [scripts] nnet1,make_denlats: prevent crash when utt-ids contain slashes (#1374)

5.0.35 82167f971 2017-01-24 [scripts] remove import statement that was creating problems in nnet3 scripts.

5.0.36 9208165a5 2017-01-25 [src] nnet3: Add the "per-frame" option to DropoutComponent (#1324)

5.0.37 e227eda38 2017-01-25 [doc] Documentation changes; add scripts to automatically add documentation of patch versions.

5.0.38 0c1517c37 2017-01-25 [egs] swbd/s5c, chain recipes: fix hardcoded directory name (#1377)

5.0.39 c96a0aa0f 2017-01-26 [build]: use BSD-compatible mktemp in get_version*.sh; thanks; @andrely.

5.0.40 6ec2eb003 2017-01-26 [build]: fix to previous commit regarding usage of mktemp.

5.0.41 3b7fd1f92 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 193bb9214 2017-01-26 [build]: minor bug fix in maintenance/documentation script.

5.0.43 5af1983f1 2017-01-27 [scripts] Fix nnet3 training scripts for bug introduced in #1371

5.0.44 2f8c33d13 2017-01-27 [scripts,egs] make steps/dict/learn_lexicon.sh more robust RE empty g2p prons (#1378)

5.0.45 9d53e051b 2017-01-29 [scripts] nnet3 training: fix for bug introduced when dropout scripting support was merged.

5.0.46 da591795e 2017-01-30 [scripts] steps/dict/learn_lexicon.sh: minor fixes (#1385)

5.0.47 01d96bf10 2017-02-01 [scripts] Fix bug in dropout code found by Tanel Alumae

5.0.48 67cabd026 2017-02-01 [build]: resolving OpenFst compilation issue with gcc-6.x (#1392)

5.0.49 f1d7891c5 2017-02-01 [egs] Add new graphemic system for Gale Arabic, with newer nnet scripts (#1298)

5.0.50 21cfe99c5 2017-02-02 [build] Windows build: generate missing base/version.h; cosmetic changes (#1397)

5.0.51 cd97bd22a 2017-02-02 [build]: Enable cross compilation, including to android. (#726)

5.0.52 c747ed5d5 2017-02-06 [build] fixing issue introduced in the previous win commit (#1399)

5.0.53 21c803145 2017-02-07 [egs] Fix to HKUST nnet2/3 scripts. (#1401)

5.0.54 dc454cc0a 2017-02-08 [egs,scripts,src] Add BABEL s5d recipe; various associated fixes (#1356)

5.0.55 9a1244ffb 2017-02-08 [egs] removing empty files in BABEL recipe (#1406)

5.0.56 2fd8da973 2017-02-09 [scripts] Give prepare_lang the option to generate more phone disambig symbols (#1408)

5.0.57 bcc71b67d 2017-02-09 [egs] sprakbanken recipe: add nnet3 examples.

5.0.58 bd73932fb 2017-02-10 [src] Get rid of clang 3.9 warnings in table-reading code (#1414)

5.0.59 cc1d677f9 2017-02-10 [egs] egs/fisher_swbd/s5/local/online/run_nnet2_ms.sh, change default stage to 0 (#1416)

5.0.60 922620255 2017-02-11 [egs] Add example scripts for Frisian-Dutch language (FAME! corpus)

5.0.61 37b5352f5 2017-02-11 [src,doc] Documentation updates; fixes to comments.

5.0.62 68cee215c 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 commits corresponding to minor version numbers 5.1.x.

5.1.0 68cee215c 2017-02-17 [src] Make various tests faster, especially without GPU (#1428)

5.1.1 214551996 2017-02-17 [build] Updating version file-- this commit marks version 5.1.0

5.1.2 9b9b561e2 2017-02-17 Kaldi 5.1.0 (#1342)

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

5.1.4 23338bf51 2017-02-19 [scripts] fix syntax error in validate_lang.pl [thanks: daniel galvez]

5.1.5 7d538e2bd 2017-02-19 [build] Increase OpenFst version 1.6.0->1.6.1. (#1434)

5.1.6 84585876f 2017-02-20 [build] Use github not sourceforge for IRSTLM [sourceforge repo dead?] (#1435)

5.1.7 d218412ac 2017-02-20 [egs] clean up the HKUST scripts and add scoring filters (#1436)

5.1.8 7b862c725 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 483192ed4 2017-02-20 [build] update .gitignore: ignore openfst-1.6.1 (#1439)

5.1.10 8c77d2cc9 2017-02-21 [src,egs,scripts] Support frame-subsampling with non-chain nnet3 models (#1238)

5.1.11 2c3df88f0 2017-02-21 [build] cloning IRSTLM, use https to access github, not ssh (#1441)

5.1.12 9866a4c4d 2017-02-22 [build] Update Travis configuration to get builds to complete on time. (#1443)

5.1.13 351da2886 2017-02-22 [egs] Iban recipe: MacOSX compatibility fixes (#1448)

5.1.14 ae4a5ef62 2017-02-23 [scripts] Make it so i-vector ID is not required for steps/nnet3/decode.sh

5.1.15 70f536071 2017-02-23 [build] Stop env.sh from crashing when set -u is active (#1451)

5.1.16 dff2a3f2c 2017-02-24 upgrade the sox calls to use more compatible options (#1453)

5.1.17 37bebd153 2017-02-25 [egs] fix typo in egs/swbd/s5c/local/nnet3/run_ivector_common.sh (#1452)

5.1.18 4cda60423 2017-02-25 [scripts] xconfig: make scripts work when LDA-like preconditioning layer is not used (#1447)

5.1.19 089e59679 2017-02-25 [build] Update OpenFst minimum version check to 1.6 in tools/Makefile. (#1455)

5.1.20 344e1adc1 2017-02-25 [src] Fix bug in decodable-online-looped.cc (prevent crash in nnet3 online decoding).

5.1.21 25b1299b6 2017-02-25 [egs] fix MacOSX incompatibilities in calls of paste (#1457)

5.1.22 d60e3cc26 2017-02-27 [egs,scripts] Misc script fixes; refactor wsj/s5 examples; update tedlium/s5_r2 (#1456)

5.1.23 3f180124f 2017-02-27 [scripts,egs] Replace SGE-specific options to queue.pl (etc.) with generic options (#1461)

5.1.24 1db4bbad2 2017-02-27 [scripts] Fix to nnet2 script (won't change results) (#1462)

5.1.25 ee45757d4 2017-02-28 [scripts] nnet3: remove import from tdnn in the xconfig script since it no longer exists (#1464)

5.1.26 0c4441ed4 2017-02-28 [egs] Add online-decoding example in some Swbd chain scripts (#1466)

5.1.27 4a58ab98f 2017-02-28 [scripts] fix_data_dir.sh, prevent function returning false in case reco2file_and_channel does not exist (#1467)

5.1.28 f6b011f71 2017-03-01 [src] kwsbin/transcripts-to-fsts.cc, fix bug introduced in the last babel recipe commit (#1470)

5.1.29 d5a9d5c94 2017-03-02 [src] add CUDA kernel for backprop of NormalizeLayer (#1458)

5.1.30 ba77d9766 2017-03-03 [src] fix kws pipeline after upgrading to openfst-1.6 (#1471)

5.1.31 828f0b9cc 2017-03-03 [egs] Add discriminative training script for WSJ/TDNN-LSTM (#1468)

5.1.32 5bad9b2d9 2017-03-06 [src] bug-fix in gst plugin code (issue on g++ 5.4.0) (#1479)

5.1.33 34128c51a 2017-03-06 [scripts,egs] sMBR on LFR xent system with shifted feats (#1477)

5.1.34 5bfa9e541 2017-03-08 [egs] Minor cosmetic changes in voxforge example script (#1483)

5.1.35 bd23a10ed 2017-03-10 [egs] Fixes to URLs in vystadial example script.

5.1.36 1a4dbf6be 2017-03-13 [src] nnet1: fixing issue in multi-task training (#1491)

5.1.37 eba49a03f 2017-03-14 [build] Bump OpenFst version to v1.6.2 (#1492)

5.1.38 5c98096d8 2017-03-16 [egs] swbd/chain : added blstm script using fast-LSTM; added BLSTM+TDNN script. (#1497)

5.1.39 3fec956be 2017-03-17 [egs] update fisher_swbd recipe (fixes to how things are installed). (#1498)

5.1.40 eac0baa6b 2017-03-19 [src] sort cuda kernel function declarations to make searching easier. (#1501)

5.1.41 25ca8e4b0 2017-03-19 [build] Android compilation, bug-fixes (#1502)

5.1.42 ed33b1fd3 2017-03-19 [doc] Add a note to README.md about Android cross compilation (#1503)

5.1.43 965cc494c 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 39ad4103e 2017-03-22 [scripts] prevent failure when final.ie.id doesn't exist (#1508)

5.1.45 ef415a7a4 2017-03-22 [src] Fix exit code of extract-rows.cc (#1510)

5.1.46 9a6feea7b 2017-03-23 [egs] fixes to babel pipeline; thanks to Fred Richardson (#1509)

5.1.47 0d0316b48 2017-03-23 [src,scripts]: Several unrelated cosmetic changes

5.1.48 24bc2221f 2017-03-27 [misc] remove eXecute permissions where not needed (#1515)

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

5.1.50 8b458ae1b 2017-03-29 [src] Adding noexcept to hashing function objects (#1519)

5.1.51 13d300fc6 2017-03-29 [src,doc] Fix several unrelated minor problems. Thanks: gaoxinglong

5.1.52 e9d79939b 2017-03-31 [src] (minor) Added missing SetZero() to NaturalGradientAffineComponent::Scale() if scale==0.0 (#1522)

5.1.53 e8ca375da 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 60f932721 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 3c9440103 2017-04-04 [build]: remove openfst check (#1531)

5.1.56 d8b34d4b5 2017-04-04 [src] cudamatrix: speed up AddColSumMat with transfrom reduce kernel template (#1530)

5.1.57 e5b141943 2017-04-04 [src] Cosmetic change: remove 'train.tra' from usage messages (#1529)

5.1.58 015768678 2017-04-05 [src] nnet1: improving the GPU diagnostics, (#1532)

5.1.59 d9efe6efa 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 5b70933c6 2017-04-12 [scripts] fix to get_egs_targets.sh (thanks: David Pye)

5.1.61 b2d5d3683 2017-04-12 [scripts] nnet3 : fix issue where LDA estimation failed for LSTMs with label delay (#1540)

5.1.62 31a528b0c 2017-04-13 [src] Change ConvertStringToReal to be locale-independent (i.e. always-US). Fixes android issue. (#1513)

5.1.63 7fcc311c1 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 179d9b63c 2017-04-14 [src] add template instantiations for ConvertStringToReal, address issue #1544

5.1.65 889175079 2017-04-14 [egs] AMI TDNN Results Update (#1545)

5.1.66 9e06caa1f 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 81346fc4b 2017-04-16 Update travis.yml so PRs to kaldi_52 are built

5.1.68 46f328527 2017-04-19 [egs] Added check for kaldi_lm being installed in fisher_swbd recipe. (#1558)

5.1.69 72234621b 2017-04-20 [doc] Small edit to hmm.dox, clarifying something

5.1.70 d82bbd7a2 2017-04-20 [src] nnet3 online silence weighting - adding frame subsampling factor (#1559)

5.1.71 d8be99a1c 2017-04-20 [src,scripts,egs] Add dropout for nnet3 LSTMs, with recipes. (#1537)

5.1.72 015c96f74 2017-04-20 [src] Add documentation for dropout function.

5.1.73 73489ae53 2017-04-21 [src] Fix to testing code signal-test.cc, change threshold to resolve failure (#1565)

5.1.74 87d95c5ef 2017-04-21 [egs] Add mini-librispeech example scripts [intended as a sanity-checker/tutorial setup] (#1566)

5.1.75 c68a576b0 2017-04-21 [egs] adding results and cleanup in mini-librispeech

5.1.76 1f51ef5d0 2017-04-23 [egs] Add soft link for mini-librispeech setup

5.1.77 06047be40 2017-04-25 [src] Minor bug-fixes in compute-wer-bootci and WSJ run.sh. Thanks: @osadjadi

5.1.78 8b9e8743c 2017-04-25 [egs] bug-fix in egs/ami/s5/run_ihm.sh (#1577)

5.1.79 a39e580db 2017-04-28 [build] Remove warning about dash (I believe we have no problem with it now)

5.1.80 fc20b7670 2017-05-01 [egs] fix small bug in wsj run.sh [thanks: Hang Lv]

5.1.81 e527572a3 2017-05-01 [sripts] extract_ivectors.sh: cosmetic fix, correct example usage. (#1600)

5.1.82 1cd6d2ac3 2017-05-02 [egs] mini-librispeech: download data from openslr if it's not present (#1598)

5.1.83 3906ae94a 2017-05-04 [src] bug-fix for memory bug in nnet computation cache code

5.1.84 ba138485f 2017-05-04 [src] Fix bug that can cause crash for for kernel-sizes=n*65536.

5.1.85 ad6491ab5 2017-05-05 [src] Add --write-per-frame-acoustic-loglikes options to alignment programs (#1601)

5.1.86 7c04d6291 2017-05-06 [scripts] nnet1: minor update i-vector and mpe scripts (#1607)

5.1.87 578c17622 2017-05-07 [src] cosmetic change to const-arpa-lm-building code; remove too-general template. (#1610)

5.1.88 6eebc0482 2017-05-09 [src,scripts,egs] Segmenting long erroneous recordings (#1167)

5.1.89 ab5c96c87 2017-05-11 [egs] thchs30 cmd and stage bug fix (#1619)

5.1.90 b1e860171 2017-05-13 [src] Change to GPU synchronization, for speed (disables GPU stats by default) (#1617)

5.1.91 8cbb74c43 2017-05-13 [src] Fix template instantiation bug causing failure if DOUBLEPRECISION=1

5.1.92 66666823a 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 a7e6183c4 2017-05-15 [src] fix a small bug: logging cuda elapsed time (#1623)

5.1.94 7af2128d6 2017-05-17 [src,scripts,egs] Add capability for multilingual training with nnet3; babel_multilang example.

5.1.95 963895084 2017-05-18 [doc] small fix RE queue configuration.

5.1.96 ae45ee2ae 2017-05-19 [scripts] Fix to long-utterance segmentation script (#1631)

5.1.97 45ee31fb3 2017-05-20 [src] Make parsing error-msg more informative (thanks: Stefan-Adrian Toma)

5.1.98 b13f56bd2 2017-05-21 [src] fix regarding first/last chunk's right-context in chain models (#1632)

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

5.1.100 dc32e0b5e 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 d6cf1bde9 2017-05-23 [scripts,egs] Fixes to long-recording segmentation (#1639)

5.1.102 b5eac0982 2017-05-24 [scripts] fix bugs in align_basis_fmllr.sh [thanks: Filip Jurcicek]

5.1.103 0f5e16ed3 2017-05-25 [build] Check python version is 2.7*, not just 2.*.

5.1.104 31683a38e 2017-05-25 [build] Change check_dependencies.sh to not look for yum if apt-get present.

5.1.105 6739d6020 2017-05-25 [scripts] Make more informative error in validate_lang.pl when path.sh prints something

5.1.106 6cc8e3ad7 2017-05-26 [src] Use STL thread support library instead of pthread. (#1350)

5.1.107 c210b444d 2017-05-26 [scripts] Fix bugs in automatic report generation for nnet3 training

5.1.108 76c8c777f 2017-05-26 [egs] Ported Fisher spanish recipe to use new LDC dir structure. Other small fixes (#1647)

5.1.109 6b906a373 2017-05-26 [egs] updated the LDC web address for wsj0-train-spkrinfo.txt (#1648)

5.1.110 0b0dbb016 2017-05-26 [scripts,egs] minor script fix; fixes in various recipes (#1649)

5.1.111 b6c34db1a 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 e9646f031 2017-05-26 [src] keyword search: fix invalid assumption about the end states (#1651)

5.1.113 93c069cec 2017-05-27 [src] Fix bug in newly refactored threading code

5.1.114 726728154 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 commits corresponding to minor version numbers 5.1.x.

5.2.0 726728154 2017-05-27 [scripts] Getting egs, limit max open filehandles to 512 (thanks: gaoxinglong9999)

5.2.1 393ef73ca 2017-05-29 [build] Upgrade .version (this is official start of kaldi 5.2)

5.2.2 cb7d17638 2017-05-29 Merge pull request #1547 from kaldi-asr/kaldi_52

5.2.3 a57eab677 2017-05-29 [scripts] Fix bug in PR #1646 (#1658)

5.2.4 972efd7a2 2017-05-31 [scripts] nnet3 script cleanups; add --proportional-shrink in more places. (#1659)

5.2.5 3e57783cf 2017-05-31 [src] minor bugfix in convolutional component (doesn't affect experiments)

5.2.6 44cd38652 2017-05-31 [build,scripts] Update scripts that make version info; remove no-op option from script.

5.2.7 fa198bb59 2017-06-01 [scripts] do not fail if the ivector extractor belongs to different user (#1662)

5.2.8 bd5fd04a1 2017-06-01 [src] keyword search tools: fix Minimize() call, necessary due to OpenFst upgrade (#1663)

5.2.9 ada5c0d80 2017-06-01 [src,scripts] Use ConstFst or decoding (half the memory; slightly faster). (#1661)

5.2.10 cdb25d114 2017-06-02 [scripts] make errors getting report non-fatal (thx: Miguel Jette); add comment RE dropout proportion

5.2.11 7728a10bc 2017-06-02 [src] Fix bug in online2-nnet3 decoding RE dropout+batch-norm (thanks: Wonkyum Lee)

5.2.12 6fe140add 2017-06-02 [src] Add #include missing from previous commit

5.2.13 13078031c 2017-06-07 [src] nnet3: fix small bug in checking code. Thanks: @maddin2000.

5.2.14 bf6ad5410 2017-06-07 [doc] Fix typo (#1669)

5.2.15 a0795ec52 2017-06-07 [scripts] Add python script to convert nnet2 to nnet3 models (#1611)

5.2.16 712c234db 2017-06-08 [scripts] Fix small bug in utils/gen_topo.pl.

5.2.17 5f680387d 2017-06-08 [build] Fix small bug in configure

5.2.18 c4dd63ac8 2017-06-08 [egs] Fix to some --proportional-shrink related example scripts (#1674)

5.2.19 7fa5f812d 2017-06-10 [src] Cosmetic fixes to usage messages

5.2.20 468c619a2 2017-06-13 [src] fix to gst-plugin/Makefile (remove -lkaldi-thread) (#1680)

5.2.21 defc8bd4e 2017-06-13 [build] when installing sequitur and mmseg, look for lib64 as well (thanks: @akshayc11) (#1677)

5.2.22 594daacc0 2017-06-13 [src] Fix bug in looped computation (#1673)

5.2.23 d46890dad 2017-06-13 [egs,scripts,src] Tune image recognition examples; minor small changes. (#1682)

5.2.24 08dbc187f 2017-06-14 [egs] CNN+TDNN+LSTM experiments on AMI (#1685)

5.2.25 ecc6a78a5 2017-06-14 [src,scripts,egs] Backstitch code+scripts, and one experiment, will add more later. (#1605)

5.2.26 9d494d250 2017-06-14 [egs] Fix failure in multilingual BABEL recipe (regenerate cmvn.scp) (#1686)

5.2.27 4d7ec0134 2017-06-15 [src] Fix to multiple-fst case of latgen-faster-mapped-parallel (memory bug) (#1688)

5.2.28 16b9918f3 2017-06-16 [egs] Rename files with Windows-incompatible names (#1690)

5.2.29 d76f088a0 2017-06-16 [src] nnet3 model-collapsing code, for slight decoding speedup (#1671)

5.2.30 20fe876fe 2017-06-19 [egs] babel recipe: check if icu4c is installed (#1697)

5.2.31 f7898b417 2017-06-20 [scripts] in subsegment_data_dir.sh, warn if utt2num_frames missing, etc. (#1702)

5.2.32 0a37d3e7e 2017-06-20 [src] Adding options to MBR/confidence code (#1696)

5.2.33 6a0768aa8 2017-06-20 [src] Fix compiler warnings and work around bug on Windows (#1698)

5.2.34 2ef9f9153 2017-06-21 [src] nnet3: fix assertion that shouldn't have been there. Thanks: @vimalmanohar

5.2.35 76c31c2e3 2017-06-21 [egs] fix problems in multilingual BABEL setup (#1691)

5.2.36 1022e9bd3 2017-06-22 [src] Fix bug in fstrmymbols RE recent const-fst changes (thanks: Jon Nichols); other cosmetic changes.

5.2.37 98d2fc7c2 2017-06-22 [egs] small update to librispeech recipe, RE const-FST.

5.2.38 a4578c4d6 2017-06-22 [egs] Adding hub4-ne broadcast spanish recipe (#1665)

5.2.39 b82b82f78 2017-06-23 [build] Update README.md / fix ci badge (#1709)

5.2.40 acb5439bf 2017-06-24 [egs,scripts]: replace non-portable read-link -f with utils/make_absolute.sh (#1694)

5.2.41 a75fb1be0 2017-06-26 [build] IRSTLM build: resolve problems with compilers by patching configure.ac (#1713)

5.2.42 456fec60f 2017-06-27 [egs] improve TDNN model in tedlium example (fewer jobs, proportinal-shrink 20) (#1715)

5.2.43 0d62760e6 2017-06-27 [build] update tools/extras/install_speex.sh to address #1718 (#1719)

5.2.44 6ae3111a1 2017-06-27 [scripts] Quote '{' in perl regexp (#1721)

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

5.2.46 c12c1b807 2017-06-27 [scripts] run.pl: Default concurrent jobs to number of GPUs (#1723)

5.2.47 2d011df4a 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 f6f784bed 2017-06-28 [src] Fix bug in lattice string-pushing, affecting lattice-push (#1724)

5.2.49 3505e86be 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 16f39dedc 2017-06-29 [scripts] bug-fix in nnet3 scripts: change type of max_lda_jobs to int (#1728)

5.2.51 29c81102d 2017-06-30 [src] Bug-fix in model-collapsing code (thanks: aarora8)

5.2.52 2a0781897 2017-07-03 [src] Make sure softmax-related functions can work in-place. (#1729)

5.2.53 cac072dfa 2017-07-03 [egs] Add updated TDNN+BLSTM scripts for swbd/s5c, with dropout etc. (#1730)

5.2.54 abf898f42 2017-07-06 [src] remove remap-leaves.h (thanks: @kkm000)

5.2.55 28c613966 2017-07-07 [egs] APIAI example: model downloads links changed (#1747)

5.2.56 39c6ddede 2017-07-08 [egs] Update Librispeech nnet3 TDNN recipe (old one did not run) (#1727)

5.2.57 12ad1f63c 2017-07-09 [build] Add configuration check for incompatible g++ compilers when CUDA is enabled. (#1749)

5.2.58 97922a856 2017-07-09 [egs] Small fix to ami/s5b/local/chain/compare_wer_general.sh (#1751)

5.2.59 1644b5bb2 2017-07-11 [egs] some small updates to scripts (installing beamformit; segmentation example)

5.2.60 113e2a719 2017-07-11 [src] Fix usage message of program (thanks:jubang0219@gmail.com)

5.2.61 6aa5ed177 2017-07-11 [src] Fix indexing error in nnet1::Convolutional2DComponent (#1755)

5.2.62 b813b9d79 2017-07-11 [scripts] Fix bug in segment_long_utterances.sh (#1758)

5.2.63 a234281c7 2017-07-11 [egs] swbd/s5c, added 5 layer (b)lstm recipes (#1759)

5.2.64 40620fca8 2017-07-14 [src] Change name of option --norm-mean->--norm-means for consistency, thanks: 415198468@qq.com

5.2.65 2fbf2df59 2017-07-14 [src] Add support for row/column ranges when reading GeneralMatrix (#1761)

5.2.66 42c059625 2017-07-16 [scripts] minor bugfix to nnet1 alignment script when creating lattices (#1764)

5.2.67 b2fc6c4ee 2017-07-16 [scripts] For nnet3 training, add option to disable the model-combination (#1757)

5.2.68 6937b98cf 2017-07-16 [src] Change to arpa-reading code to accept blank lines with whitespace (#1752)

5.2.69 aedc2fe6f 2017-07-17 [egs] Add recipe for aishell data (free Mandarin corpus, 170 hours total) (#1742)

5.2.70 c794d5584 2017-07-19 [egs] Fixes to the aishell (Mandarin) recipe (#1770)

5.2.71 98bbe11b0 2017-07-19 [egs] Update AMI chain experiments RE dropout, decay-time and proportional-shrink (#1732)

5.2.72 47f8057b7 2017-07-21 [egs] update hkust results (#1772)

5.2.73 2c51a3ff1 2017-07-21 [egs] Graphemic lexicon updates / fixes in babel/s5d recipe and hub4_spanish recipe (#1740)

5.2.74 5c3c142b6 2017-07-23 [egs] Add missing make_corpus_subset.sh in babel_multilang example (#1766)

5.2.75 dbdd284f6 2017-07-24 [scripts] Fix convert_nnet2_to_nnet3.py (#1774)

5.2.76 1fef98995 2017-07-26 [src] make dithering in feature processing more efficient by using random state, thanks: liximin244@gmail.com

5.2.77 d79e1c0e4 2017-07-26 [scripts] update nnet3 scripts to fix bug where rejecting 'bad' models was not happening (#1777)

5.2.78 caaf6fab2 2017-07-31 [tools] adding phonetisaurus install scripts (PR#1734)

5.2.79 af4b687a5 2017-07-31 [src] Circumvent Visual Studio 2017 bug regarding name resolution (#1783)

5.2.80 ff2ad5012 2017-08-02 [egs] update multi_condition script in swbd (#1788)

5.2.81 35faa4d83 2017-08-03 [src,egs,scripts] Cosmetic and other minor fixes, some required for segmentation PR (#1784)

5.2.82 c4a73526b 2017-08-04 [egs] fix bugs in Multi-database English LVCSR recipe (#1785)

5.2.83 3f61293f2 2017-08-04 [egs] Update tedlium and aspire recipes to use xconfigs (avoid crash) (#1790)

5.2.84 e0a82e424 2017-08-05 [egs] Fix bug RE xent_regularize in Aspire chain recipes. (#1797)

5.2.85 5e91c5d2e 2017-08-07 [src] Cosmetic fix to usage message (#1800)

5.2.86 53e5e1221 2017-08-08 [egs] Add chain recipe for Fisher English (#1803)

5.2.87 4d27debb7 2017-08-09 [src] Fix bug in model-update consolidation code (thanks: sriram ganapathy).

5.2.88 4a0106a75 2017-08-09 [src] Small test-code fix

5.2.89 cc2469e86 2017-08-09 [src] modify feature-extraction binaries to support downsampling (#1773)

5.2.90 c216b5403 2017-08-10 [scripts] reverting the recent change of perturb_data_dir_speed_3way.sh (#1809)

5.2.91 1a508c3a1 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 8e269d04c 2017-08-11 [build,scripts] Fix to fast-lstm xconfig layer which was not functional; cosmetic change to 'configure'.

5.2.93 aaf680e55 2017-08-11 [src,scripts,egs,build] Enable RNNLM lattice rescoring with Tensorflow (#1741)

5.2.94 d117a6422 2017-08-12 [scripts] Documentation fix in xconfig scripts

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

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

5.2.97 12fa929fc 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 5846a2d13 2017-08-15 [src] Inconsequential bug-fixes to problems found when compiling with -DKALDI_PARANOID

5.2.99 eaebe0893 2017-08-15 [build] Enable Travis cache for faster Travis builds, avoiding timeouts (#1819)

5.2.100 6c6d1dd42 2017-08-17 [build] Change to compilation flags for Sequitur on Mac (#1716)

5.2.101 87b55e10c 2017-08-17 [scripts,egs] fixed issues in multilingual training with --use-ivector option (#1828)

5.2.102 3b185c715 2017-08-17 [build] remove debug print (fixes some of the travis builds failures) (#1827)

5.2.103 4816ee5f2 2017-08-18 [scripts] fix lmrescore_rnnlm_lat.sh: fstproject doesn't work on const-arpa FST (#1830)

5.2.104 91d47c1dc 2017-08-20 [doc] Fix typos (#1833)

5.2.105 92dad5b65 2017-08-21 [doc] Add some terms to glossary

5.2.106 0e5bb81e2 2017-08-21 [scripts,egs] Nnet3 segmentation using labels from ASR (#1676)

5.2.107 6d885ee2c 2017-08-23 [scripts] Adding Swbd speech activity detection scripts missing from #1676 (#1838)

5.2.108 e89280576 2017-08-23 [egs] add swbd/s5c/conf/mfcc_hires_bp.conf missing from local/run_asr_segmentation.sh (#1841)

5.2.109 e8636e910 2017-08-24 [src] fix #include directive in compressed-matrix.h, include subfolder. #1842 (#1843)

5.2.110 d234b076a 2017-08-24 [egs] Note small bug in AMI run.sh, thanks @akreal

5.2.111 1d1373130 2017-08-24 [scripts] fixes to nnet3-based segmentation scripts (#1844)

5.2.112 e5a48fc0e 2017-08-25 [src] fixed copy-constructor bug RE test_mode option for DropoutComponent (#1845)

5.2.113 ce6b342d5 2017-08-25 [scripts,src,egs] simplify by removing --leftmost-questions-truncate option (#1840)

5.2.114 09554c614 2017-08-28 [egs] Aspire example scripts: Update autoencoder example to xconfig (#1847)

5.2.115 4af4f3699 2017-08-28 [src] Remove repeated parameter documentation. (#1849)

5.2.116 7246f2cb9 2017-08-29 [scripts] bug-fix in TFRNNLM rescoring script (no 'ark' needed for unk.probs file) (#1851)

5.2.117 bca082ed9 2017-08-29 [egs] Update to score.sh in fisher_swbd setup, allow --iter option (#1853)

5.2.118 d8e42b07d 2017-08-29 [src] Typo fixes in documenation. (#1857)

5.2.119 355f4e169 2017-08-30 [src] Adding documentation for lattice discriminative training functions (#1854)

5.2.120 807dc486c 2017-08-30 [scripts] Add --decode-extra-opts in steps/decode.sh (required for speech activity detection scripts) (#1859)

5.2.121 018e79edb 2017-08-31 [doc] Fix to how documentation is built (thanks: David van Leeuwen)

5.2.122 683e3b565 2017-09-01 [scripts] Fix default for egs.cmd in nnet3 training scripts (#1865)

5.2.123 8c792f0cb 2017-09-01 Remove memory leaks and unused variables (when CUDA is not enabled) (#1866)

5.2.124 0a8fdbfa5 2017-09-05 [build] Cosmetic fix in Makefile

5.2.125 707483088 2017-09-05 [egs] Fixed some issues in the multilingual BABEL example scripts (#1850)

5.2.126 f4a6a664f 2017-09-08 [scripts] Bug-fix in long-utterance-segmentation script (thanks: Armin Oliya) (#1877)

5.2.127 134cf7ee5 2017-09-08 [doc] Keep tutorial code up to date (thanks: Luwei Yang)

5.2.128 26e8b5616 2017-09-11 [scripts] A cosmetic change to info messages in chain training (#1880)

5.2.129 8ad898c2b 2017-09-12 [build] dependency-check: that python2.7 and python3 exist and 2.7 is default (#1876)

5.2.130 ca871fb25 2017-09-13 [egs] Fix inconseqential input-checking bug in Swbd example script (#1886)

5.2.131 1771a2543 2017-09-15 [src] Fix bug in block matrix addition (thanks: Sidhi Adkoli).

5.2.132 d1016d8df 2017-09-15 [src,scripts,egs] Attention modeling, with example scripts (#1731)

5.2.133 82686ee6b 2017-09-15 [src,scripts,egs] Transfer learning for ASR with nnet3 (#1633)

5.2.134 cddb72ce0 2017-09-17 [doc] Fix typo in the About page (#1890)

5.2.135 ecd48ca7f 2017-09-17 [build] Updates related to refactoring of the phonetisaurus build system. (#1891)

5.2.136 633310c0d 2017-09-22 [src] Fix CU_SAFE_CALL wrapper so it correctly prints CuBLAS error codes (#1900)

5.2.137 13e3a0be2 2017-09-22 [src,scripts] Remove some unused code and scripts (#1904)

5.2.138 9a6e1c070 2017-09-22 [egs,scripts] For scoring analysis scripts, guess if it's utf-8 compatible stream or not (#1903)

5.2.139 d4bb00a9b 2017-09-25 [egs] Speaker recognition scripts for FAME! Speech Corpus (#1897)

5.2.140 69e3c49de 2017-09-26 [build] Remove invalid dependency in Makefile (thanks: @qzfnihao)

5.2.141 b5d7d41e8 2017-09-26 [scripts] small fix for utils/dict_dir_add_pronprobs.sh (#1912)

5.2.142 b0cc15790 2017-09-26 [scripts] Change hostname -d to hostname -f for mac compatibility.

5.2.143 906006f5a 2017-09-27 [scripts] Fixes to data-cleanup scripts (#1902)

5.2.144 ba00b18c2 2017-09-27 [build] make configure script allow cuda 9.0 (#1916)

5.2.145 6cab750e8 2017-09-28 Modify data-validation script and dictionary-validation script to disallow exotic space characters (#1910)

5.2.146 fad21abdf 2017-09-28 [build] remove obsolete arch from cuda gencode (#1919)

5.2.147 87107ed4c 2017-10-03 [egs] fix run_ivector_common.sh in some setups to use data/lang not data/lang_nosp (#1921)

5.2.148 f348b26c1 2017-10-03 [build] Fix TensorFlow installation issues (#1920)

5.2.149 e082c17d4 2017-10-03 [src,scripts,egs] Xvectors: DNN Embeddings for Speaker Recognition (#1896)

5.2.150 0f2df8014 2017-10-04 [egs] Updating WSJ TDNN example to use batchnorm instead of renorm.

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

5.2.152 98757696e 2017-10-09 [scripts] Minor fix to nnet3 training scripts RE log parsing/time-reporting (#1926)

5.2.153 5fbdc666d 2017-10-10 [scripts] Fixing OS X compatibility issue for tabs with sed. (#1928)

5.2.154 971fe628c 2017-10-11 [egs] Replace Zenkaku-Space to Zenkaku-Underscore in CSJ recipe (#1931)

5.2.155 8bb27a921 2017-10-11 [src] Loosen a threshold in the derivative test to make it pass (#1936)

5.2.156 7ed731112 2017-10-11 [scripts] Replace sed commands using \t and \n for OS X compatiblity (#1935)

5.2.157 e3f2e0ca7 2017-10-11 [egs] minor script fix; remove unused variable (#1933)

5.2.158 fe6f86b06 2017-10-11 [egs] In csj setup, use KALDI_ROOT instead of ../../.. (#1932)

5.2.159 e3fb7c4a0 2017-10-11 [egs] Small fixes to egs/sre16/ and egs/bn_music_speech dataprep, link to pretrained models (#1934)

5.2.160 696696b6f 2017-10-13 [scripts] Fix small script typo (cleanup-related); thanks, @francoishernandez.

5.2.161 510428f86 2017-10-13 [egs] Adding new non-splicing layers in some TDNN setups. (#1937)

5.2.162 9e37c5178 2017-10-16 [src,egs] Minor tweaks in nnet3 code (diagnostics,testing); add stage option to swbd setup.

5.2.163 63774a542 2017-10-17 [scripts,egs] Use KALDI_ROOT instead of relative path (#1941)

5.2.164 167c2b904 2017-10-17 [doc] Fix path in kaldi for dummies (thanks: Ermand Hoxha)

5.2.165 fa6bee362 2017-10-19 [egs] Librispeech: make sure phone list is sorted, for repeatability (#1946)

5.2.166 20f81b5dc 2017-10-19 [egs] Adding new non-splicing layers in the AMI TDNN setup (#1947)

5.2.167 c96fb5d5e 2017-10-19 [scripts] Add new tuning option for speech activity detection (SAD) scripts (#1949)

5.2.168 e4952cfe4 2017-10-19 [egs] Fixed a missing xconfig change of the tdnn recipe in the previous commit (#1948)

5.2.169 020c50089 2017-10-19 [scripts] Simplify and remove non-useful diagnostics in nnet3 training scripts

5.2.170 edb1aae94 2017-10-20 [egs,scripts] Disambiguate cmd.sh and path.sh pathnames: add './' (#1953)

5.2.171 3c7f0ddb2 2017-10-21 [egs] fix to scoring script error in HKUST recipe (#1957)

5.2.172 f89ffeb6b 2017-10-22 [src,scripts,egs] Make it possible to specify component-level l2 regularization (#1959)

5.2.173 4006d9466 2017-10-23 [egs] Updates to Chime4 recipe (#1956)

5.2.174 582993a43 2017-10-24 [scripts] Small fix to nnet3 training scripts: pass egs_command to get_egs.sh (#1970)

5.2.175 de247358d 2017-10-24 [egs,scripts] Add support for l2-regularize to LSTM layers; give example.

5.2.176 e8e86ae0d 2017-10-24 [egs] Small egs fixes to HKUST and sre10 (#1958)

5.2.177 d38b5c5bb 2017-10-25 [egs] Further small HKUST and SRE fixes (#1971)

5.2.178 fb3778740 2017-10-25 [build] Make nvcc respect CXX (#1965)

5.2.179 34c3e2ca5 2017-10-25 [src,scripts] nnet1: various minor changes, (#1962)

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

5.2.181 ddf71be1f 2017-10-27 [build] Remove download of ATLAS header files from tools/. (#1974)

5.2.182 81bd30a28 2017-10-27 [egs] Small fix to Chime4 RE data location (#1966)

5.2.183 9d7247bd3 2017-10-29 [egs] Add example of component-level l2-regularize for WSJ scripts

5.2.184 323100178 2017-10-29 [src] Minor fix: change to error message (#1980)

5.2.185 13333d1cc 2017-11-01 [scripts] Fixes to segment_long_utterances.sh (thanks @christophfeinauer) and train_raw_dnn.py (#1993)

5.2.186 0b818c442 2017-11-02 [egs] Remove deprecated non-working scripts

5.2.187 3ea534070 2017-11-02 [egs] Minor fixes to the SRE16 v2 recipe (#1986)

5.2.188 148c884b7 2017-11-02 [egs] rotation for image augmentation in CIFAR example (#1955)

5.2.189 c0c213f4d 2017-11-03 [src,scripts] nnet1-related changes: (#1998)

5.2.190 38296ad2f 2017-11-04 [egs] fisher_callhome_spanish: updated phonetic transcription and scoring; other fixes (#1992)

5.2.191 978e38ee9 2017-11-06 [scripts] Fix edge cases (#1994,#1991) in data-cleanup scripts (#1997)

5.2.192 e003f2925 2017-11-07 [egs] Small fix to tedlium score_basic.sh (which is not used by default), thanks @danoneata

5.2.193 b01b5b41a 2017-11-07 [src] Fix to nnet training to print multiple objfs in deterministic order (and print all of them) (#2001)

5.2.194 d3dd54553 2017-11-07 [egs] Updating multi_en recipe's data selection, training procedure and lexicon preparation,.etc (#1893)

5.2.195 221664ea4 2017-11-08 [build] Tighten .gitignore exclude rules to ignore dot files in /src/*/ (#2004)

5.2.196 26be81eed 2017-11-09 [egs,src] Some inconsequential fixes (#2007)

5.2.197 8569f8df3 2017-11-09 [egs] BABEL scripts: new config files, and config-file generator script (#2006)

5.2.198 061d12682 2017-11-09 [scripts,egs] Convert tab->space, and indent correctly (#2008)

5.2.199 05b2aed18 2017-11-10 [egs] cleanup of BABEL scripts (#2011)

5.2.200 b952cf33a 2017-11-10 [scripts] Documentation fixes. Thanks: Rongjin Li.

5.2.201 640a8e3a1 2017-11-13 [egs] Update soft link run_tdnn.sh in WSJ example

5.2.202 ac8adf2cd 2017-11-13 [egs] minor fixes to multi_en recipe (#2013)

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

5.2.204 1d66675e0 2017-11-14 [egs] Babel cleanup + updated to ivector training with pca-transform (#2016)

5.2.205 0884818d2 2017-11-15 [src] nnet1: adding 'multitask' loss to 'nnet-train-perutt', (#2017)

5.2.206 f19e94c21 2017-11-18 [scripts,doc] Add check for tilde in wav.scp (thanks: tessfu geteye); update queue documentation.

5.2.207 9e7644cac 2017-11-19 [src] Minor fix: useless decoder declaration removed (#2020)

5.2.208 9b86ff225 2017-11-20 [egs] new BABEL DNN training recipes (#2021)

5.2.209 d508904e8 2017-11-20 [build] add mmseg to .gitignore (#2024)

5.2.210 54749fd07 2017-11-20 [scripts] fail when the directory does not have the right files (#2023)

5.2.211 daeac30bb 2017-11-21 [src] Fix KaldiMatrix::Resize silent failure when resize_type == kCopyData (#2025)

5.2.212 23586f5f7 2017-11-21 [build,src] Increase OpenFst version from 1.6.2 to 1.6.5 (#2026)

5.2.213 d66906dbb 2017-11-21 [scripts] minor fix: make ivector id checking more robust (#2028)

5.2.214 9c877df42 2017-11-21 [egs] babel: fix the lithuanian pitch accent handling (#2029)

5.2.215 2f90f8155 2017-11-22 [build] Update Windows installation (#2032)

5.2.216 5e7deb91a 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 components.

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

5.3.0 db2865034 2017-11-23 Kaldi 5.3 (includes nnet3-based RNNLM setup) (#1693)

5.3.1 39c8d141b 2017-11-24 [scripts,egs] replace all instance of "gensub" with gsub or sub for compatibility (#2036)

5.3.2 0ba0b124c 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)

5.3.3 e96eec1f6 2017-11-26 [src] nnet2: nnet-am-compute, adding option --divide-by-priors (default=false) (#2041)

5.3.4 1f5d747fe 2017-11-27 [build,src] Increase configure version (and add functions to CuVector) (#2042)

5.3.5 bafb68c17 2017-11-27 [src] Fix to run_lstm.sh in swbd/s5c setup: mdeish@gmail.com

5.3.6 9effa4a1e 2017-11-27 [src] add max_warnining option to SlidingWindowCmnOptions to limit the number of times the variance flooring warning is printed (#2043)

5.3.7 92c99ee51 2017-11-27 [egs] Modify some storage paths for striped data (#2038)

5.3.8 6d6e7a908 2017-11-27 [src] Various nnet3 changes, see PR for details (#2031)

5.3.9 acca2ac6d 2017-11-27 [src] Fixes/improvements in error path of TokenHolder code (#2044)

5.3.10 783ad7b26 2017-11-29 [egs] babel: remove some files no longer used (#2048)

5.3.11 35288fae9 2017-11-29 [src] Mostly cosmetic changes in error handling (#2047)

5.3.12 fbef11bb2 2017-11-29 [egs] replaced proportional-shrink with l2-regularize in the latest ami tdnn and tdnn-lstm recipes (#2045)

5.3.13 7a8f47100 2017-11-29 [src,egs,scripts] removed extract-rows, create-split-from-vad and some long-unused scripts (#2049)

5.3.14 e9abbff99 2017-11-29 [src] Fixing comments for BatchNormComponent (#2050)

5.3.15 f14e08369 2017-11-30 [build] fix TF compilation issues; fix version of TF to avoid future issues (#2052)

5.3.16 fd5e33608 2017-12-01 [src] Fix "warning: enumeration value ‘CUSPARSE_STATUS_ZERO_PIVOT’ not handled in switch [-Wswitch]" (#2054)

5.3.17 77ae8fe02 2017-12-02 [src] Bug-fix to conceptual bug in Minimum Bayes Risk/sausage code. Thanks:@jtrmal (#2056)

5.3.18 85fa84c91 2017-12-02 [scripts] Adding --num-threads option to ivector extraction scripts; script fixes (#2055)

5.3.19 a3441c243 2017-12-03 [src] Fix some small typos (#2060)

5.3.20 72dfed026 2017-12-04 [scripts] Fix bug in slurm.pl affecting log format (#2063)

5.3.21 93ceca700 2017-12-04 [egs] Add recipe for Mozilla Common Voice corpus v1 (#2057)

5.3.22 8bc989982 2017-12-04 [doc] Add documentation about matrix row and column ranges in scp files.

5.3.23 cd6562753 2017-12-04 [scripts,egs] Convert ". path.sh" to ". ./path.sh" (#2061)

5.3.24 c9481387a 2017-12-04 [egs] Update to CSJ example scripts, with chain+TDNN recipes. Thanks: @rickychanhoyin (#2035)

5.3.25 8cc5c8b32 2017-12-05 [src] Fix compilation error on MSVC: missing include. (#2064)

5.3.26 87783fc4e 2017-12-08 [src] Small fix RE CuSparse error code printing (#2070)

5.3.27 41806f648 2017-12-09 [src,egs] Small cosmetic fixes (#2074)

5.3.28 cc7c2f6d7 2017-12-10 [egs] Add a tdnn+lstm+attention+backstitch recipe for tedlium (#1982)

5.3.29 f51f8ca25 2017-12-11 [src] Bug-fix to assertion in cu-sparse-matrix.cc (RE large matrices) (#2077)

5.3.30 f5409927e 2017-12-11 [egs] Add an l2-regularize-based recipe for image recognition setups (#2066)

5.3.31 4e3c1832a 2017-12-12 [egs,scripts] Add OPGRU scripts and recipes (#1950)

5.3.32 5799dae14 2017-12-13 [scripts] Fix augment_data_dir.py (relates to non-pipe case of wav.scp) (#2081)

5.3.33 eaa6a26a2 2017-12-13 [egs] Small fix to backstitch in AMI scripts (#2083)

5.3.34 23e046398 2017-12-14 [egs] Copy dictionary-preparation-script fix from fisher-english(8e7793f) to fisher-swbd and ami (#2084)

5.3.35 e587c15af 2017-12-15 [egs] Mac compatibility fix to SGMM+MMI: remove -T option to cp (#2087)

5.3.36 2ec515d78 2017-12-16 [src] Fix bug in nnet3 optimization, affecting Scale() operation; cosmetic fixes. (#2088)

5.3.37 e7fe053f8 2017-12-19 [scripts,egs] Some fixes to OPGRU scripts from Lu Huang (#2091)

5.3.38 04458f7a2 2017-12-20 [src,egs,scripts] Merging RNNLM-related changes which were in wrong branch (#2092)

5.3.39 a3b3bfaf6 2017-12-21 [src] Prevent RNNLM training from exhausting GPU memory in diagnostic jobs (#2094)

5.3.40 f61224fa7 2017-12-21 [src] Fix bug in compilation with Scale() expressions. (#2098)

5.3.41 81b7a1947 2017-12-21 [egs] Fix to decode context option in swbd (#2100)

5.3.42 3c21ef23f 2017-12-22 [doc] Fix typo in docs (#2101)

5.3.43 d46ff7e82 2017-12-26 [src] Ensure num-tree-leaves is a multiple of 8 (RE NVidia Volta architecture) (#2097)

5.3.44 48656c314 2017-12-26 Revert "[src] Ensure num-tree-leaves is a multiple of 8 (RE NVidia Volta architecture) (#2097)" (#2105)

5.3.45 a5561c3cf 2017-12-26 [src,scripts] Simplify model combination: do simple average over last n models (#2067)

5.3.46 2b3acc585 2017-12-27 [scripts] Cosmetic change to validate_data_dir.sh

5.3.47 843bc207b 2017-12-28 [egs] Add TDNN recipes (and other changes) for chime4 (#2012)

5.3.48 0b4ea277f 2017-12-28 [src] Dropout and batchnorm fixes for discriminative training (#2109)

5.3.49 df7a41978 2017-12-28 [scripts] Fix validation-script bugs found by Somogyi Z; make validate_text.pl quieter.

5.3.50 47ea76bd1 2017-12-28 [egs] Update swbd/s5c RNNLM setup with hesitation mapping, and perplexities (#2108)

5.3.51 84f9b86a2 2017-12-28 [egs] fisher_swbd chain script bug fix (thanks: Filip Jurcicek) (#2110)

5.3.52 12706348f 2017-12-29 [egs,src] Fix cleanup script bug (thanks: CW Huang), clarify comment.

5.3.53 9ac5dd4ef 2017-12-31 [src] Make faster ApplyFloor and ApplyCeiling variants for Matrix and CuMatrix. (#2115)

5.3.54 006e3c8cc 2017-12-31 [scripts] Fig bug in validate_data_dir.sh introduced in df7a41978f2. Thx:@jcsilva

5.3.55 1431db17e 2017-12-31 [scripts] Fix lattice_oracle_align.sh bug (Thx: @roman-verbit-ai)

5.3.56 c08a1c197 2018-01-01 [build] Add new search dir for ATLAS (Thx: Sari Sultan)

5.3.57 6f9fab72f 2018-01-02 [scripts] Fix script issue affecting some xvector training (thanks: daniel garcia-romero)

5.3.58 b808365a6 2018-01-03 [egs] Improve comments for fisher_swbd tdnn_lstm_1a (#2122)

5.3.59 8292e4cbd 2018-01-04 [egs] Add OCR/Handwriting Recognition examples (#1984)

5.3.60 33db55aeb 2018-01-04 [egs] swbd/s5c: Add RNNLM setup for where Fisher text data not there. (#2118)

5.3.61 36df91d35 2018-01-05 [src] Round number of leaves to multiple of 8, will be faster with Volta architectures (#2106)

5.3.62 40a7d70d0 2018-01-06 [src] test-code change for speedup (#2128)

5.3.63 42767abec 2018-01-06 [scripts] Script fix in RNNLM setup; cosmetic change.

5.3.64 fd9284ac4 2018-01-07 [scripts] Add support for grayscale images to matrix_to_image.py (#2131)

5.3.65 e7ddb06b2 2018-01-07 [egs,scripts] source cmd.sh in RNNLM setups; rename some RNNLM setups; script fix (#2132)

5.3.66 33b0de92c 2018-01-07 [src,scripts,egs] Add n-best rescoring for Kaldi-RNNLM (#2120)

5.3.67 a0b71317d 2018-01-09 [src] Change matrix/ include structure to avoid leaking global symbols like 'real' (#2127)

5.3.68 360c96ca4 2018-01-10 [src] Temporary patch for build-tree assertaon failure.

5.3.69 e7e488edc 2018-01-10 [egs] updating fisher_swbd nnet3/chain scripts: removing non-chain examples (#2136)

5.3.70 da18a45b6 2018-01-10 [src] Fix bug in rounding num-leaves (#2145)

5.3.71 116a948a3 2018-01-10 [build] Avoid problems when installing pocolm/irstlm a 2nd time (#2144)

5.3.72 e1ead787a 2018-01-10 [scripts] Cosmetic typo fix (#2143)

5.3.73 65b856f73 2018-01-11 [egs] Add Spanish recipe based on Heroico corpus (#1882)

5.3.74 6fb73b024 2018-01-12 [scripts] Extend num-digits in get_uniform_subsegments.py.. avoid crash on long utts (#2148)

5.3.75 5a8b4a605 2018-01-12 [build] update configure and android_openblas.mk for the latest ndk in android. (#2124)

5.3.76 26df3d818 2018-01-12 [src] Bug-fix in nnet3 compilation, RE Scale() expressions

5.3.77 1fb7fd92e 2018-01-15 [scripts] OS X compatibility fix to utils/format_lm.sh, thx: @johnhosephmorgan

5.3.78 d883e305f 2018-01-15 [build] set 'rpath' for ATLAS shared libraries, (#2153)

5.3.79 9e6dbab70 2018-01-17 [egs] ami, changing path for storing downloaded wavs, (#2154)

5.3.80 26b0746f0 2018-01-17 [src,scripts,egs] ivector-based diarization recipe for CallHome (#1894)

5.3.81 829b013db 2018-01-17 [egs] Update to CSJ example: fixed typo and updated to use xconfig (#2160)

5.3.82 687d31366 2018-01-18 [src] Fix bug when compiling with flag -DNDEBUG (#2162)

5.3.83 c739ff95b 2018-01-19 [egs] Minor fix in Farsdat recipe RE sctk path (#2164)

5.3.84 85a2c60e3 2018-01-20 [src] Print informative error if num-ceps >= num-mel-bins in MFCC (#2166)

5.3.85 35950ea24 2018-01-21 [egs] add speaker recognition recipe for aishell (#2111)

5.3.86 d6391f864 2018-01-22 [scripts,egs] Fix bug in slurm.pl (thx:@kamo-naoyuki), remove outdated results.

5.3.87 96cbdd697 2018-01-22 [egs] Update chain results and add new scripts for fisher_swbd (related to #2136) (#2173)

5.3.88 8596bbf54 2018-01-23 [egs] removing broken link in babel multilang setup (#2177)

5.3.89 476cb3f6b 2018-01-23 [egs] fixes for the IAM example (#2176)

5.3.90 b73bb12e4 2018-01-23 [egs] Make sure scoring opts are passed to score_cer.sh in UW3 (#2181)

5.3.91 47de14528 2018-01-23 [scripts] Fix typos in scripts (#2182)

5.3.92 2e105fc45 2018-01-23 [scripts] Fix to get_num_frames.sh for large datasets, RE truncation in awk (#2174)

5.3.93 7cf434ce1 2018-01-23 [scripts] Fix python3 compatibility bug (#2184)

5.3.94 ed84a5107 2018-01-24 [scripts] Prevent crash when input_model is None (#2188)

5.3.95 6fed4c7dd 2018-01-24 [src] Remove CuDevice destructor (avoid cuda-memcheck warnings) (#2185)

5.3.96 7ee7893f9 2018-01-24 [src] Fix nnet3 back-compatibility issue (thx: @satmass)

5.3.97 f861b00ca 2018-01-25 [src] Speed fix to online decoding (thanks: David van Leeuwen) (#2180)

5.3.98 3031e26e6 2018-01-25 [src] Optimization to decoders for speed (#2168)

5.3.99 0f14373f4 2018-01-28 [src] Work around problem related to ungetc failures on ifstream (#2194)

5.3.100 30e9a90d3 2018-01-28 [src] Small fix to component reading, workaround for ungetc() issue.

5.3.101 e4fc87d14 2018-01-30 [scripts] bugfix for 'steps/cleanup/clean_and_segment_data.sh', (#2196)

5.3.102 1647856ee 2018-01-31 [egs] Small bug-fix in Librispeech recipe (#2190)

5.3.103 2de3b3866 2018-01-31 [src] Make arpa2fst robust against ARPA files without <s>. (#2167)

5.3.104 c82560ddb 2018-02-01 [scripts] Fixed small issue get_uniform_subsegments.py (RE rounding) (#2200)

5.3.105 b4fbe00b0 2018-02-02 [egs] Add assert to check --backstitch-training-interval option (#2203) (#2204)

5.3.106 9e2d8442b 2018-02-03 [egs,scripts] Fix and simplify speed-perturbation scripts; fix permissions. (#2205)

5.3.107 79065901b 2018-02-06 [doc] remove outdated TODOs. Thx: David Van Leeuwen.

5.3.108 027f1d796 2018-02-07 [scripts] Add missing import statement in script (#2207)

5.3.109 8e170e039 2018-02-07 [egs] multi_en: Fixed acronym normalization, swbd lexicon preparation, OOV … (#2137)

5.3.110 f2ab7d403 2018-02-08 [src] Fix small bug in Log1p (thanks: Max Lvov)

5.3.111 1f1b1089c 2018-02-08 [scripts] make format_lm.sh work when source == target directory (#2209)

5.3.112 c52ee4c52 2018-02-09 [src] rnnlm-embedding-training bug fix (thanks: @yanglin187) (#2208) (#2210)

5.3.113 ca73b1f5a 2018-02-10 [scripts] Fix warning from create_data_links.pl (#2212)

5.3.114 611aa612c 2018-02-11 [scripts,egs] Fix failures in some run_ivector_common.sh script introduced in #2205 (#2213)

5.3.115 8a384379b 2018-02-11 [egs,scripts] Recipe for voice activity detection on Switchboard (#2193)

5.3.116 ca5f128f2 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)

5.3.117 5ea9b0da3 2018-02-13 [egs,scripts] HUB4 English Broadcast News recipe (#2027)

5.3.118 6d32a0bbf 2018-02-14 [src] Fix usage message, comment of ali-to-pdf (#2218)

Version 5.4

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 (TDNN-F) 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).

Some of the larger changes that were made while 5.4 was the major version number include:

  • Improvements to handwriting recognition and OCR recipes, including BPE (word-piece) encoding.
  • An updated version of the TDNN-F configuration, including ResNet-style bypass, which is now the default in many recipes. (it's called tdnnf-layer in xconfigs).
  • A rewrite of the CUDA memory allocator to be based on a small number of large regions (since with newer drivers and hardware, allocation speed was becoming a bottleneck).
  • A decoder speedup (make use of OpenFst's NumInputEpsilons() function).

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

5.4.0 be969d7ba 2018-02-17 [build] Upgrading version of Kaldi to 5.4

5.4.1 6016c004b 2018-02-17 [doc] Add documentation for 5.4 version of Kaldi

5.4.2 9b282b58c 2018-02-18 [scripts] Fix bug in steps/diagnostic/analyze_phone_length_stats.py [thanks: Vinay Sunder.]

5.4.3 09b017669 2018-02-18 [build] Update gst-plugin Makefile (#2226)

5.4.4 b61d76049 2018-02-20 [src] Fix error in how Compress() command is printed for debugging

5.4.5 6dd9c3e3f 2018-02-21 [scripts] Fix bug in steps/libs/nnet3/train/frame_level_objf/common.py (#2231)

5.4.6 e3df6ac0c 2018-02-21 [src] Print curand return codes (#2232)

5.4.7 9191f296d 2018-02-23 [egs] Fix script bug (in error-checking statement) (#2239)

5.4.8 e0d8f13e8 2018-02-23 [scripts] Fix typo (#2237)

5.4.9 4f27915e0 2018-02-23 [scripts] Fix typo in comment (#2238)

5.4.10 f629bf89a 2018-02-24 [scripts] Bug-fix in analyze_phone_length_stats.py (thanks: @stanleyguan)

5.4.11 851c5e4c6 2018-02-27 [egs] Fix to swbd chain tdnn_blstm script bug (thanks: sameer khurana)

5.4.12 7e902f535 2018-02-27 [scripts] Fix for nnet3 model combination on CPU when --use-gpu false (#2240)

5.4.13 27f6c5ed1 2018-02-28 [src] Fix small bug in cu-math.cc affecting non-GPU LSTM training, thx: Mael Primet.

5.4.14 0ebe5b59e 2018-02-28 [egs] Simplify Aspire scripts and make it work with LDC release. (#2230)

5.4.15 9a4ba5ec0 2018-02-28 [src,scripts,egs] Add form of dropout that shares the mask across frames. (#2244)

5.4.16 8b500766f 2018-02-28 [scripts] add --max-arcs option to scripts/rnnlm/lmrescore_pruned.sh (#2245)

5.4.17 c42682602 2018-03-01 [src] Fix to cu-rand.cc RE large matrix sizes. (#2249)

5.4.18 bc0fcad41 2018-03-02 [build]: Dockerfile for kaldi installation (#2246)

5.4.19 e7b3a66cb 2018-03-03 [src] Fix macro redefinition problems in tensorflow rnnlm. (#2250)

5.4.20 03b0ea831 2018-03-03 [src,scripts,egs] Enable backstich training for RNNLM; add examples (#2096)

5.4.21 03edf8248 2018-03-04 [src] Fixed bug in GeneralDropoutComponent when block-dim set (#2252)

5.4.22 0e1822d86 2018-03-04 [egs] Port factorized TDNN script to librispeech (#2233)

5.4.23 230d013b4 2018-03-05 [scripts] python3 compatibility: change / to // (#2253)

5.4.24 4518c7769 2018-03-05 [src] Fix CPU swap methods of CuVector and CuPackedMatrix (#2254)

5.4.25 25391fb66 2018-03-05 [scripts] Add example of accessing nnet3 model from python (#2255)

5.4.26 e74b918dc 2018-03-05 [src,scripts,egs] End-to-end chain training (#2072)

5.4.27 ed05f17fa 2018-03-06 [egs] thchs-30: fix Mac compatibility issue (#2258)

5.4.28 f293ccd23 2018-03-06 [build] upgrade the install_beamformit script (#2259)

5.4.29 65186851e 2018-03-07 [src] Changes to logging information printed by nnet1 (#2261)

5.4.30 9e3ce6749 2018-03-07 [scripts] Fix python3 issues w.r.t. relative imports, in steps/libs/. Thx: Cemil Demir (#2263)

5.4.31 7f028e307 2018-03-07 [egs] Adding orth-factorized-TDNN recipe for fisher_swbd (#2264)

5.4.32 c541ea017 2018-03-08 [src] Fix small bug in nnet3 component (config was lost on read).

5.4.33 b4711ada5 2018-03-08 [src] Fix small bug in nnet3 component (config was lost on read)... 2nd try.

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

5.4.35 19dc26ff8 2018-03-12 [src] bug-fixes for end2end chain code (#2270)

5.4.36 be8f4ec44 2018-03-12 [src] Fix subsampling factor in nnet3 egs (#2265)

5.4.37 5eb57ccb7 2018-03-13 [egs] Add chime5 baseline recipe (#2262)

5.4.38 6363d5520 2018-03-13 [scripts] Add delta_opts for train_mono.sh (#2221)

5.4.39 060d92aba 2018-03-14 [egs] fix generate_plots.py to plot deriv-avg and oderiv-rms (#2274)

5.4.40 f1c927c87 2018-03-14 [tools] fix beamformit installation (#2276)

5.4.41 ec98e713f 2018-03-14 [scripts] Bug-fix in convert_data_dir_to_whole.sh (thx: @olix20) (#2277)

5.4.42 b7f9446d2 2018-03-14 [egs] Add modernized vystadial_cz recipe (#2278)

5.4.43 49a90e062 2018-03-15 [src] Fix to nnet3 looped compilation bug (thanks: Alim Misbulah) (#2279)

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

5.4.45 8ab6e5395 2018-03-16 Revert "[src] Fix to nnet3 looped compilation bug (thanks: Alim Misbulah)" (#2285)

5.4.46 1644312b8 2018-03-17 [src] Add a nnet3 optimization that tries to replace commands ending in Multi with other commands. (#2229)

5.4.47 322f698a1 2018-03-17 [scripts] Fixes to segmentation scripts (#2273)

5.4.48 df9d16c6c 2018-03-18 [scripts] Add support for --use-gpu=wait to nnet3 scripts (#2289)

5.4.49 5562583a8 2018-03-18 [egs] Add improved TDNN-F example for Switchboard. (#2291)

5.4.50 d2a2909a1 2018-03-19 [src] Enable nnet3-compute to optionally subtract priors (#2294)

5.4.51 9654a7c31 2018-03-19 [build] Remove outdated compute architecture. Thx: @CodesFarmer

5.4.52 c6b3588ed 2018-03-19 [src] Fix to nnet3 compilation issue affecting BLSTMP. Thanks: Alim Misbullah (#2286)

5.4.53 eba50e442 2018-03-20 [src] Enable reading wavs produced on iPhones with extra RIFF tags. (#2293)

5.4.54 22fbdd969 2018-03-21 [egs] fixing LM issue in CHiME5 (#2298)

5.4.55 954e13cb5 2018-03-22 [src] Make ClipGradientComponent zero gradients when clipping threshold is zero (#2301)

5.4.56 dbd513c70 2018-03-22 [src] Make CachingOptimizingCompiler thread safe. Thx: Arseniy Gorin (#2288)

5.4.57 f4a5667df 2018-03-22 [src] Fix to comment

5.4.58 9ae3eb78a 2018-03-22 [src,scripts] Make cache size configurable for xvector extraction (#2290)

5.4.59 6dbe7909d 2018-03-22 [src] Speedup and code simplification for chain supervision merging (etc.) (#2302)

5.4.60 8b415fe52 2018-03-24 [egs] remove redundant step from chime5 recipe (#2306)

5.4.61 9f7e55a0a 2018-03-24 [src] Fix issue with CUDA device initialization if 'wait' specified. Thx: @olix20 (#2295)

5.4.62 e03dd12ec 2018-03-24 [scripts,egs] Fix to perturb_speed_to_allowed_lengths.py; egs fix (thanks: @calderma) (#2307)

5.4.63 cc16eecee 2018-03-26 [windows] fix for compiling on Windows VS2017 (15.5.2) (#2310)

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

5.4.65 e5b6696c0 2018-03-27 [egs] Add end-to-end OCR recipe for IAM (thanks: @aarora8) (#2311)

5.4.66 d7e889028 2018-03-27 [egs] Fix LM/lexicon issues in IAM; Add unk decoding; Update results. (#2315)

5.4.67 785198e3c 2018-03-27 [src] Add some asserts in RNNLM code (#2314)

5.4.68 749839560 2018-03-27 [src] Fix to recent commit RE RNNLM code

5.4.69 8af60bb68 2018-03-28 [src] Apply limits prior to chain denominator computation, avoid failures. (#2308)

5.4.70 5e6bd39e0 2018-03-28 [tools, extras] morfessor installation script (#2299)

5.4.71 191b39a14 2018-03-28 [src,scripts,egs] Semi-supervised training on Fisher English (#2140)

5.4.72 b620633aa 2018-03-30 [build] Updates to Sequitur installation script (for compatibility with new setuptools) (#2323)

5.4.73 e507a7aa3 2018-04-02 [src,egs,doc] Some cosmetic changes

5.4.74 6f4fafbd4 2018-04-03 [src] Bug fix: oscillating cluster threshold in agglomerative-cluster (#2333)

5.4.75 fe36823d8 2018-04-03 [src] Fix bug causing wrong learning rate in RNNLM training with --stage option (#2330)

5.4.76 831dd38cf 2018-04-03 [src] make fst templates inline to eliminate linking errors in other places (#2329)

5.4.77 7436ed690 2018-04-03 [src] Make it so no threads are used if you set num-threads to 0.

5.4.78 a9e4f7430 2018-04-04 [build] Fix some problems with sequitur installation (#2337)

5.4.79 181427856 2018-04-04 [scripts] Make sure nj in get_utt2dur.sh does not exceed num-utts. (thx: @olix20) (#2326)

5.4.80 5294666e8 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 1a1e265ae 2018-04-05 [src,build] Fix cygwin compatibility; remove unnecessary memalign macros (#2304)

5.4.82 60862b0e9 2018-04-06 [scripts] Make nnet3 logging output look more like chain logging output (#2338)

5.4.83 c2d796d82 2018-04-06 [scripts] Fix bug in chain/get_egs.sh affecting semi-supervised training (#2339)

5.4.84 c6432957f 2018-04-07 [egs] IAM script fixes using the right lang for training/lattice generation + cleaning (#2340)

5.4.85 c0c55adeb 2018-04-08 [egs] IAM: add chain recipe starting with e2e alignments and tree (#2343)

5.4.86 9b90cbac6 2018-04-09 [egs] Fix scoring issue in IAM (#2346)

5.4.87 e10c4789d 2018-04-10 [src] Revert KALDI_MEMALIGN->aligned_alloc change from #2304, fixes #2347 (#2348)

5.4.88 8a4ab19b5 2018-04-11 [src] Fix nnet3-copy-egs bug for multiling. non-chain training (thx:Joshua Meyer) (#2350)

5.4.89 ad48342ae 2018-04-11 [scripts] Bug fix in combine_egs.sh (for multilingual training) (#2351)

5.4.90 2d0cd7930 2018-04-12 [scripts] Finish removing transform_dir options from nnet3 training (thx: @pstanisl) (#2353)

5.4.91 adcabe40e 2018-04-12 [src] Fix (rare) divergence from orthogonal constraint. Thx: Sergey Tushev. (#2336)

5.4.92 ccd50e293 2018-04-12 [egs] Adding Wellington corpus for LM in IAM OCR (#2354)

5.4.93 e99de506c 2018-04-13 [scripts] Make beam configurable, +default smaller, in pruned RNNLM rescoring (#2325)

5.4.94 535df00c1 2018-04-14 [src] small fix to comment (#2357)

5.4.95 dd7caa6fb 2018-04-14 [egs] A fix to second-stage chain recipes in IAM and lang fixes in UW3 (#2358)

5.4.96 dd1640b0f 2018-04-15 [egs] Fix script bug in IAM setup

5.4.97 4abdb5b48 2018-04-15 [src] Cosmetic code fixes in mel-computations.cc (#2359)

5.4.98 5a48ad47c 2018-04-18 [scripts] Fix to get_saturation.pl, to regex bug introduced around Jan 1 2018. Affects shrinkage of recurrent nnets. (#2371)

5.4.99 8f6bb2d39 2018-04-18 [egs,scripts] Add factorized TDNN training recipe for multi-en; fix python script bug (#2369)

5.4.100 1331a35bc 2018-04-18 [egs] Make Wellington Corpus optional in iam_ocr (#2370)

5.4.101 531810032 2018-04-19 [src,egs] Fix implementation of l2-regularize with backstitch; add ami backstitch example. (#2373)

5.4.102 3040a0ac7 2018-04-20 [egs] Fix commonvoice run.sh (source utils/parse_options.sh to enable --stage). Thx:@jjm (#2375)

5.4.103 9692a61aa 2018-04-20 [src] Fix bug in matrix compression RE stride type. Thx:@LvHang (#2376)

5.4.104 6bd7ca74c 2018-04-20 [src] Decoder fix to bug affecting unusual FST types (#2377)

5.4.105 4fda1b04a 2018-04-22 [src] Comment fix to transition-model.h (#2378)

5.4.106 8ff7fd9f8 2018-04-23 [scripts] Added utils/prepare_extended_lang.sh (extending vocab of a lang-dir) and rnnlm/change_vocab.sh (changing vocab of an existing rnnlm-dir) (#2247)

5.4.107 f0333bb05 2018-04-24 [src,scripts,egs] Support for unconstrained-egs for chain training + example recipes (#2383)

5.4.108 d25b3ef94 2018-04-25 [src] Add a cast to prevent errors from some compilers (#2384)

5.4.109 156ec6c1e 2018-04-25 [egs] Semisupervised training recipes: bug fix regarding context info (#2385)

5.4.110 6a2dce879 2018-04-25 [egs] Remove accidentally committed "exit 0" in WSJ run.sh (#2386)

5.4.111 032c0263c 2018-04-26 [src,scripts] Cosmetic fixes.

5.4.112 5eaf49f57 2018-04-26 [scripts] add wordlists mismatch test for rnnlm rescoring (#2387)

5.4.113 c0ef35615 2018-04-27 [scripts] Clarify usage of diarization make_rttm.py (#2390)

5.4.114 fb54444dc 2018-04-27 [egs] Add speaker verification recipe for the VoxCeleb2 corpus (#2380)

5.4.115 bf40d6103 2018-04-29 [src] Remove un-needed code. Thanks: anand@sayint.ai. (#2393)

5.4.116 5bac98e79 2018-04-29 [egs] Update nnet3/chain scripts for HKUST example (#2368)

5.4.117 e15f3a156 2018-04-30 [scripts] Fix in steps/nnet3/get_egs.sh to avoid failure due to broken pipe (#2397)

5.4.118 1e2a0fd1a 2018-04-30 [egs] Cleanup and update results in IAM OCR scripts (#2395)

5.4.119 64025aa72 2018-05-01 [scripts] rnnlm scripts: ignore first iteration while looking for the best model (#2399)

5.4.120 6a32fbd2e 2018-05-03 [scripts] Fix path.sh bug in vad_to_segments.sh (#2402)

5.4.121 20b2a451e 2018-05-03 [src] Remove unnecessary file chain/context-dep-topology.h (#2401)

5.4.122 080129e97 2018-05-03 [src,scripts,egs] x-vectors for diarization (#2391)

5.4.123 4edec5d0f 2018-05-05 [egs,scripts,src] Add IFN/ENIT dataset Handwriting Recognition Example (#2257)

5.4.124 f9b00e901 2018-05-06 [src] Some small cosmetic changes (#2404)

5.4.125 e18191cba 2018-05-07 [egs] Fix python error by moving __future__ import to top (#2405)

5.4.126 954e69a4f 2018-05-07 [src] make e2e/"unconstrained" numerator computation faster (#2392)

5.4.127 b03b6410f 2018-05-07 [src] Speed up VectorBase<Real>::Sum() by using BLAS (#2394)

5.4.128 08b47be72 2018-05-09 [build] update dockerfile for Ubuntu and cuda (#2408)

5.4.129 90363ea38 2018-05-10 [egs] Update VoxCeleb Recipe (#2403)

5.4.130 bce433657 2018-05-14 [egs] Speeding up i-vector training in voxceleb v1 recipe (#2421)

5.4.131 ff0da26f8 2018-05-14 [scripts] Add util to compute recordings durations before data perturbation (#2414)

5.4.132 f8b678a61 2018-05-15 [scripts] Update to decode_semisup.sh (copy input model) (#2425)

5.4.133 108832dfc 2018-05-17 [egs] Madcat Arabic handwritten text line recognition (#2356)

5.4.134 2ad8d7821 2018-05-18 [egs] Minor fixes to x-vector based recipes (#2426)

5.4.135 fd12973c9 2018-05-18 [egs] update iban tdnn CE and chain recipes (#2429)

5.4.136 558f01023 2018-05-19 [scripts] Add a warning message to nnet3/align.sh about using GPUs. (#2432)

5.4.137 f31c1e93e 2018-05-21 [src,scripts] Support word insertion penalty when getting ctm (#2433)

5.4.138 264a6a3ec 2018-05-21 [scripts] Fix fix_data_dir.sh bug introduced in #2414; thanks, @Fhrozen (#2439)

5.4.139 b1be44eb2 2018-05-21 [scripts] Adding script to compute minDCF for speaker recognition (#2431)

5.4.140 1ab3df05a 2018-05-21 [egs] Madcat arabic: easier configuration of data locations; fix wer_filter. (#2440)

5.4.141 72d89cedd 2018-05-22 [egs] egs/tedlium/s5_r2 download Tedlium LMs from kaldi-asr.org (#2441)

5.4.142 182f3829e 2018-05-23 [src] Fix bug in rnnlm-sentence-probs (failure in non-debug builds) (#2445)

5.4.143 705138484 2018-05-24 [egs] Fix affix in run_tdnn_7p recipe (swbd) (#2446)

5.4.144 447e96498 2018-05-24 [egs] Add recipes for Speakers in the Wild (SITW) (#2422)

5.4.145 b1ae952fe 2018-05-24 [scripts,egs] Support averaging forward and backward RNNLMs (#2436)

5.4.146 6b94eb715 2018-05-24 [scripts] Add retry.pl, to be used when queue is flaky. (#2450)

5.4.147 e3556a075 2018-05-25 [src] Add missing 'fst::Connect() in parallel determinization; fixes issue #2448 (#2452)

5.4.148 e0311e063 2018-05-25 [scripts] Fix bug in retry.pl. (#2453)

5.4.149 9b23b17c7 2018-05-25 [egs] Fix a small bug in swbd 7p recipe (was not decoding some test sets) (#2454)

5.4.150 d6d49d09f 2018-05-26 [scripts] Apply minimum segment duration in vad_to_segments.sh (#2447)

5.4.151 7ffc9ddeb 2018-05-26 [scripts] Make retry.pl deal correctly with keyboard interrupts; make num-tries configurable. (#2456)

5.4.152 d23cad866 2018-05-29 [scripts] Allow floating-point cv_spk_percent in nnet1 scripts (#2459)

5.4.153 3f4f42567 2018-05-29 [egs] Fix TDNN example scripts to respect given train_cmd (#2460)

5.4.154 e01405181 2018-05-30 [src] Fix bug in lattice-oracle relating to wildcards in lattice output. (#2461)

5.4.155 a486fa139 2018-05-31 [scripts] Fix harmless bug in chain/get_egs.sh, thanks: teinhonglo@gmail.com (#2466)

5.4.156 9f3aa110b 2018-05-31 [scripts] Fix failure in make_bottleneck_features.sh (#2443)

5.4.157 0fb7950be 2018-05-31 [egs] Fix to paths in iban recipe (#2467)

5.4.158 fd545bbf6 2018-05-31 [egs] bug fix in egs/sitw/v2/run.sh (#2465)

5.4.159 6f5f7785e 2018-06-01 [doc] Fix I/O documentation example (#2468)

5.4.160 eef2a093a 2018-06-01 [scripts] Fix to steps/segmentation/internal/sad_to_segments.py (#2470)

5.4.161 e0e0bec3d 2018-06-01 [egs] Add TDNN+OPGRU recipe for multi-en (#2469)

5.4.162 c8db7a906 2018-06-02 [src] TopSort lattice-oracle lattice output (#2463)

5.4.163 04b1f7d66 2018-06-03 [egs,scripts] Byte-pair encoding (BPE) applied MADCAT Arabic OCR (#2434)

5.4.164 7659d8ba7 2018-06-05 [egs] Change renorm to batchnorm in BABEL recipes (#2476)

5.4.165 ce2eb3986 2018-06-05 [src,scripts] Add steps/nnet3/chain/get_phone_post.sh, to get phone posteriors from chain system (#2471)

5.4.166 b38d263cf 2018-06-06 [egs,scripts] Fix train/test data split in make_voxceleb1.pl, make speakers disjoint (#2475)

5.4.167 28e4ee6aa 2018-06-06 [scripts] Fix typo in validate_data_dir.sh causing failure if reco2dur is present(#2478)

5.4.168 5a6477bbc 2018-06-08 [scripts] Improve encoding compatibility of rnnlm dataprep (#2455)

5.4.169 e1abd8132 2018-06-08 [build,src] Upgrade OpenFst from 1.6.5->1.6.7 (#2313)

5.4.170 40757c2f2 2018-06-09 [scripts,build] ban carriage-return (\r) in lang/; suppress 'ar' warning (#2485)

5.4.171 0f954c272 2018-06-09 [build] Update supported compilers for CUDA 9.2. (#2486)

5.4.172 8fae9254f 2018-06-10 [build] Fix syntax error in configure script introduced in #2486 (#2488)

5.4.173 4571f47f8 2018-06-10 [scripts] Small bugfix in steps/cleanup/decode_segmentation.sh (#2489)

5.4.174 707baa0c3 2018-06-11 [egs] updating results in voxceleb recipe (#2494)

5.4.175 8fd2ba557 2018-06-11 [src] Make it so very wide-context nnet3 models don't cause a crash. (#2487)

5.4.176 be96725a7 2018-06-11 [scripts] Add script to limit <unk> history of ARPA files, for OOV-modeling efficiency (#2483)

5.4.177 1e4957873 2018-06-13 [build] change the build status badge location (#2497)

5.4.178 52b28821d 2018-06-13 [src] Fix mistake in comment RE FFT dimensions (#2495)

5.4.179 ca239f22d 2018-06-13 [scripts] Make inline script in extract_ivectors.sh pyton3 compatible (#2498)

5.4.180 b4eda5725 2018-06-14 [scripts] Make inline script in extract_ivectors.sh python3 compatible, 2nd fix (#2503)

5.4.181 f49b3fc6d 2018-06-14 [scripts,src] added a script to scale arcs which output <unk> in HCLG.fst; other small fixes (#2499)

5.4.182 bfd0d3c11 2018-06-15 [src] Fix compilation issue with DOUBLE_PRECISION flag (#2496) (#2505)

5.4.183 9210f3a78 2018-06-15 [src] Speed improvement in pruned lattice-rescoring algorithm (#2504)

5.4.184 d2b1c55ea 2018-06-15 [scripts] Make soft link from steps/chain to steps/nnet3/chain (#2507)

5.4.185 2fa70e3a6 2018-06-15 [scripts,egs] Minor updates to WSJ-e2e recipes and scripts (#2506)

5.4.186 f86792e51 2018-06-18 [src] Remove unused binary 'extract-rows' (#2510)

5.4.187 598b177c0 2018-06-19 [scripts] Bug fix to failure in chain/train.py when --trainer.optimization.do-final-combination=false (#2513)

5.4.188 775c770a1 2018-06-19 [src] Minor optimizations in "e2e" numerator code (#2508)

5.4.189 42a673a5e 2018-06-20 [egs] Add recipe for AIShell2 (large Mandarin database) (#2398)

5.4.190 d16ef4bb6 2018-06-20 [src] Change smart ptr copy to move sematics, avoid cost of atomic incr/decr (#2514)

5.4.191 60141df48 2018-06-25 [scripts] enable --trainer.input-model option for non-chain nnet3 training (#2515)

5.4.192 8ce3a9576 2018-06-27 [src] Make RNNLM training single threaded (workaround for CuSparse library bugs) (#2520)

5.4.193 e4908f079 2018-06-29 [build] disable -march=native in travis build (#2511)

5.4.194 7605fe550 2018-06-29 [src] lattice-copy: fix to segfault with --include,--exclude options if not sorted (#2412)

5.4.195 c1d671952 2018-07-01 [scripts] fixing bug present since #2515 in steps/nnet3/train_raw_{dnn,rnn}.py (#2527)

5.4.196 a34aefd6f 2018-07-02 [build] Fix typo in comment in src/configure (#2529)

5.4.197 8a27e86b4 2018-07-02 [src] Add a check for utterance length when creating end2end egs (#2528)

5.4.198 be7c1aacb 2018-07-03 [scripts] Output the reco2dur file in speed-perturbation script (#2531)

5.4.199 ad93210ad 2018-07-05 [egs] Fix to training list in egs/sitw{v1,v2} recipe (#2535)

5.4.200 6edf1be70 2018-07-06 [src] Fix to nnet3-chain-get-egs corner-case bug discovered by Armando Muscarellio (#2536)

5.4.201 998a4d657 2018-07-06 [egs] Some fixes and cleanup in Aishell2 scripts (#2522)

5.4.202 eacf34a85 2018-07-07 [src,scripts,egs] Updated TDNN-F recipes incorporating resnet skip connections. (#2430)

5.4.203 295877c2e 2018-07-07 [scripts] Add decoding script that combines nnet3 outputs (#2534)

5.4.204 00bc59df7 2018-07-09 [egs] added evaluation scripts to chime-5 setup (#2521)

5.4.205 147f0b552 2018-07-10 [egs] Make validate_text.pl say more specifically which lines have banned UTF.

5.4.206 09d670632 2018-07-10 [egs] Fix to Swbd script to reflect what I actually ran

5.4.207 ae4292dcf 2018-07-10 [egs] Fix bug in Chime5 eval script (#2542)

5.4.208 6f2140b03 2018-07-10 [scripts] Fix to get_reco2dur.sh (thanks: Zhangfeifan) (#2544)

5.4.209 fdb677438 2018-07-12 [egs] Add scripts for release 3 of Tedlium corpus (#2442)

5.4.210 2c1b11aab 2018-07-15 [src] Change decodable code so nnet context does not have to be recomputed. (#2549)

5.4.211 bbba5ef57 2018-07-15 [scripts] Add missing quote in vad_to_segments.sh script (#2550)

5.4.212 79883f30b 2018-07-16 [scripts] add utility script compute_sentence_probs_arpa.py to compute probs given arpa (#2538)

5.4.213 654d66b50 2018-07-17 [scripts] BSD-compatibilty fix where the "-s" option of seq is used (#2546)

5.4.214 c02977529 2018-07-18 [src] Speed up AddDiagMat2 for very thin and tall matrices (#2555)

5.4.215 a630dd292 2018-07-21 [egs] fixed a minor issue (wrong graph dir) in CommonVoice setup (#2563)

5.4.216 1d61f1cf4 2018-07-22 [src,scripts,egs] Misc small fixes, including fix to TDNN-F results in mini_librispeech (#2565)

5.4.217 8ae505ed8 2018-07-22 [scripts] Fix to scripts/rnnlm/get_num_splits.sh RE large datasets (#2567)

5.4.218 e6fe7e816 2018-07-24 [scripts] Removing has_key() for python3 compatibility (see #2570) (#2571)

5.4.219 de03a7525 2018-07-25 [scripts] Fix an issue in BPE-related scripts (don't assume opt-sil is phone 1) (#2547)

5.4.220 06604a8b8 2018-07-25 [src] Updated cuda kernel to speedup AddDiagMatMat[kTrans, kNoTrans] (#2560)

5.4.221 1616653d6 2018-07-25 [scripts] Fix to analyze_alignments/lats.sh (double-counting) (#2573)

5.4.222 97b78df49 2018-07-25 [egs] Update TDNN-F script for Librispeech (#2574)

5.4.223 5391f0038 2018-07-26 [src] Minor code-style fixes to context-dependency code (#2576)

5.4.224 d4d968c75 2018-07-26 [src] Add binary fsts-concat to concatenate Kaldi archives of FSTs (like fsts-union) (#2562)

5.4.225 b8fd2cd9d 2018-07-27 [egs] Set the acoustic scale properly when generating e2e chain alignments for OCR tasks (#2579)

5.4.226 ec71be48e 2018-07-27 [scripts] Fix typo in steps/cleanup/decode_fmllr_segmentation.sh (#2580)

5.4.227 5cc9731af 2018-07-27 [src] added configure support for cuda on arm64 (#2577) (#2578)

5.4.228 5b27111ae 2018-07-28 [egs] Cosmetic fix in aishell recipes (#2582)

5.4.229 68c926ab9 2018-07-31 [scripts] Call the right script when fixing/validating data directories in OCR … (#2587)

5.4.230 04027ee5d 2018-08-02 [src] fix embedding training bug for RNNLM without letter features (#2586)

5.4.231 287e24955 2018-08-04 [src] Make vector-compute-plda check that num-ivectors > plda-dim, and die if not (#2591)

5.4.232 532f3845a 2018-08-06 [build] Update check_dependencies.sh so lowest required GCC is 4.8.3 (#2596)

5.4.233 d10540cca 2018-08-07 [scripts] Fix to script usage message (#2601)

5.4.234 fec68b200 2018-08-07 [src] Correct usage message of acc-lda (#2598)

5.4.235 bee102286 2018-08-07 [scripts] RNNLM script fix: to accept successive spaces in configs (etc.) #2595 (#2597)

5.4.236 f40fa5c24 2018-08-07 [scripts] Slight cleanup in lmrescore_rnnlm_lat.sh (#2554)

5.4.237 8e97639b7 2018-08-07 [src] Fix Windows out-of-range iterator issue for nnet3 (#2594)

5.4.238 b4a8e9b82 2018-08-08 [src] Update Windows installation instructions (#2607)

5.4.239 a932be6e6 2018-08-09 [egs] Fix to LibriSpeech download script [affects 2nd run] (#2611)

5.4.240 c60f212c6 2018-08-09 [src] Change RNNLM test program to clean up temporary file (#2610)

5.4.241 6926b60a0 2018-08-11 [egs] Add a BPE-based recipe for IAM handwriting recognition (#2600)

5.4.242 94e561a1b 2018-08-11 [egs] Fix TEDLIUM v3 data download (#2609)

5.4.243 d60404b25 2018-08-11 [egs] Update LM in heroico recipe; fix bug in utils/lang/limit_arpa_unk_history.py (#2613)

5.4.244 7aa9da58d 2018-08-13 [src] Fix bug in PLDA scoring for diarization.. crashed or produced garbage if PCA failed. (#2590)

5.4.245 8c0e3e311 2018-08-13 [src] Refactor CUDA allocator code based on large cached regions (#2593)

5.4.246 cd27a83f1 2018-08-14 [build] Add missing dependencies to Dockerfiles (#2622)

5.4.247 2148d09f3 2018-08-14 [scripts] Usage-message fix in RNNLM tools (#2623)

5.4.248 e31776f8e 2018-08-16 [scripts] python3 compatibility fix to log_parse.py (#2626)

5.4.249 bba22b584 2018-08-17 [scripts] python3 compatibility fixes in nnet3/chain scripts (#2629)

5.4.250 c99932903 2018-08-17 [scripts] subset_data_dir.sh: preserve the comments in STM file (#2627)

5.4.251 094d22746 2018-08-18 [egs] adding missing callhome data-prep script; thx: Dharmesh Agrawal (#2631)

5.4.252 370ed555e 2018-08-20 [scripts] Fix broken pipe problem in get_egs_targets.sh, thx:@iezhanqingran (#2634)

5.4.253 34df7e20d 2018-08-21 [scripts] Another fix for broken-pipe issue in steps/nnet3/get_egs_targets.sh (#2635)

5.4.254 b55c36960 2018-08-23 [scripts] Add basis-fMLLR version of align_lats.sh

5.4.255 d8a686d7c 2018-08-23 [scripts] Add basis-fMLLR version of align_fmllr_lats.sh, for when there is no spk info (#2639)

5.4.256 ecb97273d 2018-08-23 [scripts] Small fix to retry.pl, RE array jobs. (#2640)

5.4.257 a56f9b34c 2018-08-23 [scripts] Compatibility fixes to basis-fMLLR scripts (write transforms per speaker) (#2642)

5.4.258 0642cb9e6 2018-08-23 [src,scripts,egs] Add CNN+TDNN example scripts (#2643)

5.4.259 ed74857da 2018-08-24 [scripts,src] Add cleanup/segmentation scripts based on nnet3 (#2581)

5.4.260 b1272d934 2018-08-24 [egs] Add CNN+TDNN-F example script for Swbd (#2644)

5.4.261 74029707e 2018-08-25 [egs] Madcat Chinese OCR recipe (#2312)

5.4.262 aa4862050 2018-08-25 [src] Cosmetic fix to gmm-mixup.cc, thx: lizhixuan635760758@gmail.com (#2645)

5.4.263 bd5111dd9 2018-08-27 [scripts] Fix bug RE segment end padding in clean_and_segment_data*.sh (#2651)

5.4.264 f788b9174 2018-08-28 [scripts] RNNLM fix: change encoding from latin-1 to utf-8 for choose_features.py (#2652)

5.4.265 f4e4b7713 2018-08-29 [src] Fix unit-test for CuMatrix, avoid occasional failure (#2654)

5.4.266 aa7568917 2018-08-29 [src] Set -O1 by default; change KALDI_ERR to suppress spurious warnings (#2411)

5.4.267 2816821f5 2018-08-30 [src] Remove pre-C++11 compatibility for noexcept. (#2656)

5.4.268 1242305c6 2018-08-30 [src] Decoder speedup: check NumInputEpsilons() in ProcessNonemitting() (#2641)

5.4.269 66145ea9e 2018-08-31 [egs] Zeroth-Korean: Korean open-source corpus and its script (#2296)

5.4.270 b842c776d 2018-09-01 [src] Clarify feature extraction options; make min-energy independent of BaseFloat (#2667)

5.4.271 e50bd7308 2018-09-01 [src] Fix typos from PR 2667 (#2669)

Version 5.5

Version 5.5 is the current master branch. The change that was made between the end of 5.4 and the start of 5.5 is support for Support for grammars and graphs with on-the-fly parts. grammar decoding; this allows support for things like the "contact list scenario" where you want to use a dynamically changing contact list in a larger, fixed decoding graph.

Below are commits corresponding to minor version numbers 5.5.x.

5.5.0 ed74857da 2018-08-24 [scripts,src] Add cleanup/segmentation scripts based on nnet3 (#2581)

5.5.1 7aab92b7c 2018-09-02 [build] Upgrade version to 5.5

5.5.2 1242305c6 2018-08-30 [src] Decoder speedup: check NumInputEpsilons() in ProcessNonemitting() (#2641)

5.5.3 66145ea9e 2018-08-31 [egs] Zeroth-Korean: Korean open-source corpus and its script (#2296)

5.5.4 b842c776d 2018-09-01 [src] Clarify feature extraction options; make min-energy independent of BaseFloat (#2667)

5.5.5 e50bd7308 2018-09-01 [src] Fix typos from PR 2667 (#2669)

5.5.6 1180e467c 2018-09-02 [src] Remove `ExtractWaveformRemainder` (#2672) (#2673)

5.5.7 bdcdd4722 2018-09-02 [doc] Update version documentation for version 5.5.

5.5.8 bda1dc7cf 2018-09-02 [src,scripts,egs] Grammar decoding; upgrade version to 5.5.

5.5.9 04cfc6bae 2018-09-03 removed kaldi-gpsr

5.5.10 0621b792b 2018-09-03 Fix remaining -Wmaybe-unitialized warnings.

5.5.11 8d8c5af55 2018-09-03 Fix style errors.

5.5.12 9f0db6374 2018-09-03 Two more small fixes.

5.5.13 f0a793112 2018-09-03 [src] Fix remaining warnings caused by #2411

5.5.14 c0b18b77b 2018-09-03 resolved conflicts

5.5.15 a0bc18edc 2018-09-03 [src] Remove kaldi-gpsr.{h,cc} which was not used.

5.5.16 1669d2401 2018-09-03 [egs,scripts] chime-4 advanced baseline (#2142)

5.5.17 7a5398ea0 2018-09-04 [scripts] Avoid splitting on   (appears in some UTF-8 chars) when tokenizing lexicon (#2676)

5.5.18 03355f380 2018-09-04 [scripts] Apply encoding fix of #2676 to make_lexicon_fst_silprobs.py (#2680)

5.5.19 638566bce 2018-09-04 [egs] Small fix to madcat_zh recipe (#2681)

5.5.20 7531b6bbc 2018-09-05 [egs] Fix issue in egs/csj/s5/local/csj_data_prep.sh (failure if run twice) (#2682)

5.5.21 c40205fb9 2018-09-05 [build] Allow configure script to handle package-based OpenBLAS (#2618)

5.5.22 1cd9d41f4 2018-09-05 [egs] updating local/make_voxceleb1.pl so that it works with newer versions of VoxCeleb1 (#2684)

5.5.23 72ff0cd06 2018-09-05 [egs,scripts] Remove unused --nj option from some scripts (#2679)

5.5.24 0859b4fd6 2018-09-06 [egs] Fix to tedlium v3 run.sh (rnnlm rescoring) (#2686)

5.5.25 c81f51759 2018-09-06 [scripts,egs] Tamil OCR with training data from yomdle and testing data from slam (#2621)

5.5.26 312c40e88 2018-09-07 [egs] mini_librispeech: allow relative pathnames in download_and_untar.sh (#2689)

5.5.27 7741f7c9f 2018-09-07 [egs] Updating SITW recipe to account for changes to VoxCeleb1 (#2690)

5.5.28 c8e46d15b 2018-09-11 [src] Fix nnet1 proj-lstm bug where gradient clipping not used; thx:@cbtpkzm (#2696)

5.5.29 dcf24669e 2018-09-12 [egs] Update aishell2 recipe to allow online decoding (no pitch for ivector) (#2698)

5.5.30 a06a7df32 2018-09-12 [src] Make cublas and cusparse use per-thread streams. (#2692)

5.5.31 c99a860f2 2018-09-12 [src] improve handling of low-rank covariance in ivector-compute-lda (#2693)

5.5.32 17b8f6daf 2018-09-12 [egs] Changes to IAM handwriting-recognition recipe, including BPE encoding (#2658)

5.5.33 697723aff 2018-09-13 [scripts] Make sure pitch is not included in i-vector feats, in online decoding preparation (#2699)

5.5.34 076cc4615 2018-09-13 [src] fix help message in post-to-smat (#2703)

5.5.35 6c9c00d5b 2018-09-13 [scripts] Fix to steps/cleanup/debug_lexicon.sh (#2704)

5.5.36 62a6e5e34 2018-09-14 [egs] Cosmetic and file-mode fixes in HKUST recipe (#2708)

5.5.37 0cf2e23a7 2018-09-14 [scripts] nnet1: remove the log-print of args in 'make_nnet_proto.py', thx:mythilisharan@gmail.com (#2706)

5.5.38 2cfcfda52 2018-09-15 [egs] update README in AISHELL-2 (#2710)

5.5.39 4f108fcc4 2018-09-16 [src] Make constructor of CuDevice private (#2711)

5.5.40 ab56793bf 2018-09-16 [egs] fix sorting issue in aishell v1 (#2705)

5.5.41 88f23cec0 2018-09-17 [egs] Add soft links for CNN+TDNN scripts (#2715)

5.5.42 dfb554f5b 2018-09-18 [build] Add missing packages in extras/check_dependencies.sh (#2719)

5.5.43 1f1ed0f85 2018-09-18 [egs] madcat arabic: clean scripts, tuning, use 6-gram LM (#2718)

5.5.44 9b9196b68 2018-09-19 [egs] Update WSJ run.sh: comment out outdated things, add run_tdnn.sh. (#2723)

5.5.45 69cd71704 2018-09-19 [scripts,src] Fix potential issue in scripts; minor fixes. (#2724)

5.5.46 4566a3e34 2018-09-20 [egs] add example script for RNNLM lattice rescoring for WSJ recipe (#2727)

5.5.47 ebbae44c6 2018-09-20 [egs] add rnnlm example on tedlium+lm1b; add rnnlm rescoring results (#2248)

5.5.48 acda0f437 2018-09-25 [scripts] Small fix to utils/data/convert_data_dir_to_whole.sh (RE backups) (#2735)

5.5.49 8cf8545bf 2018-09-25 [src] fix memory bug in kaldi::~LatticeFasterDecoderTpl(), (#2737)

5.5.50 0b0e5123c 2018-09-25 [egs] Remove per-utt option from nnet3/align scripts (#2717)

5.5.51 396c7790e 2018-09-25 [egs] Small Librispeech example fix, thanks: Yasasa Tennakoon. (#2738)

5.5.52 1d079fa98 2018-09-26 [egs] Aishell2 recipe: turn off jieba's new word discovery in word segmentation (#2740)

5.5.53 f1f9a485b 2018-09-26 [egs] Add missing file local/join_suffix.py in TEDLIUM s5_r3; thx:anand@sayint.ai (#2741)

5.5.54 6d919f029 2018-09-26 [egs,scripts] Add Tunisian Arabic (MSA) recipe; cosmetic fixes to pbs.pl (#2725)

5.5.55 19a1811de 2018-09-28 [scripts] Fix missing import in utils/langs/grammar/augment_words_txt.py (#2742)

5.5.56 02d462b9c 2018-10-01 [scripts] Fix build_const_arpa_lm.sh w.r.t. where <s> appears inside words (#2745)

5.5.57 1be99b664 2018-10-01 [scripts] Slight improvements to decode_score_fusion.sh usability (#2746)

5.5.58 3d3d02edf 2018-10-02 [build] update configure to support cuda 10 (#2747)

5.5.59 168789d99 2018-10-02 [scripts] Fix bug in utils/data/resample_data_dir.sh (#2749)

5.5.60 d99aa70db 2018-10-02 [scripts] Fix bug in cleanup after steps/cleanup/clean_and_segment_data*.sh (#2750)

5.5.61 23ec7a113 2018-10-02 [egs] several updates of the tunisian_msa recipe (#2752)

5.5.62 9c813cacf 2018-10-03 [egs] Small fix to Tunisian MSA TDNN script (RE train_stage) (#2757)

5.5.63 c78875a68 2018-10-04 [src,scripts] Batched nnet3 computation (#2726)

5.5.64 8b8604ca7 2018-10-04 [build] Add python3 compatibility to install scripts (#2748)

5.5.65 2d163f4df 2018-10-04 [scripts] tfrnnlm: Modify TensorFlow flag format for compatibility with recent versions (#2760)

5.5.66 e3150a2f5 2018-10-05 [egs] fix old style perl regex in egs/chime1/s5/local/chime1_prepare_data.sh (#2762)

5.5.67 ad2bb82a9 2018-10-05 [scripts] Fix bug in steps/cleanup/debug_lexicon.sh (#2763)

5.5.68 c0e34f812 2018-10-05 [egs] Add example for Yomdle Farsi OCR (#2702)

5.5.69 4c8d446f1 2018-10-05 [scripts] debug_lexicon.sh: Fix bug introduced in #2763. (#2764)

5.5.70 f279dd948 2018-10-07 [egs] add missing online cmvn config in aishell2 (#2767)

5.5.71 f91dde6dd 2018-10-07 [egs] Add CNN-TDNN-F script for Librispeech (#2744)

5.5.72 e54462e39 2018-10-07 [src] Some minor cleanup/fixes regarding CUDA memory allocation; other small fixes. (#2768)

5.5.73 a7026219e 2018-10-08 [scripts] Update reverberate_data_dir.py so that it works with python3 (#2771)

5.5.74 00c73827b 2018-10-09 [egs] Chime5: fix total number of words for WER calculation (#2772)

5.5.75 50411bd0f 2018-10-09 [egs] RNNLMs on Tedlium w/ Google 1Bword: Increase epochs, update results (#2775)

5.5.76 735e2a5aa 2018-10-09 [scripts,egs] Added phonetisaurus-based g2p scripts (#2730)

5.5.77 43ec82e3b 2018-10-09 [egs] madcat arabic: clean scripts, tuning, rescoring, text localization (#2716)

5.5.78 535bb2ced 2018-10-10 [scripts] Enhancements & minor bugfix to segmentation postprocessing (#2776)

5.5.79 8d1eb935a 2018-10-12 [src] Update gmm-decode-simple to accept ConstFst (#2787)

5.5.80 087c21ff2 2018-10-12 [scripts] Update documentation of train_raw_dnn.py (#2785)

5.5.81 a10e56e21 2018-10-12 [src] nnet3: extend what descriptors can be parsed. (#2780)

5.5.82 8b08e00f4 2018-10-12 [src] Small fix to 'fstrand' (make sure args are parsed) (#2777)

5.5.83 dc6a49688 2018-10-12 [src,scripts] Minor, mostly cosmetic updates (#2788)

5.5.84 59d1544a7 2018-10-12 [src,scripts] Add script to compare alignment directories. (#2765)

5.5.85 7e9d8cbc1 2018-10-13 [scripts] Small fixes to script usage messages, etc. (#2789)

5.5.86 fcf9b979f 2018-10-15 [egs] Update ami_download.sh after changes on Edinburgh website. (#2769)

5.5.87 024d130d4 2018-10-17 [scripts] Update compare_alignments.sh to allow different lang dirs. (#2792)

5.5.88 f5e817124 2018-10-18 [scripts] Change make_rttm.py so output is in determinstic order (#2794)

5.5.89 26680982c 2018-10-18 [egs] Fixes to yomdle_zh RE encoding direction, etc. (#2791)

5.5.90 8e30fddb3 2018-10-20 [src] Add support for context independent phones in gmm-init-biphone (for e2e) (#2779)

5.5.91 d68c00a58 2018-10-27 [egs] Simplifying multi-condition version of AMI recipe (#2800)

5.5.92 8b4a1bfa1 2018-10-30 [build] Fix openblas build for aarch64 (#2806)

5.5.93 dafeb84f4 2018-10-31 [build] Make CUDA_ARCH configurable at configure-script level (#2807)

5.5.94 030049349 2018-11-01 [src] Print maximum memory stats in CUDA allocator (#2799)

5.5.95 faa1f3cf2 2018-11-01 [src,scripts] Various minor code cleanups (#2809)

5.5.96 f70ec641c 2018-11-05 [scripts] Fix handling of UTF-8 in filenames, in wer_per_spk_details.pl (#2811)

5.5.97 4bdb05ae7 2018-11-05 [egs] Update AMI chain recipes (#2817)

5.5.98 cc745dd77 2018-11-06 [egs] Improvements to multi_en tdnn-opgru/lstm recipes (#2824)

5.5.99 ec7e59276 2018-11-07 [scripts] Fix initial prob of silence when lexicon has silprobs. Thx:@agurianov (#2823)

5.5.100 8ea2a7e5d 2018-11-08 [scripts,src] Fix to multitask nnet3 training (#2818); cosmetic code change. (#2827)

5.5.101 5b23ace1a 2018-11-09 [scripts] Create shared versions of get_ctm_conf.sh, add get_ctm_conf_fast.sh (#2828)

5.5.102 d66bee340 2018-11-12 [src] Use cuda streams in matrix library (#2821)

5.5.103 cd6d5a583 2018-11-13 [egs] Add online-decoding recipe to aishell1 (#2829)

5.5.104 3ae133c96 2018-11-13 [egs] Add DIHARD 2018 diarization recipe. (#2822)

5.5.105 2c87b3a5d 2018-11-13 [egs] add nnet3 online result for aishell1 (#2836)

5.5.106 33ada45b2 2018-11-14 [scripts] RNNLM scripts: don't die when features.txt is not present (#2837)

5.5.107 d337921ef 2018-11-14 [src] Optimize cuda allocator for multi-threaded case (#2820)

5.5.108 741b75b47 2018-11-15 [build] Add cub library for cuda projects (#2819)

5.5.109 d9c2eb3a8 2018-11-15 [src] Make Cuda allocator statistics visible to program (#2835)

5.5.110 69a09b386 2018-11-15 [src] Fix bug affecting scale in GeneralDropoutComponent (non-continuous case) (#2815)

5.5.111 219e60cc6 2018-11-16 [build] FIX #2842: properly check $use_cuda against false. (#2843)

5.5.112 da76c6b42 2018-11-16 [doc] Add note about OOVs to data-prep. (#2844)

5.5.113 c7380171b 2018-11-17 [scripts] Allow segmentation with nnet3 chain models (#2845)

5.5.114 f02b324f2 2018-11-19 [build] Remove -lcuda from cuda makefiles which breaks operation when no driver present (#2851)

5.5.115 c026f728f 2018-11-19 [scripts] Fix error in analyze_lats.sh for long lattices (replace awk with perl) (#2854)

5.5.116 a121244c9 2018-11-19 [egs] add rnnlm recipe for librispeech (#2830)

5.5.117 0cf138232 2018-11-19 [build] change configure version from 9 to 10 (#2853) (#2855)

5.5.118 73fad9f02 2018-11-19 [src] fixed compilation errors when built with --DOUBLE_PRECISION=1 (#2856)

5.5.119 f89709c4f 2018-11-19 [build] Clarify instructions if cub is not found (#2858)

5.5.120 2489bb902 2018-11-21 [egs] Limit MFCC feature extraction job number in Dihard recipe (#2865)

5.5.121 60db6547a 2018-11-22 [egs] Added Bentham handwriting recognition recipe (#2846)

5.5.122 172e88666 2018-11-25 [src] Share roots of different tones of phones aishell (#2859)

5.5.123 875566181 2018-11-25 [egs] Fix path to sequitur in commonvoice egs (#2868)

5.5.124 64d5cf269 2018-11-26 [egs] Update reverb recipe (#2753)

5.5.125 d5bdb8847 2018-11-26 [scripts] Fix error while analyzing lattice (parsing bugs) (#2873)

5.5.126 8a87f5333 2018-11-26 [src] Fix memory leak in OnlineCacheFeature; thanks @Worldexe (#2872)

5.5.127 70aba21bf 2018-11-26 [egs] TIMIT: fix mac compatibility of sed command (#2874)

5.5.128 93a0a46aa 2018-11-27 [egs] mini_librispeech: fixing some bugs and limiting repeated downloads (#2861)

5.5.129 132eb42ab 2018-11-27 [src,scripts,egs] Speedups to GRU-based networks (special components) (#2712)

5.5.130 84435ff93 2018-11-27 [src] Fix infinite recursion with -DDOUBLE_PRECISION=1. Thx: @hwiorn (#2875) (#2876)

5.5.131 b196b7ffe 2018-11-27 Revert "[src] Fix infinite recursion with -DDOUBLE_PRECISION=1. Thx: @hwiorn (#2875) (#2876)" (#2877)

5.5.132 286e91285 2018-11-27 Revert "Revert "[src] Fix infinite recursion with -DDOUBLE_PRECISION=1. Thx: @hwiorn (#2875) (#2876)" (#2877)" (#2878)

5.5.133 21ffb84fe 2018-11-27 Revert "[src] Fix memory leak in OnlineCacheFeature; thanks @Worldexe" (#2882)

5.5.134 643623dbe 2018-11-27 [src] Remove unused code that caused Windows compile failure. Thx:@btiplitz (#2881)

5.5.135 d82fcc6c4 2018-11-28 [src] Really fix memory leak in online decoding; thx:@worldexe (#2883)

5.5.136 486de21e5 2018-11-28 [src] Fix Windows cuda build failure (use C++11 standard include) (#2880)

5.5.137 6d233d0cb 2018-11-28 [src] Add #include that caused build failure on Windows (#2886)

5.5.138 8daa02e9c 2018-11-29 [scripts] Fix max duration check in sad_to_segments.py (#2889)

5.5.139 4b149672b 2018-11-29 [scripts] Fix speech duration calculation in sad_to_segments.py (#2891)

5.5.140 9bf0b6d8d 2018-11-29 [src] Fix Windows build problem (timer.h) (#2888)

5.5.141 0e5d755fd 2018-11-30 [egs] add HUB4 spanish tdnn-f and cnn-tdnn script (#2895)

5.5.142 6209b997d 2018-12-01 [egs] Fix Aishell2 dict prepare bug; should not affect results (#2890)

5.5.143 40a9dc642 2018-12-01 [egs] Self-contained example for KWS for mini_librispeech (#2887)

5.5.144 ff514e3cb 2018-12-03 [egs,scripts] Fix bugs in Dihard 2018 (#2897)

5.5.145 a2a056464 2018-12-04 [scripts] Check last character of files to match with newline (#2898)

5.5.146 37091d6a0 2018-12-05 [egs] Update Librispeech RNNLM results; use correct training data (#2900)

5.5.147 b50a4cf4d 2018-12-07 [scripts] RNNLM: old iteration model cleanup; save space (#2885)

5.5.148 a464bd72c 2018-12-11 [scripts] Make prepare_lang.sh cleanup beforehand (prevents certain failures) (#2906)

5.5.149 c41cbb1f4 2018-12-11 [scripts] Expose dim-range-node at xconfig level (#2903)

5.5.150 aa0ac7b30 2018-12-11 [scripts] Fix bug related to multi-task in train_raw_rnn.py (#2907)

5.5.151 3e50be92f 2018-12-12 [scripts] Cosmetic fix/clarification to utils/prepare_lang.sh (#2912)

5.5.152 791cd825f 2018-12-13 [scripts,egs] Added a new lexicon learning (adaptation) recipe for tedlium, in accordance with the IS17 paper. (#2774)

5.5.153 b1261616e 2018-12-15 [egs] TDNN+LSTM example scripts, with RNNLM, for Librispeech (#2857)

5.5.154 78f01276c 2018-12-17 [src] cosmetic fix in nnet1 code (#2921)

5.5.155 44980dd6d 2018-12-21 [src] Fix incorrect invocation of mutex in nnet-batch-compute code (#2932)

5.5.156 a46f554d3 2018-12-23 [egs,minor] Fix typo in comment in voxceleb script (#2926)

5.5.157 2edb07401 2018-12-24 [src,egs] Mostly cosmetic changes; add some missing includes (#2936)

5.5.158 9b320ad0b 2018-12-26 [egs] Fix path of rescoring binaries used in tfrnnlm scripts (#2941)

5.5.159 3b0162b0c 2018-12-28 [src] Fix bug in nnet3-latgen-faster-batch for determinize=false (#2945)

5.5.160 b98454365 2018-12-28 [egs] Add example for rimes handwriting database; Madcat arabic script cleanup (#2935)

5.5.161 46826d94e 2018-12-28 [egs] Add scripts for yomdle korean (#2942)

5.5.162 3e77220b3 2018-12-30 [build] Refactor/cleanup build system, easier build on ubuntu 18.04. (#2947)

5.5.163 5a720accd 2018-12-31 [scripts,egs] Changes for Python 2/3 compatibility (#2925)

5.5.164 ca32c4e2b 2018-12-31 [egs] Add more modern DNN recipe for fisher_callhome_spanish (#2951)

5.5.165 1ea2ba7a3 2019-01-01 [scripts] switch from bc to perl to reduce dependencies (diarization scripts) (#2956)

5.5.166 969869c53 2019-01-01 [scripts] Further fix for Python 2/3 compatibility (#2957)

5.5.167 97d14df09 2019-01-02 [egs] Remove no-longer-existing option in tedlium_r3 recipe (#2959)

5.5.168 0134893a3 2019-01-02 [build] Handle dependencies for .cu files in addition to .cc files (#2944)

5.5.169 5ae6e9e28 2019-01-04 [src] remove duplicate test mode option from class GeneralDropoutComponent (#2960)

5.5.170 fef690936 2019-01-05 [egs] Fix minor bugs in WSJ's flat-start/e2e recipe (#2968)

5.5.171 b9d4b766d 2019-01-05 [egs] Fix to BSD compatibility of TIMIT data prep (#2966)

5.5.172 6b1757115 2019-01-05 [scripts] Fix RNNLM training script problem (chunk_length was ignored) (#2969)

5.5.173 32b8cf1ea 2019-01-05 [src] Fix bug in lattice-1best.cc RE removing insertion penalty (#2970)

5.5.174 10799226b 2019-01-06 [src] Compute a separate avg (start, end) interval for each sausage word (#2972)

5.5.175 205dbd8fa 2019-01-07 [build] Move nvcc verbose flag to proper location (#2962)

5.5.176 1cac23643 2019-01-07 [egs] Fix mini_librispeech download_lm.sh crash; thx:chris.keith.johnson@gmail.com (#2974)

5.5.177 37d69503b 2019-01-08 [egs] minor fixes related to python2 vs python3 differences (#2977)

5.5.178 a6aa26913 2019-01-08 [src] Small fix in test code, avoid spurious failure (#2978)

5.5.179 286446514 2019-01-08 [egs] Fix CSJ data-prep; minor path fix for USB version of data (#2979)

5.5.180 f02d2a303 2019-01-09 [egs] Add paper ref to README.txt in reverb example (#2982)

5.5.181 ff6ddf74b 2019-01-11 [egs] Minor fixes to sitw recipe (fix problem introdueced in #2925) (#2985)

5.5.182 9b6fbddac 2019-01-11 [scripts] Fix bug introduced in #2957, RE integer division (#2986)

5.5.183 c0172682c 2019-01-12 [egs] Update WSJ flat-start chain recipes to use TDNN-F not TDNN+LSTM (#2988)

5.5.184 c631fcb2f 2019-01-13 [scripts] Fix typo introduced in #2925 (#2989)

5.5.185 9f981d06f 2019-01-14 [build] Modify Makefile and travis script to fix Travis failures (#2987)

5.5.186 ae573c9c1 2019-01-15 [src] Simplification and efficiency improvement in ivector-plda-scoring-dense (#2991)

5.5.187 50af3fc01 2019-01-16 [egs] Update madcat Arabic and Chinese egs, IAM (#2964)

5.5.188 f90a98c08 2019-01-16 [src] Fix overflow bug in convolution code (#2992)

5.5.189 fd0aca9d0 2019-01-16 [src] Fix nan issue in ctm times introduced in #2972, thx: @vesis84 (#2993)

5.5.190 e8d128704 2019-01-17 [src] Fix 'sausage-time' issue which occurs with disabled MBR decoding. (#2996)

5.5.191 99dc4d885 2019-01-21 [egs] Add scripts for yomdle Russian (OCR task) (#2953)

5.5.192 7e529edfe 2019-01-21 [egs] Simplify lexicon preparation in Fisher callhome Spanish (#2999)

5.5.193 25f09e8ab 2019-01-22 [egs] Update GALE Arabic recipe (#2934)

5.5.194 4338004dd 2019-01-22 [egs] Remove outdated NN results from Gale Arabic recipe (#3002)

5.5.195 05d9a3d5e 2019-01-22 [egs] Add RESULTS file for the tedlium s5_r3 (release 3) setup (#3003)

5.5.196 1dcdf80c5 2019-01-26 [src] Fixes to grammar-fst code to handle LM-disambig symbols properly (#3000)

5.5.197 6f5651231 2019-01-30 [src] Cosmetic change to mel computation (fix option string) (#3011)

5.5.198 56cfb95d0 2019-02-01 [src] Fix Visual Studio error due to alternate syntactic form of noreturn (#3018)

5.5.199 9e358985e 2019-02-01 [egs] Fix location of sequitur installation (#3017)

5.5.200 a51bd964b 2019-02-02 [src] Fix w/ ifdef Visual Studio error from alternate syntactic form noreturn (#3020)

5.5.201 41ea8cfbc 2019-02-03 [egs] Some fixes to getting data in heroico recipe (#3021)

5.5.202 fb514dc70 2019-02-04 [egs] BABEL script fix: avoid make_L_align.sh generating invalid files (#3022)

5.5.203 afc5e78c2 2019-02-06 [src] Fix to older online decoding code in online/ (OnlineFeInput; was broken by commit cc2469e8). (#3025)

5.5.204 226cbf7bf 2019-02-08 [script] Fix unset bash variable in make_mfcc.sh (#3030)

5.5.205 6fc4c6020 2019-02-08 [scripts] Extend limit_num_gpus.sh to support --num-gpus 0. (#3027)

5.5.206 2f92bd971 2019-02-14 [scripts] fix bug in utils/add_lex_disambig.pl when sil-probs and pron-probs used (#3033)

5.5.207 403c5ee02 2019-02-18 [egs] Fix path in Tedlium r3 rnnlm training script (#3039)

5.5.208 abfbc567d 2019-02-20 [src] Thread-safety for GrammarFst (thx:armando.muscariello@gmail.com) (#3040)

5.5.209 f09d48a4d 2019-02-21 [scripts] Cosmetic fix to get_degs.sh (#3045)

5.5.210 b0fc09d1a 2019-02-21 [egs] Small bug fixes for IAM and UW3 recipes (#3048)

5.5.211 4494a85b1 2019-02-26 [scripts] Nnet3 segmentation: fix default params (#3051)

5.5.212 bf33f1fb1 2019-02-26 [scripts] Allow perturb_data_dir_speed.sh to work with utt2lang (#3055)

5.5.213 5f05d5991 2019-02-26 [scripts] Make beam in monophone training configurable (#3057)

5.5.214 c0a555e4c 2019-02-27 [scripts] Allow reverberate_data_dir.py to support unicode filenames (#3060)

5.5.215 2e26464ac 2019-03-01 [scripts] Make some cleanup scripts work with python3 (#3054)

5.5.216 d21be2d83 2019-03-04 [scripts] bug fix to nnet2->3 conversion, fixes #886 (#3071)

5.5.217 8fa9648c9 2019-03-04 [src] Make copies occur in per-thread default stream (for GPUs) (#3068)

5.5.218 bd326dc05 2019-03-04 [src] Add GPU version of MergeTaskOutput().. relates to batch decoding (#3067)

5.5.219 17b7f3f2b 2019-03-04 [src] Add device options to enable tensor core math mode. (#3066)

5.5.220 0a1f82739 2019-03-04 [src] Log nnet3 computation to VLOG, not std::cout (#3072)

5.5.221 f2a89c232 2019-03-04 [src] Allow upsampling in compute-mfcc-feats, etc. (#3014)

5.5.222 98b45c8d4 2019-03-04 [src] fix problem with rand_r being undefined on Android (#3037)

5.5.223 197214d33 2019-03-04 [egs] Update swbd1_map_words.pl, fix them_1's -> them's (#3052)

5.5.224 991a75cd2 2019-03-05 [src] Add const overload OnlineNnet2FeaturePipeline::IvectorFeature (#3073)

5.5.225 4432371be 2019-03-06 [src] Fix syntax error in egs/bn_music_speech/v1/local/make_musan.py (#3074)

5.5.226 8460fa31a 2019-03-06 [src] Memory optimization for online feature extraction of long recordings (#3038)

5.5.227 b801b988e 2019-03-07 [build] fixed a bug in linux_configure_redhat_fat when use_cuda=no (#3075)

5.5.228 ce97c472e 2019-03-07 [scripts] Add missing '. ./path.sh' to get_utt2num_frames.sh (#3076)

5.5.229 4d61452ac 2019-03-07 [src,scripts,egs] Add count-based biphone tree tying for flat-start chain training (#3007)

5.5.230 01cef6900 2019-03-08 [scripts,egs] Remove sed from various scripts (avoid compatibility problems) (#2981)

5.5.231 2f95609f0 2019-03-08 [src] Rework error logging for safety and cleanliness (#3064)

5.5.232 bcfe3f8c5 2019-03-10 [src] Change warp-synchronous to cub::BlockReduce (safer but slower) (#3080)

5.5.233 1209c07da 2019-03-10 [src] Fix && and || uses where & and | intended, and other weird errors (#3087)

5.5.234 5a5696ff3 2019-03-10 [build] Some fixes to Makefiles (#3088)

5.5.235 abd4869ca 2019-03-11 [src] Fixed -Wreordered warnings in feat (#3090)

5.5.236 9c8ba0f87 2019-03-11 [egs] Replace bc with perl -e (#3093)

5.5.237 8cbd582ef 2019-03-12 [scripts] Fix python3 compatibility issue in data-perturbing script (#3084)

5.5.238 74356619b 2019-03-12 [doc] fix some typos in doc. (#3097)

5.5.239 5bdea6963 2019-03-12 [build] Make sure expf() speed probe times sensibly (#3089)

5.5.240 b7a4feccd 2019-03-12 [scripts] Make sure merge_targets.py works in python3 (#3094)

5.5.241 94475d699 2019-03-13 [src] ifdef to fix compilation failure on CUDA 8 and earlier (#3103)

5.5.242 fc8c17b18 2019-03-13 [doc] fix typos and broken links in doc. (#3102)

5.5.243 3f8b6b295 2019-03-13 [scripts] Fix frame_shift bug in egs/swbd/s5c/local/score_sclite_conf.sh (#3104)

5.5.244 633e61c04 2019-03-13 [src] Fix wrong assertion failure in nnet3-am-compute (#3106)

5.5.245 8cafd32bd 2019-03-13 [src] Cosmetic changes to natural-gradient code (#3108)

5.5.246 b1b230c8b 2019-03-14 [src,scripts] Python2 compatibility fixes and code cleanup for nnet1 (#3113)

5.5.247 9c875ef5b 2019-03-14 [doc] Small documentation fixes; update on Kaldi history (#3031)

5.5.248 7a1908f1a 2019-03-14 [src] Various mostly-cosmetic changes (copying from another branch) (#3109)

5.5.249 fcd70d3a7 2019-03-16 [scripts] Simplify text encoding in RNNLM scripts (now only support utf-8) (#3065)

5.5.250 b4c7ab60e 2019-03-16 [egs] Add "formosa_speech" recipe (Taiwanese Mandarin ASR) (#2474)

5.5.251 461b50c2c 2019-03-16 [egs] python3 compatibility in csj example script (#3123)

5.5.252 61637e6c8 2019-03-17 [egs] python3 compatibility in example scripts (#3126)

5.5.253 1f068cde8 2019-03-17 [scripts] Bug-fix for removing deleted words (#3116)

5.5.254 8d60ee3d8 2019-03-17 [scripts] Add fix regarding num-jobs for segment_long_utterances*.sh(#3130)

5.5.255 7fb716aa0 2019-03-18 [src] Enable allow_{upsample,downsample} with online features (#3139)

5.5.256 80c143767 2019-03-19 [src] Fix bad assert in fstmakecontextsyms (#3142)

5.5.257 0d6ead55b 2019-03-19 [src] Fix to "Fixes to grammar-fst & LM-disambig symbols" (#3000) (#3143)

5.5.258 338b5868c 2019-03-19 [build] Make sure PaUtils exported from portaudio (#3144)

5.5.259 73720e639 2019-03-19 [src] cudamatrix: fixing a synchronization bug in 'normalize-per-row' (#3145)

5.5.260 f9276a593 2019-03-20 [src] Fix typo in comment (#3147)

5.5.261 252690fd0 2019-03-20 [src] Add binary that functions as a TCP server (#2938)

5.5.262 6134c290f 2019-03-20 [scripts] Fix bug in comment (#3152)

5.5.263 aead118bb 2019-03-21 [scripts] Fix bug in steps/segmentation/ali_to_targets.sh (#3155)

5.5.264 213ae52ac 2019-03-21 [scripts] Avoid holding out more data than the requested num-utts (due to utt2uniq) (#3141)

5.5.265 1ac8c922c 2019-03-23 [src,scripts] Add support for two-pass agglomerative clustering. (#3058)

5.5.266 6bd9dad4d 2019-03-24 [src] Disable unget warning in PeekToken (and other small fix) (#3163)

5.5.267 37f4f442f 2019-03-24 [build] Add new nvidia tools to windows build (#3159)

5.5.268 77ac79f70 2019-03-24 [doc] Fix documentation errors and add more docs for tcp-server decoder (#3164)

5.5.269 27034a274 2019-03-27 [scripts] Fix non-randomness in getting utt2uniq, introduced in #3142 (#3175)

5.5.270 f9828e9a2 2019-03-27 [build] Don't build for Tegra sm_XX versions on x86/ppc and vice versa; allow --cuda-arch overrides to have multiple versions (#3171)

5.5.271 419e35c7d 2019-03-29 [egs] Fixes Re encoding to IAM, uw3 recipes (#3012)

5.5.272 2ebe9762a 2019-03-30 [src] Efficiency improvement and extra checking for cudamarix, RE default stream (#3182)

5.5.273 abf7a8c19 2019-03-30 [egs] Fix small typo in tedlium download script (#3178)

5.5.274 7691d00df 2019-03-31 [github] Add GitHub issue templates (#3187)

5.5.275 9ef700fb6 2019-03-31 [build] Add missing dependency to Makefile (#3191)

5.5.276 584533433 2019-03-31 [src] Fix bug in pruned lattice rescoring when input lattice has epsilons (#3190)

5.5.277 be019cd1f 2019-04-01 [scripts] Fix bug in extend_lang.sh regarding extra_disambig.txt (#3195)

5.5.278 ffbe16bc6 2019-04-03 [egs] Update Tedlium s5_r3 example with more up-to-date chain TDNN configuration

5.5.279 b18070761 2019-04-03 [scripts] Fix bug in extend_lang.sh causing validation failure w/ extra_disambig.txt (#3202)

5.5.280 7093dfa4b 2019-04-04 [scripts] Bug-fix in make_lexicon_fst.py, which failed when --sil-prob=0 (#3206)

5.5.281 6f0a3a23f 2019-04-04 [egs] Fix very small typo in run_tdnn_1b.sh (#3207)

5.5.282 ddeac9837 2019-04-04 [build] Tensorflow version update (#3204)

5.5.283 beb015175 2019-04-06 [src] Optimizations to CUDA kernels (#3209)

5.5.284 a3a190b73 2019-04-06 [src] Move curand handle out of CuRand class and into CuDevice. (#3196)

5.5.285 faa7ff891 2019-04-06 [build] Make MKL the default BLAS library, add installation scripts (#3194)

5.5.286 76bdf206f 2019-04-07 [build] check for i686 as a valid prefix for Android triplets (#3213)

5.5.287 4ae4bb096 2019-04-09 [build] Fix configure breakage from #3194 (MKL default)

5.5.288 b96cab759 2019-04-09 [build] Add missing line continuation '\' in tfrnnlmbin/Makefile (#3218)

5.5.289 9b730e02f 2019-04-11 [src] Fix nnet2 DctComponent test failure (#3225)

5.5.290 4cfbd217a 2019-04-11 [src] Update CUDA code to avoid synchronization errors on compute capability 7.x (#3211)

5.5.291 df41d4c6c 2019-04-11 [src] fix nnet2 DCTCompnent test failure -- removing anther dct_keep_dim=1 (#3226)

5.5.292 ebfa3cb58 2019-04-14 [build] Remove references to deprecated MKL libs in gst_plugin (#3229)

5.5.293 4e8164c8f 2019-04-14 [scripts] Fix default params in nnet3 segmentation script (#3230)

5.5.294 0bfc30788 2019-04-15 [src] Correct sanity check in nnet-example-utils.cc (nnet3) (#3232)

5.5.295 f8021d765 2019-04-16 Revert "[src] Update CUDA code to avoid synchronization errors on compute capability 7.x (#3211)" (#3236)

5.5.296 06a21b14b 2019-04-17 [build] .gitignore autogenerated /tools/python/ (#3241)

5.5.297 a2d027016 2019-04-17 [scripts] Enhance argument checks in nnet3/align_lats.sh (#3243)

5.5.298 299b111d0 2019-04-17 [egs] invoke 'python2.7' not 'python' when using mmseg (#3244)

5.5.299 4ff77c53e 2019-04-18 [scripts] Make getting nnet3 model context more robust (#3247)

5.5.300 b3a6e174b 2019-04-18 [egs] Fix hkust_data_prep.sh w.r.t. iconv mac compatibility issue (#3250)

5.5.301 84ecd0e1e 2019-04-18 [egs] Update RM chain recipe with more recent configuration (#3237)

5.5.302 c3260f242 2019-04-19 [egs] Make voxceleb recipe work with latest version of the dataset (#3249)

5.5.303 f107cdba3 2019-04-20 [egs] Improve chain example script for Resource Management (RM) (#3252)

5.5.304 2c25629d7 2019-04-22 [src] GPU-related changes for speed and correctness on newer arch's. (#3221)

5.5.305 5a34a0ab4 2019-04-22 [egs] Update voxceleb v1 preparation scripts (#3255)

5.5.306 96e7b0aed 2019-04-23 [build] Note default=MKL; cosmetic fix (#3257)

5.5.307 d47e36cd6 2019-04-23 [egs] Fix to hkust_data_prep.sh w.r.t. how mmseg is checked for (#3240)

5.5.308 286e8aff2 2019-04-23 [egs] In WSJ run_ivector_common.sh, expose i-vector #jobs config to run script (#3248)

5.5.309 e3a9844aa 2019-04-23 [egs] Add Spanish dimex100 example (#3254)

5.5.310 0cc941f7e 2019-04-24 [build] Build and configure OpenBLAS; default to it on non-x64 machine (#3261)

5.5.311 9e9ae1381 2019-04-24 [scripts] Fix of a bug in segmentation.pl (#3256)

5.5.312 f8cb5cccf 2019-04-25 [src] Fixes to cuda unit tests. (#3268)

5.5.313 b8a35fdec 2019-04-26 [src] Adding GPU/CUDA lattice batched decoder + binary (#3114)

5.5.314 da4e2b8f7 2019-04-27 [src] Fix unit-test failure UnitTestCuMatrixSetRandn() (#3274)

5.5.315 203ce3787 2019-04-27 [src,build] Removed cusolver for now (not needed yet; caused build problems) (#3276)

5.5.316 1da8ebdc5 2019-04-29 [scripts] Make fix_data_dir.sh remove utterances which have bad duration. (#3275)

5.5.317 939faf8bc 2019-04-30 [scripts] Make generate_plots.py python3-compatible (#3280)

5.5.318 212474eab 2019-05-01 [scripts] Add --one-based option to split_scp.pl (#3279)

5.5.319 a045314b8 2019-05-01 [scripts] Allow UTF utterance-ids by removing unnecessary assert (#3283)

5.5.320 b1569dbb0 2019-05-01 [src] Keep nnet output in the [-30,30] range required by chain denominator (#3024)

5.5.321 b17fc8447 2019-05-02 [scripts] Clean up filehandle usage in split_scp.pl (#3285)

5.5.322 230992f0d 2019-05-02 [src] Fix to bug in online-feature.cc that caused crash at end of utterance. (#3286)

5.5.323 f7117db4c 2019-05-02 [scripts] Use correct compile-time regex syntax in split_scp.pl (#3287)

5.5.324 df1ebbc9f 2019-05-02 [scripts] Fix a typo in steps/dict/learn_lexicon_bayesian.sh (#3288)

5.5.325 155c65894 2019-05-05 [egs,scripts] Scripts and an example of BPE-based sub-word decoding (#3101)

5.5.326 f2670c320 2019-05-07 [scripts] Add trainer option --trainer.optimization.num-jobs-step (#3205)

5.5.327 9702cbc3a 2019-05-08 [egs] Add MGB-5 recipe; https://arabicspeech.org/mgb5 (#3299)

5.5.328 5ae3c198e 2019-05-09 Revert "[scripts] Clean up filehandle usage in split_scp.pl (#3285)" (#3307)

5.5.329 20fb64875 2019-05-09 [src] Fix bug in GeneralMatrix::Uncompress() (#3304)

5.5.330 a5695e97d 2019-05-09 [src] nnet1: lstm training, introducing cursors when slicing the training data (#3302)

5.5.331 9424f7ab4 2019-05-09 [doc] add an omission in Doxyfile (#3309)

5.5.332 ba165c889 2019-05-10 [scripts] Fix utils/split_scp.pl breakage (#3308)

5.5.333 4d7fe3b2b 2019-05-11 [egs] Bug-fix to shebang in fisher_callhome_spanish (#3312)

5.5.334 19c88acf0 2019-05-11 [scripts] Fix error messages in run.pl (#3314)

5.5.335 e9223333e 2019-05-11 [egs] New chime-5 recipe (#2893)

5.5.336 a861e5677 2019-05-13 [scripts,egs] Made changes to the augmentation script to make it work for ASR and speaker ID (#3119)

5.5.337 cec8958c2 2019-05-13 [egs] updated local/musan.sh to steps/data/make_musan.sh in speaker id scripts (#3320)

5.5.338 d40222e48 2019-05-14 [src] Fix sample rounding errors in extract-segments (#3321)

5.5.339 35f96db70 2019-05-14 [src,scripts]Store frame_shift, utt2{dur,num_frames}, .conf with features (#3316)

5.5.340 a2e7ba3e6 2019-05-15 [build] Initial version of Docker images for (CPU and GPU versions) (#3322)

5.5.341 91609c7d6 2019-05-15 [scripts] fix typo/bug in make_musan.py (#3327)

5.5.342 95e81c0b5 2019-05-15 [scripts] Fixed misnamed variable in data/make_musan.py (#3324)

5.5.343 c5aa3a927 2019-05-15 [scripts] Trust frame_shift and utt2num_frames if found (#3313)

5.5.344 0ff318b2e 2019-05-16 [scripts] typo fix in augmentation script (#3329)

5.5.345 62ebb44bd 2019-05-16 [scripts] handle frame_shit and utt2num_frames in utils/ (#3323)

5.5.346 c8b93bcb7 2019-05-17 [scripts] Extend combine_ali_dirs.sh to combine alignment lattices (#3315)

5.5.347 528e072cb 2019-05-17 [src] Fix rare case when segment end rounding overshoots file end in extract-segments (#3331)

5.5.348 8397e0517 2019-05-20 [scripts] Change --modify-spk-id default to False; back-compatibility fix for #3119 (#3334)

5.5.349 8b54ef83e 2019-05-20 [build] Add easier configure option in failure message of configure (#3335)

5.5.350 ce8798bf5 2019-05-22 [scripts,minor] Fix typo in comment (#3338)

5.5.351 9e0a7f60b 2019-05-23 [src,egs] Add option for applying SVD on trained models (#3272)

5.5.352 0e5e07b27 2019-05-23 [src] Add interfaces to nnet-batch-compute that expects device input. (#3311)

5.5.353 52e7ecf65 2019-05-27 [build] Update GCC support check for CUDA toolkit 10.1 (#3345)

5.5.354 29f3c1419 2019-05-27 [egs] Fix to aishell1 v1 download script (#3344)

5.5.355 a5dd6bdc8 2019-05-27 [scripts] Support utf-8 files in some scripts (#3346)

5.5.356 8c6cd31db 2019-05-28 [src] Fix potential underflow bug in MFCC, RE energy floor, thx: Zoltan Tobler (#3347)

5.5.357 e643c7303 2019-05-28 [scripts]: add warning to nnet3/chain/train.py about ineffective options (#3341)

5.5.358 8706f068c 2019-05-29 [scripts] Fix regarding UTF handling in cleanup script (#3352)

5.5.359 800924d98 2019-06-01 [scripts] Change encoding to utf-8 in data augmentation scripts (#3360)

5.5.360 eedd9fa99 2019-06-03 [src] Add CUDA accelerated MFCC computation. (#3348)

5.5.361 0b443bd67 2019-06-03 [src] Optimizations for batch nnet3. The issue fixed here is that (#3351)

5.5.362 16097b4c1 2019-06-03 [scripts,minor] Remove outdated comment (#3361)

5.5.363 ced53e19f 2019-06-03 [egs] A kaldi recipe based on the corpus named "aidatatang_200zh". (#3326)

5.5.364 f8a4376e1 2019-06-03 [src] nnet1: changing end-rule in 'nnet-train-multistream', (#3358)

5.5.365 9c734a551 2019-06-03 [scripts] Fix how the empty (faulty?) segments are handled in data-cleanup code (#3337)

5.5.366 b276d7055 2019-06-03 [src] Fix to bug in ivector extraction causing assert failure, thx: sray (#3364)

5.5.367 de4a3e31d 2019-06-03 [src] Fix to bug in ivector extraction causing assert failure, thx: sray (#3365)

5.5.368 1a4aa52a3 2019-06-03 [scripts] add script to compute dev PPL on kaldi-rnnlm (#3340)

5.5.369 173500372 2019-06-04 [scripts,egs] Small fixes to diarization scripts (#3366)

5.5.370 338cc5865 2019-06-05 [egs] Modify split_scp.pl usage to match its updated code (#3371)

5.5.371 254d63665 2019-06-05 [src] Fix non-cuda `make depend` build by putting compile guards around header. (#3374)

5.5.372 3648df5c1 2019-06-06 [build] Docker docs update and minor changes to the Docker files (#3377)

5.5.373 0071003f1 2019-06-06 [egs] Scripts for MATERIAL ASR (#2165)

5.5.374 acff3f656 2019-06-06 [src] Batch nnet3 optimizations. Batch some of the copies in and copies out (#3378)

5.5.375 23ba98260 2019-06-07 [build] Widen cuda guard in cudafeat makefile. (#3379)

5.5.376 04cf43b0f 2019-06-10 [scripts] nnet1: updating the scripts to support 'online-cmvn', (#3383)

5.5.377 c10e02f2b 2019-06-11 [build,src] Enhancements to the cudamatrix/cudavector classes. (#3373)

5.5.378 b0a6e7662 2019-06-11 [egs] Fix perl `use encoding` deprecation (#3386)

5.5.379 63c54e2de 2019-06-11 [scripts] Add max_active to align_fmllr_lats.sh to prevent rare crashes (#3387)

5.5.380 7c7a1767e 2019-06-11 [src] Implemented CUDA acclerated online cmvn. (#3370)

5.5.381 c7876a338 2019-06-11 [egs] Fixed file path RE augmentation, in aspire recipe (#3388)

5.5.382 0552e22d9 2019-06-13 [scripts] Update taint_ctm_edits.py, RE utf-8 encoding (#3392)

5.5.383 63b38496a 2019-06-14 [src] Change nnet3-am-copy to allow more manipulations (#3393)

5.5.384 c2163854e 2019-06-15 [egs] Remove confusing setting of overridden num_epochs variable in aspire (#3394)

5.5.385 bd1da143a 2019-06-17 [build] Add a missing dependency for "decoder" in Makefile (#3397)

5.5.386 674410ecb 2019-06-19 [src] CUDA decoder performance patch (#3391)

5.5.387 10f2fcba9 2019-06-19 [build,scripts] Dependency fix; add cross-references to scripts (#3400)

5.5.388 76557e95d 2019-06-20 [egs] Fix cleanup-after-partial-download bug in aishell (#3404)

5.5.389 5abb1a08d 2019-06-20 [src] Change functions like AppiyLog() to all work out-of-place (#3185)

5.5.390 777f8c110 2019-06-20 [src] Make stack trace display more user friendly (#3406)

5.5.391 d5a1451df 2019-06-22 [egs] Fix to separators in Aspire reverb recipe (#3408)

5.5.392 09697c3cf 2019-06-22 [egs] Fix to separators in Aspire, related to #3408 (#3409)

5.5.393 fe541d222 2019-06-23 [src] online2-tcp, add option to display start/end times (#3399)

5.5.394 c5c09e966 2019-06-24 [src] Remove debugging assert in cuda feature extraction code (#3411)

5.5.395 837839a85 2019-06-24 [scripts] Fix to checks in adjust_unk_graph.sh (#3410)

5.5.396 563b258d7 2019-06-24 [src] Added GPU feature extraction (will improve speed of GPU decoding) (#3390)

5.5.397 ec13b71d1 2019-06-24 [src] Fix build error introducted by race condition in PR requests/accepts. (#3412)

5.5.398 5b4d2c911 2019-06-24 [src] Added error string to CUDA allocation errors. (#3413)

5.5.399 00963e2a3 2019-06-25 [src] Fix CUDA_VSERION number in preprocessor checks (#3414)

5.5.400 14cc15642 2019-06-25 [src] Fix build of online feature extraction with older CUDA version (#3415)

5.5.401 5cc7ce063 2019-06-25 [src] Update Insert function of hashlist and decoders (#3402)

5.5.402 524db1986 2019-06-26 [src] Fix spelling mistake in #3415 (#3416)

5.5.403 36a7e9956 2019-06-26 [build] Fix configure bug RE CuSolver (#3417)

5.5.404 533469c38 2019-06-26 [src] Enable an option to use the GPU for feature extraction in GPU decoding (#3420)

5.5.405 42315f3dc 2019-06-27 [egs] Replace $cuda_cmd with $train_cmd for FarsDat (#3426)

5.5.406 31df26cdd 2019-06-27 [src] Remove outdated comment (#3148) (#3422)

5.5.407 2e02eb75a 2019-06-27 [src] Adding missing thread.join in CUDA decoder and fixing two todos (#3428)

5.5.408 f5a5f84ed 2019-06-27 [build] Add missing lib dependency in cudafeatbin (#3427)

5.5.409 fa2e8c3b7 2019-06-28 [egs] Small fix to aspire run_tdnn_7b.sh (#3429)

5.5.410 21c0d9b7e 2019-06-28 [build] Fix to cuda makefiles, thanks: yiyidhuang@gmail.com (#3431)

5.5.411 f5d34d728 2019-06-28 [build] Add missing deps to cuda makefiles, thanks: yiyidhuang@gmail.com (#3432)

5.5.412 8c0277e10 2019-06-29 [egs] Fix encoding issues in Chinese ASR recipe (#3430) (#3434)

5.5.413 b7845ddb9 2019-06-29 Revert "[src] Update Insert function of hashlist and decoders (#3402)" (#3436)

5.5.414 0dcc2c91c 2019-06-29 [src] Update Insert function of hashlist and decoders (#3402) (#3438)

5.5.415 c449031ad 2019-06-29 [build] Fix the cross-compiling issue for Android under MacOS (#3435)

5.5.416 9a3800716 2019-07-01 [src] Marking operator as __host__ __device__ to avoid build issues (#3441)

5.5.417 ab4eca0c2 2019-07-02 [egs] Fix perl encoding bug (was causing crashes) (#3442)

5.5.418 893181fdf 2019-07-02 [src] Cuda decoder fixes, efficiency improvements (#3443)

5.5.419 a4b638870 2019-07-03 [scripts] Fix shebang of taint_ctm_edits.py to invoke python3 directly (#3445)

5.5.420 e15f68969 2019-07-03 [src] Fix to a check in nnet-compute code (#3447)

5.5.421 f53556ecc 2019-07-03 [src,scripts] Various typo fixes and stylistic fixes (#3153)

5.5.422 7800a0bbb 2019-07-07 [scripts] Scripts for VB (variational bayes) resegmentation for Callhome diarization (#3305)

5.5.423 85d1acd3e 2019-07-08 [scripts] Extend utils/data/subsegment_data_dir.sh to copy reco2dur (#3452)

5.5.424 1badfd9d6 2019-07-08 [src,scripts,egs] Add code and example for SpecAugment in nnet3 (#3449)

5.5.425 39b789822 2019-07-09 [scripts] Make segment_long_utterance honor frame_shift (#3455)

5.5.426 b5385b46c 2019-07-09 [scripts] Fix to steps/nnet/train.sh (nnet1) w.r.t. incorrect bash test expressions (#3456)

5.5.427 98aa1d8ff 2019-07-17 [egs] fixed bug in egs/gale_arabic/s5c/local/prepare_dict_subword.sh that it may delete words matching '<*>' (#3465)

5.5.428 7664fa290 2019-07-18 [src,build] Small fixes (#3472)

5.5.429 abfb99d0a 2019-07-18 [egs] Add MGB-2 Arabic recipe (#3333)

5.5.430 29b326510 2019-07-20 [scripts] Check/fix utt2num_frames when fixing data dir. (#3482)

5.5.431 4f4d3ff27 2019-07-23 [src] A couple small bug fixes. (#3477)

5.5.432 06442e187 2019-07-23 [src,scripts] Cosmetic,file-mode fixes; fix to nnet1 align.sh introduced in #3383 (#3487)

5.5.433 b876c28cc 2019-07-26 [egs] Add missing script in MGB2 recipe (#3491)

5.5.434 07c9d978b 2019-07-26 [egs] Fixing nnet1 but introduced in #3383 (rel. to #3487) (#3494)

5.5.435 7637de77e 2019-07-28 [src] Fix for nnet3 bug encountered when implementing deltas. (#3495)

5.5.436 ffda51ea5 2019-08-02 [scripts,egs] Replace LDA layer with delta and delta-delta features (#3490)

5.5.437 cbae141d4 2019-08-03 [egs] Add updated tdnn recipe for AMI (#3497)

5.5.438 b0f0ae68a 2019-08-03 [egs] Create MALACH recipe based on s5b for AMI (#3496)

5.5.439 5b2604a33 2019-08-03 [scripts] add --phone-symbol-table to prepare_lang_subword.sh (#3485)

5.5.440 0986892a7 2019-08-05 [scripts] Option to prevent crash when adapting on much smaller data (#3506)

5.5.441 53b654954 2019-08-05 [build,scripts] Make OpenBLAS install check for gfortran; documentation fix (#3507)

5.5.442 fb5e7ac63 2019-08-05 [egs] Update chain TDNN-F recipe for CHIME s5 to match s5b, improves results (#3505)

5.5.443 b2b4ee8b9 2019-08-05 [egs] Fix to #3505: updating chime5 TDNN-F script (#3508)

5.5.444 b0be2e01f 2019-08-06 [scripts] Fixed issue that leads to empty segment file (#3510)

5.5.445 83aeeacb3 2019-08-08 [egs] Fix bug in AMI s5b RE overlapping segments that causes Fixed overlap segment bug (#3503)

5.5.446 5766a8373 2019-08-11 [egs] Small cosmetic change in extend_vocab_demo.sh (#3516)

5.5.447 97f0a45fc 2019-08-12 [src] Cosmetic changes; fix windows-compile bug reported by @spencerkirn (#3515)

5.5.448 289edad0a 2019-08-12 [src] Move cuda gpu from nnetbin to nnet3bin. (#3513)

5.5.449 1f6c760f8 2019-08-12 fix a bug in egs/voxceleb/v1/local/make_voxceleb1_v2.pl when preparing the file data/voxceleb1_test/trials (#3512)

5.5.450 662dc57fc 2019-08-12 [egs] Fixed some bugs in mgb_data_prep.sh of mgb2_arabic (#3501)

5.5.451 1ff668adb 2019-08-12 [src,scripts] fix various typos and errors in comments (#3454)

5.5.452 998b22047 2019-08-14 [src] Move cuda-compiled to nnet3bin (#3517)

5.5.453 be26e6272 2019-08-14 [src] Fix binary name in Makefile, RE cuda-compiled (#3518)

5.5.454 3f95ed918 2019-08-15 [src] buffer fix in cudafeat (#3521)

5.5.455 6cdc4957a 2019-08-19 [src] Hopefully make it possible to use empty FST in grammar-fst (#3523)

5.5.456 317cad43b 2019-08-20 [src] Add option to convert pdf-posteriors to phones (#3526)

5.5.457 6c816e5f9 2019-08-21 [src] Fix GetDeltaWeights for long-running online decoding (#3528)

5.5.458 0b7c9a95f 2019-08-23 [src] Small fix to post-to-phone-post.cc (problem introduced in from #3526) (#3534)

5.5.459 013fc50ec 2019-08-23 [src]: adding Dan's fix to a bug in nnet-computation-graph (#3531)

5.5.460 ca523c998 2019-08-23 [egs] Replace prep_test_aspire_segmentation.sh (#2943) (#3530)

5.5.461 93bdc41a3 2019-08-23 [egs] OCR: Decomposition for CASIA and YOMDLE_ZH datasets (#3527)

5.5.462 080b5a260 2019-08-26 [build] check_dependencies.sh: correct installation command for fedora (#3539)

5.5.463 63110571d 2019-08-26 [src,doc] Fix bug in new option of post-to-phone-post; skeleton of faq page (#3540)

5.5.464 ed1d139a8 2019-08-27 [egs,scripts] Adding possibility to have 'online-cmn' on input of 'nnet3' models (#3498)

5.5.465 9f3d81f91 2019-08-27 [scripts] Fix to build_tree_multiple_sources.sh (#3545)

5.5.466 605732af9 2019-08-28 [doc] Fix accidental overwriting of kws page (#3541)

5.5.467 f3b5f5b13 2019-08-28 [egs] Fix regex filter in Fisher preprocessing (was excluding 2-letter sentences like "um") (#3548)

5.5.468 93d5baa76 2019-08-28 [scripts] Fix to bug introduced in #3498 RE ivector-extractor options mismatch. (#3549)

5.5.469 745c0e856 2019-08-28 [scripts] Fix awk compatibility issue; be more careful about online_cmvn file (#3550)

5.5.470 61bc12e61 2019-08-28 [src] Add a method for backward-compatibility with previous API (#3536)

5.5.471 9a8368139 2019-08-28 [src] Feature bank feature extraction using CUDA (#3544)

5.5.472 66c9889b9 2019-08-28 [src] Fix missing semicolon (#3551)

5.5.473 fb5dbf465 2019-08-28 [src] fix a typo mistaking not equal for assign sign in CUDA feature pipeline (#3552)

5.5.474 8875a80b9 2019-08-28 [src] Fix issue #3401 (crash in ivector extraction with max-remembered-frames+silence-weight) (#3405)

5.5.475 54e9a8487 2019-08-28 [egs] Librispeech: in RESULTS, change best_wer.sh => utils/best_wer.sh (#3553)

5.5.476 72ca1eb3e 2019-08-29 [egs] semisupervised recipes: fixing some variables in comments (#3547)

5.5.477 36525ba25 2019-08-30 [scripts] fix utils/lang/extend_lang.sh to add nonterm symbols in align_lexicon.txt (#3556)

5.5.478 fcea01aa6 2019-08-31 [scripts] Fix to bug in steps/data/data_dir_manipulation_lib.py (#3174)

5.5.479 f3e77b1b6 2019-09-03 [src] Fix in nnet3-attention-component.cc, RE required context (#3563)

5.5.480 8834e8bf2 2019-09-03 [src] Temporarily turn off some model-collapsing code while investigating a bug (#3565)

5.5.481 7c8e66e0f 2019-09-06 [scripts] Fix to data cleanup script RE utf-8 support in uttearnce

5.5.482 09abddacc 2019-09-07 [src,scripts,egs] online-cmvn for online2 with chain models, (#3560)

5.5.483 ad09b19ba 2019-09-10 [build,src] Change to error message; update kaldi_lm install script (and kaldi_lm) to fix compile issue (#3581)

5.5.484 1738fe67c 2019-09-14 [src] Clarify something in plda.h (cosmetic change) (#3588)

5.5.485 a74807bc6 2019-09-16 [src] Small fix to online ivector extraction (RE #3401/#3405), thanks: Vladmir Vassiliev. (#3592)

5.5.486 06887c808 2019-09-16 [egs] Add recipe for Chinese training with multiple databases (#3555)

5.5.487 2453b615e 2019-09-17 [src] Remove duplicate `num_done++` in apply-cmvn-online.cc (#3597)

5.5.488 cf1bcb63e 2019-09-18 [src] Fix to CMVN with CUDA (#3593)

5.5.489 21bd4cf67 2019-09-19 [src] Fix two bugs in batched-wav-nnet3-cuda binary. (#3600)

5.5.490 fdab49d94 2019-09-19 [scripts] propagated bad whitespace fix to validate_dict_dir.pl (cosmetic change) (#3601)

5.5.491 effe62ea6 2019-09-20 [scripts] bug-fix on subset_data_dir.sh with --per-spk option (#3567) (#3572)

5.5.492 b2f64fe4a 2019-09-22 [src] Code changes to support GCC9 + OpenFST1.7.3 + C++2a (namespace issues) (#3570)

5.5.493 8634823a1 2019-09-25 [scripts] Training ivector-extractor: make online-cmvn per speaker. (#3615)

5.5.494 fb2bd46b2 2019-09-25 [src] cached compiler I/O for nnet3-xvector-compute (#3197)

5.5.495 7e52cf965 2019-09-29 [src] Fixed online2-tcp-nnet3-decode-faster.cc poll_ret checks (#3611)

5.5.496 cc62e1712 2019-09-29 [scripts] Call utils/data/get_utt2dur.sh using the correct $cmd and $nj (#3608)

5.5.497 6b1ef76e5 2019-09-29 [scripts] Enable tighter control of downloaded dependencies (#3543) (#3573)

5.5.498 5d1fff2dd 2019-09-29 [scripts] Make reverberate_data_dir.py handle vad.scp (#3619)

5.5.499 b10e474e1 2019-09-29 [scripts] Don't get utt2dur in librispeech.. will be made by make_mfcc.sh now (#3610) (#3620)

5.5.500 924b146fc 2019-09-29 [scripts] Make combine_ali_dirs.sh work when queue.pl is used (#3537) (#3561)

5.5.501 a617bc449 2019-09-29 [egs] Fix duplicate removal of unk from Librispeech decoding graphs (#3476) (#3621)

5.5.502 cebe11446 2019-09-29 [build] Check for gfortran, needed by OpenBLAS (for lapack) (#3622)

5.5.503 fc64b27c1 2019-09-29 [scripts] VB resegmentation: load MFCCs only when used (save memory) (#3612)

5.5.504 cb1b273bb 2019-09-29 [build] removed old Docker files - see docker in the root folder for the latest files (#3558)

5.5.505 76b808a07 2019-09-29 [src] Fix to compute-mfcc-feats.cc (thanks: @puneetbawa) (#3623)

5.5.506 6ffde4b41 2019-09-29 [egs] Update AMI tdnn recipe to reflect what was really run, and add hires feats. (#3578)

5.5.507 8dcae078b 2019-10-02 [egs] Fix to run_ivector_common.sh in swbd (crash when running from stage 3) (#3631)

5.5.508 7b4c57760 2019-10-03 [scripts] Make data augmentation work with UTF-8 utterance ids/filenames (#3633)

5.5.509 e1be9b87f 2019-10-03 [src] fix a bug in src/online/online-faster-decoder.cc (prevent segfault with some models) (#3634)

5.5.510 41140d03a 2019-10-03 [scripts] Make extend_lang.sh support lexiconp_silprob.txt (#3339) (#3632)

5.5.511 317e1758a 2019-10-04 [scripts] Fix typo in analyze_alignments.sh (#3635)

5.5.512 68cfbbad3 2019-10-04 [scripts] Change the GPU policy of align.sh to wait instead of yes (#3636)

5.5.513 743eb23d8 2019-10-04 [egs] Added tri3b and chain training for Aurora4 (#3638)

5.5.514 526ade1f7 2019-10-05 [build] fixed broken Docker builds by adding gfortran package (#3640)

5.5.515 b5f4cfc91 2019-10-05 [src] Fix bug in resampling checks for online features (#3639)

5.5.516 c2e039419 2019-10-08 [build] Bump OpenBLAS version to 0.3.7 and enable locking (#3642)

5.5.517 8a1be79d2 2019-10-09 [scripts] Update nnet3_to_dot.py to ignore Scale descriptors (#3644)

5.5.518 a4de025c7 2019-10-09 [src] Speed optimization for decoders (call templates properly) (#3637)

5.5.519 06bf62a57 2019-10-10 [doc] update FAQ page to include some FAQ candidates from Kaldi mailing lists (#3646)

5.5.520 e601fda74 2019-10-11 [egs] Small fix: duplicate xent settings from examples (#3649)

5.5.521 e45dfb07f 2019-10-11 [doc] Fix typo (#3648)

5.5.522 e2b9180ca 2019-10-11 [egs] Fix a bug in Tedlium run_ivector_common.sh (#3647)

5.5.523 eeef08076 2019-10-12 [src] Fix to matrix-lib-test to ignore small difference (#3650)

5.5.524 3492d6e4f 2019-10-13 [doc] update FAQ page: (#3651)

5.5.525 f8bf71735 2019-10-15 [scripts] Modify split_data.sh to split data evenly when utt2dur exists (#3653)

5.5.526 2f1bca312 2019-10-15 [doc] update FAQ page: added section for free dataset, python wrapper, etc. (#3652)

5.5.527 b39ed47c7 2019-10-16 [src] Some CUDA i-vector fixes (#3660)

5.5.528 01cfda3df 2019-10-16 [src] CUDA batched decoder pipeline fixes (#3659)

5.5.529 b57ff1707 2019-10-18 [egs] Small fix to aspire example: pass in num_data_reps (#3665)

5.5.530 880df12bd 2019-10-18 [doc] Update FAQ page (#3663)

5.5.531 ea85eedb1 2019-10-19 [src] Add batched xvector computation (#3643)

5.5.532 be88f3044 2019-10-19 [src] CUDA decoder: write all output to single stream (#3666)

5.5.533 47d516d4e 2019-10-19 [egs] Fix sox command in multi-Updated sox command (#3667)

5.5.534 7f0c9c111 2019-10-21 [src] Change data-type for hash in lattice alignment (avoid debugger complaints) (#3672)

5.5.535 815101781 2019-10-22 [egs] Two fixes to multi_en setup (#3676)

5.5.536 e6d5614c3 2019-10-23 [scripts] Fix misspelled variable in reverb script (#3678)

5.5.537 a91120882 2019-10-23 Update cudamatrix.dox (#3674)

5.5.538 eb836834d 2019-10-23 [scripts] Add reduced-context option for TDNN-F layers. (#3658)

5.5.539 e2c006c2a 2019-10-26 [egs] Make librispeech run_tdnn_discriminative.sh more efficient with disk (#3685)

5.5.540 e3a1b99d1 2019-10-27 [egs] Remove pitch from multi_cn nnet3 recipe (#3686)

5.5.541 935755359 2019-10-27 [egs] multi_cn: clarify metric is CER (#3687)

5.5.542 d91beea6a 2019-10-28 [src,minor] Fix typo in comment in kaldi-holder.h (#3691)

5.5.543 d649afdc1 2019-10-28 [egs] update run_tdnn_discriminative.sh in librispeech recipe (#3689)

5.5.544 03dccb21d 2019-10-31 [egs] Aspire recipe: fixed typo in utterance and speaker prefix (#3696)

5.5.545 7249cc0dd 2019-10-31 [src] cuda batched decoder, fix memory bugs (#3697)

5.5.546 f21d7e768 2019-11-07 [scripts] Change make_rttm.py to read/write files with UTF-8 encoding (#3705)

5.5.547 c2a55384f 2019-11-09 [src] Removing non-compiling paranoid asserts in nnet-computation-graph. (#3709)

5.5.548 bf0ee72db 2019-11-09 [build] Fix gfortran package name for centos (#3708)

5.5.549 f1dd9e2f2 2019-11-11 [scripts] Change the Python diagnostic scripts to accept non-ASCII UTF-8 phone set (#3711)

5.5.550 45cae5ade 2019-11-12 [scripts] Fix some issues in #3653 in split_scp.pl (#3710)

5.5.551 898c8daee 2019-11-12 [scripts] Fix 2 issues in nnet2->nnet3 model conversion script (#886)(#3713)

5.5.552 f679c7848 2019-11-13 Removing changes to split_scp.pl (#3717)

5.5.553 ab36598a6 2019-11-15 [scripts] Improve how combine_ali_dirs.sh gets job-specific filenames (#3720)

5.5.554 d97f1d824 2019-11-16 [src] Add --debug-level=N configure option to control assertions (#3690) (#3700)

5.5.555 0cc71f19a 2019-11-21 [src] Adding some more feature extraction options (needed by some users..) (#3724)

5.5.556 249e2b246 2019-11-21 [src,script,egs] Goodness of Pronunciation (GOP) (#3703)

5.5.557 59255aed4 2019-11-21 [src] Making ivector extractor tolerate dim mismatch due to pitch (#3727)

5.5.558 eb28a6ae3 2019-11-21 Revert "[src] Making ivector extractor tolerate dim mismatch due to pitch (#3727)" (#3728)

5.5.559 bbbc79ba6 2019-11-28 [src] Fix NVCC compilation errors on Windows (#3741)

5.5.560 f88c47590 2019-11-28 [build] Add CMake Build System as alternative to current Makefile-based build (#3580)

5.5.561 1d0b2674a 2019-11-30 [scripts] Modify split_data_dir.sh and split_scp.pl to use utt2dur if present, to balance splits

5.5.562 915bb786b 2019-11-30 [scripts] fix slurm.pl error (#3745)

5.5.563 666b8cb32 2019-12-01 Revert "[scripts] Modify split_data_dir.sh and split_scp.pl to use utt2dur if present, to balance splits" (#3746)

5.5.564 413c7c801 2019-12-02 [egs] Children's speech ASR recipe for cmu_kids and cslu_kids (#3699)

5.5.565 1cd7ee9eb 2019-12-02 [src] Incremental determinization [cleaned up/rewrite] (#3737)

5.5.566 d77457d11 2019-12-03 [scripts] Add scripts to create combine fmllr-tranform dirs(#3752)

5.5.567 018d18085 2019-12-05 [src] CUDA decoder: fix invalid-lattice error that happens in corner cases (#3756)

5.5.568 be2dbf4c9 2019-12-05 [egs] Add Chime 6 baseline system (#3755)

5.5.569 daf9d6e3f 2019-12-05 [scripts] Fix issue in copy_lat_dir.sh affecting combine_lat_dirs.sh (missing phones.txt) (#3757)

5.5.570 07d02da4f 2019-12-06 [src] Add missing #include, needed for CUDA decoder compilation on some platforms (#3759)

5.5.571 6f329a62e 2019-12-08 [scripts] fix bug in steps/data/reverberate_data_dir.py (#3762)

5.5.572 d0007f3de 2019-12-11 [src] CUDA allocator: fix order of next largest block (#3739)

5.5.573 454fb08ff 2019-12-11 [egs] some fixes in Chime6 baseline system (#3763)

5.5.574 42c3888d0 2019-12-11 [src] CUDA decoding: add support for affine transforms to CUDA feature extractor (#3764)

5.5.575 5ca36b9ad 2019-12-11 [src] relax assertion constraint slightly (RE matrix orthonormalization) (#3767)

5.5.576 cba392cbb 2019-12-12 [src] CUDA decoder: fix bug in NumPendingTasks() (#3769)

5.5.577 ea5757a19 2019-12-12 [src] Add options to select specific gpu, reuse cuda context (#3750)

5.5.578 799e1f06c 2019-12-13 [src] Move CheckAndFix to config struct (#3749)

5.5.579 e27bbda4b 2019-12-14 [egs,scripts] Add recipes for CN-Celeb (#3758)

5.5.580 1be47502c 2019-12-14 [src] CUDA decoder: remove unecessary sync that was added for debugging (#3770)

5.5.581 fe7b9226e 2019-12-17 [src] CUDA decoder: shrink channel vectors instead of vector holding those vectors (#3768)

5.5.582 c464dca11 2019-12-17 [src] Make decoders handle infinity in scores more gracefully #3679 (#3773)

5.5.583 b5bcf2f10 2019-12-17 [src] (cosmetic): replace a broken web link in wave-reader.h (#3774)

5.5.584 ba92f608f 2019-12-18 [src] stop at first successful gpu select (fix bug from #3750) (#3776)

5.5.585 f1c9ae0b0 2019-12-19 [src] Add nnet2 Chunking on GPU (#3761)

5.5.586 7d6cc37c7 2019-12-20 [build] Add -c (continue) option to wget in tools/Makefile (#3780)

5.5.587 7b762b1b3 2019-12-20 [build,src] Upgrade TensorFlow RNN to 2.0 (#3771)

5.5.588 83c986599 2019-12-24 [egs] In `egs/cmu_cslu_kids`, adding some early error handling to avoid confusion down the line (#3785)

5.5.589 e2a67e776 2019-12-25 [src] Fix bug in previous bugfix PR #3639 in resampling checks for online features (#3792)

5.5.590 92c8c6ce2 2019-12-26 [egs] Fix issue #3662 in Chime example script (#3794)

5.5.591 1f357ceb5 2019-12-26 [misc] Add option on github for kaldi10-related issues (#3796)

5.5.592 c101557fc 2020-01-05 [src] fix fstmakecontextfst duplicated disambig symbols (#3811)

5.5.593 f93c192b4 2020-01-06 [src] Fix wrong error message format in make_lexicon_fst.py

5.5.594 2b30a1e43 2020-01-06 [egs] Update librispeech TDNN-F recipe (#3813)

5.5.595 8e2bbd2fc 2020-01-07 [src] Enable multiple threads for chain-generic-numerator to remove CPU bottleneck (#3766)

5.5.596 129e28bd6 2020-01-08 [scripts] allowed_durations computation in standalone script

5.5.597 b0f6bcb76 2020-01-09 [src] Make compute-gop work with missing alignments (#3830)

5.5.598 cbdbedefc 2020-01-09 Update .travis config to build the pybind11 branch

5.5.599 1358f3839 2020-01-12 [src] Allow reading const FST in decode-faster-mapped (#3838)

5.5.600 611ff121d 2020-01-12 [build] Update the default MKL package to the newest version that was signed by the updated Intel key (#3839)

5.5.601 c7027423e 2020-01-13 [egs] use python not $PYTHON in librispeech text-norm (#3843)

5.5.602 f19692283 2020-01-14 [egs] recipe for GALE Arabic speech translation project (#3845)

5.5.603 5ba9d6668 2020-01-17 [egs] cmu_cslu_kids: using $train_cmd not queue.pl (#3853)

5.5.604 6247d3cf9 2020-01-17 [src] update Matrix in TableWriter to MatrixBase for more generality (#3847)

5.5.605 4bbacd0e3 2020-01-18 [scripts] Clarify error message from scp.pl improve (#3854)

5.5.606 06276449b 2020-01-20 [src] Fix for how lattice-incremental-decoder deals with failure (#3855)

5.5.607 33255ed22 2020-01-21 [src] Allow reading const Fst through ReadFstKaldiGeneric

5.5.608 1a46d94c4 2020-01-22 [egs] Add recipe for Mandarin BN/BC data, for speech translation project. (#3866)

5.5.609 2b3e7641e 2020-01-22 [src] #include <algorithm> in kaldi-thread.h (necessary when using CMake+MSVC) (#3864)

5.5.610 23868d594 2020-01-22 Revert "[src] Allow reading const Fst through ReadFstKaldiGeneric" (#3871)

5.5.611 fdb2d57df 2020-01-24 [egs] fix displayed WER fraction in CHiME6 (#3872)

5.5.612 216c5181e 2020-01-25 [src] Add online-batched-cuda-cmvn. (#3875)

5.5.613 ea6e1b7a7 2020-01-26 Revert "[src] Add online-batched-cuda-cmvn. (#3875)" (#3876)

5.5.614 1dcb70d7a 2020-01-26 [src] Add batched GPU-based online CMVN feature extraction (#3877)

5.5.615 56ee1927d 2020-01-27 [src] fix the compilation issues (#3883)

5.5.616 a4fb20122 2020-01-28 [src] Fix issue found by Remi Francis in incremental decoder, causing failure (#3874)

5.5.617 fd6aabb25 2020-01-28 [scripts] make adjust_unk_graph.sh output const-FST (#3884)

5.5.618 48d2115e4 2020-01-29 [scripts,egs] Fix shebangs on bash scripts to #!/usr/bin/env bash, for portability (#3881)

5.5.619 1121c3121 2020-01-29 [src] Batched spectral feature extraction on GPU (#3889)

5.5.620 5882dc517 2020-01-29 [egs] gale_arabic: add python script to process xml file (#3886)

5.5.621 5a706bc5a 2020-01-30 Upstream online batched pipeline (#3891)

5.5.622 dce1dccd4 2020-01-30 [src] add CUDA compile guard (#3895)

5.5.623 6c5176c38 2020-02-01 [src] Fix to batch i-vector computation RE undefined data (#3898)

5.5.624 a4f2f341c 2020-02-01 [src] Fix compilation issue with older toolkit/compiler, add __host__ (#3900)

5.5.625 f55bc9ab1 2020-02-02 [src] Build fixes when CUDA version is less than 9.1 (#3901)

5.5.626 24e9cfa2a 2020-02-03 [src] Enable compilation (->runtime failure) with CUDA < 10.0 for CUDA batched feats (#3903)

5.5.627 98f2edfeb 2020-02-03 [src] Make ivector-extract-online2.cc ignore pitch in case of dim mismatch (#3742)

5.5.628 0609ace4a 2020-02-04 [src] Cosmetic fix to error messages, decodable-matrix.cc (#3905)

5.5.629 7a17e9553 2020-02-04 [src] Cosmetic fix to error message in decodable-matrix.h (#3904)

5.5.630 ac6b12a9e 2020-02-04 [src] use const& for catch; avoid compiler warnings for gcc>8 (#3909)

5.5.631 321d3959d 2020-02-05 [egs] Make find follow symbolic links in formosa recipe (#3912)

5.5.632 4225a2aca 2020-02-06 [src] (GPU decoding/features) Fix memory corruption by making cmvn_state local (#3914)

5.5.633 84d19f6a1 2020-02-06 [egs] In formosa recipe, remove \u3000 and \u00a0 to prevent failure in validate_text.pl (#3913)

5.5.634 2c216c9ec 2020-02-07 [egs] Add script to prepare Arabic Gigawords as external data for LM training, add results (#3917)

5.5.635 2c4f1dad0 2020-02-07 [scripts] updated_fix_subsegment_feats.pl to handle row_start >= file length (#3915)

5.5.636 7a50987e7 2020-02-08 [scripts] Bug-fix: ensure allowed lengths all written as int (#3919)