├── .gitignore ├── LICENSE ├── Makefile ├── README.md ├── kaldi-adapt-lm ├── kaldiadaptlm ├── __init__.py └── templates │ ├── kaldi-cmd.sh │ ├── kaldi-model-dist.sh │ ├── kaldi-path.sh.template │ └── kaldi-run-adaptation.sh └── setup.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | MANIFEST 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | .pytest_cache/ 49 | 50 | # Translations 51 | *.mo 52 | *.pot 53 | 54 | # Django stuff: 55 | *.log 56 | local_settings.py 57 | db.sqlite3 58 | 59 | # Flask stuff: 60 | instance/ 61 | .webassets-cache 62 | 63 | # Scrapy stuff: 64 | .scrapy 65 | 66 | # Sphinx documentation 67 | docs/_build/ 68 | 69 | # PyBuilder 70 | target/ 71 | 72 | # Jupyter Notebook 73 | .ipynb_checkpoints 74 | 75 | # pyenv 76 | .python-version 77 | 78 | # celery beat schedule file 79 | celerybeat-schedule 80 | 81 | # SageMath parsed files 82 | *.sage.py 83 | 84 | # Environments 85 | .env 86 | .venv 87 | env/ 88 | venv/ 89 | ENV/ 90 | env.bak/ 91 | venv.bak/ 92 | 93 | # Spyder project settings 94 | .spyderproject 95 | .spyproject 96 | 97 | # Rope project settings 98 | .ropeproject 99 | 100 | # mkdocs documentation 101 | /site 102 | 103 | # mypy 104 | .mypy_cache/ 105 | 106 | 107 | lm.arpa 108 | models/ 109 | old/ 110 | tst/ 111 | work.1/ 112 | work/ 113 | 114 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | SHELL := /bin/bash 2 | 3 | all: dist 4 | 5 | dist: 6 | python setup.py sdist 7 | python setup.py bdist_wheel --universal 8 | 9 | upload: 10 | twine upload dist/* 11 | 12 | clean: 13 | rm -f *.html 14 | rm -rf dist build kaldi_adapt_lm.egg-info 15 | 16 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # kaldi-adapt-lm 2 | 3 | Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different 4 | language model. 5 | 6 | Constructive comments, patches and pull-requests are very welcome. 7 | 8 | Tutorial 9 | -------- 10 | 11 | To create the language model we would like to adapt our kaldi model to, we first 12 | need to create a set of sentences. To get started, download and uncompress a generic set 13 | of sentences for you language, e.g. 14 | 15 | wget 'http://goofy.zamia.org/zamia-speech/misc/sentences-en.txt.xz' 16 | unxz sentences-en.txt.xz 17 | 18 | now suppose the file utts.txt contained the sentences you would like the model to 19 | recognize with a higher probability than the rest. To achieve that, we add these 20 | sentences five times in this examples to our text body: 21 | 22 | cat utts.txt utts.txt utts.txt utts.txt utts.txt sentences-en.txt >lm.txt 23 | 24 | we also want to limit our language model to the vocabulary the audio model supports, 25 | so let's extract the vocabulary next: 26 | 27 | MODEL="models/kaldi-generic-en-tdnn_sp-latest" 28 | cut -f 1 -d ' ' ${MODEL}/data/local/dict/lexicon.txt >vocab.txt 29 | 30 | with those files in place we can now train our new language model using KenLM: 31 | 32 | lmplz -o 4 --prune 0 1 2 3 --limit_vocab_file vocab.txt --interpolate_unigrams 0 lm.arpa 33 | 34 | Now we can start the kaldi model adaptation process: 35 | 36 | kaldi-adapt-lm ${MODEL} lm.arpa mymodel 37 | 38 | You should now be able to find a tarball of the resulting model inside the work subdirectory. 39 | 40 | If at the end of adaptation process you have a lot of messages like "cp: cannot stat 41 | 'exp/adapt/graph/HCLG.fst': No such file or directory", then highly likely you run out of memory 42 | during adaptation process. (For example adapting kaldi-generic-en-tdnn_250 model consumes near 12Gb 43 | of RAM) 44 | 45 | Links 46 | ----- 47 | 48 | - [Kaldi ASR] 49 | - [Zamia Speech] 50 | 51 | Requirements 52 | ------------ 53 | 54 | - Python 2 55 | - Kaldi ASR 56 | 57 | License 58 | ------- 59 | 60 | My own code is Apache-2.0 licensed unless otherwise noted in the 61 | script’s copyright headers. 62 | 63 | Author 64 | ------ 65 | 66 | Guenter Bartsch \<\> 67 | -------------------------------------------------------------------------------- /kaldi-adapt-lm: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # 5 | # Copyright 2016, 2017, 2018 Guenter Bartsch 6 | # 7 | # Licensed under the Apache License, Version 2.0 (the "License"); 8 | # you may not use this file except in compliance with the License. 9 | # You may obtain a copy of the License at 10 | # 11 | # http://www.apache.org/licenses/LICENSE-2.0 12 | # 13 | # Unless required by applicable law or agreed to in writing, software 14 | # distributed under the License is distributed on an "AS IS" BASIS, 15 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 16 | # See the License for the specific language governing permissions and 17 | # limitations under the License. 18 | # 19 | 20 | # 21 | # adapt an existing kaldi model to a new language model 22 | # 23 | 24 | import os 25 | import sys 26 | import logging 27 | 28 | from optparse import OptionParser 29 | from nltools import misc 30 | from kaldiadaptlm import kaldi_adapt_lm 31 | 32 | DEFAULT_KALDI_ROOT = '/opt/kaldi' 33 | DEFAULT_WORK_DIR = 'work' 34 | 35 | # 36 | # init 37 | # 38 | 39 | misc.init_app ('kaldi-adapt-lm') 40 | 41 | # 42 | # commandline parsing 43 | # 44 | 45 | parser = OptionParser("usage: %prog [options] src_model_dir lm.arpa dst_model_name") 46 | 47 | parser.add_option ("-f", "--force", action="store_true", dest="force", 48 | help="overwrite work dir if it exists") 49 | 50 | parser.add_option ("-k", "--kaldi-root", dest="kaldi_root", type = "str", default=DEFAULT_KALDI_ROOT, 51 | help="kaldi root dir (default: %s)" % DEFAULT_KALDI_ROOT) 52 | 53 | parser.add_option ("-v", "--verbose", action="store_true", dest="verbose", 54 | help="enable verbose logging") 55 | 56 | parser.add_option ("-w", "--work-dir", dest="work_dir", type = "str", default=DEFAULT_WORK_DIR, 57 | help="work dir (default: %s)" % DEFAULT_WORK_DIR) 58 | 59 | (options, args) = parser.parse_args() 60 | 61 | if options.verbose: 62 | logging.basicConfig(level=logging.DEBUG) 63 | else: 64 | logging.basicConfig(level=logging.INFO) 65 | 66 | if len(args) != 3: 67 | parser.print_usage() 68 | sys.exit(1) 69 | 70 | src_model_dir = args[0] 71 | lm_fn = args[1] 72 | dst_model_name = args[2] 73 | work_dir = options.work_dir 74 | 75 | if os.path.exists(work_dir): 76 | if options.force: 77 | # 78 | # cleanup leftovers from previous runs 79 | # 80 | cmd = 'rm -rf %s' % work_dir 81 | logging.info(cmd) 82 | os.system(cmd) 83 | else: 84 | logging.error("work dir %s already exists." % work_dir) 85 | sys.exit(1) 86 | 87 | kaldi_root = options.kaldi_root 88 | 89 | # 90 | # main 91 | # 92 | 93 | kaldi_adapt_lm (kaldi_root, src_model_dir, lm_fn, work_dir, dst_model_name) 94 | 95 | logging.info ( "All done." ) 96 | 97 | -------------------------------------------------------------------------------- /kaldiadaptlm/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # 5 | # Copyright 2016, 2017, 2018 Guenter Bartsch 6 | # 7 | # Licensed under the Apache License, Version 2.0 (the "License"); 8 | # you may not use this file except in compliance with the License. 9 | # You may obtain a copy of the License at 10 | # 11 | # http://www.apache.org/licenses/LICENSE-2.0 12 | # 13 | # Unless required by applicable law or agreed to in writing, software 14 | # distributed under the License is distributed on an "AS IS" BASIS, 15 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 16 | # See the License for the specific language governing permissions and 17 | # limitations under the License. 18 | # 19 | 20 | # 21 | # adapt an existing kaldi model to a new language model 22 | # 23 | 24 | import os 25 | import sys 26 | import logging 27 | 28 | from nltools import misc 29 | 30 | def kaldi_adapt_lm(kaldi_root, src_model_dir, lm_fn, work_dir, dst_model_name): 31 | 32 | steps_path = '%s/egs/wsj/s5/steps' % kaldi_root 33 | if not os.path.exists (steps_path): 34 | raise Exception ('%s does not exist - is kaldi really installed in %s ?' % (steps_path, kaldi_root)) 35 | 36 | tmpl_dir = os.path.dirname(os.path.abspath(__file__)) + '/templates' 37 | 38 | # 39 | # copy dictionary and phoneme sets from original model 40 | # 41 | 42 | logging.info("copying dictionary and phoneme sets from original model...") 43 | 44 | misc.mkdirs('%s/data/local/dict' % work_dir) 45 | misc.copy_file ('%s/data/local/dict/lexicon.txt' % src_model_dir, '%s/data/local/dict/lexicon.txt' % work_dir) 46 | misc.copy_file ('%s/data/local/dict/nonsilence_phones.txt' % src_model_dir, '%s/data/local/dict/nonsilence_phones.txt' % work_dir) 47 | misc.copy_file ('%s/data/local/dict/silence_phones.txt' % src_model_dir, '%s/data/local/dict/silence_phones.txt' % work_dir) 48 | misc.copy_file ('%s/data/local/dict/optional_silence.txt' % src_model_dir, '%s/data/local/dict/optional_silence.txt' % work_dir) 49 | misc.copy_file ('%s/data/local/dict/extra_questions.txt' % src_model_dir, '%s/data/local/dict/extra_questions.txt' % work_dir) 50 | 51 | # 52 | # language model 53 | # 54 | 55 | misc.copy_file (lm_fn, '%s/lm.arpa' % work_dir) 56 | 57 | # 58 | # create skeleton dst model 59 | # 60 | 61 | logging.info("creating skeleton destination model...") 62 | 63 | misc.mkdirs ('%s/exp/adapt' % work_dir) 64 | 65 | misc.copy_file ('%s/model/final.mdl' % src_model_dir, '%s/exp/adapt/final.mdl' % work_dir) 66 | misc.copy_file ('%s/model/cmvn_opts' % src_model_dir, '%s/exp/adapt/cmvn_opts' % work_dir) 67 | misc.copy_file ('%s/model/tree' % src_model_dir, '%s/exp/adapt/tree' % work_dir) 68 | 69 | for optional_file in [ 'final.mat', 'splice_opts', 'final.occs', 'full.mat' ] : 70 | if os.path.exists('%s/model/%s' % (src_model_dir, optional_file)): 71 | misc.copy_file ('%s/model/%s' % (src_model_dir, optional_file), '%s/exp/adapt/%s' % (work_dir, optional_file)) 72 | 73 | if os.path.exists('%s/extractor' % src_model_dir): 74 | 75 | misc.mkdirs ('%s/exp/extractor' % work_dir) 76 | 77 | misc.copy_file ('%s/extractor/final.mat' % src_model_dir, '%s/exp/extractor/final.mat' % work_dir) 78 | misc.copy_file ('%s/extractor/global_cmvn.stats' % src_model_dir, '%s/exp/extractor/global_cmvn.stats' % work_dir) 79 | misc.copy_file ('%s/extractor/final.dubm' % src_model_dir, '%s/exp/extractor/final.dubm' % work_dir) 80 | misc.copy_file ('%s/extractor/final.ie' % src_model_dir, '%s/exp/extractor/final.ie' % work_dir) 81 | misc.copy_file ('%s/extractor/splice_opts' % src_model_dir, '%s/exp/extractor/splice_opts' % work_dir) 82 | 83 | misc.mkdirs ('%s/exp/ivectors_test_hires/conf' % work_dir) 84 | 85 | misc.copy_file ('%s/ivectors_test_hires/conf/splice.conf' % src_model_dir, '%s/exp/ivectors_test_hires/conf' % work_dir) 86 | misc.copy_file ('%s/ivectors_test_hires/conf/ivector_extractor.conf' % src_model_dir, '%s/exp/ivectors_test_hires/conf' % work_dir) 87 | misc.copy_file ('%s/ivectors_test_hires/conf/online_cmvn.conf' % src_model_dir, '%s/exp/ivectors_test_hires/conf' % work_dir) 88 | 89 | misc.mkdirs ('%s/conf' % work_dir) 90 | misc.copy_file ('%s/conf/mfcc.conf' % src_model_dir, '%s/conf/mfcc.conf' % work_dir) 91 | misc.copy_file ('%s/conf/mfcc_hires.conf' % src_model_dir, '%s/conf/mfcc_hires.conf' % work_dir) 92 | misc.copy_file ('%s/conf/online_cmvn.conf' % src_model_dir, '%s/conf/online_cmvn.conf' % work_dir) 93 | 94 | # 95 | # copy scripts and config files 96 | # 97 | 98 | misc.copy_file ('%s/kaldi-run-adaptation.sh' % tmpl_dir, '%s/run-adaptation.sh' % work_dir) 99 | misc.copy_file ('%s/kaldi-cmd.sh' % tmpl_dir, '%s/cmd.sh' % work_dir) 100 | misc.render_template ('%s/kaldi-path.sh.template' % tmpl_dir, '%s/path.sh' % work_dir, kaldi_root=kaldi_root) 101 | misc.copy_file ('%s/kaldi-model-dist.sh' % tmpl_dir, '%s/model-dist.sh' % work_dir) 102 | 103 | misc.symlink ('%s/egs/wsj/s5/steps' % kaldi_root, '%s/steps' % work_dir) 104 | misc.symlink ('%s/egs/wsj/s5/utils' % kaldi_root, '%s/utils' % work_dir) 105 | 106 | cmd = '/bin/bash -c "pushd %s && bash run-adaptation.sh && popd"' % work_dir 107 | logging.info (cmd) 108 | os.system (cmd) 109 | 110 | cmd = '/bin/bash -c "pushd %s && bash model-dist.sh "%s" && popd"' % (work_dir, dst_model_name) 111 | logging.info (cmd) 112 | os.system (cmd) 113 | 114 | 115 | -------------------------------------------------------------------------------- /kaldiadaptlm/templates/kaldi-cmd.sh: -------------------------------------------------------------------------------- 1 | # "queue.pl" uses qsub. The options to it are 2 | # options to qsub. If you have GridEngine installed, 3 | # change this to a queue you have access to. 4 | # Otherwise, use "run.pl", which will run jobs locally 5 | # (make sure your --num-jobs options are no more than 6 | # the number of cpus on your machine. 7 | 8 | 9 | #activate this if you want to run the corpus with gridengine (http://gridengine.org/) 10 | #export train_cmd="queue.pl -l 'arch=*64*'" 11 | #export decode_cmd="queue.pl -l 'arch=*64*'" 12 | #export cuda_cmd="queue.pl -l gpu=1" 13 | 14 | export train_cmd="utils/run.pl" 15 | export decode_cmd="utils/run.pl" 16 | export cuda_cmd="utils/run.pl -l gpu=1" 17 | 18 | export nJobs=12 19 | export nDecodeJobs=12 20 | -------------------------------------------------------------------------------- /kaldiadaptlm/templates/kaldi-model-dist.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | if [ $# != 1 ] ; then 4 | echo "usage: $0 " 5 | exit 2 6 | fi 7 | 8 | MODEL=$1 9 | 10 | EXPNAME=adapt 11 | EXPDIR="exp" 12 | 13 | AMNAME="kaldi-${MODEL}-${EXPNAME}" 14 | 15 | echo "$AMNAME ..." 16 | 17 | rm -rf "$AMNAME" 18 | mkdir -p "$AMNAME/model" 19 | 20 | cp $EXPDIR/$EXPNAME/final.mdl $AMNAME/model/ 21 | cp $EXPDIR/$EXPNAME/final.mat $AMNAME/model/ 2>/dev/null 22 | cp $EXPDIR/$EXPNAME/final.occs $AMNAME/model/ 2>/dev/null 23 | cp $EXPDIR/$EXPNAME/full.mat $AMNAME/model/ 2>/dev/null 24 | cp $EXPDIR/$EXPNAME/splice_opts $AMNAME/model/ 2>/dev/null 25 | cp $EXPDIR/$EXPNAME/cmvn_opts $AMNAME/model/ 2>/dev/null 26 | cp $EXPDIR/$EXPNAME/tree $AMNAME/model/ 2>/dev/null 27 | 28 | mkdir -p "$AMNAME/model/graph" 29 | 30 | cp $EXPDIR/$EXPNAME/graph/HCLG.fst $AMNAME/model/graph/ 31 | cp $EXPDIR/$EXPNAME/graph/words.txt $AMNAME/model/graph/ 32 | cp $EXPDIR/$EXPNAME/graph/num_pdfs $AMNAME/model/graph/ 33 | cp $EXPDIR/$EXPNAME/graph/phones.txt $AMNAME/model/graph/ 34 | 35 | mkdir -p "$AMNAME/model/graph/phones" 36 | cp $EXPDIR/$EXPNAME/graph/phones/* $AMNAME/model/graph/phones/ 37 | 38 | if [ -e $EXPDIR/extractor/final.mat ] ; then 39 | 40 | mkdir -p "$AMNAME/extractor" 41 | 42 | cp $EXPDIR/extractor/final.mat $AMNAME/extractor/ 43 | cp $EXPDIR/extractor/global_cmvn.stats $AMNAME/extractor/ 44 | cp $EXPDIR/extractor/final.dubm $AMNAME/extractor/ 45 | cp $EXPDIR/extractor/final.ie $AMNAME/extractor/ 46 | cp $EXPDIR/extractor/splice_opts $AMNAME/extractor/ 47 | 48 | mkdir -p "$AMNAME/ivectors_test_hires/conf" 49 | 50 | cp $EXPDIR/ivectors_test_hires/conf/ivector_extractor.conf $AMNAME/ivectors_test_hires/conf/ 51 | cp $EXPDIR/ivectors_test_hires/conf/online_cmvn.conf $AMNAME/ivectors_test_hires/conf/ 52 | cp $EXPDIR/ivectors_test_hires/conf/splice.conf $AMNAME/ivectors_test_hires/conf/ 53 | 54 | fi 55 | 56 | mkdir -p "$AMNAME/data/local/dict" 57 | cp data/local/dict/* $AMNAME/data/local/dict/ 58 | 59 | cp -rp data/lang $AMNAME/data/ 60 | 61 | mkdir -p "$AMNAME/conf" 62 | cp conf/mfcc.conf $AMNAME/conf/mfcc.conf 63 | cp conf/mfcc_hires.conf $AMNAME/conf/mfcc_hires.conf 64 | cp conf/online_cmvn.conf $AMNAME/conf/online_cmvn.conf 65 | 66 | rm -f "$AMNAME.tar" "$AMNAME.tar.xz" 67 | tar cfv "$AMNAME.tar" $AMNAME 68 | xz -v -8 -T 12 "$AMNAME.tar" 69 | 70 | rm -r "$AMNAME" 71 | 72 | -------------------------------------------------------------------------------- /kaldiadaptlm/templates/kaldi-path.sh.template: -------------------------------------------------------------------------------- 1 | export KALDI_ROOT={{kaldi_root}} 2 | export LD_LIBRARY_PATH="$KALDI_ROOT/tools/openfst/lib:$KALDI_ROOT/src/lib:$LD_LIBRARY_PATH" 3 | export PATH=$KALDI_ROOT/src/lmbin/:$KALDI_ROOT/../kaldi_lm/:$PWD/utils/:$KALDI_ROOT/src/bin:$KALDI_ROOT/tools/openfst/bin:$KALDI_ROOT/src/fstbin/:$KALDI_ROOT/src/gmmbin/:$KALDI_ROOT/src/featbin/:$KALDI_ROOT/src/lm/:$KALDI_ROOT/src/sgmmbin/:$KALDI_ROOT/src/sgmm2bin/:$KALDI_ROOT/src/fgmmbin/:$KALDI_ROOT/src/latbin/:$KALDI_ROOT/src/nnetbin:$KALDI_ROOT/src/nnet2bin/:$KALDI_ROOT/src/online2bin/:$KALDI_ROOT/src/ivectorbin/:$KALDI_ROOT/src/kwsbin:$KALDI_ROOT/src/nnet3bin:$KALDI_ROOT/src/chainbin:$PWD:$PATH 4 | export LC_ALL=C 5 | -------------------------------------------------------------------------------- /kaldiadaptlm/templates/kaldi-run-adaptation.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Copyright 2016, 2017, 2018 G. Bartsch 4 | # Copyright 2015 Language Technology, Technische Universitaet Darmstadt (author: Benjamin Milde) 5 | # Copyright 2014 QCRI (author: Ahmed Ali) 6 | # 7 | # Licensed under the Apache License, Version 2.0 (the "License"); 8 | # you may not use this file except in compliance with the License. 9 | # You may obtain a copy of the License at 10 | # 11 | # http://www.apache.org/licenses/LICENSE-2.0 12 | # 13 | # Unless required by applicable law or agreed to in writing, software 14 | # distributed under the License is distributed on an "AS IS" BASIS, 15 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 16 | # See the License for the specific language governing permissions and 17 | # limitations under the License. 18 | # 19 | # adapted from kaldi-tuda-de run.sh 20 | # adapted from wsj's run.sh 21 | 22 | # 23 | # adapt kaldi model to our current dict and srilm-generated LM 24 | # 25 | 26 | # now start preprocessing with KALDI scripts 27 | 28 | if [ -f cmd.sh ]; then 29 | . cmd.sh; else 30 | echo "missing cmd.sh"; exit 1; 31 | fi 32 | 33 | #Path also sets LC_ALL=C for Kaldi, otherwise you will experience strange (and hard to debug!) bugs. It should be set here, after the python scripts and not at the beginning of this script 34 | if [ -f path.sh ]; then 35 | . path.sh; else 36 | echo "missing path.sh"; exit 1; 37 | 38 | fi 39 | 40 | # echo "Runtime configuration is: nJobs $nJobs, nDecodeJobs $nDecodeJobs. If this is not what you want, edit cmd.sh" 41 | 42 | #Make sure that LC_ALL is C for Kaldi, otherwise you will experience strange (and hard to debug!) bugs 43 | export LC_ALL=C 44 | 45 | # remove old lang dir if it exists 46 | rm -rf data/lang 47 | rm -rf data/local/lang 48 | 49 | #Prepare phoneme data for Kaldi 50 | utils/prepare_lang.sh data/local/dict "nspc" data/local/lang data/lang 51 | 52 | lmdir=data/local/lm.adapt 53 | lang=data/lang.adapt_test 54 | 55 | rm -rf $lmdir 56 | mkdir $lmdir 57 | rm -rf $lang 58 | cp -r data/lang $lang 59 | 60 | echo 61 | echo "creating G.fst..." 62 | 63 | if [ -f lm.arpa ] ; then 64 | 65 | cat lm.arpa | utils/find_arpa_oovs.pl $lang/words.txt > $lmdir/oovs_lm.txt 66 | 67 | cat lm.arpa | \ 68 | grep -v ' ' | \ 69 | grep -v ' ' | \ 70 | grep -v ' ' | \ 71 | arpa2fst - | fstprint | \ 72 | utils/remove_oovs.pl $lmdir/oovs_lm.txt | \ 73 | utils/eps2disambig.pl | utils/s2eps.pl | fstcompile --isymbols=$lang/words.txt \ 74 | --osymbols=$lang/words.txt --keep_isymbols=false --keep_osymbols=false | \ 75 | fstrmepsilon > $lang/G.fst 76 | 77 | fi 78 | 79 | if [ -f G.src.fst ] ; then 80 | cat G.src.fst | fstcompile --isymbols=$lang/words.txt --osymbols=$lang/words.txt --keep_isymbols=false --keep_osymbols=false | fstrmepsilon > $lang/G.fst 81 | # fstdraw --isymbols="${MODEL}/words.txt" --osymbols="${MODEL}/words.txt" -portrait G.fst | dot -Tjpg >G.jpg 82 | fi 83 | 84 | if [ -f G.jsgf ] ; then 85 | sphinx_jsgf2fsg -jsgf G.jsgf -fsm G.fsm 86 | fstcompile --acceptor --isymbols=$lang/words.txt --osymbols=$lang/words.txt --keep_isymbols=false --keep_osymbols=false G.fsm | fstrmepsilon > $lang/G.fst 87 | fi 88 | 89 | # 90 | # adapt our model 91 | # 92 | 93 | expdir=exp/adapt 94 | 95 | utils/mkgraph.sh $lang $expdir $expdir/graph || exit 1; 96 | 97 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup( 4 | name = 'kaldi-adapt-lm', 5 | version = '0.1.4', 6 | description = 'Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model.', 7 | long_description = open('README.md').read(), 8 | author = 'Guenter Bartsch', 9 | author_email = 'guenter@zamia.org', 10 | maintainer = 'Guenter Bartsch', 11 | maintainer_email = 'guenter@zamia.org', 12 | url = 'https://github.com/gooofy/kaldi-adapt-lm', 13 | packages = [ 'kaldiadaptlm' ], 14 | install_requires = [ 'py-nltools' ], 15 | scripts = [ 'kaldi-adapt-lm' ], 16 | classifiers = [ 17 | 'Operating System :: POSIX :: Linux', 18 | 'License :: OSI Approved :: Apache Software License', 19 | 'Programming Language :: Python :: 2', 20 | 'Programming Language :: Python :: 2.7', 21 | 'Intended Audience :: Developers', 22 | 'Topic :: Software Development :: Libraries :: Python Modules', 23 | 'Topic :: Multimedia :: Sound/Audio :: Speech', 24 | 'Topic :: Scientific/Engineering :: Artificial Intelligence' 25 | ], 26 | license = 'Apache', 27 | keywords = 'natural language processing nlp asr speech recognition kaldi', 28 | package_data = {'kaldiadaptlm': ['templates/*']}, 29 | include_package_data = True 30 | ) 31 | 32 | --------------------------------------------------------------------------------