{
    "info": {
        "author": "Guenter Bartsch",
        "author_email": "guenter@zamia.org",
        "bugtrack_url": null,
        "classifiers": [
            "Intended Audience :: Developers",
            "License :: OSI Approved :: Apache Software License",
            "Operating System :: POSIX :: Linux",
            "Programming Language :: Python :: 2",
            "Programming Language :: Python :: 2.7",
            "Topic :: Multimedia :: Sound/Audio :: Speech",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Software Development :: Libraries :: Python Modules"
        ],
        "description": "# kaldi-adapt-lm\n\nAdapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different\nlanguage model.\n\nConstructive comments, patches and pull-requests are very welcome.\n\nTutorial\n--------\n\nTo create the language model we would like to adapt our kaldi model to, we first\nneed to create a set of sentences. To get started, download and uncompress a generic set\nof sentences for you language, e.g.\n\n    wget 'http://goofy.zamia.org/zamia-speech/misc/sentences-en.txt.xz'\n    unxz sentences-en.txt.xz\n\nnow suppose the file utts.txt contained the sentences you would like the model to\nrecognize with a higher probability than the rest. To achieve that, we add these\nsentences five times in this examples to our text body:\n\n    cat utts.txt utts.txt utts.txt utts.txt utts.txt sentences-en.txt >lm.txt\n\nwe also want to limit our language model to the vocabulary the audio model supports,\nso let's extract the vocabulary next:\n\n    MODEL=\"models/kaldi-generic-en-tdnn_sp-latest\"\n    cut -f 1 -d ' ' ${MODEL}/data/local/dict/lexicon.txt >vocab.txt\n\nwith those files in place we can now train our new language model using KenLM:\n\n    lmplz -o 4 --prune 0 1 2 3 --limit_vocab_file vocab.txt --interpolate_unigrams 0 <lm.txt >lm.arpa\n\nNow we can start the kaldi model adaptation process:\n\n    kaldi-adapt-lm ${MODEL} lm.arpa mymodel\n\nYou should now be able to find a tarball of the resulting model inside the work subdirectory.\n\nLinks\n-----\n\n- <http://kaldi-asr.org/> [Kaldi ASR] \n- <https://zamia-speech.org> [Zamia Speech] \n\nRequirements\n------------\n\n- Python 2\n- Kaldi ASR\n\nLicense\n-------\n\nMy own code is Apache-2.0 licensed unless otherwise noted in the\nscript\u2019s copyright headers.\n\nAuthor\n------\n\nGuenter Bartsch \\<<guenter@zamia.org>\\>\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/gooofy/kaldi-adapt-lm",
        "keywords": "natural language processing nlp asr speech recognition kaldi",
        "license": "Apache",
        "maintainer": "",
        "maintainer_email": "",
        "name": "kaldi-adapt-lm",
        "package_url": "https://pypi.org/project/kaldi-adapt-lm/",
        "platform": "",
        "project_url": "https://pypi.org/project/kaldi-adapt-lm/",
        "project_urls": {
            "Homepage": "https://github.com/gooofy/kaldi-adapt-lm"
        },
        "release_url": "https://pypi.org/project/kaldi-adapt-lm/0.1.3/",
        "requires_dist": [
            "py-nltools"
        ],
        "requires_python": "",
        "summary": "Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model.",
        "version": "0.1.3"
    },
    "last_serial": 4202874,
    "releases": {
        "0.1.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "498ea12488241df69f207ca0d1b0615c",
                    "sha256": "108fb4ee444188095fb74569daa01e95b4de66af47405d0670b6e23b2b95a74a"
                },
                "downloads": -1,
                "filename": "kaldi_adapt_lm-0.1.3-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "498ea12488241df69f207ca0d1b0615c",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 10248,
                "upload_time": "2018-08-24T08:35:56",
                "url": "https://files.pythonhosted.org/packages/1e/45/b253ce5673905b0ff1772b16a3f3160bf39fb94e947fa08d83bf611e7650/kaldi_adapt_lm-0.1.3-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "68efdfb55437fae31bea4e1bd77fd165",
                    "sha256": "81a094adee4d27e22e7a6877d4cdd0c9948a70c69fac2822e7a7fb5f22cb2bc1"
                },
                "downloads": -1,
                "filename": "kaldi-adapt-lm-0.1.3.tar.gz",
                "has_sig": false,
                "md5_digest": "68efdfb55437fae31bea4e1bd77fd165",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4090,
                "upload_time": "2018-08-24T08:35:57",
                "url": "https://files.pythonhosted.org/packages/41/10/ea00fb6ed3ef886b6f3e31dc1e8fb9adda5fce4eb1f33fc23288ca8d1aff/kaldi-adapt-lm-0.1.3.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "498ea12488241df69f207ca0d1b0615c",
                "sha256": "108fb4ee444188095fb74569daa01e95b4de66af47405d0670b6e23b2b95a74a"
            },
            "downloads": -1,
            "filename": "kaldi_adapt_lm-0.1.3-py2.py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "498ea12488241df69f207ca0d1b0615c",
            "packagetype": "bdist_wheel",
            "python_version": "py2.py3",
            "requires_python": null,
            "size": 10248,
            "upload_time": "2018-08-24T08:35:56",
            "url": "https://files.pythonhosted.org/packages/1e/45/b253ce5673905b0ff1772b16a3f3160bf39fb94e947fa08d83bf611e7650/kaldi_adapt_lm-0.1.3-py2.py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "68efdfb55437fae31bea4e1bd77fd165",
                "sha256": "81a094adee4d27e22e7a6877d4cdd0c9948a70c69fac2822e7a7fb5f22cb2bc1"
            },
            "downloads": -1,
            "filename": "kaldi-adapt-lm-0.1.3.tar.gz",
            "has_sig": false,
            "md5_digest": "68efdfb55437fae31bea4e1bd77fd165",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 4090,
            "upload_time": "2018-08-24T08:35:57",
            "url": "https://files.pythonhosted.org/packages/41/10/ea00fb6ed3ef886b6f3e31dc1e8fb9adda5fce4eb1f33fc23288ca8d1aff/kaldi-adapt-lm-0.1.3.tar.gz"
        }
    ]
}