{
"info": {
"author": "CoEDL",
"author_email": "n.lambourne@uq.edu.au",
"bugtrack_url": null,
"classifiers": [
"Operating System :: OS Independent",
"Programming Language :: Python :: 3.6",
"Topic :: Text Processing :: Linguistic"
],
"description": "# CoEDL Kaldi Helpers
\n\nA set of scripts to use in preparing a corpus for speech-to-text processing with the [Kaldi](http://kaldi-asr.org/) \nAutomatic Speech Recognition Library.\n\nRead about [setting up Docker](https://github.com/CoEDL/elpis/wiki/2018-summer-workshop-preparation) to run all this.\n\nFor more information about data requirements, see the \n[data guide](https://github.com/CoEDL/elpis/wiki/2018-summer-workshop-preparation).\n\n## Requirements\nThis pipeline relies on Python 3.6 and several open-source Python packages (listed [here](./requirements.txt)).\nIt also assumes you have Kaldi, [sox](http://sox.sourceforge.net/) and [task](https://taskfile.org/) installed. We \nhighly recommend using [our docker image](https://github.com/CoEDL/elpis/wiki/2018-summer-workshop-preparation).\n\n## Tasks\nThis library uses the [task](https://taskfile.org) tool to run the more complex processes automatically. Once \nyou've set up Kaldi Helpers, you can run the various pipeline tasks we've developed (or out of the box in the docker \nimage). You can read about these tasks [here](https://github.com/CoEDL/elpis/wiki/tasks). \n\n## Workflow\n
\n \n