https://github.com/CoEDL/elpis

🙊 software for creating speech recognition models.
https://github.com/CoEDL/elpis

automatic-speech-recognition computational-linguistics docker kaldi linguistics python transcription

Last synced: 5 months ago
JSON representation

🙊 software for creating speech recognition models.

• Host: GitHub
• URL: https://github.com/CoEDL/elpis
• Owner: CoEDL
• License: apache-2.0
• Created: 2018-10-25T02:00:37.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2024-06-02T23:15:46.000Z (over 1 year ago)
• Last Synced: 2024-11-15T11:36:28.978Z (11 months ago)
• Topics: automatic-speech-recognition, computational-linguistics, docker, kaldi, linguistics, python, transcription
• Language: Python
• Homepage: https://elpis.readthedocs.io/en/latest/
• Size: 82.5 MB
• Stars: 152
• Watchers: 15
• Forks: 33
• Open Issues: 76
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE
  • Codeowners: CODEOWNERS

Awesome Lists containing this project

• low-resource-languages - Elpis - Elpis is software for creating speech recognition models and applying them to the transcription of audio. As of 2022, it gives access to Kaldi and Huggingface Transformers. (Software / Utilities)

README

          


# Elpis (Accelerated Transcription)

[![Build Status](https://travis-ci.org/CoEDL/elpis.svg?branch=master)](https://travis-ci.org/CoEDL/elpis)

[![Coverage Status](https://coveralls.io/repos/github/CoEDL/elpis/badge.svg?branch=master)](https://coveralls.io/github/CoEDL/elpis?branch=master)

Elpis is a tool which allows language workers with minimal computational experience to build their own speech recognition models 

to automatically transcribe audio. Elpis provides a way to use multiple speech recognition systems for orthographic or phonemic transcription. The current systems included are [Kaldi](https://kaldi-asr.org) and [Huggingface Transformers wav2vec2](https://huggingface.co/docs/transformers/model_doc/wav2vec2).



    



## How can I use Elpis?

Documentation is [here](https://elpis.readthedocs.io/).

## I'm An Academic, How Do I Cite This In My Research?

This software is the product of academic research funded by the Australian Research Council 

[Centre of Excellence for the Dynamics of Language](http://www.dynamicsoflanguage.edu.au/). If you use the software in 

an academic setting, please cite it appropriately as follows:

> Foley, B., Arnold, J., Coto-Solano, R., Durantin, G., Ellison, T. M., van Esch, D., Heath, S., Kratochvíl, F.,

Maxwell-Smith, Z., Nash, D., Olsson, O., Richards, M., San, N., Stoakes, H., Thieberger, N. & Wiles,

J. (2018). Building Speech Recognition Systems for Language Documentation: The CoEDL Endangered

Language Pipeline and Inference System (Elpis). In S. S. Agrawal (Ed.), *The 6th Intl. Workshop on Spoken

Language Technologies for Under-Resourced Languages (SLTU)* (pp. 200–204). Available on https://www.isca-archive.org/sltu_2018/foley18_sltu.pdf.