Generate subtitles for your videos via Automatic Speech Recognition.
A PeerTube plugin generating subtitles for your videos via _Automatic Speech Recognition_.
> Powered by Vosk.
Browse to Administration > Plugin/Themes > Search and type _transcription_ in the search bar:
![Searching the PeerTube plugins catalogue][installation]
Click Install then Confirm.
``bash`
yarn plugin:install -n peertube-plugin-transcription
> In production you may have to specify env variables:
>
> `bash`
> cd /var/www/peertube/peertube-latest/
> NODE_ENV=production NODE_CONFIG_DIR=/var/www/peertube/config yarn plugin:install -n peertube-plugin-transcription
>
Setup PeerTube CLI:
https://docs.joinpeertube.org/maintain-tools?id=installation
`bash``
peertube plugins install --npm-name peertube-plugin-transcription
The video transcription happens when you Update a video and set its language.
The process is executed in the background and, in our tests, lasted for half the time of the video.
> For example, it took approximately 5 minutes to transcript a 10 minutes long video.
There are currently no notifications to warn the user when the process is over (see Chocobozzz/PeerTube#5076.
If it succeeded, a caption should be present in the Captions tab of the video edition page.
> If not, feel free to fill an issue.
By default, a _light_ language training model is used, so you may be disappointed by the quality of the transcript
and may wish to choose a larger _model_ for better results (see below).
From the transcription plugin settings page, you may choose a language training model for the available languages.
![Transcription plugin configuration page][configuration]
You'll probably need to configure only the few you'll be using on your instance since some of them may weight up to 2 Gb!
> Only languages with available training are currently proposed.
> Checkout the following page for a better description of each available _models_:
> https://alphacephei.com/vosk/models
- [Development][]
- [Continuous Integration][]
- [Continuous Deployment][]
- [Vosk][]
- [ffmpeg][]
Initial codebase developed with the financial support of the _Direction du Numérique pour l'Éducation_ (DNE)
for the ministry of _Éducation nationale, de la Jeunesse et des Sports_ (french ministry of education) in the context of the apps.education.fr initiative.
[EUPL][]
[development]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/blob/main/docs/development.md
[continuous integration]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/blob/main/docs/development.md#continuous-integration
[continuous deployment]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/blob/main/docs/development.md#continuous-deployment
[vosk]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/blob/main/docs/vosk.md
[ffmpeg]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/blob/main/docs/ffmpeg.md
[EUPL]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/blob/main/LICENSE
[installation]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/raw/main/docs/images/installation.png
[configuration]: https://gitlab.com/apps_education/peertube/plugin-transcription/-/raw/main/docs/images/configuration.png