stergro
July 23, 2021, 8:55am
1
Hey everyone,
to make Deepspeech usable for non-tech folks, I would love to create a small frontend for the subtitle creator script (that can be found in the DeepSpeech-examples repo).
I was thinking about a simple GUI, with three input fields for the model, the scorer and a wav-file. The software should be standalone, easy to install and ideally platform independent.
Which tech-stack would be ideal for this? I have no experiences with python GUIs. What are your thoughts?
EDIT: I just found the electron example app, this might be a great place to start: DeepSpeech-examples/electron/Readme.md at r0.9 · mozilla/DeepSpeech-examples · GitHub
EDIT2: I opened an issue about this on GitHub:
opened 09:30AM - 23 Jul 21 UTC
Hey everyone, thanks a lot for your great work.
To make Deepspeech more accessi… ble to non-tech folks, it would be great to have a small desktop client. The electron example shows that this is doable and that a cross-platform app is relatively easy to create. I want to work on this, but I have very little experience with electron apps, so it might take a while and I might need some help.
I imagine a very minimalistic frontent that contains:
- A input field for the model
- A input field for the scorer
- A input field for the wav-file
- A progress bar
- A way to show or save the generated srt file.
What are your thoughts on this? I want to start working on this during August and start by adapting the example app in a separated repo. Do you think this is a doable plan? I am also open for other proposals.
stergro
July 27, 2021, 10:49am
2
I just found bumblebee, another electron app that looks very promising: https://github.com/jaxcore/bumblebee/blob/master/electron-app/INSTALL.md
othiele
August 8, 2021, 2:35pm
3
Not for DeepSpeech here, but the coqui guys work on an inference engine that should run on many platforms. Windows is quite challenging currently.
1 Like