A SpeechToText application that uses OpenAI's whisper via faster-whisper to transcribe audio and send that information to VRChats textbox system and/or KillFrenzyAvatarText over OSC. Also supports various other methods like OBS via Browsersource and a SteamVR overlay!
License: GNU General Public License v3.0
Error response
Error code: 404
Message: Not Found.
Error code explanation: 404 - Nothing matches the given URI.
Pretty self-explanatory. Allow for using different configs seemlessly.
Feature request on Discord: https://discord.com/channels/1069609487805202552/1186947020758454332
Problem : CascadiaCode does not currently support Chinese Japanese Korean characters
Request : Would like to have a feature that enables user select custom fonts.
Add a feature that lets you choose any given font. Probably for both the Overlay and the Program itself.
Probably use a folder specifically for fonts, that can get loaded into the program on startup.
Error response
Error code: 404
Message: Not Found.
Error code explanation: 404 - Nothing matches the given URI.
I've tried restarting it a few times and running from the obs only launcher
still nothing
For multilingual models, Fine-Tune Whisper seems to have improved recognition of specific languages. Is it possible to load models on Hugging Face?
Would be good to add a timeout for the text in steamvr's overlay so it doesn't stay there forever
I've added the HTML file to a Browser source in OBS
I've added http://localhost:5000 as a URL too
Neither seem to show any text when I type in to the TextboxSTT app
and similarly also show nothing when I use the Speech to Text function
Idk what I'm doing wrong as there's no documentation on the OBS Source option
Originally posted by Mage-Enderman October 12, 2023
Even with use KAT set to off I've noticed it's continuously sending "/avatar/parameters/KAT_Pointer"
Is this feature possible if you have spare time?Thank you so much for considering this request.
Feature request on Discord: https://discord.com/channels/1069609487805202552/1186920811534241802
Problem : When translation is enabled, the original transcription is overwritten
Request : Would like to have a feature that enables user to put both transcription and translation in the same message ( or in a format they choose )
Enable either customization for formatting or just add a toggle to show both in a fixed format.
Originally posted by Mage-Enderman July 21, 2023
As typing in VR is difficult even with good keyboard like XSOverlay, Oculus Link, Desktop+, etc
I think it'd be really good to have a button to copy the text from what you've said to be able to paste it to other places like Discord
Implement as follows:
Discussed in discord server.
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.