Skip to content

MLG-SERBUR/transcribebot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

All you have to do is download whisper release and the model. You can customize it however you want and add more features but it does work. https://github.com/ggml-org/whisper.cpp/releases/download/v1.8.0/whisper-blas-bin-x64.zip

https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin?download=true

Extract release zip into the bot dir and rename it whisperer, put the model .bin file inside this whisperer dir, then simply run mvn clean install, and java -jar .\target\transcribebot-1.0-SNAPSHOT.jar your_bot_token

you probably know how to invite the bot with client id https://discord.com/oauth2/authorize?client_id=your_client_id&permissions=36700160&scope=bot%20applications.commands

Oh also make sure Message Content Intent for your bot is toggled on.

Commands

/t start /t stop to start and stop (it will join,record on start and return text or error and leave on stop)

start just records audio /t stop actually calls the whisperer

Troubleshooting

Transcription failed. Whisper process exited with code: -1073741515

Whisper requires redistriubutable runtime dll stuff to be installed. Idk which versions but this one will do all of them. https://www.techpowerup.com/download/visual-c-redistributable-runtime-package-all-in-one/

About

ai attempt #2

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages