Nikorasu/LiveWhisper

execuse me, how can i use it? could you please give me an tutorial examples?

kanseaveg opened this issue · 3 comments

execuse me, how can i use it? could you please give me an tutorial examples?

You should be able to drop the repo files into the same folder where you have a python virtual environment setup with Whisper, tho I haven't setup their latest version in a while, so I'm not sure what if anything, has changed. I'll have to look into that. How much did you need to know, cause you'll need to have Whisper setup already for this to work.
Running livewhipser.py should transcribe audio straight from a microphone, to the terminal. It was an example of how to use Whisper in "real-time" using the sounddevice library, and can be imported by other scripts. Various options can be configured by adjusting the globals near the top of the file.
There's also assistant.py, which imports livewhisper and uses it's output for a basic voice-activated virtual assistant. Tho my methods to make that work, might be a bit strange. heh
What would you like to use it for?

You should be able to drop the repo files into the same folder where you have a python virtual environment setup with Whisper, tho I haven't setup their latest version in a while, so I'm not sure what if anything, has changed. I'll have to look into that. How much did you need to know, cause you'll need to have Whisper setup already for this to work. Running livewhipser.py should transcribe audio straight from a microphone, to the terminal. It was an example of how to use Whisper in "real-time" using the sounddevice library, and can be imported by other scripts. Various options can be configured by adjusting the globals near the top of the file. There's also assistant.py, which imports livewhisper and uses it's output for a basic voice-activated virtual assistant. Tho my methods to make that work, might be a bit strange. heh What would you like to use it for?

How would you use it is the question. There's no tutorial of any sort, and it's forcing me to look through the files to try and deduce how to work it out.

If I ever do get the hang of it, I'll be sure to try and explain it to others :-)

I haven't updated my install of Whisper in a while, so maybe a newer version changed something. I'll try to update later, and see if I need to fix something. I've been a bit busy, and focused on other projects lately.

Otherwise if it's not related to any update changes.. I tried to make my ReadMe as clear as I could about what each file does, and the various requirements it needs to have on the system. I use a python virtual environment, with Whisper installed, and I put my 3 code files in there. If I wanna show a live output of what the mic "hears" in the terminal, I run livewhisper.py, or if I wanna play around with a basic assistant, I run assistant.py. Tho compared to what the latest LLM chatbots can do, this is ancient.

There's not much else to it. So I'm not sure what specific part of this you need a tutorial for.. I'm not very good at setting up automated installers or anything like that.

Note: I didn't really design this to work as a library for other things either, as I'm not sure the best way to do that.. So it's more of just a tech-demo, and an alternative way to do things, cause my odd Linux system has certain library limitations. Honestly, I'm a little shocked how popular it became.