As I said. It works flawless and without hiccups
Getting fusion360 running on linux is 10 seconds of google. It works perfectly fine and i use it for without any hiccups.
Method 1: Get Bottles and use the provided installer inside that.
Method 2: Use this script
No, this is the correct image.
This is the Pope of our new AI-driven world
Should this really be in "Technology" ?
This isn't "Technology" imho.
Most of the times we decide spontaneously what ability to use for a certain skill. The fixed stat+skill is super annoying and breaks immersion.
The wisdom 20 / int 8 Druid not being good in medicine? ... yeah maybe not good in school-medicine but knowing what herb can treat what illness is a thing of wisdom, not intelligence by default.
Then, yes, Strenght for intimidation.
Intelligence for deception - think of an elaborate network of pseudo-facts and weave them together in a complex way so the "opponent" is so overwhelmed that he just choses to believe you.
And so on so on...
Oh my that 4060Ti will reduce the response time to the bare minimum that whisper is capable of i am sure!
You don't have to customize the docker-compose at all. That's the plug'n'play part. You have to make sure to build the docker image so it uses the makefile and the run.sh file.
Also make sure your docker environment is able to use the 4060Ti.
Easiest way is to run docker run -it --rm --gpus all ubuntu nvidia-smi and see if you get a proper nvidia-smi
First of all: It increases performance tremendously. For comparison
- RPI4B
- tiny-int8 -- WER 40% -- Processing time ~5s
- base-int8 -- WER 70% -- Processing Time ~10s
- medium-int8 -- Impossible
- HP EliteDesk 800 G5
- tiny-int8 -- Irrelevant
- base-int8 WER 70% -- Processing time ~2s
- medium-int8 WER 95% -- Processing time ~ 8s
- External Server with GTX1660
- medium-int8 WER 95% -- Processing time ~0.5s
So running it on a cheap 100€ used GPU can get you results where Alexa, Siri and Google have to respect you in terms of accuracy and speed. This is a gamechanger for me. I already installed 3 M5Stack ATOM ECHOs in my Home and more will soon come in. It's incredibly accurate and quick.
The important part is to pick the correct docker image. The default one that's available at rhasspy doesn't have GPU support.
Now, to get it running it's actually pretty easy. First go to this link and download all the files. You have to build a custom docker image with those files. I have no idea how to do that with barebones docker as i am using portainer for everything. In Portainer you have to do:
- "Images" in the navigation menu
- "+ Build new image" on the right hand of the header of your images list
- name it wyoming-whisper
- Copy and paste the content of "Dockerfile" you downloaded earlier into the "Web Editor"
- Under "Upload" you click on "Select Files" and select the Makefile and run.sh
- Click on "Build the image"
Next you go
- "Stacks" in your Navigation menu
- "+ Add stack" at the right side
- Give it a name (whisper e.g.)
- Copy the content of docker-compose.example.yml from the files you downloaded earlier.
That will spin up a docker-compose with the local custom image you just built, running faster-whisper that is compatible with the wyoming protocol in home assistant and that can run on an NVidia GPU with cuda acceleration.
As you can see in the docker-compose it will expose port 10300. Next:
- go into Home Assistant
- open Integrations
- click on Wyoming
- add a device
- input the IP of your external GPU server and the port 10300
It will automagically know that it's whisper and will be fully integrated into your system. You can now add it into your voice assistant.
If you look at the logs of your new docker container you can see every voice command that is sent to your new whisper.
I'm very confused and interested in an explanation as well
I just setup whisper on my external GPU server to run the medium model with 0.5s of processing time but the built-in intends are somewhat lacking.
Das ist kein kleiner Tipp, das ist absolut Notwendig
Also meiner Meinung nach
I don't want to hear the realistic argumentation of why this is proceeding. I want to live in my fantasy headspace where comments like this can stop superpower megacorps from being assholes....okay? 😅
can they please just like... don't?
+1 Bottom right