im a dumb shit lol plz help #38
Comments
|
|
|
Wow I love that light!! Did you make that yourself? I kinda want one 😁 Did you follow the install guide on this repo? There is a pull request in place to update this guide as it's a couple of steps behind. Can you confirm the glados_settings.yaml file is there. Also, are you trying to launch the program from the main directory? |
|
Lpl i wish i designed it i did build it thow and slightly modified it swoped oyt the led for neopixel and an esp32 and then the companion cube is going to holed the computer im just making the radio to holed the speakers and the security camera is next for glados eyes |
|
Ya i found them there in the settings file but like i sayed im vary new to the whole python and programming think. So far all iv been able to do is arduino and esp32 and neopixel loghts lol |
|
|
|
If you could screenshot the output that you get from running the glados.py file that would be helpful in seeing where it is failing. You will need to make sure you are in the root directory ie: |
|
|
|
Thanks for the screenshot. I see your problem. You need to be in the glados directory when you execute the python script. Type this: |
|
Wow somthing new cool i thinkbyour getting me closer thanks its tobad this
cant be just an exe file lol
…On Fri, Aug 4, 2023, 9:33 p.m. eternalliving ***@***.***> wrote:
Thanks for the screenshot. I see your problem. You need to be in the
glados directory when you execute the python script. Type this:
cd Desktop\glados-voice-assistant-main\
Then try running the command you did in the screenshot. Also note you
shouldn't need the full path if you are in the folder with the glados.py
file. You can simply run:
python glados.py
—
Reply to this email directly, view it on GitHub
<#38 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/BBVTHLSANZLYDVLGYZYIMOTXTWPIFANCNFSM6AAAAAA3BIOQDQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
|
I know... but if it was an exe it would be much harder to develop and customize according to your needs. You'll get there :) |
|
Ok i forgot to put this pic here. Qustion would this be easer to do on a raspberry pi laptop |
|
It just looks like your missing some python modules. At least the word2number one... for all modules you'll want to do the following: In terms of windows vs linux, what you use is really up to you and your familiarity with each command line. I have the speech-to-text running on my windows laptop, and the main program running on my raspberry pi. It also depends on what your end goal is. |
|
O god, the end goal id love would be for her to hear and see and be able to tell the difference between people but my son would just love for her to talk lol |
|
If you chose to go the raspberryOS on the laptop it would make a simple migration to an actual raspberry pi that could live in the cube itself, or at least live on a smaller device than a laptop. Being able to tell who is speaking is possible, openCV is a great python library for face recognition. It's a bit of a learning curve, but it's capable. Or even using online voice detection services through something like tensorflow. |
|
It sounds like i have lots of work on my plate. lol im a good builder but not a programmer. I'll just have to take it slow, i guess thanks for all your help |
|
Ill just work on gettingvher talking first and go from there |
|
|
|
Took a brack from lerning python and made here eye |
|
That looks sweet! I'm excited to see the end result. |
|
And i also got this almost dun its all bluetooth lol
…On Wed, Aug 9, 2023, 7:05 p.m. eternalliving ***@***.***> wrote:
That looks sweet! I'm excited to see the end result.
—
Reply to this email directly, view it on GitHub
<#38 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/BBVTHLQNEK3DTBMED5F4SG3XUQJU3ANCNFSM6AAAAAA3BIOQDQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
|
Ok new problem iv been trying for a day or so but cant get torch to install this program stuff is hard lol but vary interesting |
|
Ok, i have an idea, and i know it won't work,and its probably dumb as shit but if im missing modules or packages is there a way justvto add all of them even if im not using them add every pythin packages there is i have a 500 gig hdd sobi can take them all i would think |
|
Ok, a couple of things first... are you wanting your program to do on-site text-to-speech (TTS)(generate Glados' voice)? If you want decent performance, waiting less than a few seconds for a response, you'll need to have decent hardware, maybe a laptop with a dedicated gpu, or a pretty new cpu. Sadly I've tried to get the TTS engine to run on a raspberry pi but haven't been able to. Supposedly it's possible with different voice models that are linked here, but that's much more advanced. If you're just running the raspberry pi OS on a laptop, there may be ways to get the TTS engine running, but that still depends on your laptops hardware and if it is supported. Best case is to have it do online TTS and store the voice to reuse it when needed. I believe this is done automatically so it doesn't have to keep generating the same responses. Im not sure if the current online TTS engine is active, but you'll find that option in your glados-settings.yaml Torch is only required for the TTS engine and cannot run on a raspberry pi. It should be able to run on the OS though. You could change the line in the requirements.txt file from torch==1.10.3 to torch>=1.10.3. This might help in finding the package. At the same time, only needed for local TTS. |
|
Ok i think im at the end of the line with this no matter what i do its error after error thanks for all your help but i dont think this will ever work |
|
You are getting close. I'm guessing you would like to run the text to speech engine locally instead of remotely? The glados-tts engine is a different repo that needs to be downloaded into the glados-tts folder. You would be best trying to get it working with the remote engine first, and then try make it local down the road when you've got everything else working. |
|
How would i do that
…On Wed, Aug 16, 2023, 5:46 p.m. eternalliving ***@***.***> wrote:
You are getting close. I'm guessing you would like to run the text to
speech engine locally instead of remotely? The glados-tts engine is a
different repo that needs to be downloaded into the glados-tts folder.
You would be best trying to get it working with the remote engine first,
and then try make it local down the road when you've got everything else
working.
—
Reply to this email directly, view it on GitHub
<#38 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/BBVTHLU6VE3S6LBDIKP3C7LXVU5SXANCNFSM6AAAAAA3BIOQDQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
|
In the glados-settings.yaml set the remote tts api to the following: Then make sure you are starting the program with the glados.py file and not a different one. |
|
Ok i think im getting closer lol |
|
Hey, it looks like your trying to run the tts engine. I guess we should rename glados.py in the tts engine folder. You are just running the wrong script. Go back to the root glados-voice-assistant folder and run the glados.py script found there. Those screenshots show that you are in the glados-tts sub folder. Espeak is for the local tts engine. |
|
Well somthing new it sayed somthung about nivida drivers but i dont have thows i have a Radeon andvit still wants pytorch |
|
It shouldn't be trying to load the gladosTTS.py file at all. Comment out the Unless you are trying to do local TTS? |
hi all I'm making a glados robot for my son and I'm just learning python and every thing so im a little slow lol
im just trying to get the voice to work on a laptop. i thot i installed all the python parts right i even did the yaml but when i launch it in command prompt i get the error........ settings/glados_settings.yaml file not found can any 1 tell me what im doing wrong
The text was updated successfully, but these errors were encountered: