- Видео 75
- Просмотров 22 040
Xavi Ch.
США
Добавлен 8 ноя 2014
Welcome to my channel :) Also Known as @Xuhsy on TT And Xavi Ch.
Make Tkinter Look Good in Under 3 Minutes.
Make Tkinter Look Good in Under 3 Minutes.
Просмотров: 2 242
Видео
Local Tiny Vision Model: State of the Art Efficiency
Просмотров 25911 месяцев назад
Local Tiny Vision Model: State of the Art Efficiency
Local Voice Cloning Using XTTS Api Server
Просмотров 4 тыс.11 месяцев назад
Local Voice Cloning Using XTTS Api Server
OBSIDIAN LOCAL AI TEXT GENERATOR OFFLINE AND PRIVATE
Просмотров 40111 месяцев назад
OBSIDIAN LOCAL AI TEXT GENERATOR OFFLINE AND PRIVATE
Replace Github Copilot with a Local LLM
Просмотров 1,3 тыс.Год назад
Replace Github Copilot with a Local LLM
T.I.T.S. For Youtube. or Y.I.T.S. (Twitch Integration Throwing System)
Просмотров 144Год назад
T.I.T.S. For RUclips. or Y.I.T.S. (Twitch Integration Throwing System)
How to Set up Ai Vtube Studio Assistant.
Просмотров 2,2 тыс.Год назад
How to Set up Ai Vtube Studio Assistant.
AGAIN? WHATS WITH THE MINGLE???? yes i made a statement privately to you and for my server i hope you understood how i felt with my side i may come back and stay as friends but i dont think i can recover from that incident last night. i will give more info why i am hesitant to join back due to the small lack of inclusitivioty i felt in that server and having my time wasted i know the world is like a chess game but i cant stand to look back
yoo i see myself (princess)
First also hear me out ✨
Damn I’m always gonna join best game ever ngl
5:08 I meant by like a day ago it was like 9:28 pm my time and i was walking around my house after eating I saw u on spelling bee, then evade, then pop haven 17+ then mic up 17+
I saw u on evade next i went to try and revive you but those nextbots(??) ram into me ☠️☠️☠️
32:02 - 32:05 bro called [] brackets as parenthesis () 😭
59:31 I came in the room 👀 in the pack….
11:34 U HAD ME PANICKING WITH HOW MUCH TIME WAS LEFT 😡😡 I HAD NO CHOICE 😔
ERRRRMMMM
Ty bro
Bro looks like gojo that does fentanyl
YOOO ITS MIMI
ALMOST 3 HOURS OF STREAMING IS CRAZY
So funny! Great video!! 🎉
At 32:30 minutes you said “ i don’t want children or anytime soon”😡😡😡😡
Kid…
New fit?
Yes will be updating it again sometime soon when I get the chance :)
@ alsooooooo are you gonna come live tn?
It’s me coco!
Wait your still alive?
Always have been
@ ermmmmmmmm
Hey, it’s Kai. TikTok never notifies me that you go live, do you still go live on TikTok?
I do :) I was just live today
@ alright, thanks :)
I was in this live 💅
DAD IT ME COCO❤
Dad what is this lol? 😂
Hi there, thanks for the great video. Have you found any other open source projects that produce more realistic cloned voices than XTTS V2?
Tbh I’ve found that about anything better than xtts has to do with better pre trained models and high quality datasets, if you can get those 2 down you can make any TTS framework sound really good, I haven’t released any new discoveries of mine since it will be a headache to reproduce for other computers since I also don’t know much about docker, and the projects are old and I didn’t keep notes on what packages are needed
I never switch named
DADD IT'S ME BEOMGYUFAN AND HII
WSGGG BRO
is that you or just a pic from the internet?
Ain’t no way you think that is me and my room lmfao
Hi!! Its me 🕸Sky🕸
NAUR I MISSED MY CHANCE ON BULLYING YOU
btw am dreamyyyy :3
@RandomlyAwesome. I stream on TikTok now @xuhsy
That was rude :( VIVI HES MEAN
when you try to "venv\Scripts\activate" if you get a "cannot be loaded because the execution of scripts is disabled on this system" error make sure you are running powershell (or CMD) as administrator, if you still get that error this is the fix: According to Microsoft Tech Support, setting Execution Policy to unrestricted should help. How to do that: Set-ExecutionPolicy Unrestricted -Force This should allow you to continue. Also you can run "nvidia-smi" in command prompt to see your CUDA version in the upper right.
Claudie Estates
Very helpful tutorial, i already made my own assistant for uni assignment but was struggling to connect it to vtube studio. That said this only works windows for mac its alot more painfull as you can't assign specific devices to specific apps
Glad to know , I’ve never used Mac OS, just Linux and Windows so far,
Buck Drive
I don’t have any names black listed now scram
i have a trouble installing spacy on the xtts server instalation with pip ,
the way i handle packages with python repos is by having virtual environments using anaconda, that way if u mess up somewhere u can just create another virtual environment and start from scratch and delete the other, usually when u install pip packages w out a virtual environment you can run into package complications becuase they’re all installed into one folder for multiple projects
but if you’re continuing to have the same problem there is a github repo issue tab where you can check to see if someone has had the same issues and maybe resolved it or is in the progress of resolving it
@@i6od Yes I was installing in a virtual environment. thank you so much. I'll check the problems page. If not, I think I would have to use coqui-tts for what I want to do hehe
no matter how many pip install (something) there's always ModuleNotFoundError: No module named '(something)' when I attempt to launch a api server
dang , there’s a issues tab on github repository to see if u have the same problem as someone else also if u post there someone will likely assist you, but not garunteed since it is an open sourced project , it all depends on the community goodluck!
didnt work for me
Yea i havent updated this project in a while , could be getting depricated the source code is still there if you wanna figure out what needs to be changed to fix your problems though. Also i have had some people come to me with there problems just for it to be user error :)
damn that's crazy Reinyku
I want to make it work in Korean, but is there any way?
This program uses Silero TTS, if silero has korean voice models more than likely, and also to transcribe Voice to text it uses whisper openai, You may need a fine tuned Korean model,
@@i6odoh thx I've decided on the Korean model. I'm planning to use the saltlux/Ko-Llama3-Luxia-8B model. So, are there any other processes or additional processes that need to be added??
Not sure yet i’m sure some googling around github repo’s or/and hugging face there should be fine tuned models,
@@i6od ah, so you think it would be difficult to modify this model??
@@i6od sir, so much thank you I'll be back.
🎉
oh man, i found pure gold!
Do you need Python installed in the background for this ? Or just your app ?
So the app is Called Twitch integrated Throwing System. My Python Files simply Read the RUclips Livestream Chat, And passes the Text to a Command with in The python, once a Trigger word is Read from Chat it will Trigger/Call The T.I.T.S. Api system.
here's the app my python file works in tango with remasuri3.itch.io/tits
Wow. I did not realize that was you on my stream until now. I am very sorry :(
@@Grouwdi no its fine i'm updating the app now to Take the Name of The Triggers as the Trigger Words and Removing the Whole Copy and Paste Thing, DIdn't realize it was a problem lmfao,
just uploaded the program to the kofi if u want to give it another try, let me know if u run into anything :) @@Grouwdi
This is really cool, is there a way to change the voice of the avatar? If so, can you somehow add custom voicemodels into it?
this uses silero to generate a voice, for it to be changed going into documents of silero tts can help change the voice u want, if you want to get a more accurate change of voice you want i'd look into rvc pipeline since with rvc u can train voice models into what u want the voice to be and there are ton of voice models out there with rvc.
can you please train on xtts on local windows. when i try in colab, gpu disconnected automatically say over use.
can u lead me to a colab source or an article about this to better understand this ?
Beautiful! I'm getting some "max retries exceeded with url..." error... do you know any fix for that?
That seems to be that your ip address is wrong in the “Chatbot.py” file
what are you using locally? Oobabooga Webui ? Ollama? LM Studio? , Usually every Local Api address changes per “back end” program you’re using , for example LM Studio is defualport is “localhost:1234/v1” or “0.0.0.0:1234/v1” and for ooba webui defualt address is “0.0.0.0:5000/v1”
Thanks for bringing this onto my radar.
But how do I run?
Oobabooga has an extension called “openai” it activates an api that can be called from the extension, same LM-Studio and the other LLM Backend Softwares they create an api to connect to, Once set up you can run the extensions and connect to them :) ,
@@i6od please do a video
@TakuCoding a more in depth video on how to get everything to work? i only didnt do that in this video becuase usually the github “readme” repositories have instructions how to set up everything
@@TakuCoding You call yourself TakuCoding, but you don't want to research? What are you coding? HTML?
@@_modiX hahaha well that's quite funny but yes I also work with Html but I'm at a stage in both life and my career in which I don't have time to dive down and research most things. When I see something exciting like this I could spend a few hours trying to get it to work, but that's time I could watch my little girl explain the new word she discovered or I'm busy trying to keep a legacy code base from throwing a tantrum 😂 but I get your argument however my hands are tied while I continue to use copilot it will be cool to see a local version running I guess
Hii
dang it i had one opportunity to bother you >:(