I graduated with a B.S. in Mechatronic Engineering and here on this channel, I like to share my experience for learning and hope others can benefit from my mistakes and/or knowledge! I share things I'm passionate about whether that be technology and AI stuff or anime and Japanese :)! Thanks for visiting my channel!
Пікірлер
Any idea why my web guide always spits out the phrase “I am very (emotion I selected) when I skip a line or randomly throughout?
What files do I need to move around to use a voice I trained on the web guide for the audio books?
is this only for singing or is regular voice also ok?
How do you create an audiobook with multiple different voices?
please review rtx 4060ti 16gb, is it good for ai?
if i use Linux with wine will it work?
MPVacious gives me a warning, I wanna know if it's possible to fix it "Your version of mpv does not support libaom-av1. mpvacious won't be able to create snapshot files"
they all feel like lazy code people trought out there, none of them even have a proper Ui or can even be considerd a proper program. You have to literallty do all the work rather than just getting something you can just trough text and have it work, imagine actually working on a full book with this itd be a nightmare. Why are you all just cool with this level of shit.
If you count in the energy you need to run adequate card number to reach performance of 4090 especialy in EU with shitty scammy green transformation (choking everything from business owners trying to survive to population trying to own money to pay energy bills) the advantage of mutliple cheaper cards would melt each month more and more... so yeah ... this is nice for someone who want to try cheap build out but maybe its not super nice for someone who plan to use build for AI for living some years to come ... not to mention that cards are calculated to last for x days when solder will give up and GPU end up not funcitonal (dead or reparable - reparable means you fix one solder point and other just wainit to fail) plus you also need to thing in advance so its better to buy all toher stuff newer that are calculated for situations when you would want to switch GPU for newer option. So spending little more now can make you last longer without need to change the rest stuff... so if youre buing old card then the rest of it should be able to make newer cards like 4090 or better to work close to 100% efficiency (as whole setup are like army composition where youre as fast as slowest unit)... so use of logic and strategic planing is a key
When I train a voice, terminal always says "\ai-voice-cloning-3.0>pause" at 98,7% and it doesn't move anymore, it happens in every try. Any solution?
Sir, some Japanese youtube video i watch on mpv don't have subtitles with them, i can't sentence mining, what should i do ?
can you make a video on how to install applio on mac?
can you share how u memorize them.
Instant like for “an RTX”
💥 You chose some really weird voices, bro. Looks like a horror movie. These japanese voices suck. Some of these. I use coqui and it has fantastic voices. Also, you didn't even mention the best one: ELEVEN LABS. Unmatched ! 🙏👍💥
in the language section what are the supported languages? other than en english of course
your mic was hissing a lot in this vid
Jarod, can you make a video of how to Train a music Instrument, that will be amazing and very helpful for Future music producers
many of these voices are fantastic!
Is it possible to create a pretrain for training voice models in different languages with a small dataset? Do I need to train Bert additionally to create a high-quality voice model?
I'm from the future: Don't install Python 3.12, use 3.10.
thank you for you work it's amazing tutorial, I need Help! in the run training in CDM i get this error // [Training] [2024-07-21T21:17:31.911112] 24-07-21 21:17:31.910 - INFO: Start training from epoch: 0, iter: 0 [Training] [2024-07-21T21:17:33.282338] [2024-07-21 21:17:33,282] torch.distributed.elastic.multiprocessing.redirects: [WARNING] NOTE: Redirects are currently not supported in Windows or MacOs.// and in the [ ai-voice-cloning-3.0\training\RobbySpeech\finetune_archived_240721-211723\models] 0_gpt.pth Size 1.676,723 KB. whene i klick on (Re)Load TTS after select (./training/RobbySpeech/finetune/models/0_gpt.pth) I get this error (Error Connection errored out.) ?
Why does it have that tingy, metallic sound sometimes?
Tortoise TTS
hey i wanna that repo of bookmaker
Awesome bro you are so goated
Hi. My train tab doesn’t show any training g files. Where do I get them please
Is there some collection of voices i can use to my videos?
Why your are not using tensorRT? I am waiting for reply :)
Amazing work. Will you also be making a version for mac in the future?
I'm getting Error: [WinError 10061] No connection could be made because the target machine actively refused it, retrying... (1/3) Error: [WinError 10061] No connection could be made because the target machine actively refused it, retrying... (2/3) Error: [WinError 10061] No connection could be made because the target machine actively refused it, retrying... (3/3) When trying to select the text file & then start audiobook generation
Tray games plz
Are you planning to replace TortoiseTTS in the audiobook maker with StyleTTS2 or XTTSv2?
Bro sorry but i cannot understand there is so much ai models. What is the best for: TTS REALTIME VOICE CLONING VOICE CLONING ( Im a beginner, and i have a good pc but my net is mid... And i can't install all the models to try them so i wish u can help me cuz i need it for this 3 topics ) Thanks man i appreciate your work ❤
Combining 4(sets) * 12 GB RTX 3060 might be better than RTX 4090 (24 GB) in half of the investment.
really cool setup. the biggest issue I am having is if I am using one of my voices, if I go to long, it starts randomly switching to different voices. I had one output have as many as 5 voices in one. Thanks!
I just wanna say you have such a good vibe, I clicked on the video and immediately got a smile on my face, thanks!
THANK YOU FOR YOUR HARD WORK BRO.
Can you please guide me on how did you added emotions tab? And how can we add other emotions here?
Thx for an awesome video with chill and exciting content.
I have been wondering if you could use dual 3060 for the same testing that you did. i am not sure if its SLi/NVLinkable ( not likely ) but a dual gpu setup would prob work quite nicely. i understand tensorflow is able to recognise the 2 gpu's. should the Gpu be linkable then you might have a 24Gb setup for quite a steal. still researching on whether this could even work
Hey there Jarod 👋😊
Tortoise samples sounded more expressive but there is a weird vibrato in some cases that is very artificial...
Hi, i see error " can't open file '/content/Retrieval-based-Voice-Conversion-WebUI/infer-web.py': [Errno 2] No such file or directory" at start the web step. How can I fix it?
For those on a budget, I found that nvidia is the way to go right now since AMD ROCm is only compatible with their top end RX/PRO 7900/7800 series GPUs. Using Fooocus 2.4.3, an 8GB RTX3050 produces images in 35-60 seconds versus the otherwise much better RX7600 images take 150-240 seconds per image.
So running the bat file keeps coming up with a "path not found" on line "runtime\python.exe .\src\main.py %*" - anyone have a clue what I can do to get past this?
Oh, and I checked and in my System32 directory there is no runtime directory - Python is installed but not there, I guess. Windows 11 - anyone have a clue?
Yipes - I note I don't even have a runtime directory in C:\ root - as was set in the first line of this bat. This bat looks totally wonked for at least my system.
Great Jarod, I'm so greatful. Also, is there a way to create a full song with singing voice, giving that we have lyrics and a prefer melody to develop the song base on that. I'm looking into Juke box but it's still not really clear how to do it yet. Can you light up the way?
You may have to use another software
Try searching singing voice ai you might be able to find something on KZread
Does those LOCALs AI Voices support Indonesian language?