I failed in the last video....but this time 😁

Рет қаралды 151,782

Күн бұрын

Пікірлер: 329

@NetworkChuck Ай бұрын

Stop storing your secrets and API keys in your code!! Try Keeper, a password manager you can use in the terminal: (built for devs/admins): www.keeper.io/networkchuck I did it…..after days of frustration, blood, sweat and coffee..I finally figured out a way to clone a voice to use with my fully local, AI voice assistant!!!! This isn’t using cloud-based products like ElevenLabs…no…we are using a fully-local, open-source project called Piper TTS. This works wonderfully with the Assist voice pipeline in Home Assistant. 📝GUIDE and WALKTHROUGH: blog.networkchuck.com/posts/how-to-clone-a-voice/ 🔥🔥Join the NetworkChuck Academy!: ntck.co/NCAcademy **Sponsored by Keeper

@LukeCottrell-b1h Ай бұрын

i like you content

@brennanmahto5305 Ай бұрын

why not just slow down your videos have your ai hear it then slowly train the ai to speed it up that way it can hear you annunciate

@brennanmahto5305 Ай бұрын

i often have to slow down your videos to see and take notes what youre doing why not have it do the same (not even fully done with the video yet very happy with this my dad has wanted a morgan freeman ai assistant

@Yuriel1981 Ай бұрын

That laptop 3080 is more like a 3070 or a 3070ti at best..... but still better than my 3050 6gb running my ollama lol.

@MacGuffin1 Ай бұрын

@@Yuriel1981 Your being very generous

@nickolde5341 Ай бұрын

With all the dependency issues and fiddling around, someone should totally make this toolkit into a docker image!

@coffeegonewrong Ай бұрын

The problem is you can’t access GPU from Docker…. Well, you can but you’ll end up doing all the same fiddling but with extra headache of the Docker layer

@josevaldoandredasilvajunio4691 26 күн бұрын

@@coffeegonewrong dont remind me of this it gives me ptsd, when tried to do a similar project i almost pulled my hairs out making it pick up my GPU

@coffeegonewrong 26 күн бұрын

@@josevaldoandredasilvajunio4691 I spent the better part of a day trying to make John the Ripper run from a snap so it could use OpenCL. The. I learned the only way was to mount the snap and run it directly from there

@ZiggyDaZigster 23 күн бұрын

Someone should make a shell script that can be editable that asked user for inputs, then just install and runs everything. Not that hard. Crazy, no one has done it.

@dusi125 21 күн бұрын

@coffeegonewrong yeah, but if you are not that worried about performance, and you are patient, you could just let it use the CPU.

@PreNetwork255 28 күн бұрын

18:14 "You have no idea how amazing it is to get to this point with no errors" -- really hit home

@iggr415 18 күн бұрын

Chuck, @22:13 there is a warning that says 173 utterances were skipped, and probably that's why the end model sounded so badly. The same happened to me and I've read that this may happen when the length/number of words of each transcription or wav file is too large. Instead of 15 second clips, I experimented with 10-second or lower ones and didn't have this error. Edit: This is issue #663 on the piper github page.

@drenpirraku3024 Ай бұрын

It probably has been years since i watched a 37 min video without skipping once let alone a tech video. I feel like my attention span has been permanently increased.

@TheFlow2006 Ай бұрын

thanks for bringing that to my attention, i hadn´t realized it was that long , crazy

@Ecker00 17 күн бұрын

Give "Stolen Focus" a read, and you'll start to see why.

@FuchsDanin Ай бұрын

Quick note -- instead of removing silence, you would have been better served splitting at silence. The output would have been more intelligible for transcription, would not have required as many mid-word cuts which cause issues, etc etc

@decepti0n Ай бұрын

Bravo, this is the peak educational youtube content. Learning with a twisted bit of fun

@yangenmanuel2659 Ай бұрын

The end results of all the methods were so cool. Worth watching the entire video.

@exploittutorial8689 Ай бұрын

Him: a CPU will work Me: looking at my HP 540 g3

@ZIonDaWolfo Ай бұрын

🥲

@Yuriel1981 Ай бұрын

Yeah, naw dawg......I feel for you.

@WWSchoof Ай бұрын

It will work - sooner or later

@daverahn1711 Ай бұрын

@@WWSchoof later, much much later

@SineN0mine3 19 күн бұрын

You can get free cloud computing that would do better btw if you've got a decent internet connection

@kingston396 Ай бұрын

Just bought a new house and am currently working on setting up automation and localizing everything offline. Challenge I'm hitting right now is getting mics in every space that go back to the assistant instead of having pi's everywhere. Also trying to limit the response to the room from which the request came from. Thanks for all the content! You have definitely made the process way more understandable and fun.

@revelmonger 27 күн бұрын

I'm working towards that direction. Any tips with the progress you've made so far?

@mitchellpayne3674 Күн бұрын

@NetworkChuck this video exemplifies the fact that you're bringing the total package here (more than just a pretty face lol ;P ). Your technical savvy, relatable and engaging casual vernacular, and absolutely top-notch production quality leaves nothing left to be desired. It's a foregone conclusion that I'm automatically and unabashedly looking forward to the next video. I've been watching you for a few years now and you just keep making it happen! It's not an easy thing to do (so I've heard, and so it would seem based on empirical observations). So as loud as I can say it in all caps, THANK YOU NETWORKCHUCK! :)

@shane7070 Ай бұрын

Hey thanks for all your videos on home automation. I've started my own home automation journey watching your channel and learning what's possible. Now looking forward to commanding my home like the USS Enterprise.... "Computer; make coffee" :D

@freshseeds323 Ай бұрын

I had like flash backs for the 1st 10seconds, from being a kid yelling at those recorded talk back hamster toys with that same audio playing back XP

@DiaburoDev Ай бұрын

That was intense. I can't imagine, how much time, work, coffee and nerves you put in this project, but it really was worth it. Terry sounds great! I hope the next project is less nerve wrecking. xD

@satnlafsasurot 16 күн бұрын

I went through the same exact nightmare. I finally was able to coax my WSL into getting through a successful install. I laughed so hard and cried along with you. I 100% feel your pain. I was in a little race to see if I could train mine before you posted.

@TomDavenport Ай бұрын

Honestly the chuck voice had me laughing so hard after 30 min of development 😂

@stevetb7777 21 күн бұрын

Alright! I can get my Samuel L Jackson voice back! I was so annoyed when Amazon disabled my Ask Sam, I paid $2 for that! Time to ditch my echo devices.. lol!

@dunther 12 күн бұрын

I was thinking EXACTLY the same. How I long to be once again viciously browbeaten for having the audacity to inquire "Hey Samuel, what's the weather like today?" XD

@marquisjohnson3849 Ай бұрын

I'm so excited to try this out, each video I've tried to keep up and implement the home assistant and local ai. The voice is a wild addition

@jcbenge08 Ай бұрын

OMG the Terry voice is AMAZING!!!!!

@SolarBuck 23 күн бұрын

You should make your Terry clone voice available for purchase. LOL my wife wants her Voice Assistant to sound like him. My daughter wants Adam Sandler. My son's preference is "Amy" and he prefers "OK NABU" as the wake word. I called mine Alfred but is using your voice. I might try to clone Morgan Freeman's voice but this takes so much effort. My wife says your cloned voice is a little too fast. I might try to see if it can slowed down with a setting versus having to relearn. I love the idea of taking my home automation local. this has consumed all of my free time of late but with your guidance have made leaps and strides. Mine is a bit too slow. I will see what I can do to speed that up. I have 48 CPU threads and 128GB of RAM but my GPU is a single RTX 3060 12G model. as a proof of concept this has exceeded my expectations but to take it to the next level I will need more. Upgrading the Power Supply has solved my crashing issue. Keep up the awesome work. I tried making a crude Adam Sandler voice with low sample rate but it just didn't work. I am surprised there is not some repository of these files. Maybe there is. Probably not for free but for the right price and save me a week worth of my free time I would probably pay. Getting your voice to work was awesome but very tedious. and your sample voice files you made super easy. Getting those files are proving tricky.

@RangerDK21 Ай бұрын

Be careful with showing yt-dlp...

@lucasdealmeidacarotta3174 Ай бұрын

Linus had a strike for similar reasons, I think this video might receive the same "attention" from KZbin unfortunately

@Aineasg Ай бұрын

Thanks, Chuck! I was really looking forward to this video. I absolutely love your content!

@maximilianschmidt1872 Ай бұрын

I also wanted to train my local ai voice assistant with my voice and started using the piper studio in the German language. It wanted me to say a lot of sentences that sounds like they're from an software call-center and could be used for software scam calls i.E. "The activation key you've entered is invalid" and in combination with other sentences like "Then call the police and see how far you get there" it sounds pretty strange to me. Then I saw a disclaimer on the page that says "By clicking Submit, you agree to dedicate your recorded audio to the public domain (CC0)". Is there anything known that the voice recorded by the software is distributed to the www and used for malicious phone calls?

@andreas4959 29 күн бұрын

Ah, finally the day has come where I'll be able to have Chuck's voice play whenever I come through the front door, greeting me with a "Welcome home, daddy ;)"

@dr.hinneredv932 Ай бұрын

This is awesome. Thank you for all your work. And special Thanks for sparing us the crying. :-)

@DIYenthusiastfreak Ай бұрын

Thanks Chuck, that vid had me wanting more, what a project! I hope some other shanagins come about from this😊

@rickssantanna 17 күн бұрын

Everything was perfect! you're the man! 👏🏼 The icing on the cake is being able to stop the speech when you say the wakeword again or “stop”. Is that possible?

@rogerhuston8287 Ай бұрын

Awesome! Now I can put your voice to the life-size doll I have of you....

@marcomoraschi3972 Ай бұрын

You were my hero just with the other video, and now @just 1:23 you are more hero than hero .... LOL

@WG-0 29 күн бұрын

remember when you had 100k subs years ago, so happy to see you with big success!

@vevojckproin3046 Ай бұрын

Please need to talk about cash for servers, how it is done, and from what background should I learn this technique, and do you have courses about it?

@dave_kimura Ай бұрын

Had a lot of issues getting it running on macOS, but was able to successfully get it up and running on my Ubuntu machine with python 3.10.12. After a few minutes of training, I tested it out and was surprised with the results. Pretty cool! If I have hours of quality recordings, what would the amount be to get a quality voice? Did you ever figure out why yours was a bit quirky?

@anderfrank1 4 күн бұрын

@ 29:23 Hi NetworkChuck...Chuck here..... Love the vsauce reference!

@TheDWehrle 29 күн бұрын

29:21 The Vsauce music caught me off guard!

@Danielddiniz Ай бұрын

Wow the Terry crews voice was amazing! Proper voice for your beefy Terry AI server! Congratulations

@satirical_snake Ай бұрын

Now we're talking. Been waiting for this one!

@jokelot5221 Ай бұрын

I made a Pi Led Agent a couple days ago. I can turn Led ON and OFF using whisper(small model) to translate my voice to llama3.2:3b, then llama generates a response that executes a condition based on the string it provides and toggles the LED. Also model can respond using voice of piper(small model) with another prompt that llama does, besides the one that controls the LED. I use pre-promts to guide. Like explain to the LLM what it is, comands it should generate, and give it a few examples of how its done, as this can improve its responses.

@emad2615 Ай бұрын

Hey Chuck, awesome video! I’m working on image detection, and it gave me an idea for your next project. How about a video on training custom image detection models? Like recognizing specific objects (e.g., PET bottles, toys) to expand what a home assistant can do. It could add some cool features to your Raspberry Pi assistant. Would love to see your take on it!

@iamdihan Ай бұрын

I ended up trying a bunch of API LLMs and Open Ai 's Conversation agent and TTS is awesome and fast if you dont want to use your own hardware

@jackelo911 Ай бұрын

I now know what I'm doing when I get home, Thanks Chuck!

@WWSchoof Ай бұрын

The topic is so crazy and fascinating, I think I‘ll do a home project like this. The only thing that bothers me that I don‘t want to run my desktop pc 24/7.

@jldevezas Ай бұрын

Oh man, love it! Freakin' cool! Totally worth the effort! 😁

@vaxiwaxi2113 26 күн бұрын

That's sick!!! Amazing content sir!

@philrendell1767 Ай бұрын

I nearly wet myself when you played your voice after the training! Technology can't live without it😂

@VorpalForceField Ай бұрын

Absolute Beast Mode..!!! You Rock ...!! Cheers :)

@timoknols3303 Ай бұрын

This is amazing, great you figured everything out. And ofcourse i want this in my home assistant 😮

@liszcgsedt 7 күн бұрын

Mr. President, would you mind making me some coffee? Yes. It will be the most awesome coffee ever. Or perhaps Gunnery Sergeant Hartman, your senior drill instructor. ...because "I am sorry, I am afraid I cannot do that" is going to become a cliche. :D

@stevetb7777 21 күн бұрын

"Hello, my name is suck, my voice has just been trained" 🤣🤣🤣🤣🤣🤣

@oldekline Ай бұрын

Bro has Brad Boimler vibes! I'm here for it.

@ethanberg1 Ай бұрын

He just needs the Boimler scream!

@oldekline Ай бұрын

@@ethanberg1 That could be the beard that Boimler has been growing all season.

@NFTwizardz Ай бұрын

Lmfao your 1000% becoming my voice assistant when I have the time!

@kalebfenley1199 Ай бұрын

Nice, I never recognized Mike as the voice of Mandark on Dexter's Laboratory before now. That's awesome.

@JoseMR1992 Ай бұрын

When chuck asked. Dont you want this in your home? I was like. F YEAH I DO!

@pjf Ай бұрын

I will try it, hope it works for me, is the project i have been waiting for! Thanks for sharing

@starlord2606 Ай бұрын

Hey there Chuck, Great video, One more request or suggestion, whatever seems right, Make it talk with emotions, like the LLM is giving the responses and it is just reading it as it is, Maybe it should emphasize on those words, add some filler words and talk actually like it is a human talking. For example *talks intensely* shouldn't be read, instead adapted as emotion. Thank you, this is one of a gem Channel I have found which actually teaches cool stuffs.

@i_Kruti 3 күн бұрын

28:45 Hello my name is Chuck ❌ Hello my name is Suck ✅😂🤣

@bringerod5141 9 күн бұрын

22:00 sure more training is almost always better up to a certain point. There is something called "overtraining" but I am not sure if that applies to these speech models. It does to the regular old classification and object detection models

@bertaboy Ай бұрын

Lookin forward to building a local digital assistant with Multiple Personality Disorder, where Dr. Jekyl sounds like Morgan Freeman and Mr. Hyde sounds like Samuel L Jackson....

@arnorenirving Ай бұрын

Fun fact: Demirkapı means iron door in Turkish (bill probably are)

@BurkenProductions Ай бұрын

The instructions on your blog is incomplete... stuff missing and lots of libraries fail with torch and stuff. Cna you please try on a fresh ubuntu wsl install and follow your own guide and correct the errors coming up.

@dahat42 29 күн бұрын

Ditto. Training is failing for me currently (and I'm trying to find answers to that), but to get there I also had to do the following to get some missing dependencies when running in Ubuntu on WSL: sudo apt install gcc build-essential python3-dev

@tzursoffer6103 28 күн бұрын

If you encounter the error "Could not load library libcudnn_cnn_infer.so.8. Error: libcuda.so: cannot open shared object file: No such file or directory", then run the following command: cd /usr/lib/wsl/lib/ sudo rm -r libcuda.so.1 sudo rm -r libcuda.so sudo ln -s libcuda.so.1.1 libcuda.so.1 sudo ln -s libcuda.so.1.1 libcuda.so sudo ldconfig Other then this one issue, this has got to be one of the coolest things I have done in a while, thanks for the great tutorial!

@DarkFeanorbr 2 сағат бұрын

you are a lifesaver. Thanks a lot

@Smoth48 Ай бұрын

Lmao, the mike monologues were the best thing I've ever heard. I really need to buy a new Pi so I can set up home assistant... I have an old RPi2, but it doesn't have the specs needed to run home assistant :(

@pilotedge Ай бұрын

Not sure if anyone has thought of this... But I just downloaded an Audible with a celebrity reading and now have 3 hours of perfect training material 😂

@SineN0mine3 19 күн бұрын

They're called audiobooks, audible is just the app that ruined the commercial audiobook landscape.

@pilotedge 19 күн бұрын

Do you need coffee? I like coffee 😊

@issaissa6257 Ай бұрын

Networkchucks voice with an chinease accent sounds so funny 😆😆

@deejayx256 Ай бұрын

I can't sleep without watching your video's 🎉🎉

@Danielddiniz Ай бұрын

Next video must be putting your voice in a Chuck the assassin doll with creepy phrases pleaaasse 😂

@notedown1010 Ай бұрын

@NetworkChuck what kind of keyboard do you use? I'm dying to know because it just sounds SO good

@alfadat Ай бұрын

Hey Chuck fantastic and clear video! thank you! However you bring mixed messages, when you mention Keeper you said that is good that is "Cloud Based", but in your video, it seems like you prefer local installations (1:11 mark)

@NetworkChuck Ай бұрын

What is good for an individual (local hardware) may not be good for a company. As an individual, I’m willing to accept the cost and pain of maintaining a local infrastructure because it’s fun. For a business, the highest value becomes reliability.

@semondemon3787 Ай бұрын

@NetworkChuck Hello my name is suck 😁🤣

@meenstreek Ай бұрын

Was it _really_ free, though? haha. Awesome job! Thanks for this!

@Handelhere 4 күн бұрын

Your voice actually might be perfect for a voice assistant

@Felicia-bi5wu Ай бұрын

I copied your last video and was like damn, i wish i could make my own, literally you a bit later, thank you :) The Ai thing is running in a virtualmachine in proxmox with a gtx970 so it's a little sheit but it works XD

@ArifBillahOnGoogle Ай бұрын

When this guy opens up his camera gear, bugs and errors completely stop existing... I wish reality was like that.

@wayne8113 Ай бұрын

Thanks Chuck, I think I'm to dumb to do that, But it looks so cool and out of the cloud 👍

@danielstellmon5330 Ай бұрын

Chuck says "So many little things to remember" all I hear is "take notes and write a script as you will never remember them all"

@4bytesuserpage Ай бұрын

Nice to see your still uploading, used to watch you after school everyday ages ago through my window (we were neighbors)

@TheCommunistRabbit Ай бұрын

WHAT

@dancannyonge Ай бұрын

That was amazing..I am currently building mine❤❤

@marcsmith5880 Ай бұрын

Thanks! This is going to make my life so much easier. Going to use a pi zero 2 W and a keyestudio 2 mic hat.

@andrewdepew3518 29 күн бұрын

Awesome! Love it! Are you going to release the Terry voice as well?

@derivitiv Ай бұрын

I just wanna say.. I am fully onboard with making my own AI assistant based on your video guides. However, the only thing holding me back is that I get Amazon Music via my Alexa. Would it be possible to include this service with this setup?

@derivitiv Ай бұрын

Nevermind. I just found an article on how to do it.

@ramppage Ай бұрын

@@derivitivcan you post a link?

@SineN0mine3 19 күн бұрын

@@ramppagelikely no, comments with links are usually removed automatically on KZbin.

@SU3D3 Ай бұрын

I remember thinking ".wav" files were huge!

@rhynox4751 25 күн бұрын

Which python version are you using @NetworkChuck ?

@texturebyte 28 күн бұрын

what keyboard does @networkchuck use ?

@Robban31013 Ай бұрын

Hi Chuck! I want to integrate this to all the bedrooms in my soon to be home. I already plan to build in Sonos speakers into the ceiling(Sonos in-ceiling speakers). Is it possible to use this speakers instead of the small speaker that you are currently using? Thanks mate! Really enjoying your content! 🙌 (About to build my dream home and wants to make it smart/AI)

@DezFutak Ай бұрын

"Hey Chuck! Show me how to groom my beard like yours!" "Sure! All ya gotta do is drink a LOT of my coffee!" ;)

@rajackar Ай бұрын

Super cool video. Tried the steps and I get an error trying to install numpy 1.24.4. : "module 'pkgutil' has no attribute 'ImpImporter'." Did you run into this as well? Can't find a solution just yet.

@mal-avcisi9783 Ай бұрын

bro there are much easier ways to clone voice locally. but still fun to watch this video 👌👌

@jimhark Ай бұрын

@NetworkChuck, the Terry Crews voice clone does sound great, but I feel like you must have left something out. You attempted to use an automated process to generate an onnx file from your recorded voice, but the results were poor. You went back to Piper Recording Studio to get a decent voice clone. You said Mike spent some quality time with Piper Recording Studio for good results. I don't imagine Terry used Piper Recording Studio. So what did you do differently to achieve such a good result from prerecorded audio?

@TristanCampbell-Reynolds Ай бұрын

This was so cool!

@MTEX-tr6vd Ай бұрын

Hey chuck, still you didn't fix that longer conversation....any way to fix it? Kr summarise the context?

@LordDartonStaker Ай бұрын

I've literally been following this series that you have been updating, From the Start to now - I have Ollama with AlwaysReddy setup on my Ubuntu 24.04 OS - Running this - I will be trying to implement this on a New Raspberry Pi 5 (Quick question, will it be beneficial to add the AI HAT that you get for the Pi?) But really interested in this project and thank you so much for the inspiration to follow along the journey. Much respect, Great Channel.