I Built an A.I. Voice Assistant using PyTorch - part 1, Wake Word Detection

[@ItachiUchiha-nx2sw]

First few minutes : Alright, this sounds so cool Middle part: Da fuq Last few minutes : Alright, this sounded cool

[@theaihacker777]

😂

[@christopherdimitrov1652]

Hahahaha

[@vinayak354]

Hahaha

[@AfafPrinceOSH]

@@theaihacker777 is there any way u could change the voice of Google assistant to any random voice?

[@GeometryDashEndermaster]

You're like an alternate reality Michael Reeves

[@soon3794]

Basically a less suicidal version lol

[@dareokoski8158]

@@soon3794 he is still yung, give him time XD

[@TeamVexVideos]

The other Micheal isn't as good with Man's AI. He just uses like google API or existing software. And Micheal Reeves just does comedy not education.

[@sgodsell2]

At 10:00 you said two words that sound similar, like MOLLY, and FOLLY, FALLEY. If you were to include those 2 or 3 words in your model data under a different category. Then they will never trigger when you say any of those words, except when you say hey wally.

[@mohamedfasil4932]

The weather is M####F#### hot I thought that and in deep thinking this doesn't sounds right

[@user-fj4ih3lo9f]

Could you make a more detailed tutorial? I couldn't find any other videos on how to make an AI Voice Assistant, i really liked the vid altough it was sometimes hard to follow. Would really enjoy a full detailed series on this :D

[@bryanfeliciano4102]

The best way to learn is to mess with it my dude. Go into the GitHub and read the code, and start writing your own following his example but alter it to suit your tastes .

[@johnhandley1870]

I’m watching this video on my iPad and when you said “Hey Siri”, Siri woke up... By the way, I’d be really interesting in seeing a video in which you explain how to set up a computer to carry out Machine Learning tasks. :)

[@theaihacker777]

Would love to do that!

[@JorgeHernandez-iw2fd]

How does someone even get to this level? I'm assuming years of practice and stuff but what/how did you practice?

[@shubhamthapa7586]

no one year is enough

[@robinranabhat3125]

While internet is full of AI guru's teaching basics with some slides and a jupyter notebook, this guy actually teaches ML with a production level code. Why are you underrated !!

[@p._7555]

True. On the learning curve, we need basic and high level AI teaching too

[@dillonridder8737]

"Apple's okay" lol

[@schwarzarbyter]

thats exactly when this video got its 72nd dislike.

[@theaihacker777]

thanks for the support!

[@leninbabu5797]

Its been cool to see U Can we make this model using raspberry Pi zero !!

[@maritzadelascasas2727]

the mot ovios wake word is wake up a.i.

[@elliotmarks06]

This project looks super cool! I'm a little late to the party, but I think this would be awesome to revisit with the new AI chat tools! Especially something like GPT-Neo or the other open-source implementations.

[@andreashon]

This video is exactly what I was looking for. All other voice assistant youtube guides use shitty Google services and other proprietary sources. Thank you. Looking forward for next vids on this topic. Also that'd be interesting if you reveal how much time have your machine spent on all that learning.

[@theaihacker777]

Next video coming up soon! For wakeword, training was really fast. only spent like 30 minutes training.

[@leif1075]

@@theaihacker777 Was this process mostly fun and enjoyable? If not how did you not give up when it got hard and not get bored and frustrated? Thanks for sharing.

[@rangefreewords]

Awesome! I was looking for a totally offline LAN based smart A.I. like what you just presented Objective: To control everything on my sailboat, take helm, drop anchor, play music or movies from my pi based server and work alongside my autopilot systems and chart plotter. I know often during my voyages I won't be accessing any internet but, I want to have all the same ubiquitous control as a smart home, etc. I am trying to source as much as I can from KZbin to build a decent system. Keep up the awesome work!

[@subhajitkundu7546]

Hey, good day mate, The project that you talked about sounds awesome. I am just checking in to know how the project is coming along and where are you headed with this project currently.

[@danielogunlolu]

I am working on something similar on channel. Kindly check it out

[@mathewpatterson2187]

Ahoy there! I'm also checking in, how's it going with the project sounds awesome and very reminiscent of what I want to do! Have you had much success?

[@daanzap]

I have the exact same idea! It's going to feel a bit like being on the enterprise.

[@justsomeguywithtattoos6267]

This could be easily applied for translations, so that you can have an earplugs that instantly translates what someone is saying to you

[@gamecraftczjaajenomja1057]

Amazing video! Finally someone not just showing some random jupyter notebook. I love how you show the real problems: not enough wake word samples, voice streaming, long training times, etc. Continue if possible, I would greatly appreciate it!

[@ramoncaceres4399]

Pretty interesting. For about 2 years I’ve been obsessed with turning my house into an AI assistant. Yet have the voice Overlay of ( BT from titanfall ). Yet pretty hard to do that.

[@JohnSmith-ox3gy]

Why mess with perfection?

[@shallinkumar9042]

I'm getting this error in dataset.py (extension.py", line 14 warnings.warn('torchaudio C++ extension is not available.') )

[@leisana4097]

Extremely extremely intelligent AI. You asked what next to try - Can you try - Self driving car with Raspberry Pi and Pytorch. A small rover

[@AshrafAli-hg4zd]

Could u please help me with name of ur war Machine

[@RichardBaileyrichoncode]

Looking forward to next episodes.

[@adarshvinayak]

Your videos are amazing man. You've just earned a fan. By the way, I'd love to see you make the speech recognition model next.

[@theaihacker777]

It seems that speech recognition is popular!

[@microgamawave]

You can make a video about gait recognition biometrics in python recognized you from your walk model ????

[@dirtydan69]

Where can I talk to you about help on building my own AI? I’m still learning how to code and would mean a lot to me if you gave me a helping hand

[@user-tu9ox4hj9g]

I would like to hire you for a simple project and will pay substantial for you to implement speech recognition into python for me. Please contact for further detail if we can link to another platform to communicate

[@samueldemissie2403]

imagine running the trainer script on a 4gb ram pc😂😂 i need to buy that pc

[@blandcoffeeamv4107]

I am currently building a bot for my thesis and want to test out everything´s working. i don´t have the parts at home and it´s kinda late to order the parts. i should be able to test it on my laptop too, right?

[@cheenamaejafar]

" and I had to sell my left kidney for this" - Hilarious!

[@matthewfelgate]

Wouldn't a trigger word with an X or K make it easier to detect? (Like Alexa or Ok Google)

[@theaihacker777]

Probably...

[@baskett98]

Install an Anaconda and you're set to start. Get more modules and libraries as and when required.

[@aaronchantrill7338]

I use "MagicVoice" which seems to work well. Does that count as using a 'K'? How are you choosing 'X' and 'K'?

[@luvsec5469]

The Michael Reeves we always wanted but never got. Until now.

[@anshpatel8083]

“ Apple’s okay. “ Im subscribing this channel

[@backinyourcommentsectionag3191]

eleven minutes of off-brand Michael reeves speaking greek

[@hs4lhp828]

Interesting video. Looks like fun. You're smart af. In other news, I've always suspected that I'm dumb af. This is now confirmed.

[@jeremyuzan1169]

Hi ! congrats for your work. How do you install Pytorch properly in a Raspberry Pi bro ? Thanks a lot :) Jeremy

[@PritishMishra]

You are a genius.. Subscribed !!

[@MatejMikulas]

can i make it in different language?

[@ali-g]

Oh man, you are amazing! Just inspired me, thanks for the great content.

[@Pablo-wf8dh]

Im in this video and I dont like it

[@vulcanviduus252]

I'm only 48 seconds in... but isn't that a picroft? The pi version of Mycroft

[@aaronchantrill7338]

PiCroft still uses a remote server to do the heavy lifting. Actually, the last time I checked with Mycroft, they were just passing your voice data through to Google STT Cloud. So if you are using Mycroft, you are still sending random bits of audio to a third party to process, and because they also do the Text to Speech on their remote hardware, both your request and the response are being handled by a third party. This requires quite a bit of trust on your part (it appears that the actual intent parsing is happening locally, but if both the STT and TTS are remote, then what is the benefit?) This is doing all the processing on a raspberry pi. Hardware you control. Also, I think the author's intent is more about showing how this works in a concrete way. He's providing a jumping off point.

[@mrCetus]

Your videos are amazing man. You've just earned a fan. By the way, I'd love to see you make the speech recognition model next.

[@lukewhatley8043]

Awesome video! Do you know if the dataset you decide to train it on has to be in .wav format? So close to getting your example working! Let me know if theres somewhere I can ask some questions regarding your code. Again great video man!

[@theaihacker777]

Hey Luke! If you have discord, join the discord server and I can help you there. The link is in the description.

[@phoenix1799]

Bro I use a setup with 128GB RAM with RTX 4080 16GB, RTX 3060 OC 12GB, RTX 2060 super 8GB on it with 5TB SSD M2 but I use as a open AIR setup for faster cooling. But you cabinet setup looks very efficient and cool. Could you send me the link for it

[@Nitro-Infusions]

My name is Michael too

[@தமிழோன்]

I wonder why your channel is still not famous. 🤔You deserve millions of subscribers!!!

[@AdityaChauhan-mk7lp]

Michael reeves from sarojni

[@Rottingflare]

This looks like an awesome project, can't wait to see more development!

[@ZolekaMncwabe]

I'm soo high, I understand everything....but tomorrow I wont🤣🤣🤣🤣🤣😭😭😭😭😭 fuck

[@sodapopcowboy8620]

Good news I understand this. Bad News I am overly perfectionistic.

[@mashudahmedtalukdar3005]

where is the next part we are waiting. please make more videos about AI Assistant

[@DIYRobotGirl]

But can we make it sing or match voice with pitch.h like we do with the buzzer. How do we get an AI voice to sing.😮

[@aperson1181]

Will it support other languages? I am trying to help my elderly mom, who speaks Ukrainian/Russian. I tried to have her speak into a Windows PC in Russian to transcribe this text and then translate it to English. Is there a tool for this? For some reason, Windows does not support Russian speech recognition. Yes, offline is a Big plus.

[@harjunmnath]

common man, give us the next video of this series we have been waiting too long

[@sreeram9220]

I'm not gonna lie when I hear your one minute speech I find some hope

[@ryandeguara1983]

Hi i tried joining your discord link but it does not let me (maybe server is full?), could I please be given a spot as I would love to join the server as I am looking to complete the project myself. Thanks

[@bradc6056]

I haven’t seen the rest yet, but have you thought of creating a blacklist of all the words that sounds like Wally, and that should increase overall accuracy.

[@tuandroidgeneral2091]

how did you get so fast response

[@aryagupta6965]

Part 2?

[@devdoctor6351]

Part 2?

[@vinijajain2909]

Check out more notes here if you're looking for details on speech AI: www.linkedin.com/feed/update/urn:li:activity:6954297492020613120/

[@egs-zs8-127]

Great video! Thank you so much!

[@THEREAL8030]

Hey there . What if we use computer motherboard and good processor, rams and SSD .so after it will work fast or will it even work or not . .

[@jenneralkiller7132]

I'm getting into Python and machine learning man any chance you could be a good teacher? I'll pay you. I need this from a robotics engineering and I'd rather have a mentor so if you're willing to teach show me where to start I mean I understand I need to learn Python but right now I'm homeless and I'm starting to learn Python at the same time I got screwed over with my financial aid doing my robotics cuz my family was being an asshole the older guy I'm just trying to make my way I got a job going for 25 an hour sucks but something's better than nothing. So maybe if you mentioned me in this I can mentor you and robotics

[@1minutechess]

Hey I am robotic researcher from India how to contact with you please help

[@doddianil6946]

my project is making authorized voice assistant it means the assistant respond only owner of the device commands only ,it not respond others commands by finding his voice. for this my idea is frist store user voice and give any command it compare stored voice with live voice both voices are match it respond otherwise not respond how to make it plz explain 😍

[@hussainbhavnagarwala2596]

Can we use CNN instead of RNN here for the classification of MFCC images?

[@loloxx7460]

I just download soft soft. Are you using the paid version or the free tutorial one? Because your screen looked way different than mine.

[@iventab2052]

Please make video for live remove speech around you will you listen to people for sample there's a list of music and any one playing on of this music this script will remove this and listen clear speech from person you talking with the music list could be songs or car voice etc...

[@AshrafAli-hg4zd]

Hi, My name is Ashraf Ali and I am from India could you please help me with my project

[@wojtekgame]

For now, i don't own an speaker running Python code...

[@melaniedavis6379]

Love this, but you see what had happened was I'm in confusion the words you say are too technical for my brain 😂

[@chrisw1462]

Sounds like a great project. Too bad you believe profanity adds to the quality of your work. It does not.

[@ErgsYT]

My boy went ham coding but didn't show us how he got the code in the damn thing 😂😂😂

[@saltofearth4902]

Omgurd your awesome.. First five min freaking had me laughing hard!

[@Mrprashu99]

nice tuto Saved , tNice tutorials should be a lot Nice tutorialgher. Thank you.

[@archlunarwolf]

He sticks it to Amazon and then goes ahead and orders the SD card from Amazon...

[@goldengun1214]

Woukd this work if i pprogramed it to sound like either goku or vegeta??? Ive thought about doing this for a big project i want to do

[@TuxTechLabs]

How to connect that with a Chatbot present on Private network computer . Please this will be a fucking new product

[@wmacosx]

Hi, thanks for the great video, can you tell me how much power/cpu this wake-word implementation consumes? I've always wanted to build something like that but I'm worried about the PI having to constantly process audio to catch that wake-word that I would use 2 or 3 times a day. I was thinking that maybe for the wake-word part, some specialized hardware would be preferable, so that the PI will be under load only for a short period of time after each wake-word activation.

[@Elian-]

Great video! High qualiy, entertaining and inspiring

[@aylinkaradag8487]

Anthony Angel first of all, I said no homo. Second, I didn’t understand how that softed gay at that ti and I still don’t understand how it

[@harleyehuffinejr2082]

Did you going to be the next Elon Musk but better stride stay alive you have no choice but the lift your voice this is Ohio Harley e 9

[@TheVikingActual]

I just want to make an AI I can talk to, I know it sounds sad It is sad 😔

[@simonedebellis6783]

does exist any way to run it on windows? i get an error where "torchaudio C++ extension is not available"

[@payamtorna2]

I bet you play video games on your war machine!

[@COOLIGANFN]

Im trying to build a robot and have some data that could be used for a good a.i can you help?

[@daynedement2645]

Is there a email I contact you I have a disability and would like your help to build one

[@NathanaelNewton]

"Ok, Now that we got the code.." Wow.. that was so information dense.. SUBBED AND BELL WOW.. I'm going to learn a lot here I think :)

[@Omkar-ey3ls]

really nice video. may I ask which resources you used to learn code that good in python for neural networks using OOP. i am freshman in computer science and wanted to get good at writing python code for neural networks using OOP. Thanks.

[@theaihacker777]

Hey! If you look into PyTorch, it’s very Object oriented paradigm to write neural networks

[@esimitley4729]

Where Practice Weight,? Because It is just for fun .

[@arisoda]

HOW LONG DID IT TAKE TO TRAIN ?????????????????????? approximately...?

[@aayushbajaj2260]

this is insane. thank you for building this.

[@sunilshewale913]

can u make google in alexa. like if i ask alexa to search from google website ..

[@kalyanstock8058]

Wow...can you do a video on text to speech for any voice?

[@chriz__3656]

is it possible to build this on raspberry pi 3 plezzz reply 😇

[@adeelmalik6257]

Yo does somebody has the source code because in his github it is nowhere to be found!

[@fortunateprogrammer7116]

Personal AI assistant using python "JARVIS" : kzbin.info/www/bejne/anicdnidrL98b7M

[@obviousabsurdity3181]

dont waste your time going to this link, he doesnt show any code, just a demo of his home version of jarvis :(

[@user-mr8cw4ud8n]

He had when he "pitched down the Nice tutorialgh hats at the end of the phrase. "

[@askminrui]

You dont need all these just for a wake up word detection.

[@helloqasim]

Next time make the video using your voice assistant

[@HappiFix]

daaaaayum good stuff homie g gangsta

[@jojo-gg1iz]

Damn he totally abandoned this project

[@thom2503]

Great video, liking the format

[@seesah]

this is so amazing!