Видео

Haha fair enough! We can definitely add that in :)

Happy you enjoyed it!

Hey Laku, So happy you’re enjoying the tutorials! Hosting on a raspberry pi is amazing and a great idea! Could you confirm what your init_db function looks like? Also, it might be easier to find the specific issue if you join the discord in the description. No pressure though if you’d prefer to chat here :)

Hmm, it looks like you might need torch installed. Try doing pip install torch and then close your terminal and try again.

Thank you!

So happy it helped you in some way :)

Hmm, interesting. Are you sure that it’s saving the .wav file to the same directory as your py file?

Thanks! While I would love to upload more, weekly is as best as I can do while working a full time job and having a family and other interests. I do hope to be able to get some series out maybe faster though some day :)

​@@jakeeh okay. and please in next project make a social forum.😊

@sumanchess oh that’s a fun idea! We could certainly do something like that!

So happy you’re enjoying it!

Awesome! I’ll look into making a basic one at some point :)

Hey, Yeah, that should definitely be possible! You would need to create a model that’s capable of doing that, but there are some free libraries that can help with that already. One example is tortoise. Maybe I’ll make a video about it in the future :)

Thanks! It should be coming out this weekend :)

Oh! I don’t mean fast as in processing speed, just that it’s relatively simple to create an HTTP server

Happy you found it useful! :)

Thanks a lot! The video will be coming :)

Absolutely! Surprisingly flask isn’t limited to just simple stuff, it’s can work for some larger things too :) although it’s almost certainly not vanilla flask in those cases :)

Thanks! To be honest, I had no idea speech_recognition had that. How does it compare?

Thanks for the comment :)

Thank you!

You’re most welcome! Thanks for your comment too :)

Thanks Ashenone!

Thanks Drak!

It should be possible, yeah. You’ll need to investigate voice mimicking. I think all you would need to do is take the input, run it through a model of your choice, and then get the string as output and run it through your custom voice. If you want it be able to be smart based on the response though, that would be much more difficult though. You’d need custom models, that’s something big companies are still figuring out

Happy you found it useful! :)

Great question! I think it depends on your goal for the app and what you’re trying to learn from it. I’ve been really enjoying flutter because it means the app will work for Android, iOS, and web. However, if you’re looking for a job, it might not be as useful to learn flutter. Many larger companies will have native app implementations for their platforms. There are some benefits to making a native app as well such as performance and access to some of the more unique things of the OS. For me, I’ve written large apps for iOS natively, and made some smaller ones for Android. I like flutter because it’s fun to learn something new and surprisingly easy to get things going, but I know it won’t really help me with my professional career. If I wanted to make an app to just get started though for an idea I had to try to sell on the app stores, I probably would start with flutter though.

ffmpeg can be annoying to work with at first but it can be super powerful if you get used to it :)

@@jakeeh I got the speech in , image in , text in ... I got the speech out , the text out , (no diffusion yet) .. I would like the video in ! ... Perhaps to pictures to description ... I would like sound in to description (like that's the sound of a man ... Driving a car ? ) .. and sound out , generate the sound of a dolphin ? ... So this version of speech in is actually not bad .. still a playoff between this and whisper ... But this has enabled me to have the microphone live instead so it's great 👍

Yeah, that would be an amazing tool if you can get all that working! Diffusion in my experience takes a while, although I don’t have an Nvidia GPU so it’s just using CPU.

@@jakeeh the audio diffusion is actually quite quick ... i have the stable diffusion for imgae also but i think it was quite heavy ... i think there maybe a different option... i think the stable diffusion method is actually bad ... not for soun but for vison ... its too heavy and too many parts !

There’s a link in the description with the code :)

Thank you :)

Kanban can be super handy!

Haha did it make you feel like you needed to get back to working on a project you forgot about? :P

That's exactly why you need something to help track your projects! haha

Sure thing! Just added it to the description :)

Thanks for the comment!

Yeah at the time llama wasn’t easily available for windows. There are definitely some better things available now

Thank you! 😊

It’s a mix of just in my head and usually a Google Sheet or Doc. I tend to have a few projects I want to work on and then one with interest me a lot and I’ll dig into that until either it’s done or something else catches my eye 😂

Great point! I think what you could do would be similar to what many home assistants do which is have a small lightweight program that runs all the time just listening for a single word or a stream of words. Then it saves that if it heard the keyword at the start, like “Alexa”. Then it executes another separate program that does the heavy lifting of understanding the audio and it returns a response. Still not super ideal, but you’ll need something running to listen :)

@@jakeeh I think that you need to have a wake (two words) ... Like "hey Alexa" ... The extra word enable for less confusions with other potential simple words which may activate it by accident ... .. so like hay Jarvis ... Or hey computer ... Is perfect ...

It depends on the case! 🕵️

Yay! I’ll definitely add it to the list. Thanks for your comment :)