Видео

Absolutely no words to describe...........amazing❤

for future peeps if you get an error that says cannot convert x to shape i fixed it with this: return Input(shape = (self.latent_space_dim,), name = 'decoder_input')

amazing content, keep up the good work bro!

By far, this is one of the best series on deep learning. I've watched many videos on deep learning, but the information often felt jumbled in my head. With this series, I was able to link the concepts together, making everything more meaningful. Valerio, you are not only a good engineer but also an excellent tutor, a skill many people lack. I sincerely thank you for your videos.

Thank you so much for this series. I want to know if there is any way I can convert the music files (may be .wav or .mp3) into .krn files? Kindly reply.

Excellent course ! And thank you for teaching !

Hey Valerio, This is just amazing content, i like the depth, the way you explain in so simple terms, you satisfied my curiosity for this whole topic.

Greattt playlist!!

Thanks a lot! This series is fantastic!

I wish there was an Ai that i could upload an instrumental with the tempo and key and it generates the lyrics and voice and melodies to complete the song on top of the instrumental

I can't believe that such a content exists for free! Thanks Mr. Velardo so much.

Fantastic video! It's engaging all the way through and a wonderfully clear explanation of everything.

Citing you in my master's thesis. Thank you for these videos!

Great video. I was confused how the gradient descent function updates the weights for the MLP. As I was coding along, the functionality wasn't correct until I added ```self.weights[i] = weights``` to the bottom of the main loop of the gradient_descent function. How did your version work without this line? Is there something about python memory I am not realizing here?

Thank you so much for this valuable tutorial!

you should have a million subscription man, you deserve it among the all these trashes/

thank you very much, this video was very useful

Velario, I'm mid writing my PhD thesis on music generation and this video is incredibly useful for ensuring my explanations make sense and is a great source to cite. Thanks for making it! Also at 1:00:38, why is your dimension model 2 for the cos(pos/10000^2i / dimension model) examples? Just want to make sure if I'm misunderstanding something :) Thanks again!

but the model has seen the data (the example you gave it for inference was itself used for training) is that normal ?!

Hi , any AI generative tools or software suggestion that help just arrangement on the song, assume that already have the melody midi or wave file.. ???? the arrangment may be add back the drum pattern or chord match , intro, bridge fill in, and so on. ??? thanks!1

I notice in the librosa docs they don't square the magnitude but then use amplitude to db, does anyone know if this make any difference to the final results? Guess I'll have to try to understand everything properly later! Great video!

It was in th description.................... LintIDE vs Jupyter Notebooks(pycharm) 2:43 Produce Claen Code 3:35 Lint your code(pylint) 3:57 Test, test, test! (pytest) 6:41 Track experiments (ml flow),model regsiter 8:06 Version data (DVC) 9:13 Use a pipeline(DVC) 11:01 Takeaways

Thank you

Bro outraged everyone with light theme on

i believe you need to use python 3.10 to get that version 2.13 of tensorflow, otherwise the karas text preprocessor is deprecated.

So is this correct?: We could use RAVE to encode a wav into a Z. Then, train a transformer with a bunch of Z's, and finally use a dataset of Z's to generate a new wav?

Excellent video. Thank you for the explanation. I do have a concern about your sine wave formula, and maybe somebody has already mentioned this, or maybe you talked about it and I missed it. If you want phi to be equal to the phase shift in your sine function, the horizontal scale factor (2pi•f) must be shown as a coefficient on the binomial (t - phi), as horizontal dilation is done before horizontal translation (otherwise the dilation changes the translation), and when shown in with the variable, must be written in the opposite order (last transformation closest to the variable). The way you have represented your sine function in this problem, the true phase shift would be phi/(2pi•f). Contrary to most physics texts, I find it more straightforward mathematically to let phi represent the true phase shift and show the argument of the sine function as 2pi•f(t - phi). Some physics texts and math texts do this, but not many. Having taught college algebra many times, I think this format is more consistent with the logic of transformations of parent functions, and therefore more conducive to a deeper understanding of the geometry of the sine wave. But, to each their own, I suppose.

Thank you!! Very helpful & clear!

It appears the process of training is skimmed over. Is there another video/series that can help me learn how to train the transformer. Do I need to watch the other series from 4 years ago to learn this? "Deep Learning (for Audio) with Python"

Excellent workshop. Question? I'm producing a Hip-hop track and am looking for a generative music system that can write a classical string arrangement for the song. Any suggestions?

Ciao Valerio, ho una domanda. Se ho già acquisito un suono, campionato a una certa frequenza fs e avendo acquisito un certo numero di punti N, come funziona il time stretching ?

Are the spikes in the ZCR for voice occuring when two people are speaking at the same time?

I thought you glossed over vibrato a bit too quickly, perhaps it'll be expanded upon in later videos (phase function design). really good explanations other than that. I answered my immediate question by looking at this: ruclips.net/video/UcLTYwfDeaU/видео.html

Hello! Thanks a lot for the videos, it helped me a lot to do my undergradute thesis c:

Generative Music aside these are excellent videos for learning Python.

This would have helped me in my last role

The real strength of an audio model is its ability to be fine-tuned to hone down on the sound you want. I've been trying to fine-tune musicgen and trying to work with Dora and Hydra has been ridiculous. Have you tried fine-tuning the others on this list to see if they're easier?

Shoutout Leanhard Euler

❤❤❤

in waiting for part 3 of the course!! thanks!!

even though 2 years have passed I wanted to thank you. this video helped me lots!

thanks a lot, great work

i probably can say that this video is the best on whole RUclips about this topic, i searched really a lot and all i found was very superficial courses. Great job.

Thanks Valerio

I was trying to understand the aspects related to perceptual attributes of sound when i found your videos. I should say that you are a true teacher and good communicator. I have tried many videos but yours is the best. I am able to understand the basics of sound now.

These video are helping me so much in understanding Audio Processing! Thank you so much! This has so so much value to me.

24:49 or you could use a higher order markov chain and decide how far back you want to track the previous states. Great presentation!

Thankyou so much for this very well explained series, loved following along to every bit of it! Hoping to use all the knowledge for my personal projects :))

How do you get the users token in the new Spotify for developers i cant find it

You teach so well. I have a question. I’m going to detect phonological feathers of African American English from some interviews, and I want to make the detection process automated. What do you recommend?