Build a Deep Audio Classifier with Python and Tensorflow

My vscode cant install tensorflow-gpu while i could install tensorflow, cause it says my python is 3.11 while gpu only supported 3.8 or 3.6 but i cant download them anymore since the python web removed the file. Could i just using standard tensorflow for voice emotion classification? or at least latest tensorflow-cpu? Please answer me for my thesis, thank you

The sampling rate has nothing to do with the magnitude of amplitude of the waveform. Sample rate is defined as how many samples are taken (datapoints for amplitude of the waveform) per second. 44.1kHz means 44100 data points of the amplitude were taken in a single second. The magnitude of amplitude will depend on the intensity of the signal, not the sampling frequency.

In other words, sampling rate tells you how many datapoints of amplitude are in a given time diferential. 16kHz = 16k datapoints for amplitude every second.

Nice tutorial. A few inaccuracies there though about stft() usage: "abs()" there is not for getting rid of negatives, but for complex values amplitude. frame_length would probably better be power of 2...

Hey, Im facing an issue while compiling the model
model = Sequential([
Conv2D(16, (3,3), activation='relu', input_shape = (1491, 257,1)),
Conv2D(16, (3,3), activation='relu'),
Flatten(),
Dense(units = 128, activation = 'relu'),
Dense(units = 1, activation = 'sigmoid')
])
how to avoid ResourceExhaustError from the above code
I cannot install tensorflow-gpu, ig coz i only have a GeForce MX450 and am unable to install cuda
So can anyone help me out

Bro, great video and very good detailed explanation. 👍👍👍

hello,
for some reason

wave = load_wav_16k_mono(CAPUCHIN_FILE)
nwave = load_wav_16k_mono(NOT_CAPUCHIN_FILE)

is giving an error
"the procedure entry point cannot be located"
though I have stored the 3 audio folders in the same directory

This video is Awesome!!!
I got to know from this video that we convert Audio data to image data, to approach audio related tasks in ML!!!

Thanks a lot

It's a very interesting video. But can we do the test using sound sensor?

Thanks for such a great tutorial. I have a question:
What happens when resampling is done to an audio file? Does its total time changes or its number of sample changes or both changes or it depends on specific algorithm?

How can we use Linear predictive coding in the preprocessing function of this code?

Thank you so much for these nice tutorials! They are quite helpful! I have a small question. I saw your process of building up models and training and testing them. If I want to spend less time in classifying the model, do you think it's possible to introduce some existing datasets such as esc-10 or esc-50 in your method?

good video, new subscriber, but is there a way to export that training model, to be able to use it from a python file that can do sound detection through the use of said model

when I to retrieve the dataset with "tf.data.Dataset.list_files" I get "Expected 'tf.Tensor(False, shape=(), dtype=bool)' to be true.". I am mounting Google Drive as I have loaded the data there. I tried everything to make it work, but I can not seem to find a solution. Any help would be greatly appreciated, thanks!

thee best .!😍

good tutorial. Note that sample rate has nothing to do with the amplitude of an audio file but rather the number of times the audio file is sampled per seconds.

Amazing job Nicholas!! I have just a question, why didn't you calculate also the standard deviation of files' lenght so to have a more precise interval for your window?

Can I use this to re-create a voice of a singer and then use this model in SVC?