Silly question but how is the Vector quantization reduction of the encoded Floats to quantized Ints a representation of music that is more able to be treated like text? In other words, how is the constant stream of Ints more Text like than the vector of Floats, when speaking abstractly? Do you mean because we use ASCII and already use a stream of Ints for language on computers, and that is the natural form rather than encoding language into tokens? - Matt Jackson

​@@soma808 Yes, I probably should have explained that distinction better. Text (at least in the context of transformer-based models like LLMs) is usually represented as a stream of integer 'tokens' which are derived from the input text using a tokenizer (usually not with a 1:1 correspondence to characters, but rather common groups of characters). LLMs are learning the categorical probability distribution over this discrete set of tokens given the previous tokens, very much like an advanced autocomplete. You could do the same with float vectors, but it doesn't usually work as well because you have to make assumptions about the continuous distribution which results in a much less expressive model. There's also a bunch of nitty-gritty architecture reasons why integer tokens work well with transformers. So ignoring the deeper philosophical aspect, the answer is basically "Ints work better for text in practice".

Not true, the travelling waves form of the solution and the Fourier solution are equivalent

Watch a slow motion video of a guitar string being plucked.

yeah it's kind of annoying

The Korg Z1 and other Physical modeling synthesizers from the 1990’s had already plucked and bowed string models. Here is a Korg Z1 demonstration of the bowed string model: kzbin.info/www/bejne/jqrWgHp5eKqGmLc And another demostration that pushes the parameters to the limit: kzbin.info/www/bejne/laSak6V4mdNjpLs&pbjreload=101 The sophistication of the NESS model is obviously higher, almost 20 years later.

I read your user as atomictwat for a second then. was about to say. very fitting

@@johndozesoph4136 you developed a youtube post! <3

how did it go?

@@philosyche I had to gather 1 million Mexican pesos and even with the 3 scholarships I was granted with I was short 200k, I had everything else placed except the money, so I'll live a bit frustrated by that the rest of my life jaja

​@@SlebenGates Aw, I'm sorry! I am certain it was their loss! I was a bit curious, the university website lists the fees to be £26,300 for international students, which seems less than a million Mexican pesos. Were you trying out for the BSc program by any chance? That would be more expensive than the MSc.

@@philosyche I had to pay the travel, the staying and the expenses of each month such as traveling, food, clothing for that weather and documentation fees for the VISA and national documentations (passport, national/international permits). Even working in the Library or the cafeteria as they suggest you do I would have still been cut short and probably having to retire. It is worth noting that at that time I couldn't apply for a scholarship that required mortgaging a house since I didn't have anyone owning a house that could have lended it to me. Thank you for your kind words

@@SlebenGates ahh yes, that sure was quite the bill. Thank you so much for your replies! Hope you are doing well!