Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

github.com

Post reply on HN
Print view View original

51–60 of 163 posts

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#51

Post by keyth72 »

romwell wrote: post #38
keyth72 wrote: post #33

Earlier quoted context omitted.

Thank you and much appreciated, will definitely do that before posting again. I probably shouldn't have internetted today.. closes computer sheepishly

> I probably shouldn't have internetted today.. Well, you did get the attention :) Now that you are here, you can update the project description. I feel like the point that this way of making a plug-in allows anyone with the hardware to easily create an emulator for it is not really coming through. That's the selling point of deep learning.

Opens computer back up Excellent point, and it looks like my title was corrected, thank you for fixing it and not deleting it, whoever that was.

What I'm really aiming to do in the long run is to get other musicians and machine learning enthusiasts to train and share models that will work with these plugins for a variety of hardware. It's very much a new technology to me and I'd like to figure out what all it can do.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#52

Post by joeel84 »

MrBuddyCasino wrote: post #49
w0mbat wrote: post #44

For people who don’t play guitar, this is really commonplace technology now. Engineers worked out how to model the circuit behavior of any amp a while ago. Powerful valve guitar amps have really interesting effects on the waveform particularly when driven hard, but that valve technology is expensive, unreliable, bulky, and very loud when producing some of the most sought after tones. The most popular guitar amps now…

Is latency an issue?

Yes.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#53

Post by mhh__ »

MrBuddyCasino wrote: post #49
w0mbat wrote: post #44

For people who don’t play guitar, this is really commonplace technology now. Engineers worked out how to model the circuit behavior of any amp a while ago. Powerful valve guitar amps have really interesting effects on the waveform particularly when driven hard, but that valve technology is expensive, unreliable, bulky, and very loud when producing some of the most sought after tones. The most popular guitar amps now…

Is latency an issue?

Latency can be an issue if you are playing through a desktop computer or laptop, but its very manageable (for the most part) if you set up your buffers right.

I have never ever noticed any latency issues with any physical hardware, even for equipment from years ago.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#55

Post by keyth72 »

romwell wrote: post #37
soperj wrote: post #32

Earlier quoted context omitted.

Okay, but why would you pick a Blues Jr. instead of an Original Fender Champ?

Probably that's what the author had available? I mean, for a free plug-in it's not like there's a budget to go and splurge on hardware. Looks like the point of the project is that this can be used to make their own models easily.

Yeah I'm not a company here, just a musician with an interest in machine learning and a few amps cluttering up the bedroom. I'd love for other people to train and share new models with this technology. I think that making this free and open source gives it the potential for much smarter people to make something bigger than I can do on my own in my free time.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#56

Post by mhh__ »

sosborn wrote: post #14
tgv wrote: post #9

Earlier quoted context omitted.

IANAG, but it sounds like it's recorded through a speaker in the room, and the miking wasn't optimal. Now that might be the recording we watch, or the actual output of the plugin; no way to tell. But apart from that, it's quite good, IMO. (I Am Not A Guitarist)

As a guitarist, it is important to understand that any time you tell a guitarist that the sound is digital, the guitarist will scoff and say it doesn't sound like real tube amp, regardless of what they said or thought before knowing it was digital.

Exactly the same with analogue synthesizers.

A lot of the time they don't mean analogue when they say they don't want digital - they mean that they want knobs and switches to play with. I think some modern Moog's even have a digital stage in the signal path (I might be making that up but I have some vague recollection of it in a schematic)

Making a synth sound good has very little to do whether it uses analogue or digital synthesis these days, but analogue equipment is (for the same price) less reliable, uses more power, less flexible, and more susceptible to being damaged by impacts (and keep in mind that you can't repair a lot of modern gear with SMD soldering experience anyway)

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#57

Post by keyth72 »

MrBuddyCasino wrote: post #49
w0mbat wrote: post #44

For people who don’t play guitar, this is really commonplace technology now. Engineers worked out how to model the circuit behavior of any amp a while ago. Powerful valve guitar amps have really interesting effects on the waveform particularly when driven hard, but that valve technology is expensive, unreliable, bulky, and very loud when producing some of the most sought after tones. The most popular guitar amps now…

Is latency an issue?

Second Yes. I would not play this at a live gig myself, but it does run fine on my Acer laptop with i5 processor, which is not meant for serious audio processing. If you try it and are getting latency issues, try adjusting the sample rate. Also the stand alone app seems to run much slower than the VST plugin, but most people interested in this I expect would use the plugin anyway.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#58

Post by TylerE »

offtop5 wrote: post #15

Would be cool if you could run this thing on a raspberry pi and actually use it like an on stage amp

That's unlikely to end well. You really need custom audio hardware - or at least dedicated commercial-grade stuff, for this sort of application. Latency is HUGELY important. 2-3ms can be felt, and most consumer level stuff uses buffers WAY bigger than that.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#59

Post by marketingPro »

qwertox wrote: post #50
bserge wrote: post #39

Earlier quoted context omitted.

Funny enough, esp8266 boards is all I can find in my country. Probably because it's cheap and versatile. I need to try it, but can't think of anything to use it for.

Nowadays it's better to directly start using an ESP32, if you want to experiment. It has bidirectional I2S, (for example mic in, apply dsp, then out to speaker), is dual core, which would allow you to do the audio-related stuff on one core, and everything else (like communications) on another core. If you then see that you don't require all the good things an ESP32 has to offer, maybe because you only want to drive a…

Why go for a esp32 if you can use i2c for reading many values and driving relays?

Serious, because I am building a complex product and trying to keep costs down.

Or are you referring to hobbyists?

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#60

Post by albutr »

aeleos wrote: post #6

Just tried it out, I don't know if I would say it sounds like a $600 tube amp especially in high gain scenarios (it really didn't like my active pickups), for a free plugin it is definitely great. In comparison to the Archetype Nolly plugin from Neural DSP it doesn't really compare, but but for something thats free and can be trained at home on custom audio samples its pretty cool.

wow, I was literally just about to download the trial for the archetype nolly (after being iffy on whether the fortin nameless was right for what I wanted), what are the chances it's being discussed on HN.

I'm hoping that the nolly plugin can cover both dirty and clean sounds well enough to not need a second plugin, fingers crossed

Post reply on HN