NAM: Neural Amp Modeler

[Mongillo19]

NAM just went another level above:

View attachment 31986

TONEZONE3000: Training Made Simple

NAM is the fastest, most accurate--and now (I'd argue), easiest--way to make a neural model of your gear.TONEZONE3000 is a third-party website that puts the standard snapshot training process in a streamlined, easy-to-use website. Like the GUI and Colab trainers I've developed, users can reamp a...

www.neuralampmodeler.com

That's insane. Curious to see the results.

NAM is pushing the envelope on how I wish big box capture players would. Super fun to see

 

[Los-D]

The M4 Mac Mini at the same price as the Nano Cortex looking mighty tempting for NAM.

 

[Southpaw-DD]

I've started leaning toward a setup of plug-ins only for home use and then keeping a few real amps. I need to check out the latest with NAM this week.

 

[banned]

NAM coming on hard...but I still prefer modeling...I like knowing that the real physics and interactions are all being captured.

They need modeling augmented profiles or something like that.

 

[Mongillo19]

like knowing that the real physics and interactions are all being captured.

I'd argue a NAM capture is going to be more accurate than a model, you just don't get the flexibility of a model.

 

[2dor]

NAM coming on hard...but I still prefer modeling...I like knowing that the real physics and interactions are all being captured.

They need modeling augmented profiles or something like that.

Parametric NAM is a thing: https://www.neuralampmodeler.com/post/the-first-publicly-available-parametric-neural-amp-model

It's just that, for now, it's not something too many folks have attempted. I expect we'll see more stuff like this in the next year or 2.

 

[James Freeman]

Parametric NAM is a thing: https://www.neuralampmodeler.com/post/the-first-publicly-available-parametric-neural-amp-model

It's hapenning!
Who's going to be the first to deliver a full 6 knob JCM800 parametric NAM model?
Let the full amp capture race begin!

 

[LeftyLoungeLizard]

Did I mention that I dig NAM?

I did, and I'll do so once again.

 

[2dor]

It's hapenning!
Who's going to be the first to deliver a full 6 knob JCM800 parametric NAM model?
Let the full amp capture race begin!

I'd love to take a stab at it. I think Two Notes did it with their TSM-AI amps already:

Hektor - Two notes

About HEꓘTŌR Enter the next evolution in GENOME’s premier amplifier component line-up - the TSM-Ai Series. Fusing immaculate proprietary Ai captures, meticulously modelled tonestacks and expertly engineered power amp emulation, the TSM-Ai Series delivers on a singular mantra: empower players of...

www.two-notes.com

RockRider - Two notes

About RockRider Enter the next evolution in GENOME’s premier amplifier component line-up - the TSM-Ai Series. Fusing immaculate proprietary Ai captures, meticulously modelled tonestacks and expertly engineered power amp emulation, the TSM-Ai Series delivers on a singular mantra: empower players...

www.two-notes.com

THE 400 - Two notes

About THE 400 Enter the next evolution in GENOME’s premier amplifier component line-up - the TSM-Ai Series. Fusing immaculate proprietary Ai captures, meticulously modelled tonestacks and expertly engineered power amp emulation, the TSM-Ai Series delivers on a singular mantra: empower players of...

www.two-notes.com

MOLLY - Two notes

About MOLLY Enter the next evolution in GENOME’s premier amplifier component line-up - the TSM-Ai Series. Fusing immaculate proprietary Ai captures, meticulously modelled tonestacks and expertly engineered power amp emulation, the TSM-Ai Series delivers on a singular mantra: empower players of...

www.two-notes.com

 

[banned]

Parametric NAM is a thing: https://www.neuralampmodeler.com/post/the-first-publicly-available-parametric-neural-amp-model

It's just that, for now, it's not something too many folks have attempted. I expect we'll see more stuff like this in the next year or 2.

Woah...didn't know that was a thing. That looks like a parametric OD model. Have they published any amp models? I'd like to try out!

 

[2dor]

Woah...didn't know that was a thing. That looks like a parametric OD model. Have they published any amp models? I'd like to try out!

This is the only one Steve's published so far.

 

[Dom Mcsweeney]

Gigfast lite also has some parametric models - I've not tried yet, but people seem to be enjoying.

 

[2dor]

Gigfast lite also has some parametric models - I've not tried yet, but people seem to be enjoying.

Oh yeah! That's right - I forgot about those!

 

[CakeEater]

I concede... I've been trying really hard to get a new ultimate preset in my Helix. I've got my wet effects completely sorted and I like to put them into an edge-of-breakup amp in stereo that can easily push to thick overdrive. Every time I get the amps sounding good on one set of speakers, they sound tinny in high pitched or flubby in another. I opened up NAM again today and I tried a Supro Black Magic and a Marshall JMP and both were instantly perfect. Huge full mids, not too much highs, not too much lows.

Maybe I just can't dial in amps very well, I haven't had that much experience with a wide variety of tube amps, but this was just so effortlessly easy. The Supro was a full rig and sounded perfect out of the box. I put the JMP with the default settings of the M25 412 cab from the Helix and it also sounded instantly perfect. At this point I think I just want a stereo NAMM player that's hardware so I don't have to deal with my somewhat temperamental Microsoft Surface 3. I do miss the stereo effects but the amp tones are so so good.

 

[Humbug]

NAM just went another level above:

View attachment 31986

TONEZONE3000: Training Made Simple

NAM is the fastest, most accurate--and now (I'd argue), easiest--way to make a neural model of your gear.TONEZONE3000 is a third-party website that puts the standard snapshot training process in a streamlined, easy-to-use website. Like the GUI and Colab trainers I've developed, users can reamp a...

www.neuralampmodeler.com

Ok, this sounds like something very useful for me and my weird amps:

"1. Imagine playing the model.
2. Imagine asking "but can it handle XYZ?" (E.g. cleaning up when you roll back the volume)
3. Do that so it gets to train on it and the answer will be "yes!"" - Steve Ack

I'm definitely going to give the Wet/Dry training a go as soon as I have the time. If it can accurately capture the interaction between guitar volume knob, cable and amp I will be very happy.

 

[Humbug]

Ok, this sounds like something very useful for me and my weird amps:

"1. Imagine playing the model.
2. Imagine asking "but can it handle XYZ?" (E.g. cleaning up when you roll back the volume)
3. Do that so it gets to train on it and the answer will be "yes!"" - Steve Ack

I'm definitely going to give the Wet/Dry training a go as soon as I have the time. If it can accurately capture the interaction between guitar volume knob, cable and amp I will be very happy.

...And another thing that just occurred to me: Fuzz! Because this solution allows you to feed the device an actual guitar signal it should be possible to accurately capture proper fuzzes that rely on the guitar's impedance for gain control (the ones that don't work well with active pickups and buffers). I think this will be my first experiment.

 

[2dor]

...And another thing that just occurred to me: Fuzz! Because this solution allows you to feed the device an actual guitar signal it should be possible to accurately capture proper fuzzes that rely on the guitar's impedance for gain control (the ones that don't work well with active pickups and buffers). I think this will be my first experiment.

Now *this* will be interesting

 

[paisleywookiee]

The M4 Mac Mini at the same price as the Nano Cortex looking mighty tempting for NAM.

16GB RAM standard is nice too.

 

[bikescene]

Did you guys try Tonezone3000 yet? I only briefly looked at it and didn’t sign up yet. Can you train more than 1 at a time? The way I worked around the slow speeds of the Colab page was by doing training in parallel. What are the speeds like for 700-100 Epochs?

 

[2dor]

Did you guys try Tonezone3000 yet? I only briefly looked at it and didn’t sign up yet. Can you train more than 1 at a time? The way I worked around the slow speeds of the Colab page was by doing training in parallel. What are the speeds like for 700-100 Epochs?

I used it to train all of the reamps (111) in the Badlander pack with the LITE architecture.

You can upload reamps in sequence (for now; batch training's coming soon) and they'll train concurrently just fine.

ToneZone's great as long as you're staying within the limits of the default profile architectures (Feather, Nano, Lite, Standard) NAM comes with by default.

It gives you the chance to use up to 1000 epochs per reamp training session as well as tweaking the "learning rate" and "learning rate decay" which may allow the model to still converge even past the 650 - 700 epoch threshold (as long as you figure out the right combinations).