Solo as in no other instruments or sounds are present, only guitar sounds. Chord riffs are definitely okay. 
3 Likes
Will it work on lower-register instruments like baritone or bass?
1 Like
I wouldn’t expect good or accurate results with instruments other than guitar, as it was trained on electric guitar sounds and using guitar Amp-sims.
However, let us know if you had a meaningful experience with your instrument.
4 Likes
just asted 45 mins trying to get it to work 
all goes well until the step
“Pedalboard successfully uploaded to your device!”
nothing happens on my dwarf, tone doesnt change, nothing changes on screen
connectivity is ok,
reconnect,
reboot,
update
none of it helps
tips?
Before to download the pedalboard from Assistant try do save the current pedalboard on your device and than download. Or better… create a new (default) pedalboard on device and than diwnload from assistant. In my case the second solution wotks…
3 Likes
that worked @Rino2
Thanks
@friedsilence
Once again, I’m faced with a maxed out CPU 
Am I the only one maxing out while using the Mutant on a Dwarf?
nasty interruptions/clip/cutouts due to cpu maxing out.
always happens when using the Mutant, even with this prefab board
I haven’t noticed that - I have a few pedalboards with the Mutant feeding into Vintage cab and a few effects, sometimes with Roamer and Bass Cabinet on the second input.
I tried the pedalboard, also my dwarf will explode without buffering to 256 frame.
However i think that the more CPU hungry effect is the room reverb ( 44% CPU used when is alone in the screen), Mutant only uses 27%.
In my pedalboard the Mutant never gave me problems, instead dragonfly reverb ( Hall and Room ) are really too “heavy” to use them ( and a pair of other plugin) witout use the buffer.
Usually i use the “early reflection”+“plate” combination for similar result and for save some CPU as showed by Roger Couto here: AROG Clean Klein 02 - MOD Audio
I tried them on your pedalbord and it became usable.
Clearly in this way the assistant need some assistance 
1 Like
I’ve noticed that the Dragonfly reverbs really bog down a pedalboard as well. They’re beautiful and I want to love them but they’re so impractical unless you have a pedalboard that’s JUST the reverb.
1 Like
@CarloDossi @RashDecisionAudio
Not much experience with the reverbs but the main reason I don’t use the Mutant is because of it being the plugin maxig out my boards in other setups too. It’s really a pity because it has the best sound for my heavy metal / thrash band. The Dwarf just can’t deal with it properly and up till now, It seems like one of the sole voices speaking aobut that so I guess it’s not “the Dwarf” but “my Dwarf” that can’t handle it properly.
I’m steering this off topic hough.
I love how this tool works as a creator for a tone primer.
Got me wondering how you can detect suff like that. Crazy math? 
update on the Mutant+verb+cab sim cpu issue.
@Jan did an update on the mutant that chips off 5% cpu load and it made the difference for me
Read about it in the Veja Mutant thread
6 Likes
I’m happy to announce we got a 20k€ government grant from a German innovation subsidy program approved for the “AI Pedalboard Assistant” project!
Quite some paperwork and payout is spread over the year, but it’s a meaningful contribution for this stage.
26 Likes
cool, that promises some more granular and precise results in the future?
But yeah, reverse engineering a sound to different components DOES sound like witch craft!
Congratulations!
3 Likes
that is really cool to hear.
Is this bound to this specific project? Meaning you can also pay for the development time for the “supporting” tools with this grant?
1 Like
Hope there’s dev money for bassists in there… 
7 Likes
For bass we will do some experiments @RashDecisionAudio. The general approach should be applicable as well, but hard to say what it takes to get to good results at this point in time honestly.
3 Likes
Absolutely expect more precise results moving forward @LievenDV, each serious usage of the MOD Assistant Beta with feedback is contributing!
What sounds like witchcraft is neural feature detection married with the power of the MOD platform. This allows @itskais to have the AI explore a huge amount of combinations in a highly automated fashion.
While there is still a long way of learning to go, I believe we are on a very interesting and accelerating path.
1 Like
@Luke101 be assured most of our development resources go to short term effective improvements. Actually fixing known timing issues you mentioned is in progress and planned for release with MOD OS 1.14 to support Delay and Live Looping marketing specials we want to do later this year.
Not having projects like the AI Assistant would free up a bit resources now, while making it harder to grow them moving forward. Beside the essential polishing of the user experience, we need fresh innovation to get more funds. The 20k€ is a small but important proof point. Won’t stop there.
5 Likes
Do you plan to also use the guitar input as part ofthe training data in some way?
I might be wrong (i havent yet actually had time to try it out yet). But it looks like right now from what i saw visiting the link that the guitar input is ignored.
Some examples are like how hot is the output of the guitar or the tonal eq and which pickups are selected etc.
It may make sense to have two separate stacks one to try and match guitar to a reference and then the next to turn the matched reference into the desired sound
Different guitars and setups have very different tones and may not use the same pedal stack.
I.e. i would love to be able to have a reference track as well as a sample of me (trying) playing the same thing on my guitar and ask it to try and match as best as possible to make my guitar sound like the reference.
3 Likes