HISE Logo Forum
    • Categories
    • Register
    • Login

    Neural Amp Modeler (NAM) in HISE

    Scheduled Pinned Locked Moved General Questions
    26 Posts 14 Posters 2.6k Views
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • B
      Ben Catman @aaronventure
      last edited by

      @aaronventure

      🀞

      Wow, that would be SO awesome! Can provide you with some quite nice models then :)

      1 Reply Last reply Reply Quote 0
      • FortuneF
        Fortune @aaronventure
        last edited by

        @aaronventure said in Neural Amp Modeler (NAM) in HISE:

        @Ben-Catman we're all holding our breath until January.

        What will happen in January?

        A 1 Reply Last reply Reply Quote 0
        • A
          aaronventure @Fortune
          last edited by

          @Fortune Chris will be resuming work on HISE.

          Christoph HartC 1 Reply Last reply Reply Quote 0
          • Christoph HartC
            Christoph Hart @aaronventure
            last edited by

            @aaronventure actually Iβ€˜ve already implemented NAM on a local branch of HISE but itβ€˜s not stable yet and quite CPU intensive. I hope we get the CPU down to competitive speeds with other implementations but that has indeed to wait until January.

            Dan KorneffD orangeO 2 Replies Last reply Reply Quote 3
            • Dan KorneffD
              Dan Korneff @Christoph Hart
              last edited by

              @Christoph-Hart January 1st or 2nd? πŸ˜‚πŸ˜‚πŸ˜‚

              Dan Korneff - Producer / Mixer / Audio Nerd

              Christoph HartC 1 Reply Last reply Reply Quote 0
              • orangeO
                orange @Christoph Hart
                last edited by orange

                @Christoph-Hart

                In case it helps:

                When I create Neural custom node and try to open it as Hardcoded FX, it doesn't work.

                I had to embed the Neural network .json even with the Hardcoded FX too.

                I thought maybe this was causing HISE to make extra efforts.

                develop Branch / XCode 13.1
                macOS Monterey / M1 Max

                1 Reply Last reply Reply Quote 0
                • Christoph HartC
                  Christoph Hart @Dan Korneff
                  last edited by

                  @Dan-Korneff more like January 17th..

                  Dan KorneffD 1 Reply Last reply Reply Quote 1
                  • Dan KorneffD
                    Dan Korneff @Christoph Hart
                    last edited by

                    @Christoph-Hart
                    giphy.gif

                    πŸ˜… πŸ˜… πŸ˜…

                    Dan Korneff - Producer / Mixer / Audio Nerd

                    1 Reply Last reply Reply Quote 1
                    • S
                      Sclass
                      last edited by

                      Any updates?

                      Christoph HartC 1 Reply Last reply Reply Quote 0
                      • Christoph HartC
                        Christoph Hart @Sclass
                        last edited by

                        @Sclass nope, working on other stuff.

                        S L 2 Replies Last reply Reply Quote 1
                        • S
                          Sclass @Christoph Hart
                          last edited by

                          @Christoph-Hart Still keeping an eye out for the NAM update :)

                          1 Reply Last reply Reply Quote 0
                          • L
                            Lurch @Christoph Hart
                            last edited by

                            @Christoph-Hart Any news? This would be an amazing addition to HISE.

                            A 1 Reply Last reply Reply Quote 1
                            • A
                              aaronventure @Lurch
                              last edited by aaronventure

                              @Lurch I mean, it works? The performance is seemingly twice as bad as the NAM plugin, but only because the neural node in HISE is processing two channels, and the NAM plugin is processing one.

                              If you use the multi node to force mono processing and before that collapse the stereo signal into mono, you get roughly the same performance.

                              Create your NAM file in the colab https://colab.research.google.com/github/sdatkinson/NAMTrainerColab/blob/main/notebook.ipynb

                              Put in into the Samples directory.

                              const neuralNetwork = Engine.createNeuralNetwork("MidDrive");
                              
                              const namModel = FileSystem.getFolder(FileSystem.Samples).getChildFile("model.nam").loadAsObject();
                              
                              neuralNetwork.loadNAMModel(namModel);
                              

                              Create a ScriptFX DSPNetwork and load the math.neural node.

                              It would be cool to be able to embed the .nam files into the plugin instead of having to install them separately.

                              Christoph HartC 1 Reply Last reply Reply Quote 0
                              • Christoph HartC
                                Christoph Hart @aaronventure
                                last edited by

                                @aaronventure said in Neural Amp Modeler (NAM) in HISE:

                                If you use the multi node to force mono processing and before that collapse the stereo signal into mono, you get roughly the same performance.

                                Haha wasn't all that drama about it being 8x slower than the NAM plugin?

                                It would be cool to be able to embed the .nam files into the plugin instead of having to install them separately.

                                Can't you just embed the JSON content of the NAM file into a script and it will be embedded in the plugin?

                                A 1 Reply Last reply Reply Quote 0
                                • A
                                  aaronventure @Christoph Hart
                                  last edited by

                                  @Christoph-Hart said in Neural Amp Modeler (NAM) in HISE:

                                  Haha wasn't all that drama about it being 8x slower than the NAM plugin?

                                  I have no idea, I'm only now touching it for the first time.

                                  I ran direct comparisons in Reaper and a Waveform Synth with NAM on stereo channels consumes 1% of CPU (20% of RT CPU), while two NAM plugins in total consume 0.9% of CPU and 18% of RT CPU.

                                  So HISE is about 10% less efficient, which is good enough and entirely shippable if you ask me.

                                  @Christoph-Hart said in Neural Amp Modeler (NAM) in HISE:

                                  Can't you just embed the JSON content of the NAM file into a script and it will be embedded in the plugin?

                                  I sure can. I feel silly now. Thank you.

                                  O 1 Reply Last reply Reply Quote 0
                                  • O
                                    Orvillain @aaronventure
                                    last edited by

                                    @aaronventure
                                    1e4b768a-e69c-4c6b-a7d7-b457c9837ee1-image.png

                                    I'm seeing about 25% here with this. Not sure I understood about the multi container thing.

                                    A 1 Reply Last reply Reply Quote 0
                                    • A
                                      aaronventure @Orvillain
                                      last edited by

                                      @Orvillain you can still see the two cables going into it. You multi node should contain a neural node and an empty chain node.

                                      1 Reply Last reply Reply Quote 0
                                      • whoopsydoodleW
                                        whoopsydoodle
                                        last edited by

                                        How well does this nam implementation handle different sample rates? I know some get tripped up if you try to run a sample rate that's different than what your model was trained on.

                                        1 Reply Last reply Reply Quote 0
                                        • S
                                          scottmire
                                          last edited by

                                          Strange....
                                          I'm getting a "function not found" error when calling loadNAMModel

                                          1 Reply Last reply Reply Quote 0
                                          • First post
                                            Last post

                                          37

                                          Online

                                          1.8k

                                          Users

                                          12.0k

                                          Topics

                                          104.4k

                                          Posts