Show HN: Neural_tilde – Run neural amplifier captures in Max/MSP

apresta1 pts0 comments

GitHub - apresta/neural_tilde: Max/MSP external for running neural amplifier captures · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

apresta

neural_tilde

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star<br>34

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>16 Commits<br>16 Commits

deps

deps

dsp

dsp

.clangd

.clangd

.gitignore

.gitignore

.gitmodules

.gitmodules

CMakeLists.txt

CMakeLists.txt

LICENSE

LICENSE

README.md

README.md

build.sh

build.sh

neural_tilde.cpp

neural_tilde.cpp

neural_tilde.def

neural_tilde.def

toolchain-mingw.cmake

toolchain-mingw.cmake

win_jit_stub.cpp

win_jit_stub.cpp

win_prefix.h

win_prefix.h

View all files

Repository files navigation

neural~

This Max/MSP object loads and runs neural amplifier models in real time.

It supports NAM and AIDA-X models, and handles resampling to the host rate.

Smooth model switching is implemented, avoiding audible noise when swapping<br>amplifier captures.

Sound demo via Max for Live: Live Amp Modeler.

The object's inlet accepts the following messages:

(signal): The mono audio signal.

load : Load a neural amp model (.nam or .json/.aidax). Accepts<br>absolute or relative paths (relative paths are resolved against the<br>patcher's directory first, then Max's file-search path). If the model<br>specifies recommended input/output level adjustments, they are applied<br>automatically around the model's processing.

clear: Unload the current model.

prewarm: (NAM-only) Prewarm the model to avoid digital artifacts.

bang: Report model status.

Attributes

quality : Model quality scale factor, from 0.0 (fastest /<br>lowest quality) to 1.0 (slowest / highest quality). Only affects models that<br>support quality scaling (such as slimmable NAM A2 models).<br>The value persists and is applied to any model loaded afterward.

The object's first outlet outputs:

(signal): The processed audio signal.

The object's second outlet outputs the following messages:

loaded : Path to model upon successful load.

latency : Audio latency (non-zero when model and host sample rates differ).

quality_supported : 1 if the loaded model supports quality adjustment<br>via the quality attribute, 0 otherwise.

queued : Signals that the model was parked while waiting for the<br>audio engine to start.

cleared: Confirms that the model was unloaded from the object.

error : The object encountered an error.

The build script has been tested on MacOS. Windows cross-compilation is<br>supported via mingw-w64.

Dependencies:

https://cmake.org

https://github.com/Cycling74/min-devkit

https://github.com/mikeoliphant/NeuralAudio

https://clang.llvm.org/ (for MacOS build)

https://github.com/mstorsjo/llvm-mingw (for Windows build)

About<br>Max/MSP external for running neural amplifier captures<br>www.nyquistlimited.com<br>Resources<br>Readme<br>MIT license<br>Activity<br>Stars<br>34 stars<br>Watchers<br>0 watching<br>Forks<br>2 forks<br>Report repository

Releases

Packages

Contributors

Languages

You can’t perform that action at this time.

model neural_tilde quality neural search object

Related Articles