NatML
Search…
NatML
NatML for Unity
Preliminaries
Getting Started
Requirements
Workflows
Core Concepts
Fetching Models
Vision Predictors
Audio Predictors
API Reference
IMLPredictor
IMLAsyncPredictor
MLModelData
MLModel
MLFeature
MLFeatureType
MLPredictorExtensions
Integrations
Media Devices
Augmented Reality
Video Recording
Insiders
Publishing
Changelog
Open Source
GitHub
Discord
Blog
Powered By GitBook
Audio Predictors
Using ML for audio and speech.
Using machine learning for audio and speech tasks is becoming more popular, as it opens up a new surface for human-computer interaction. NatML provides infrastructure for making predictions on audio models--specifically those that work with raw audio waveforms. Let's walk through the typical workflow:

Creating an Audio Predictor

INCOMPLETE.

Making Audio Predictions

INCOMPLETE.
Workflows - Previous
Vision Predictors
Next - API Reference
IMLPredictor
Last modified 1mo ago
Copy link
Contents
Creating an Audio Predictor
Making Audio Predictions