Posts by Ben Thomas
GPU Support for Raven Intelligence
Starting in version 1.1, Raven Intelligence can run model Inference with GPU support for PyTorch and ONNX models. We currently can’t run Tensorflow models with GPU support. Here are steps to get the required dependencies in place for Windows. Requirements 1. Check Compatibility Fist, verify your GPU can support the required CUDA versions. 12.8 is…
Read MoreRaven Intelligence
Part 1: Running a model To run a model, simply select the model settings, choose your audio data and postprocessing steps, and click run. Part 1 of the documentation provides details on each of these steps. Note: throughout this documentation we will refer to the Models folder. This folder is located under the user home directory, under…
Read MoreSpectrogram Parameters in Raven Workbench
Spectrogram parameters determine how audio signals are transformed into the visual frequency-over-time representation known as a spectrogram. This document explains the available settings, their technical impact on resolution, and how to choose the best configuration for your data. This applies to Raven Expedition and Raven Annotate. Accessing Spectrogram Parameters You can open the Configure Spectrogram…
Read MoreRaven Workbench Signals
Raven Workbench Signals (SignalSource) In Raven, a SignalSource (also known as a Raven Signal or .ravensignal file) is a specialized format used to define and track a collection of audio files that make up a dataset. This applies to all Raven Workbench applications. What is a SignalSource? A SignalSource is an enhanced list file. While…
Read MorePresets and Preferences
This document provides an overview of how to use Presets and Preferences within Raven to customize your workflow and application settings. This applies to all Workbench applications. Presets Presets allow you to save and reuse specific configurations for various tools and views within the application. Instead of manually configuring settings every time, you can save…
Read More