Skip to content

Home

Jump to bottom
Georgy Treshchev edited this page Mar 11, 2023 · 21 revisions

Runtime Speech Recognizer Documentation

Runtime Speech Recognizer is an open-source plugin that enables real-time, offline speech recognition. Based on Whisper OpenAI technology and supports multiple language models pre-selected in the plugin's settings.

How to install

There're two ways to install the plugin:

  1. Through the marketplace (in progress).
  2. Manual installation. Select and download the release for the required engine version, extract the archive into your plugins project folder to get the following path: "[ProjectName] / Plugins / RuntimeSpeechRecognizer". Then download the language models by following this page.

Basic description

This plugin provides real-time speech recognition using advanced algorithms based on whisper.cpp library. It matches incoming audio data, provided as a stream or unified input, against pre-trained language models in ggml format.

Clone this wiki locally