Skip to content
This repository has been archived by the owner on Oct 16, 2023. It is now read-only.

Latest commit

 

History

History
36 lines (31 loc) · 1.91 KB

README_EN.md

File metadata and controls

36 lines (31 loc) · 1.91 KB
Raw

VOSK ASR for Unity

[中文|English]

This is a project that implements ASR (Automatic Speech Recognition) inside Unity via the Vosk libraries. This project was built and improved upon the Sample linked on the official website.

What is VOSK

Vosk is a speech recognition toolkit. Some advantages of Vosk include:

  • Supports 20+ languages and dialects
  • Works offline, even on lightweight devices
  • Model comes in ~50 MB size for Mobile & ~2 GB size for Server
  • Allows manual configuration of keywords for better accuracy

Getting Started

  • Download a language model from the Official List
  • Extract the model to the Application.streamingAssetsPath of the project
  • Larger model is more accurate but takes longer to load
  • (Optionally) Install Newtonsoft Json Unity Package

How to Use

  • Inside the script that uses the ASR, add using Vosk.APIs;
  • Call VoskASR.Init with the necessary arguments
  • Subscribe to VoskASR.OnTranscriptionResult to process the results
  • The results are sent in a Json format. Hence why Newtonsoft.Json is recommended.
  • Refer to Demo.cs for examples
  • Use LoudnessMeter to visualize the input volume
  • Use ChineseUtil to convert between Simplified Chinese and Traditional Chinese
    • Chinese models are often trained on Simplified Chinese

Parameters

  • caller: Pass in the MonoBehaviour for Unity to call StartCoroutine on
  • modelName: Pass in the folder name of the model
  • autoStart: Should the ASR start after Init
  • maxAlternatives: How many variants of results does the ASR generate
  • microphoneIndex: The index of Microphone to use
  • keyPhrases: Manual configuration of keywords to detect