README_en.md

JP | EN

speech_recognition_whisper

Table of Contents

1. Introduction
2. Getting Started
   • Requirements
   • Installation
3. Launch and Usage
4. Milestone
5. Acknowledgements

Introduction

A locally running speech recognition package.
It can be used in the same way as other speech recognition packages, through Service communication.
GPU PC is recommended due to its nature.

Note

It works on CPU, but there is a slight lag in response. Please go online to install.sh.

(back to top)

Getting Started

This section describes how to set up this repository.

Requirements

System	Version
Ubuntu	20.04 (Focal Fossa)
ROS	Noetic Ninjemys
Python	3.8

Note

If you need to install Ubuntu or ROS, please check our SOBITS Manual.

(back to top)

Installation

1. Change directory

   $ cd ~/catkin_ws/src

2. clone TeamSOBITS/speech_recognition_whisper

   $ git clone https://github.com/TeamSOBITS/speech_recognition_whisper.git

3. Change directory

   $ cd speech_recognition_whisper/

4. Install dependent packages

   $ bash install.sh

5. compile

   $ cd ~/catkin_ws/
   $ catkin_make

(back to top)

Launch and Usage

launch the file

roslaunch speech_recognition_whisper speech_recognition_whisper.launch

This will start the Server.

(back to top)

Services

• /speech_recognition (Service: sobits_msgs/SpeechRecognitionWhisper)

(back to top)

Milestone

See the open issues for a full list of proposed features (and known issues).

Acknowledgements

• ROS Noetic

(back to top)