stream_vits_zh. 本项目基于 vits_chinese,提供一个支持流式输出的中文 VITS 模型接口。
9X3Plus-Embodied. 2023 Computer Science Project: An Embodied Intelligence Path Planning System Based on YahboomCar X3 Plus, open-sourcing the practical achievements of the freshman team.
5whisper_ros1. This repository contains a ROS1 node for real-time speech-to-text transcription using the **Whisper** model. The node subscribes to an audio stream and publishes the transcribed text to a specified topic.
4audio_publisher. The **Audio Publisher Node** is a ROS (Robot Operating System) node designed to capture audio data from a microphone, publish it as a ROS topic, and optionally save it to a WAV file. It also supports playing the received audio in real time.
3