package
module
Version:
v0.0.0-...-11b2c39
Opens a new window with list of versions in this module.
Published: Oct 24, 2023
License: MIT
Opens a new window with license information.
Imports: 9
Opens a new window with list of imports.
Imported by: 0
Opens a new window with list of known importers.
README
¶
VoiceRecog
介绍
语音识别模块
软件架构
本程序只支持在 macOS 上运行
- 启动
ffmpeg
进程,捕捉麦克风音频流,并转换为 pcm_s16le
格式
- 调用 阿里云语音识别 接口进行实时识别
- 投递识别结果到
HTTP
端点
配置文件
aliyun-nls-url wss://nls-gateway.cn-shanghai.aliyuncs.com/ws/v1
aliyun-access-key-id xxxxxxxx
aliyun-access-key-secret xxxxxxxxx
aliyun-nls-app-key xxxxxxx
target-url https://voicerecog.tok715.example.com/master/submit
使用方法
-
安装 ffmpeg
-
列出本机可用的音频输入设备
go run ./cmd/voicerecog -check
-
启动程序
go run ./cmd/voicerecog -conf voicerecog.conf -device 2
许可证
TOK715 Developers, MIT License
Documentation
¶
type AliyunSpeechTranscriptionResult struct {
Payload struct {
Result string `json:"result"`
} `json:"payload"`
}
type Options struct {
Config *nls.ConnectionConfig
Device string
}
Source Files
¶
Directories
¶
cmd
|
|
|
|
Click to show internal directories.
Click to hide internal directories.