使用 snowboy 配置多个热词唤醒

落日映苍穹つ 2021-07-27 02:46 699阅读 0赞

> 实验环境：荔枝派zero 代码：使用python3代码
> 
> snowboy 是一个开源的、轻量级语音唤醒引擎，可以通过它很轻松地创建属于自己的类似“hey, Siri” 的唤醒词。它的主要特性如下：
> 
> 高度可定制性。可自由创建和训练属于自己的唤醒词 始终倾听。可离线使用，无需联网，保护隐私。精确度高，低延迟 轻量可嵌入。耗费资源非常低（单核  
> 700MHz 树莓派只占用 10% CPU） 开源跨平台。开放源代码，支持多种操作系统和硬件平台，可绑定多种编程语言  
> 详细看了官网提供的安装配置教程（已经很久没更新，有点过于繁琐了），几番尝试之后，感觉下面的介绍算是最新也相对最简单的方法了吧。
> 
> PS：只针对 Linux 系统（包含树莓派），其他平台可参考 [Github][]

**1、从Git获取[snowboy源码][Github]**

获取源代码：$ git clone https://github.com/Kitt-AI/snowboy.git

**2、安装相关依赖**

安装 PyAudio：$ sudo apt-get install python3-pyaudio
    安装 PyAudio：$ sudo apt-get install sox
    安装 SWIG（>3.0.10)：$ sudo apt-get install swig
    安装 ATLAS：$ sudo apt-get install libatlas-base-dev

**3、编译源代码**

安装： `cd snowboy ；python3 setup.py install`  
编译 Python3 绑定：`$ cd snowboy/swig/Python3 && make`

**4、测试**

官方源代码使用 Python3 测试有报错，经测试需修改 snowboy/examples/Python3 目录下的 snowboydecoder.py 文件。  
将第 5 行代码 from \* import snowboydetect 改为 import snowboydetect 即可直接运行。

#使用自己训练的‘’小白‘’模型
     python3 demo.py resources/models/xiaobai.pmdl

运行如下：

root@ubuntu:/yangfeiwu/sonwboy/examples/Python3# python3 demo.py resources/models/xiaobai.pmdl
    Listening... Press Ctrl+C to exit
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.front
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround21
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround21
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround40
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround41
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround50
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround51
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround71
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.iec958
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.iec958
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.iec958
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
    ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
    ALSA lib pcm_dmix.c:1018:(snd_pcm_dmix_open) unable to create IPC semaphore
    Cannot connect to server socket err = No such file or directory
    Cannot connect to server request channel
    jack server is not running or cannot be started
    JackShmReadWritePtr::~JackShmReadWritePtr - Init not done for -1, skipping unlock
    JackShmReadWritePtr::~JackShmReadWritePtr - Init not done for -1, skipping unlock
    INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:40:54
    INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:40:57
    INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:40:58
    INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:41:07
    INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:41:11
    INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:51:18

成功识别会输出如下信息：  
INFO:snowboy:Keyword 1 detected at time: 2020-03-09 05:40:54

**5、多个模型和回调**

demo2.py演示了如何同时监听多个模型:

import snowboydecoder
    import sys
    import signal
    
    interrupted = False
    
    
    def signal_handler(signal, frame):
        global interrupted
        interrupted = True
    
    
    def interrupt_callback():
        global interrupted
        return interrupted
    
    if len(sys.argv) != 3:
        print("Error: need to specify 2 model names")
        print("Usage: python demo.py 1st.model 2nd.model")
        sys.exit(-1)
    
    models = sys.argv[1:]
    
    # capture SIGINT signal, e.g., Ctrl+C
    signal.signal(signal.SIGINT, signal_handler)
    
    sensitivity = [0.5]*len(models)
    detector = snowboydecoder.HotwordDetector(models, sensitivity=sensitivity)
    callbacks = [lambda: snowboydecoder.play_audio_file(snowboydecoder.DETECT_DING),
                 lambda: snowboydecoder.play_audio_file(snowboydecoder.DETECT_DONG)]
    print('Listening... Press Ctrl+C to exit')
    
    # main loop
    # make sure you have the same numbers of callbacks and models
    detector.start(detected_callback=callbacks,
                   interrupt_check=interrupt_callback,
                   sleep_time=0.03)
    
    detector.terminate()

[Github]: https://github.com/Kitt-AI/snowboy