环境配置
查看收音设备
arecord -l
查看输出设备
aplay -l
更新系统
sudo apt-get update
sudo apt-get upgrade
编辑 ~/.asoundrc 指定对应的设备
pcm.!default {
type asym
playback.pcm {
type plug
slave.pcm "hw:0,0"
}
capture.pcm {
type plug
slave.pcm "hw:1,0"
}
}
安装 PortAudio
sudo apt-get install python-pyaudio python3-pyaudio sox
安装 Python 绑定
pip install pyaudio
编译 SnowBoy 新版
官网有树莓派 1、2、3、Zero 的预编译包,不知道 4 能不能用,我尝试自己编译一个试试
sudo apt-get install autotools-dev automake libpcre3 libpcre3-dev libatlas-base-dev byacc
./autogen
./configure
make
sudo make install
训练热词
模型训练可以通过网页录制上传,也可以自己录制编写代码训练。
网页录制上传请访问官网:https://snowboy.kitt.ai/
点击 Create Hotword 就可以了,按照提示来。
我没有选择这种模式,因为我树莓派没有接显示屏不方便使用网页,如果用电脑怕环境不一样,采集样本有区别,主要的是自己想写代码折腾一下:
录制训练样本数据:
arecord bb1.wav
或者,这里根据麦克风指定了波特率
rec -r 16000 b1.wav
编写程序本地训练:
import sys
import base64
import requests
def get_wave(fname):
with open(fname, 'rb') as infile:
return base64.b64encode(infile.read())
# api 地址
endpoint = "https://snowboy.kitt.ai/api/v1/train/"
############# 修改参数 #############
# api 令牌,官网注册申请,必须
token = ""
# 热词,如果未知必须
hotword_name = "笨笨"
# 语言
language = "zh"
# 年龄段 0_9, 10_19, 20_29, 30_39, 40_49, 50_59, 60+
age_group = "40_49"
# 性别 F = female M = Male
gender = "M"
# 麦克类型
microphone = "macbook microphone"
############### END OF MODIFY ##################
if __name__ == "__main__":
try:
# 获取运行参数,三个训练音频和一个输出模型
[_, wav1, wav2, wav3, out] = sys.argv
except ValueError:
print("Usage: %s wave_file1 wave_file2 wave_file3 out_model_name" % sys.argv[0])
sys.exit()
# 训练参数结构
data = {
"name": hotword_name,
"language": language,
"age_group": age_group,
"gender": gender,
"microphone": microphone,
"token": token,
# 训练数据是三个 wav 格式的录音音频
"voice_samples": [
{"wave": get_wave(wav1)},
{"wave": get_wave(wav2)},
{"wave": get_wave(wav3)}
]
}
# 提交训练数据
response = requests.post(endpoint, json=data)
if response.ok:
# 训练成功,保存模型到指定文件
with open(out, "wb") as outfile:
outfile.write(response.content)
print ("Saved model to '%s'." % out)
else:
print ("Request failed.")
print (response.text)
训练样本生成模型:
python3 training.py b1.wav b2.wav b3.wav model.umdl
编写测试程序
from . import snowboydecoder
import sys
import signal
import wave
import os
import pyaudio
import time
"""
使用说明:
In [1]: import snowboydecoder
In [2]: def detected_callback():
....: print "hotword detected"
....:
In [3]: detector = snowboydecoder.HotwordDetector("resources/snowboy.umdl", sensitivity=0.5, audio_gain=1)
In [4]: detector.start(detected_callback)
"""
TOP_DIR = os.path.dirname(os.path.abspath(__file__))
RESOURCE_FILE = os.path.join(TOP_DIR, "resources/common.res")
DETECT_DING = os.path.join(TOP_DIR, "resources/imhere.wav")
DETECT_DONG = os.path.join(TOP_DIR, "resources/dong.wav")
interrupted = False
def play_audio_file(fname):
"""Simple callback function to play a wave file. By default it plays
a Ding sound.
:param str fname: wave file name
:return: None
"""
ding_wav = wave.open(fname, 'rb')
ding_data = ding_wav.readframes(ding_wav.getnframes())
audio = pyaudio.PyAudio()
stream_out = audio.open(
format=audio.get_format_from_width(ding_wav.getsampwidth()),
channels=ding_wav.getnchannels(),
rate=44100, # ding_wav.getframerate(),
input=False, output=True)
stream_out.start_stream()
stream_out.write(ding_data)
time.sleep(0.2)
stream_out.stop_stream()
stream_out.close()
audio.terminate()
def detected_callback():
print ("hotword detected")
play_audio_file(DETECT_DING)
# 响应中断信号,设置中断变量为 True
def signal_handler(signal, frame):
global interrupted
interrupted = True
# 返回中断状态
def interrupt_callback():
global interrupted
return interrupted
# 输入参数处理
if len(sys.argv) == 1:
print("Error: need to specify model name")
print("Usage: python demo.py your.model")
sys.exit(-1)
# 模型文件
model = sys.argv[1]
# 初始化中断信号处理
signal.signal(signal.SIGINT, signal_handler)
# 实例化热词监测
detector = snowboydecoder.HotwordDetector(model, sensitivity=0.5)
print('Listening... Press Ctrl+C to exit')
# 启动实例,开始热词监测
detector.start(detected_callback=detected_callback,
interrupt_check=interrupt_callback,
sleep_time=0.03)
detector.terminate()
因为麦克风的采样率问题,需要修改 snowboydecoder.py 的采样率,大约在115 行
self.stream_in = self.audio.open(
input=True, output=False,
format=self.audio.get_format_from_width(
self.detector.BitsPerSample() / 8),
channels=self.detector.NumChannels(),
rate=44100, #self.detector.SampleRate(),
frames_per_buffer=2048,
stream_callback=audio_callback)
功能演示
需要注意的是 python3 的相对引用问题
python demo.py model.umdl
python3 -m Python3.demo Python3/model.umdl
python3 -m Python3.demo5 Python3/model.umdl
参考资料
pocketsphinx snowboy
https://github.com/wanleg/snowboyPi
https://pimylifeup.com/raspberry-pi-snowboy/
https://snowboy.kitt.ai/docspartials/docs/index.html#access-microphone
视频讲解
使用树莓派 4 和 SnowBoy 实现热词唤醒