python语音聊天程序

python语音对话

安装相关库：pyaudio、AipSpeech、pyttsx3、urllib、requests。
pip install …
手动添加镜像源：
pip install package_name -i http://mirrors.aliyun.com/pypi/simple/
pip命令设置镜像源：
当前用户文件夹下创建pip文件夹，其中添加pip.ini文件。
pip.ini文件内容：
[global]
index-url = http://mirrors.aliyun.com/pypi/simple/
[install]
trusted-host=mirrors.aliyun.com
设置完成后pip命令自动从配置的镜像源安装。

1. 接收语音输入。

Speak.py

import time
import wave
from pyaudio import PyAudio, paInt16

framerate = 16000  # 采样率
num_samples = 2000  # 采样点
channels = 1  # 声道
samplewidth = 2  # 采样宽度
filepath = 'voices/myvoice.wav'


class Speak():
    def save_wave_file(self, filepath, data):
        wave_open = wave.open(filepath, 'wb')
        wave_open.setnchannels(channels)
        wave_open.setsampwidth(samplewidth)
        wave_open.setframerate(framerate)
        wave_open.writeframes(b''.join(data))
        wave_open.close()

    # 接收语音输入
    def record(self):
        audio = PyAudio()
        stream = audio.open(format=paInt16, channels=channels, rate=framerate, input=True,
                            frames_per_buffer=num_samples)
        buf = []
        t = time.time()
        print("正在说话...")
        while time.time() < t + 5:
            audio_data = stream.read(num_samples)
            buf.append(audio_data)
        print("结束说话")
        self.save_wave_file(filepath, buf)
        stream.close()

在路径下的voices目录下生成wav格式文件。

2. 语音识别。

ReadWav.py

from aip import AipSpeech

# app info
APP_ID = '27017392'
APP_KEY = 'HfVYutlUKqYKIGloczfQzVm1'
SECRET_KEY = 'oc4rlYpWKZETosbz7HFF8u2QuAVRkqDz'

client = AipSpeech(APP_ID, APP_KEY, SECRET_KEY)


class ReadWav():
    def get_file_content(self, filepath):
        with open(filepath, 'rb') as r:
            return r.read()

    def predict(self):
        # 识别
        return client.asr(self.get_file_content('voices/myvoice.wav'), 'wav', '16000', {'dev_pid': 1537})

3. 语音机器人。

Robot.py

import pyttsx3

class Robot():
    def __init__(self):
        self.engine = pyttsx3.init()
        self.rate = self.engine.getProperty('rate')
        self.engine.setProperty('rate', self.rate - 50)

    def say(self, msg):
        self.engine.say(msg)
        self.engine.runAndWait()

4. 主程序。

Main.py

import urllib.parse

import requests
from Speak import Speak
from ReadWav import ReadWav
from Robot import Robot

def talking(msg):
    url = 'http://api.qingyunke.com/api.php?key=free&appid=0&msg=%s' % urllib.parse.quote(msg)
    resp = requests.get(url)
    return resp.json().get('content')


speak = Speak()
wav = ReadWav()
robot = Robot()

while True:
    speak.record()
    text = wav.predict().get('result')[0]
    print('本人说：' + text)
    content = talking(text)
    print("对方回答：" + content)
    robot.say(content)

智能聊天Api接口：http://api.qingyunke.com/
常用镜像源：
清华：https://pypi.tuna.tsinghua.edu.cn/simple
阿里云：http://mirrors.aliyun.com/pypi/simple/
中国科技大学 https://pypi.mirrors.ustc.edu.cn/simple/
华中理工大学：http://pypi.hustunique.com/
山东理工大学：http://pypi.sdutlinux.org/
豆瓣：http://pypi.douban.com/simple/