專案說明：

在windows平臺下，使用speech_recognition記錄音訊，並轉換為16k的wav， 之後利用ffmpeg將wav轉化為pcm檔案，上傳到百度語音端，返回語音資訊，並利用pyttsx3添加了簡單的互動功能。

需求模組：

speech_recognition， pyttsx3， pyaudio， wave， aip， ffmpeg

模組安裝：

• speech_recognition: https://pypi.org/project/SpeechRecognition/
• pyttsx3: https://blog.csdn.net/dss_dssssd/article/details/82693742
• pyaudio: https://pypi.org/project/PyAudio/
• aip:https://ai.baidu.com/docs#/ASR-Online-Python-SDK/top
• ffmpeg (Windows下） 注意是系統的環境變數，不是個人的path
  https://blog.csdn.net/zhuiqiuk/article/details/72834385

程式碼如下

import speech_recognition as sr
import pyttsx3
import pyaudio
import wave
from aip import AipSpeech
import
 
 os

# 讀取wav檔案並播放
def read_wav():
    CHUNK = 1024
# 測試語音
    wf = wave.open('./2.wav', 'rb')
        # read data
    data = wf.readframes(CHUNK)
    p = pyaudio.PyAudio()
    FORMAT = p.get_format_from_width(wf.getsampwidth())
    CHANNELS = wf.getnchannels()
    RATE = wf.getframerate()

    print('FORMAT: {} \nCHANNELS: {} \nRATE: {}'
 
.format(FORMAT, CHANNELS, RATE))
    stream = p.open(format=FORMAT,

                    channels=CHANNELS,
                    rate=RATE,
                    frames_per_buffer=CHUNK,
                    output=True)
    # play stream (3)
    while len(data) > 0:
        stream.write(data)
        data = wf.readframes(CHUNK)



def wav_to_pcm(wav_file):
    # 假設 wav_file = "音訊檔案.wav"
    # wav_file.split(".") 得到["音訊檔案","wav"] 拿出第一個結果"音訊檔案"  與 ".pcm" 拼接 等到結果 "音訊檔案.pcm"
    pcm_file = "%s.pcm" %(wav_file.split(".")[0])
    # 就是此前我們在cmd視窗中輸入命令,這裡面就是在讓Python幫我們在cmd中執行命令
    os.system("ffmpeg -y  -i %s  -acodec pcm_s16le -f s16le -ac 1 -ar 16000 %s"%(wav_file,pcm_file))

    return pcm_file

def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()


""" 你的 APPID AK SK """
# 需要根據自己申請的填寫
# APP_ID = '你的 App ID'
# API_KEY = '你的 Api Key'
# SECRET_KEY = '你的 Secret Key'
# 這是測試id，key
APP_ID = '14545668'
API_KEY = 'BLG4GIxozxXia9U8KKtLBl2j'
SECRET_KEY = 'z0ITqlx8OXiveTePBvD7jkSCdGKthZAy'

def speech_interaction():
    # 初始化pyttsx3 engine
    engine = pyttsx3.init()

    # obtain audio from the microphone
    # 從麥克風記錄資料
    r = sr.Recognizer()
    with sr.Microphone() as source:
        # print("Say something!")
        engine.say("門外有客人來訪，需要開門嗎, 請一秒後回答？")
        engine.runAndWait()
        r.adjust_for_ambient_noise(source)
        audio = r.listen(source)

    engine.say("錄音結束, 識別中")
    engine.runAndWait()
    # 將資料儲存到wav檔案中
    with open("2.wav", "wb") as f: 
        f.write(audio.get_wav_data(convert_rate=16000))
     
     # 將記錄的語音播放出來
     read_wav()      
    # 建立百度語音識別客戶端
    client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

    # 轉成pcm格式
    pcmFile = wav_to_pcm("./2.wav")
    result = client.asr(get_file_content(pcmFile), 'pcm', 16000, {
        'dev_pid': 1537,
    })
    print(result)
    # print(result['err_msg'], result['result'][0])

    # 上傳到百度雲識別
    try:
        success = True if result['err_msg'] == 'success.' else False
        print(success)
        if success:
            text = result['result'][0]
            if "不" in text :
                engine.say("好的，那請您自己去開門")
                engine.runAndWait()
            elif "開" in text or '好' in text:
                engine.say("請您稍等，我去幫您開門，")
                engine.runAndWait()
            else:
                engine.say("語音識別錯誤")
                engine.runAndWait()
            # engine.say(text)
            # engine.runAndWait()
    except Exception as e:
        engine.say("抱歉， 識別錯誤")
        engine.runAndWait()

# 執行程式碼
speech_interaction()

注意：

pyttsx3的pyttsx3.engine()初始化不能放線上程中進行，會錯。

說明：

• 如果返回timeout錯誤，在網路暢通的情況下，建議換一個id和key試一下。

專案放在github上了:
https://github.com/MengRe/speech_commmunication/tree/master