import pyaudio,wave
import numpy as np
def listen():
    temp = 20
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1
    RATE = 16000
    RECORD_SECONDS = 2
    SAMPLE_WIDTH = 2 # 2 bytes per sample
    WAVE_OUTPUT_FILENAME = 'test.wav'

    mindb=2000    #最小声音，大于则开始录音，否则结束
    delayTime=0.5  #小声1.3秒后自动终止
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)
    #snowboydecoder.play_audio_file()
    print("开始!计时")

    frames = []
    flag = False            # 开始录音节点
    stat = True				#判断是否继续录音
    stat2 = False			#判断声音小了

    tempnum = 0				#tempnum、tempnum2、tempnum3为时间
    tempnum2 = 0

    while stat:
        data = stream.read(CHUNK,exception_on_overflow = False)
        frames.append(data)
        audio_data = np.frombuffer(data, dtype=np.short)
        temp = np.max(audio_data)
        if temp > mindb and flag==False:
            flag =True
            print("开始录音")
            tempnum2=tempnum

        if flag:

            if(temp < mindb and stat2==False):
                stat2 = True
                tempnum2 = tempnum
                print("声音小，且之前是是大的或刚开始，记录当前点")
            if(temp > mindb):
                stat2 =False
                tempnum2 = tempnum
                #刷新

            if(tempnum > tempnum2 + delayTime*15 and stat2==True):
                print("间隔%.2lfs后开始检测是否还是小声"%delayTime)
                if(stat2 and temp < mindb):
                    stat = False
                    #还是小声，则stat=True
                    print("小声！")
                else:
                    stat2 = False
                    print("大声！")


        print(str(temp)  +  "      " +  str(tempnum))
        tempnum = tempnum + 1
        if tempnum > 150:				#超时直接退出
            stat = False
    print("录音结束")

    stream.stop_stream()
    stream.close()
    p.terminate()
    
    # 写入 WAV文 件
    # WAVE_OUTPUT_FILENAME = 'test.wav'
    # wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    # wf.setnchannels(CHANNELS)
    # wf.setsampwidth(p.get_sample_size(FORMAT))
    # wf.setframerate(RATE)
    # wf.writeframes(b''.join(frames))
    # wf.close()

    # 打开 PCM 文件
    WAVE_OUTPUT_FILENAME = 'test.pcm'
    FORMAT = pyaudio.paInt16
    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()

listen()

科大讯飞识别pcm文件并输出中文

# -*- coding:utf-8 -*-
#
#   author: iflytek
#
#  本demo测试时运行的环境为：Windows + Python3.7
#  本demo测试成功运行时所安装的第三方库及其版本如下，您可自行逐一或者复制到一个新的txt文件利用pip一次性安装：
#   pip uninstall websocket websocket-client websockets
#   pip install websocket-client
#
#  语音听写流式 WebAPI 接口调用示例 接口文档（必看）：https://doc.xfyun.cn/rest_api/语音听写（流式版）.html
#  webapi 听写服务参考帖子（必看）：http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=38947&extra=
#  语音听写流式WebAPI 服务，热词使用方式：登陆开放平台https://www.xfyun.cn/后，找到控制台--我的应用---语音听写（流式）---服务管理--个性化热词，
#  设置热词
#  注意：热词只能在识别的时候会增加热词的识别权重，需要注意的是增加相应词条的识别率，但并不是绝对的，具体效果以您测试为准。
#  语音听写流式WebAPI 服务，方言试用方法：登陆开放平台https://www.xfyun.cn/后，找到控制台--我的应用---语音听写（流式）---服务管理--识别语种列表
#  可添加语种或方言，添加后会显示该方言的参数值
#  错误码链接：https://www.xfyun.cn/document/error-code （code返回错误码时必看）
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread

STATUS_FIRST_FRAME = 0  # 第一帧的标识
STATUS_CONTINUE_FRAME = 1  # 中间帧标识
STATUS_LAST_FRAME = 2  # 最后一帧的标识

final_result = ""

class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, AudioFile):
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        self.AudioFile = AudioFile

        # 公共参数(common)
        self.CommonArgs = {"app_id": self.APPID}
        # 业务参数(business)，更多个性化参数可在官网查看
        self.BusinessArgs = {"domain": "iat", "language": "zh_cn", "accent": "mandarin", "vinfo":1,"vad_eos":10000}

    # 生成url
    def create_url(self):
        url = 'wss://ws-api.xfyun.cn/v2/iat'
        # 生成RFC1123格式的时间戳
        now = datetime.now()
        date = format_date_time(mktime(now.timetuple()))

        # 拼接字符串
        signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"
        signature_origin += "date: " + date + "\n"
        signature_origin += "GET " + "/v2/iat " + "HTTP/1.1"
        # 进行hmac-sha256进行加密
        signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),
                                 digestmod=hashlib.sha256).digest()
        signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')

        authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (
            self.APIKey, "hmac-sha256", "host date request-line", signature_sha)
        authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
        # 将请求的鉴权参数组合为字典
        v = {
            "authorization": authorization,
            "date": date,
            "host": "ws-api.xfyun.cn"
        }
        # 拼接鉴权参数，生成url
        url = url + '?' + urlencode(v)
        # print("date: ",date)
        # print("v: ",v)
        # 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致
        # print('websocket url :', url)
        return url


# 收到websocket消息的处理
def on_message(ws, message):
    try:
        code = json.loads(message)["code"]
        sid = json.loads(message)["sid"]
        if code != 0:
            errMsg = json.loads(message)["message"]
            print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))

        else:
            data = json.loads(message)["data"]["result"]["ws"]
            # print(json.loads(message))
            result = ""
            for i in data:
                for w in i["cw"]:
                    result += w["w"]
            #print("sid:%s call success!,data is:%s" % (sid, json.dumps(data, ensure_ascii=False)))
            global final_result
            final_result=final_result+result
            

    except Exception as e:
        print("receive msg,but parse exception:", e)



# 收到websocket错误的处理
def on_error(ws, error):
    print("### error:", error)


# 收到websocket关闭的处理
def on_close(ws,a,b):
    #print("### closed ###")
    global final_result
    print(final_result)

# 收到websocket连接建立的处理
def on_open(ws):
    def run(*args):
        frameSize = 8000  # 每一帧的音频大小
        intervel = 0.04  # 发送音频间隔(单位:s)
        status = STATUS_FIRST_FRAME  # 音频的状态信息，标识音频是第一帧，还是中间帧、最后一帧

        with open(wsParam.AudioFile, "rb") as fp:
            while True:
                buf = fp.read(frameSize)
                # 文件结束
                if not buf:
                    status = STATUS_LAST_FRAME
                # 第一帧处理
                # 发送第一帧音频，带business 参数
                # appid 必须带上，只需第一帧发送
                if status == STATUS_FIRST_FRAME:

                    d = {"common": wsParam.CommonArgs,
                         "business": wsParam.BusinessArgs,
                         "data": {"status": 0, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(buf), 'utf-8'),
                                  "encoding": "raw"}}
                    d = json.dumps(d)
                    ws.send(d)
                    status = STATUS_CONTINUE_FRAME
                # 中间帧处理
                elif status == STATUS_CONTINUE_FRAME:
                    d = {"data": {"status": 1, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(buf), 'utf-8'),
                                  "encoding": "raw"}}
                    ws.send(json.dumps(d))
                # 最后一帧处理
                elif status == STATUS_LAST_FRAME:
                    d = {"data": {"status": 2, "format": "audio/L16;rate=16000",
                                  "audio": str(base64.b64encode(buf), 'utf-8'),
                                  "encoding": "raw"}}
                    ws.send(json.dumps(d))
                    time.sleep(1)
                    break
                # 模拟音频采样间隔
                time.sleep(intervel)
        ws.close()

    thread.start_new_thread(run, ())


if __name__ == "__main__":
    # 测试时候在此处正确填写相关信息即可运行
    time1 = datetime.now()
    wsParam = Ws_Param(APPID='xxx', APISecret='xxxxx',
                       APIKey='xxxxxx',
                       AudioFile=r'test.pcm')
    websocket.enableTrace(False)
    wsUrl = wsParam.create_url()
    ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)
    ws.on_open = on_open
    ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
    time2 = datetime.now()
    #print(time2-time1)