在树莓派中写入科大讯飞语音转文字识别程序

最新推荐文章于 2023-09-17 21:14:14 发布

萧鼎

最新推荐文章于 2023-09-17 21:14:14 发布

阅读量2.5k

点赞数

分类专栏：人工智能算法文章标签：语音识别 python 人工智能

本文链接：https://blog.csdn.net/liaoqingjian/article/details/124644152

版权

人工智能算法专栏收录该内容

37 篇文章 28 订阅

订阅专栏

在树莓派桌面里新建一个xunfei_zhuan.py文件，然后打开文件，然后使用默认软件编程
在这里插入图片描述

点击terminal，在里面使用以下命令安装cffi==1.12.3库

pip3 install cffi==1.12.3

在这里插入图片描述

使用以下命令安装gevent==1.4.0库

pip3 install gevent==1.4.0

在这里插入图片描述

使用以下命令安装greenlet==0.4.15库

pip3 install greenlet==0.4.15

在这里插入图片描述

使用以下命令安装pycparser==2.19库

pip3 install pycparser==2.19

在这里插入图片描述

使用以下命令安装six==1.12.0库

pip3 install six==1.12.0

在这里插入图片描述

使用以下命令安装websocket==0.2.1库

pip3 install websocket==0.2.1

在这里插入图片描述

使用以下命令安装websocket-client==0.56.0库

pip3 install websocket-client==0.56.0

在这里插入图片描述

导入下面python库

import wave
import pyaudio
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

定义音频帧的标识


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

定义一个类叫Ws_Param

class Ws_Param(object):

初始化这个类

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}

在类里面定义一个函数create_url，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

定义一个函数on_message，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(result)
            # print(json.dumps(data, ensure_ascii=False))
    except Exception as e:
        print("receive msg,but parse exception:", e)

收到websocket错误的处理

def on_error(ws, error):
    pass

收到websocket关闭的处理

def on_close(ws):
print("### closed ###")

定义一个函数on_open，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, ())

定义一个录音函数record，能够将实时说话的语音保存

def record(time):    #录音程序
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1
    RATE = 16000
    RECORD_SECONDS =time
    WAVE_OUTPUT_FILENAME = "./output.pcm"
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)
    print("* recording")
    frames = []
    for i in range(0,int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)
    print("* done recording")
    stream.stop_stream()
    stream.close()
    p.terminate()
    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()

程序入口，开始执行程序

if __name__ == "__main__":
    record(3)
    time1 = datetime.now()
    wsParam = Ws_Param(APPID='d69356bc', APIKey='c3f938a4da84f7449bd2f958d461e7e1',
                       APISecret='ZjE4ZGE4ZGU4YzViZmFhNTI0ZmYyNTE0',
                       AudioFile=r'./output.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()

完整代码呈现

import wave
import pyaudio
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


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(result)
            # print(json.dumps(data, ensure_ascii=False))
    except Exception as e:
        print("receive msg,but parse exception:", e)




def on_error(ws, error):
    pass

def on_close(ws):
    print("### closed ###")



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 

        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, ())
def record(time):    #录音程序
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1
    RATE = 16000
    RECORD_SECONDS =time
    WAVE_OUTPUT_FILENAME = "./output.pcm"
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)
    print("* recording")
    frames = []
    for i in range(0,int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)
    print("* done recording")
    stream.stop_stream()
    stream.close()
    p.terminate()
    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()

if __name__ == "__main__":
    record(3)
    time1 = datetime.now()
    wsParam = Ws_Param(APPID='d69356bc', APIKey='c3f938a4da84f7449bd2f958d461e7e1',
                       APISecret='ZjE4ZGE4ZGU4YzViZmFhNTI0ZmYyNTE0',
                       AudioFile=r'./output.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()

然后使用命令进入桌面路径
cd /home/pi/Desktop
在这里插入图片描述

最后使用以下命令运行
python3 xunfei_zhuan.py
在这里插入图片描述
最后运行通之后，可以实时讲话，同时程序会将你说的话转成文字输出出来。

萧鼎

关注

0
点赞
踩
37

收藏

觉得还不错? 一键收藏
打赏
8
评论
在树莓派中写入科大讯飞语音转文字识别程序

在树莓派桌面里新建一个xunfei_zhuan.py文件，然后打开文件，然后使用默认软件编程点击terminal，在里面使用以下命令安装cffi==1.12.3库pip3 install cffi==1.12.3使用以下命令安装gevent==1.4.0库pip3 install gevent==1.4.0使用以下命令安装greenlet==0.4.15库pip3 install greenlet==0.4.15使用以下命令安装pycparser==2.19库pip3 ins
复制链接

扫一扫