目录
1、语音转文字模块
#使用语音
import threading
import websocket
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
# 该模块为客户端和服务器端的网络套接字提供对传输层安全性(通常称为“安全套接字层”)
# 的加密和对等身份验证功能的访问。
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
import pyaudio
import os
import chatonecewithbot
import texthandle
import pushpicturegeturl
import textgetandclean
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
BEGTIMTIME = time.time()
CURRENTIME = time.time()
file_path1 = '/home/jetson/Desktop/enviro.txt'
file_path2 = '/home/jetson/Desktop/motion.txt'
class Ws_Param(object):
# 初始化
def __init__(self, APPID, APIKey, APISecret):
self.APPID = APPID
self.APIKey = APIKey
self.APISecret = APISecret
# 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):
#current_file_path = os.path.abspath(__file__)
#current_file_path = os.getcwd()
#current_directory = os.path.dirname(current_file_path)
#file_name = "listencontent.txt"
#file_path = os.path.join(current_directory, file_name) # 文本返回存入文件内
#print(file_path)
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"]
result = ""
for i in data:
for w in i["cw"]:
result += w["w"]
result = texthandle.remove_until_first_chinese_character(result)
if result == '。' or result == '.。' or result == ' .。' or result == ' 。' or result == '.' or result == '' or result == '?':
pass
else:
#t.insert(END, result) # 把上边的标点插入到result的最后
#with open('/home/jetson/Desktop/MyProject/ComWithGpt/listencontent.txt
#', 'w', encoding='utf-8') as file:
with open('/home/jetson/Desktop/MyProject/ComWithGpt/listencontent.txt', 'w', encoding='utf-8') as file:
file.write(result)
print("翻译结果: %s。" % (result))
a.pause()
try:
# 调用与机器人对话的函数
#reslut = textgetandclean.textintegration(result)
with open(file_path1, 'r') as file:
content1 = file.read()
with open(file_path2, 'r') as file:
content2 = file.read()
#print("打印1和2:" + content1 + " " + content2)
#print("信息对话:" + result)
if content1 != '':
result = "与你对话用户所处状态为:" + content1 + "他的情绪为:" + content2 + "。" + "用户所说的话为:" + result
else:
result = "用户的情绪为:" + content2 + "。" + "用户所说的话为:" + result
print(result)
chatonecewithbot.chatonece(result)
if content1 != '':
with open(file_path1, 'w') as file:
file.truncate(0)
#thread.start_new_thread(run, ())
finally:
# 恢复语音监听线程
#a.resume()
pass
#chatonecewithbot.chatonece(result)
#print("翻译结果: %s。" % (result))
result = ''
except Exception as e:
pass
#print("receive msg,but parse exception:", e)
# 收到websocket错误的处理
def on_error(ws, error):
#print("### error:", error)
run()
# 收到websocket关闭的处理
def on_close(ws):
pass
# 收到websocket连接建立的处理
def on_open(ws):
def run(*args):
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
CHUNK = 520 # 定义数据流块
FORMAT = pyaudio.paInt16 # 16bit编码格式
CHANNELS = 1 # 单声道
RATE = 16000 # 16000采样频率
# 实例化pyaudio对象
p = pyaudio.PyAudio() # 录音
# 创建音频流
# 使用这个对象去打开声卡,设置采样深度、通道数、采样率、输入和采样点缓存数量
stream = p.open(format=FORMAT, # 音频流wav格式
channels=CHANNELS, # 单声道
rate=RATE, # 采样率16000
input=True,
frames_per_buffer=CHUNK)
print("- - - - - - - Start Recording ...- - - - - - - ")
# 添加开始表示 ——start recording——
global text
tip = "——start recording——"
for i in range(0, int(RATE / CHUNK * 60)):
# # 读出声卡缓冲区的音频数据
buf = stream.read(CHUNK)
if not buf:
status = STATUS_LAST_FRAME
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
thread.start_new_thread(run, ())
def beignchat():
a = Job()
a.start()
def run():
global wsParam
# 讯飞接口编码
wsParam = Ws_Param(APPID='',
APIKey='',
APISecret='')
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}, ping_timeout=2)
def runc():
run()
class Job(threading.Thread):
def __init__(self, *args, **kwargs):
super(Job, self).__init__(*args, **kwargs)
self.__flag = threading.Event() # 用于暂停线程的标识
self.__flag.set() # 设置为True
self.__running = threading.Event() # 用于停止线程的标识
self.__running.set() # 将running设置为True
def run(self):
while self.__running.isSet():
self.__flag.wait() # 为True时立即返回, 为False时阻塞直到内部的标识位为True后返回
runc()
time.sleep(1)
def pause(self):
self.__flag.clear() # 设置为False, 让线程阻塞
def resume(self):
self.__flag.set() # 设置为True, 让线程停止阻塞
def stop(self):
self.__flag.set() # 将线程从暂停状态恢复, 如何已经暂停的话
self.__running.clear() # 设置为False
if __name__ == '__main__':
current_file_path = os.path.abspath(__file__)
current_directory = os.path.dirname(current_file_path)
file_name = "listencontent.txt"
file_path = os.path.join(current_directory, file_name) # 文本返回存入文件内
print(file_path)
# 启动多线程,用函数无法正常运行
a = Job()
a.start()
# 主程序每60s上传一次图片,5s上传一次情绪
print("启动上传图片,上传情绪")
while True:
CURRENTIME = time.time()
if CURRENTIME - BEGTIMTIME >= 70:
print("上传图片")
pushpicturegeturl.pushpicture()
BEGTIMTIME = CURRENTIME
上述代码,用多线程方式实时获取用户语音,每个线程会独立监听一段时间并将接收到的语音数据传递到讯飞服务端,断开连接并开启新的线程
主要是将识别到的语音处理并传递到讯飞服务平台获取解析到的语音转成的汉字信息