因为比赛要用到人机进行对话所以写以下python代码。以下为3.8
代码中相关api以及密匙都更改过，请自己去获得密匙
科大讯飞网址讯飞开放平台-以语音交互为核心的人工智能开放平台 (xfyun.cn)
百度千帆文心一言百度智能云千帆大模型 (baidu.com)
首先通过麦克风获取人的声音，并且调用科大讯飞api实现语音转文字，接着根据人说的话在不在用户固定的对答库中进行判断，如果在则根据问答库固定内容进行回答，如果不在则发给文心一言api进行回答。
import pyttsx3
import websocket
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from pydub import AudioSegment
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
import pyaudio
import sys
import os
import requests
from yy import text_to_speech #文字转语音函数调用
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
silence_counter = 0
SILENCE_THRESHOLD = 5 # 静音阈值，单位为帧数
# 定义保存文件路径
save_folder = r"C:\Users\=xxxxxxxxxxt" # 替换为你想保存文件的路径
# 修改成文心一言sapi key和secret key
API_KEY = "ylY7jwOX6OMa0PxxxxxxxGq"
SECRET_KEY = "6eCR15qZxO2sYnHbH5wxxxxxxxxxb3"
question = ['你是谁', '我是不失，你的小笨蛋',
‘ 我是不是世界上最帅的’， ’是的‘，
]
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):
result = ''
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"]
for i in data:
for w in i["cw"]:
result += w["w"]
if result == '。' or result=='？' or result=='，':
result = ''
pass
if result == "再见" or result == "退出":
print("用户："+result)
sys.exit()
elif result in question:
print ( "用户: %s" % (result) )
# reply是机器人回答的话
reply = question[question.index ( result ) + 1]
else:
print("people: %s" % (result))
# 根据语音识别文字给出智能回答
#此处是百度的智能机器人api
url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant?access_token=" + get_access_token()
payload = json.dumps({
"messages": [
{
"role": "user",
"content": result
}
]
})
headers = {'Content-Type': 'application/json'}
response = requests.request("POST", url, headers=headers, data=payload).json()
reply = response['result']
except Exception as e:
print("receive msg,but parse exception:", e)
ws.close()
# 打开文件准备写入
file_path = os.path.join(save_folder, "result.txt")
with open(file_path, "a", encoding="utf-8") as file:
# 在回调函数中写入结果
file.write("people: %s\n" % result) # 将用户的消息写入文件
file.write("robot: %s\n" % reply) # 将机器人的回复写入文件
# 输出回答
print("AI: %s" % reply) # 打印AI的回答
ws.close()
# 语音合成
text_to_speech(reply, save_folder) # 使用讯飞的语音合成 API
progress_bar(3) # 运行5秒的进度条
text_to_speech("请说话", save_folder)
# dialogue_flag = True
def progress_bar(duration):
for i in range(101): # 0 to 100
sys.stdout.write("\r[%-100s] %d%%" % ('='*i, i)) # 打印进度条
sys.stdout.flush() # 刷新输出缓冲区
time.sleep(duration/100) # 暂停
sys.stdout.write("\n") # 新的一行
def get_access_token():
"""
使用 AK，SK 生成鉴权签名（Access Token）
:return: access_token，或是None(如果错误)
"""
url = "https://aip.baidubce.com/oauth/2.0/token"
params = {"grant_type": "client_credentials", "client_id": API_KEY, "client_secret": SECRET_KEY}
return str(requests.post(url, params=params).json().get("access_token"))
# 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):
pass
print("### closed record ###")
def on_open(ws):
def run(*args): # 将wsParam作为参数传递
status = STATUS_FIRST_FRAME
CHUNK = 520
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK)
print("- - - - - - - Start Recording ...- - - - - - - ")
for i in range(0,int(RATE/CHUNK*60)):
buf = stream.read(CHUNK)
if not buf:
print("over")
status = STATUS_LAST_FRAME
silence_counter += 1
else:
silence_counter = 0
if silence_counter >= SILENCE_THRESHOLD:
print("Long time no sound detected. Entering sleep mode.")
break
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
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))
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
stream.stop_stream()
stream.close()
p.terminate()
ws.close()
thread.start_new_thread(run, ()) # 不再传递 wsParam
# def run():
if __name__ == "__main__":
# global wsParam
#此处是讯飞语音的api接口
wsParam = Ws_Param(APPID='a54xxxxd', APIKey='a0da0eb117e75cxxxxxxx',
APISecret='YjU5MjYwZmNmODM0Yxxxxxxxxxxxxxxx')
websocket.enableTrace(False)
wsUrl = wsParam.create_url()
while True: # 添加一个无限循环
ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)
ws.on_open = lambda ws: on_open(ws)
ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE}, ping_timeout=5)
以上代码实现了语音转文字并且和文心一言大模型对话，对话记录可以打印在终端上并且保存在txt文档里面。text_to_speech文字转语音函数移步我的另一个博客。