利用python实现调用讯飞大模型语音识别

废话不多说直接上代码

SparkPythondemo.py:

# coding: utf-8
import SparkApi
from gtts import gTTS
import speech_recognition as sr
import os
import time

#以下密钥信息从控制台获取   https://console.xfyun.cn/services/bm35
appid = "..."     #填写控制台中获取的 APPID 信息
api_secret = "..."   #填写控制台中获取的 APISecret 信息
api_key ="..."    #填写控制台中获取的 APIKey 信息

domain = "generalv3.5"    # v3.0版本

Spark_url = "wss://spark-api.xf-yun.com/v3.5/chat"  # v3.5环服务地址

#初始上下文内容，当前可传system、user、assistant 等角色
text =[
    # {"role": "system", "content": "你现在扮演李白，你豪情万丈，狂放不羁；接下来请用李白的口吻和用户对话。"} , # 设置对话背景或者模型角色
    # {"role": "user", "content": "你是谁"},  # 用户的历史问题
    # {"role": "assistant", "content": "....."} , # AI的历史回答结果
    # # ....... 省略的历史对话
    # {"role": "user", "content": "你会做什么"}  # 最新的一条问题，如无需上下文，可只传最新一条问题
]




def getText(role,content):
    jsoncon = {}
    jsoncon["role"] = role
    jsoncon["content"] = content
    text.append(jsoncon)
    return text



def getlength(text):
    length = 0
    for content in text:
        temp = content["content"]
        leng = len(temp)
        length += leng
    return length

def checklen(text):
    while (getlength(text) > 8000):
        del text[0]
    return text
    


if __name__ == '__main__':
    recognizer = sr.Recognizer()
    microphone = sr.Microphone()
    print("语音助手已启动！")
    while (1):
        while True:
            print("请说话...")
            with microphone as source:
                recognizer.adjust_for_ambient_noise(source)
                audio = recognizer.listen(source)

            try:
                # user_input = recognizer.recognize_google(audio, language="zh-CN") # 识别语言：中文为"zh-CN"，英文为"en-US"
                user_input = recognizer.recognize_google(audio, language="zh-CN") # 识别语言：中文为"zh-CN"，英文为"en-US"
                print("你说：", user_input)

                # Input = input("\n" + "我:")
                question = checklen(getText("user", user_input))
                SparkApi.answer = ""
                print("星火:", end="")
                SparkApi.main(appid, api_key, api_secret, Spark_url, domain, question)
                # print(SparkApi.answer)
                respose = getText("assistant", SparkApi.answer)


            except sr.UnknownValueError:
                print("抱歉，我无法识别你说的话。")
            except sr.RequestError:
                print("无法连接到语音识别服务。")

SparkApi.py:

import _thread as thread
import base64
import os
import datetime
import hashlib
import hmac
import json
import time
from urllib.parse import urlparse
import ssl
from datetime import datetime
from time import mktime
from urllib.parse import urlencode
from wsgiref.handlers import format_date_time

import websocket  # 使用websocket_client
answer = ""
sid = ''

class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, Spark_url):
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        self.host = urlparse(Spark_url).netloc
        self.path = urlparse(Spark_url).path
        self.Spark_url = Spark_url

    # 生成url
    def create_url(self):
        # 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: " + self.host + "\n"
        signature_origin += "date: " + date + "\n"
        signature_origin += "GET " + self.path + " 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 = base64.b64encode(signature_sha).decode(encoding='utf-8')

        authorization_origin = f'api_key="{self.APIKey}", algorithm="hmac-sha256", headers="host date request-line", signature="{signature_sha_base64}"'

        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": self.host
        }
        # 拼接鉴权参数，生成url
        url = self.Spark_url + '?' + urlencode(v)
        # print(url)
        # 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
        return url


# 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,one,two):
    print(" ")


# 收到websocket连接建立的处理
def on_open(ws):
    thread.start_new_thread(run, (ws,))


def run(ws, *args):
    data = json.dumps(gen_params(appid=ws.appid, domain= ws.domain,question=ws.question))
    ws.send(data)


# 收到websocket消息的处理
def on_message(ws, message):
    # print(message)
    # print(time.time())
    data = json.loads(message)
    code = data['header']['code']
    if code != 0:
        print(f'请求错误: {code}, {data}')
        ws.close()
    else:
        global sid
        sid = data["header"]["sid"]
        choices = data["payload"]["choices"]
        status = choices["status"]
        content = choices["text"][0]["content"]
        print(content,end ="")
        global answer
        answer += content
        # print(1)
        if status == 2:
            ws.close()


def gen_params(appid, domain,question):
    """
    通过appid和用户的提问来生成请参数
    """
    data = {
        "header": {
            "app_id": appid,
            "uid": "1234"
        },
        "parameter": {

            "chat": {
                "domain": domain,
                "temperature": 0.8,
                "max_tokens": 2048,
                "top_k": 5,

                "auditing": "default"
            }
        },
        "payload": {
            "message": {
                "text": question
            }
        }
    }
    return data


def main(appid, api_key, api_secret, Spark_url,domain, question):
    wsParam = Ws_Param(appid, api_key, api_secret, Spark_url)
    websocket.enableTrace(False)
    wsUrl = wsParam.create_url()
    ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close, on_open=on_open)
    ws.appid = appid
    ws.question = question
    ws.domain = domain
    ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})