xf_tools.py

import websocket
import datetime
import hashlib
import base64
import hmac
import json
import os
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

# 全局变量，用于存储转换结果
result_text = None


class WsParam(object):
    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}

    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)
        return url


audio_file_path = os.path.expanduser('~/.SmartMemo/data.txt')

wsParam = WsParam(APPID='your_APPID', APISecret='your_APISecret',
                   APIKey='your_APIKey',
                   AudioFile=audio_file_path)


def on_message(ws, message):
    """
    收到websocket消息的处理
    """
    global result_text
    try:
        code = json.loads(message)["code"]
        sid = json.loads(message)["sid"]
        if code != 0:
            errMsg = json.loads(message)["message"]
            print("Error:", errMsg)
        else:
            data = json.loads(message)["data"]["result"]["ws"]
            result = ""
            for i in data:
                for w in i["cw"]:
                    result += w["w"]
            # 检查是否是第一帧消息
            if not hasattr(ws, 'first_frame_received'):
                # print("%s " % (json.dumps(result, ensure_ascii=False)))
                result_text = json.dumps(result, ensure_ascii=False)
                ws.first_frame_received = True  # 标记第一帧消息已接收
                ws.close()  # 关闭websocket连接
            else:
                # 如果是后续帧，可以选择不打印或者处理
                pass

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


def on_error(ws, error):
    """
    收到websocket错误的处理
    """
    print("迅飞语音听写请求出错:", error)


def on_close(ws, a1, a2):
    """
    收到websocket关闭的处理
    """
    print("迅飞语音听写请求结束")


# 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
        interval = 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(interval)
        ws.close()

    thread.start_new_thread(run, ())


def audio_to_text():
    global result_text
    result_text = None  # 初始化全局变量
    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})
    thread.start_new_thread(lambda: ws.run_forever(sslopt={"cert_reqs": ssl.CERT_OPTIONAL}), ())
    # 等待结果
    while result_text is None:
        time.sleep(0.1)  # 短暂的等待，避免CPU占用过高

    result_text = result_text.strip('"')
    return result_text  # 返回结果


if __name__ == "__main__":
    res = audio_to_text()
    res = res.strip('"')
    print(res)