speech2text.py

import os
import numpy as np
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
import pyaudio
import wave
import uuid

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


GLOBAL_RESULT = ""
wsParam = Ws_Param(APPID='41073149', APISecret='YTU4N2MzNjI0NjNkNmQ5MWNmYWE2ZmE5',
                   APIKey='3bd3fed540ce3c819f133ed0459e4213', AudioFile=r'')


# 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("sid:%s call success!,data is:%s" % (sid, json.dumps(data, ensure_ascii=False)))
            global GLOBAL_RESULT
            GLOBAL_RESULT = GLOBAL_RESULT + result
    except Exception as e:
        print("receive msg,but parse exception:", e)


# 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, a, b):
    # print("### closed ###")
    pass


# 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 speech2text():
    def audio_recording(path):
        print("Recording...")

        # 设置参数
        CHUNK = 1024
        FORMAT = pyaudio.paInt16
        CHANNELS = 1
        RATE = 16000
        THRESHOLD = 400  # 声音强度阈值
        SILENCE_DURATION = 1.5  # 连续静音时长（秒）

        # 初始化PyAudio
        p = pyaudio.PyAudio()

        # 打开流
        stream = p.open(format=FORMAT,
                        channels=CHANNELS,
                        rate=RATE,
                        input=True,
                        frames_per_buffer=CHUNK)

        # 录音数据
        frames = []
        silence_frames = 0
        max_silence_frames = int(RATE / CHUNK * SILENCE_DURATION)

        try:
            while True:
                data = stream.read(CHUNK)
                frames.append(data)
                # 将数据转换为numpy数组
                audio_data = np.frombuffer(data, dtype=np.int16)
                # 计算音频强度
                volume = np.abs(audio_data).mean()
                # 检查音量是否低于阈值
                if volume < THRESHOLD:
                    silence_frames += 1
                else:
                    silence_frames = 0
                # 如果连续静音超过指定时长，结束录音
                if silence_frames > max_silence_frames:
                    break
        except KeyboardInterrupt:
            # 允许用户使用Ctrl+C中断录音
            pass

        print("Finished recording.")

        # 停止并关闭流
        stream.stop_stream()
        stream.close()
        p.terminate()

        # 保存录音文件
        wf = wave.open(path, 'wb')
        wf.setnchannels(CHANNELS)
        wf.setsampwidth(p.get_sample_size(FORMAT))
        wf.setframerate(RATE)
        wf.writeframes(b''.join(frames))
        wf.close()

    audio_id = uuid.uuid4()
    audio_path = f'audio_output/{audio_id}.wav'
    audio_recording(audio_path)

    while not os.path.exists(audio_path):
        time.sleep(0.5)
        pass

    wsParam.AudioFile = rf'{audio_path}'

    # 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.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})

    print(GLOBAL_RESULT)
    return GLOBAL_RESULT


if __name__ == '__main__':
    speech2text()