python 百度语音识别API 和腾讯云识别API

python 百度语音识别API 和腾讯云识别API

百度语音识别API

1. 需要先去注册百度语音识别获取到个人的APP_ID、API_KEY、SECRET_KEY
2. 安装百度API包
   pip install baidu-aip
3. 样例代码

from aip import AipSpeech
APP_ID = '********'
    API_KEY = '************'
    SECRET_KEY = '****************'
    client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

    # 识别本地文件
    res = client.asr(get_file_content("文件路径"), 'wav', 16000, {
        'dev_pid': 1537,  # 默认1537（普通话 输入法模型）
    })
    print(res.get("result")[0])

说明

使用腾讯语音识别API

1. 需要去腾讯云注册并获取需要的SecretId、SecretKey
2. 安装腾讯pythonSDK
   pip install --upgrade tencentcloud-sdk-python
3. 样例代码

import json
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.asr.v20190614 import asr_client, models

file = open("./2.wav", "rb").read()  # 读取二进制文件
    base64_string = base64.b64encode(file).decode("utf-8")

    file_size = os.path.getsize('音频路径') # 获取音频字节长度

    SecretId="****************************"
    SecretKey="*************************"
    cred = credential.Credential(SecretId, SecretKey)
    # 实例化一个http选项，可选的，没有特殊需求可以跳过
    httpProfile = HttpProfile()
    httpProfile.endpoint = "asr.tencentcloudapi.com"

    # 实例化一个client选项，可选的，没有特殊需求可以跳过
    clientProfile = ClientProfile()
    clientProfile.httpProfile = httpProfile
    # 实例化要请求产品的client对象,clientProfile是可选的
    client = asr_client.AsrClient(cred, "", clientProfile)

    # 实例化一个请求对象,每个接口都会对应一个request对象
    req = models.SentenceRecognitionRequest()
    params = {
        "ProjectId": 0,
        "SubServiceType": 2,
        "EngSerViceType": "16k_zh",
        "SourceType": 1,
        "VoiceFormat": "wav",  
        "UsrAudioKey": "111",  
        "Data": base64_string,
        "DataLen": file_size
    }
    req.from_json_string(json.dumps(params))

    # 返回的resp是一个SentenceRecognitionResponse的实例，与请求对象对应
    resp = client.SentenceRecognition(req)
    # 输出json格式的字符串回包
    print(resp.to_json_string())
    resp1 = json.loads(resp.to_json_string())
    print(resp1['Result'])

说明