腾讯云语音识别总结：cos存储到文字获取
需求背景：对尽调录音进行录音整理。
设计：先将录音存储到腾讯云cos对象存储
（为啥选腾讯云，当然是腾讯的最便宜啊。。。免费的一个月10小时录音转文字，40g永久免费的存储）
代码开发：（直接抄腾讯云自带api生成）
# -*- coding=utf-8
# appid 已在配置中移除,请在参数 Bucket 中带上 appid。Bucket 由 BucketName-APPID 组成
# 1. 设置用户配置, 包括 secretId，secretKey 以及 Region
from qcloud_cos import CosConfig
from qcloud_cos import CosS3Client
import sys
import logging
logging.basicConfig(level=logging.INFO, stream=sys.stdout)
secret_id = '' # 替换为用户的 secretId
secret_key = '' # 替换为用户的 secretKey
def send_file(path,file,secret_id,secret_key):
region = 'ap-shanghai' # 替换为用户的 Region
token = None # 使用临时密钥需要传入 Token，默认为空，可不填
scheme = 'https' # 指定使用 http/https 协议来访问 COS，默认为 https，可不填
config = CosConfig(Region=region, SecretId=secret_id, SecretKey=secret_key, Token=token, Scheme=scheme)
# 2. 获取客户端对象
client = CosS3Client(config)
# 参照下文的描述。或者参照 Demo 程序，详见 https://github.com/tencentyun/cos-python-sdk-v5/blob/master/qcloud_cos/demo.py
filename = path+file
response = client.upload_file(
Bucket='cos-bucket',
Key='/尽职调查/' + file,
LocalFilePath=filename,
PartSize=10,
MAXThread=5,
)
response = client.put_object_acl(
Bucket='cos-bucket',
Key='/尽职调查/' + file,
ACL='public-read'
)
url = 'cos的存储地址'+file
return url
if __name__ == '__main__':
send_file(r'/尽调/', '.m4a')
print('OK')
import json
import base64
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
import urllib.parse
def send(data,secret_id,secret_key,style=0):
try:
cred = credential.Credential(secret_id, secret_key)
httpProfile = HttpProfile()
httpProfile.endpoint = "asr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = asr_client.AsrClient(cred, "", clientProfile)
req = models.CreateRecTaskRequest()
if style == 0:
params = {
"EngineModelType": "16k_zh",
"ChannelNum": 1,
"SpeakerDiarization": 1,#是否开启说话人分离
"SpeakerNumber": 0,#说话人分离人数（需配合开启说话人分离使用），取值范围：0-10，0代表自动分离（目前仅支持≤6个人）
"ResTextFormat": 2,
"SourceType": 1,
"Data":str(data,'utf-8'),
"FilterModal": 1,
}
else:
params = {
"EngineModelType": "16k_zh",
"ChannelNum": 1,
"SpeakerDiarization": 1, # 是否开启说话人分离
"SpeakerNumber": 0, # 说话人分离人数（需配合开启说话人分离使用），取值范围：0-10，0代表自动分离（目前仅支持≤6个人）
"ResTextFormat": 2,
"SourceType": 0,
"Url": data,
"FilterModal": 1,
}
#
# params = {
# "Url": data,
# "ChannelNum": 1,
# "EngineModelType": "16k_zh",
# "ResTextFormat": 0,
# "SourceType": 0,
# "FilterModal": 1,
# "SpeakerDiarization": 1, # 是否开启说话人分离
# "SpeakerNumber": 0, # 说话人分离人数（需配合开启说话人分离使用），取值范围：0-10，0代表自动分离（目前仅支持≤6个人）
# }
req.from_json_string(json.dumps(params))
resp = client.CreateRecTask(req)
#print(resp.to_json_string())
user_dict = eval(resp.to_json_string())
return user_dict['Data']['TaskId']
except TencentCloudSDKException as err:
print(err)
if __name__ == '__main__':
data = '.m4a'
http = ''
a = send(http, secret_id,secret_key,style=2)
with open('taskid.txt', 'a', encoding='utf8') as f:
f.write(str(a) + ':' + data[:-4]+'\n')
print(a)
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
import time
secret_id = '' # 替换为用户的 secretId
secret_key = '' # 替换为用户的 secretKey
def get(id,text,secret_id,secret_key):
try:
while True:
cred = credential.Credential(secret_id, secret_key)
httpProfile = HttpProfile()
httpProfile.endpoint = "asr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = asr_client.AsrClient(cred, "", clientProfile)
req = models.DescribeTaskStatusRequest()
params = {
"TaskId": id #
}
req.from_json_string(json.dumps(params))
resp = str(client.DescribeTaskStatus(req))
user_dict = json.loads(resp)
# print(user_dict)
# user_dict = eval(resp.to_json_string())
# print(user_dict['Data']['Result'])
# print(user_dict['Data']['StatusStr'])
if user_dict['Data']['StatusStr'] == 'success':
with open(text, 'a', encoding='utf8') as f:
f.write(user_dict['Data']['Result'])
print('完成success')
break
elif user_dict['Data']['StatusStr'] == 'failed':
print('数据异常')
break
else:
print("doing")
time.sleep(10)
# cred = credential.Credential("AKID0oMTM2Y11lHbP4ueWXJrAQWQXOK4Om9L", "4uc8QREVYN3dolRrYPzJMdhU7aqFPM4a")
# httpProfile = HttpProfile()
# httpProfile.endpoint = "asr.tencentcloudapi.com"
#
# clientProfile = ClientProfile()
# clientProfile.httpProfile = httpProfile
# client = asr_client.AsrClient(cred, "", clientProfile)
#
# req = models.DescribeTaskStatusRequest()
# params = {
# "TaskId": id #
# }
#
# req.from_json_string(json.dumps(params))
# resp = str(client.DescribeTaskStatus(req))
# user_dict = json.loads(resp)
# print(user_dict)
# #user_dict = eval(resp.to_json_string())
# print(user_dict['Data']['Result'])
# with open(text,'a',encoding='utf8') as f:
# f.write(user_dict['Data']['Result'])
return 0
except TencentCloudSDKException as err:
print(err)
if __name__ == '__main__':
text = '.txt'
path = r'/尽调/'+text
get(xxxxxxxxxx,path,secret_id,secret_key)
from get_tx import get
from send_tx import send
from send_file import send_file
import urllib.parse
secret_id = '' # 替换为用户的 secretId
secret_key = '' # 替换为用户的 secretKey
filename = ''+'.aac'
path = r'\尽调/'
s = send_file(path, filename,secret_id,secret_key)
print('OK')
data = filename
http = 'cosurl地址' +\
urllib.parse.quote(data)
# https = 'https://.cos.ap-shanghai.myqcloud.com/%E5%B0%BD%E8%81%8C%.m4a'
a = send(http,secret_id,secret_key, style=2)
with open('taskid.txt', 'a', encoding='utf8') as f:
f.write(str(a) + ':' + data[:-4] + '\n')
print(a)
text = filename.split('.')[0] + '.txt'
wpath = path + text
get(int(a), wpath,secret_id,secret_key)