4cfad5ae0f
- 全新ui - 全面优化websocket逻辑，提高数字人和ui连接的稳定性及资源开销 - 全面优化唤醒逻辑，提供稳定的普通唤醒模式和前置词唤醒模式 - 优化拾音质量，支持多声道麦克风拾音 - 优化自动播放服务器的对接机制，提供稳定和兼容旧版ue工程的对接模式 - 数字人接口输出机器人表情，以适应新fay ui及单片机的数字人表情输出 - 使用更高级的音频时长计算方式，可以更精准控制音频播放完成后的逻辑 - 修复点击关闭按钮会导致程序退出的bug - 修复没有麦克风的设备开启麦克风会出错的问题 - 为服务器主机地址提供配置项，以方便服务器部署
139 lines
5.1 KiB
Python
139 lines
5.1 KiB
Python
import http.client
|
||
import urllib.parse
|
||
import json
|
||
from aliyunsdkcore.client import AcsClient
|
||
from aliyunsdkcore.request import CommonRequest
|
||
from core.authorize_tb import Authorize_Tb
|
||
import time
|
||
from utils import util, config_util
|
||
from utils import config_util as cfg
|
||
import wave
|
||
|
||
class Speech:
|
||
def __init__(self):
|
||
self.key_ali_nls_key_id = cfg.key_ali_tss_key_id
|
||
self.key_ali_nls_key_secret = cfg.key_ali_tss_key_secret
|
||
self.ali_nls_app_key = cfg.key_ali_tss_app_key
|
||
self.token = None
|
||
self.authorize_tb = Authorize_Tb()
|
||
self.__history_data = []
|
||
|
||
def connect(self):
|
||
pass
|
||
|
||
def __get_history(self, voice_name, style, text):
|
||
for data in self.__history_data:
|
||
if data[0] == voice_name and data[1] == style and data[2] == text:
|
||
return data[3]
|
||
return None
|
||
|
||
def set_token(self):
|
||
token = self.__check_token()
|
||
if token is None or token == 'expired':
|
||
token_info = self.__get_token()
|
||
if token_info is not None and token_info['Id'] is not None:
|
||
expires_timedelta = token_info['ExpireTime']
|
||
expiry_timestamp_in_milliseconds = expires_timedelta * 1000
|
||
if token == 'expired':
|
||
self.authorize_tb.update_by_userid(self.key_ali_nls_key_id, token_info['Id'], expiry_timestamp_in_milliseconds)
|
||
else:
|
||
self.authorize_tb.add(self.key_ali_nls_key_id, token_info['Id'], expiry_timestamp_in_milliseconds)
|
||
token = token_info['Id']
|
||
else:
|
||
print(f"请检查阿里云tts对接")
|
||
token = None
|
||
|
||
self.token = token
|
||
|
||
|
||
def __check_token(self):
|
||
self.authorize_tb.init_tb()
|
||
info = self.authorize_tb.find_by_userid(self.key_ali_nls_key_id)
|
||
if info is not None:
|
||
if info[1] >= int(time.time())*1000:
|
||
return info[0]
|
||
else:
|
||
return 'expired'
|
||
else:
|
||
return None
|
||
|
||
def __get_token(self):
|
||
try:
|
||
global _token
|
||
__client = AcsClient(
|
||
self.key_ali_nls_key_id,
|
||
self.key_ali_nls_key_secret,
|
||
"cn-shanghai"
|
||
)
|
||
|
||
__request = CommonRequest()
|
||
__request.set_method('POST')
|
||
__request.set_domain('nls-meta.cn-shanghai.aliyuncs.com')
|
||
__request.set_version('2019-02-28')
|
||
__request.set_action_name('CreateToken')
|
||
info = json.loads(__client.do_action_with_exception(__request))
|
||
_token = info['Token']
|
||
return info['Token']
|
||
except Exception as e:
|
||
print(f"阿里云tts对接有误： {str(e)}")
|
||
return None
|
||
|
||
|
||
|
||
def to_sample(self, text, style) :
|
||
try:
|
||
history = self.__get_history(config_util.config["attribute"]["voice"], style, text)
|
||
if history is not None:
|
||
return history
|
||
self.set_token()
|
||
if self.token != None:
|
||
host = 'nls-gateway-cn-shanghai.aliyuncs.com'
|
||
url = 'https://' + host + '/stream/v1/tts'
|
||
# 设置HTTPS Headers。
|
||
httpHeaders = {
|
||
'Content-Type': 'application/json'
|
||
}
|
||
text = f"<speak><break time='0.2s'/>{text}</speak>"
|
||
# 设置HTTPS Body。
|
||
body = {'appkey': self.ali_nls_app_key, 'token': self.token,'speech_rate':0, 'text': text, 'format': 'wav', 'sample_rate': 16000, 'voice': config_util.config["attribute"]["voice"]}
|
||
body = json.dumps(body)
|
||
conn = http.client.HTTPSConnection(host)
|
||
conn.request(method='POST', url=url, body=body, headers=httpHeaders)
|
||
# 处理服务端返回的响应。
|
||
response = conn.getresponse()
|
||
tt = time.time()
|
||
contentType = response.getheader('Content-Type')
|
||
body = response.read()
|
||
if 'audio/mpeg' == contentType :
|
||
file_url = './samples/sample-' + str(int(time.time() * 1000)) + '.wav'
|
||
with wave.open(file_url, 'wb') as wf:
|
||
wf.setnchannels(1)
|
||
wf.setsampwidth(2)
|
||
wf.setframerate(16000)
|
||
wf.writeframes(body)
|
||
|
||
else :
|
||
util.log(1, "[x] 语音转换失败！")
|
||
util.log(1, "[x] 原因: " + str(body))
|
||
file_url = None
|
||
return file_url
|
||
conn.close()
|
||
print(time.time() - tt)
|
||
return file_url
|
||
else:
|
||
util.log(1, "[x] 语音转换失败！")
|
||
util.log(1, "[x] 原因: 对接有误" )
|
||
file_url = None
|
||
return file_url
|
||
except Exception as e :
|
||
util.log(1, "[x] 语音转换失败！")
|
||
util.log(1, "[x] 原因: " + str(str(e)))
|
||
file_url = None
|
||
return file_url
|
||
|
||
|
||
def close(self):
|
||
pass
|
||
|
||
|