zhuchaowe/maxkb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: 讯飞接口校验发送demo验证

Browse Source
This commit is contained in:
CaptainB 2024-09-14 22:43:30 +08:00 committed by 刘瑞斌
parent b0f443f3d2
commit 467b864895
3 changed files with 14 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
apps/setting/models_provider/impl/xf_model_provider/model/iat_mp3_16k.mp3 Normal file
View File

Binary file not shown.

14
apps/setting/models_provider/impl/xf_model_provider/model/stt.py
View File

@ -8,6 +8,8 @@ import datetime
import hashlib import hashlib
import hmac import hmac
import json import json
import logging
import os
from datetime import datetime from datetime import datetime
from typing import Dict from typing import Dict
from urllib.parse import urlencode, urlparse from urllib.parse import urlencode, urlparse
@ -25,6 +27,7 @@ ssl_context = ssl.SSLContext(ssl.PROTOCOL_TLS_CLIENT)
ssl_context.check_hostname = False ssl_context.check_hostname = False
ssl_context.verify_mode = ssl.CERT_NONE ssl_context.verify_mode = ssl.CERT_NONE
max_kb = logging.getLogger("max_kb")
class XFSparkSpeechToText(MaxKBBaseModel, BaseSpeechToText): class XFSparkSpeechToText(MaxKBBaseModel, BaseSpeechToText):
spark_app_id: str spark_app_id: str
@ -89,11 +92,9 @@ class XFSparkSpeechToText(MaxKBBaseModel, BaseSpeechToText):
return url return url
def check_auth(self): def check_auth(self):
async def check(): cwd = os.path.dirname(os.path.abspath(__file__))
async with websockets.connect(self.create_url(), ssl=ssl_context) as ws: with open(f'{cwd}/iat_mp3_16k.mp3', 'rb') as f:
pass self.speech_to_text(f)
asyncio.run(check())
def speech_to_text(self, file): def speech_to_text(self, file):
async def handle(): async def handle():
@ -112,8 +113,7 @@ class XFSparkSpeechToText(MaxKBBaseModel, BaseSpeechToText):
sid = message["sid"] sid = message["sid"]
if code != 0: if code != 0:
errMsg = message["message"] errMsg = message["message"]
print("sid:%s call error:%s code is:%s" % (sid, errMsg, code)) raise Exception(f"sid: {sid} call error: {errMsg} code is: {code}")
return errMsg
else: else:
data = message["data"]["result"]["ws"] data = message["data"]["result"]["ws"]
result = "" result = ""

15
apps/setting/models_provider/impl/xf_model_provider/model/tts.py
View File

@ -10,6 +10,7 @@ import datetime
import hashlib import hashlib
import hmac import hmac
import json import json
import logging
import os import os
from datetime import datetime from datetime import datetime
from typing import Dict from typing import Dict
@ -20,6 +21,8 @@ import websockets
from setting.models_provider.base_model_provider import MaxKBBaseModel from setting.models_provider.base_model_provider import MaxKBBaseModel
from setting.models_provider.impl.base_tts import BaseTextToSpeech from setting.models_provider.impl.base_tts import BaseTextToSpeech
max_kb = logging.getLogger("max_kb")
STATUS_FIRST_FRAME = 0 # 第一帧的标识 STATUS_FIRST_FRAME = 0 # 第一帧的标识
STATUS_CONTINUE_FRAME = 1 # 中间帧标识 STATUS_CONTINUE_FRAME = 1 # 中间帧标识
STATUS_LAST_FRAME = 2 # 最后一帧的标识 STATUS_LAST_FRAME = 2 # 最后一帧的标识
@ -92,11 +95,7 @@ class XFSparkTextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
return url return url
def check_auth(self): def check_auth(self):
async def check(): self.text_to_speech("你好")
async with websockets.connect(self.create_url(), max_size=1000000000, ssl=ssl_context) as ws:
pass
asyncio.run(check())
def text_to_speech(self, text): def text_to_speech(self, text):
@ -119,13 +118,13 @@ class XFSparkTextToSpeech(MaxKBBaseModel, BaseTextToSpeech):
# print(message) # print(message)
code = message["code"] code = message["code"]
sid = message["sid"] sid = message["sid"]
audio = message["data"]["audio"]
audio = base64.b64decode(audio)
if code != 0: if code != 0:
errMsg = message["message"] errMsg = message["message"]
print("sid:%s call error:%s code is:%s" % (sid, errMsg, code)) raise Exception(f"sid: {sid} call error: {errMsg} code is: {code}")
else: else:
audio = message["data"]["audio"]
audio = base64.b64decode(audio)
audio_bytes += audio audio_bytes += audio
# 退出 # 退出
if message["data"]["status"] == 2: if message["data"]["status"] == 2: