解决百度语音合成的一些问题和参数化设置 (#676)

* 解决百度语音合成的一些问题和参数化设置

* 补充百度语音说明
This commit is contained in:
zhanws
2023-03-30 14:59:52 +08:00
committed by GitHub
parent 83136e3142
commit 06b02f5df8
3 changed files with 98 additions and 16 deletions

View File

@@ -2,6 +2,8 @@
"""
baidu voice service
"""
import json
import os
import time
from aip import AipSpeech
from bridge.reply import Reply, ReplyType
@@ -21,29 +23,47 @@ from config import conf
- 1837四川话
要使用本模块, 首先到 yuyin.baidu.com 注册一个开发者账号,
之后创建一个新应用, 然后在应用管理的"查看key"中获得 API Key 和 Secret Key
填入 config.json 中.
baidu_app_id: ''
baidu_api_key: ''
baidu_secret_key: ''
baidu_dev_pid: '1536'
"""
然后在 config.json 中填入这两个值, 以及 app_id, dev_pid
"""
class BaiduVoice(Voice):
APP_ID = conf().get('baidu_app_id')
API_KEY = conf().get('baidu_api_key')
SECRET_KEY = conf().get('baidu_secret_key')
DEV_ID = conf().get('baidu_dev_pid')
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
def __init__(self):
pass
try:
curdir = os.path.dirname(__file__)
config_path = os.path.join(curdir, "config.json")
bconf = None
if not os.path.exists(config_path): #如果没有配置文件,创建本地配置文件
bconf = { "lang": "zh", "ctp": 1, "spd": 5,
"pit": 5, "vol": 5, "per": 0}
with open(config_path, "w") as fw:
json.dump(bconf, fw, indent=4)
else:
with open(config_path, "r") as fr:
bconf = json.load(fr)
self.app_id = conf().get('baidu_app_id')
self.api_key = conf().get('baidu_api_key')
self.secret_key = conf().get('baidu_secret_key')
self.dev_id = conf().get('baidu_dev_pid')
self.lang = bconf["lang"]
self.ctp = bconf["ctp"]
self.spd = bconf["spd"]
self.pit = bconf["pit"]
self.vol = bconf["vol"]
self.per = bconf["per"]
self.client = AipSpeech(self.app_id, self.api_key, self.secret_key)
except Exception as e:
logger.warn("BaiduVoice init failed: %s, ignore " % e)
def voiceToText(self, voice_file):
# 识别本地文件
logger.debug('[Baidu] voice file name={}'.format(voice_file))
pcm = get_pcm_from_wav(voice_file)
res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.DEV_ID})
res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.dev_id})
if res["err_no"] == 0:
logger.info("百度语音识别到了:{}".format(res["result"]))
text = "".join(res["result"])
@@ -57,9 +77,8 @@ class BaiduVoice(Voice):
return reply
def textToVoice(self, text):
result = self.client.synthesis(text, 'zh', 1, {
'spd': 5, 'pit': 5, 'vol': 5, 'per': 111
})
result = self.client.synthesis(text, self.lang, self.ctp, {
'spd': self.spd, 'pit': self.pit, 'vol': self.vol, 'per': self.per})
if not isinstance(result, dict):
fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
with open(fileName, 'wb') as f: