|
|
@@ -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: |
|
|
|