style: 为代码添加头部注释说明
This commit is contained in:
parent
37534ac211
commit
d7f80c1ac8
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
语音识别的语言模型
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
语音识别的语言模型
|
||||
|
@ -241,7 +259,8 @@ if(__name__=='__main__'):
|
|||
#str_pinyin = ['wo3', 'men5', 'qun2', 'li3', 'xiong1', 'di4', 'jian4', 'mei4', 'dou1', 'zai4', 'shuo1']
|
||||
#str_pinyin = ['su1', 'an1', 'ni3', 'sui4', 'li4', 'yun4', 'sui2', 'cong2', 'jiao4', 'ming2', 'tao2', 'qi3', 'yu2', 'peng2', 'ya4', 'yang4', 'chao1', 'dao3', 'jiang1', 'li3', 'yuan2', 'kang1', 'zhua1', 'zou3']
|
||||
#str_pinyin = ['da4', 'jia1', 'hao3']
|
||||
str_pinyin = ['kao3', 'yan2', 'yan1', 'yu3', 'ci2', 'hui4']
|
||||
#str_pinyin = ['kao3', 'yan2', 'yan1', 'yu3', 'ci2', 'hui4']
|
||||
str_pinyin = ['mei2', 'xiang3', 'jing4', 'ran2', 'can3', 'bai4']
|
||||
#r = ml.decode(str_pinyin)
|
||||
r=ml.SpeechToText(str_pinyin)
|
||||
print('语音转文字结果:\n',r)
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
|
@ -1,8 +1,27 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
||||
import platform as plat
|
||||
import os
|
||||
import time
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
一个对于单一音频时间长度不作限制的版本,正在测试
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
"""
|
||||
|
|
246
asrserver.py
246
asrserver.py
|
@ -1,16 +1,36 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
语音识别API的HTTP服务器程序
|
||||
|
||||
"""
|
||||
|
||||
import http.server
|
||||
import urllib
|
||||
import socket
|
||||
import keras
|
||||
from SpeechModel251 import ModelSpeech
|
||||
from LanguageModel import ModelLanguage
|
||||
|
||||
|
||||
datapath = './'
|
||||
modelpath = 'model_speech/'
|
||||
ms = ModelSpeech(datapath)
|
||||
|
@ -19,127 +39,115 @@ ms.LoadModel(modelpath + 'm251/speech_model251_e_0_step_12000.model')
|
|||
ml = ModelLanguage('model_language')
|
||||
ml.LoadModel()
|
||||
|
||||
class TestHTTPHandle(http.server.BaseHTTPRequestHandler):
|
||||
def setup(self):
|
||||
self.request.settimeout(10)
|
||||
http.server.BaseHTTPRequestHandler.setup(self)
|
||||
|
||||
def _set_response(self):
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'text/html')
|
||||
self.end_headers()
|
||||
|
||||
def do_GET(self):
|
||||
|
||||
buf = 'ASRT_SpeechRecognition API'
|
||||
self.protocal_version = 'HTTP/1.1'
|
||||
|
||||
self._set_response()
|
||||
|
||||
buf = bytes(buf,encoding="utf-8")
|
||||
self.wfile.write(buf)
|
||||
|
||||
def do_POST(self):
|
||||
'''
|
||||
处理通过POST方式传递过来并接收的语音数据
|
||||
通过语音模型和语言模型计算得到语音识别结果并返回
|
||||
'''
|
||||
path = self.path
|
||||
print(path)
|
||||
#获取post提交的数据
|
||||
datas = self.rfile.read(int(self.headers['content-length']))
|
||||
#datas = urllib.unquote(datas).decode("utf-8", 'ignore')
|
||||
datas = datas.decode('utf-8')
|
||||
datas_split = datas.split('&')
|
||||
token = ''
|
||||
fs = 0
|
||||
wavs = []
|
||||
#type = 'wavfilebytes' # wavfilebytes or python-list
|
||||
|
||||
for line in datas_split:
|
||||
[key, value]=line.split('=')
|
||||
if('wavs' == key and '' != value):
|
||||
wavs.append(int(value))
|
||||
elif('fs' == key):
|
||||
fs = int(value)
|
||||
elif('token' == key ):
|
||||
token = value
|
||||
#elif('type' == key):
|
||||
# type = value
|
||||
else:
|
||||
print(key, value)
|
||||
|
||||
if(token != 'qwertasd'):
|
||||
buf = '403'
|
||||
print(buf)
|
||||
buf = bytes(buf,encoding="utf-8")
|
||||
self.wfile.write(buf)
|
||||
return
|
||||
|
||||
#if('python-list' == type):
|
||||
if(len(wavs)>0):
|
||||
r = self.recognize([wavs], fs)
|
||||
else:
|
||||
r = ''
|
||||
#else:
|
||||
# r = self.recognize_from_file('')
|
||||
|
||||
if(token == 'qwertasd'):
|
||||
#buf = '成功\n'+'wavs:\n'+str(wavs)+'\nfs:\n'+str(fs)
|
||||
buf = r
|
||||
else:
|
||||
buf = '403'
|
||||
|
||||
#print(datas)
|
||||
|
||||
self._set_response()
|
||||
|
||||
#buf = '<!DOCTYPE HTML> \n<html> \n<head>\n<title>Post page</title>\n</head> \n<body>Post Data:%s <br />Path:%s\n</body> \n</html>'%(datas,self.path)
|
||||
print(buf)
|
||||
buf = bytes(buf,encoding="utf-8")
|
||||
self.wfile.write(buf)
|
||||
|
||||
def recognize(self, wavs, fs):
|
||||
r=''
|
||||
try:
|
||||
r_speech = ms.RecognizeSpeech(wavs, fs)
|
||||
print(r_speech)
|
||||
str_pinyin = r_speech
|
||||
r = ml.SpeechToText(str_pinyin)
|
||||
except:
|
||||
r=''
|
||||
print('[*Message] Server raise a bug. ')
|
||||
return r
|
||||
pass
|
||||
|
||||
def recognize_from_file(self, filename):
|
||||
pass
|
||||
|
||||
import socket
|
||||
class ASRTHTTPHandle(http.server.BaseHTTPRequestHandler):
|
||||
def setup(self):
|
||||
self.request.settimeout(10)
|
||||
http.server.BaseHTTPRequestHandler.setup(self)
|
||||
|
||||
def _set_response(self):
|
||||
self.send_response(200)
|
||||
self.send_header('Content-type', 'text/html')
|
||||
self.end_headers()
|
||||
|
||||
def do_GET(self):
|
||||
buf = 'ASRT_SpeechRecognition API'
|
||||
self.protocal_version = 'HTTP/1.1'
|
||||
|
||||
self._set_response()
|
||||
|
||||
buf = bytes(buf,encoding="utf-8")
|
||||
self.wfile.write(buf)
|
||||
|
||||
def do_POST(self):
|
||||
'''
|
||||
处理通过POST方式传递过来并接收的语音数据
|
||||
通过语音模型和语言模型计算得到语音识别结果并返回
|
||||
'''
|
||||
path = self.path
|
||||
print(path)
|
||||
#获取post提交的数据
|
||||
datas = self.rfile.read(int(self.headers['content-length']))
|
||||
#datas = urllib.unquote(datas).decode("utf-8", 'ignore')
|
||||
datas = datas.decode('utf-8')
|
||||
datas_split = datas.split('&')
|
||||
token = ''
|
||||
fs = 0
|
||||
wavs = []
|
||||
|
||||
for line in datas_split:
|
||||
[key, value]=line.split('=')
|
||||
if('wavs' == key and '' != value):
|
||||
wavs.append(int(value))
|
||||
elif('fs' == key):
|
||||
fs = int(value)
|
||||
elif('token' == key ):
|
||||
token = value
|
||||
#elif('type' == key):
|
||||
# type = value
|
||||
else:
|
||||
print(key, value)
|
||||
|
||||
if(token != 'qwertasd'):
|
||||
buf = '403'
|
||||
print(buf)
|
||||
buf = bytes(buf,encoding="utf-8")
|
||||
self.wfile.write(buf)
|
||||
return
|
||||
|
||||
if(len(wavs)>0):
|
||||
r = self.recognize([wavs], fs)
|
||||
else:
|
||||
r = ''
|
||||
|
||||
if(token == 'qwertasd'):
|
||||
buf = r
|
||||
else:
|
||||
buf = '403'
|
||||
|
||||
self._set_response()
|
||||
|
||||
print(buf)
|
||||
buf = bytes(buf,encoding="utf-8")
|
||||
self.wfile.write(buf)
|
||||
|
||||
def recognize(self, wavs, fs):
|
||||
r=''
|
||||
try:
|
||||
r_speech = ms.RecognizeSpeech(wavs, fs)
|
||||
print(r_speech)
|
||||
str_pinyin = r_speech
|
||||
r = ml.SpeechToText(str_pinyin)
|
||||
except Exception as ex:
|
||||
r=''
|
||||
print('[*Message] Server raise a bug. ', ex)
|
||||
return r
|
||||
pass
|
||||
|
||||
def recognize_from_file(self, filename):
|
||||
pass
|
||||
|
||||
|
||||
class HTTPServerV6(http.server.HTTPServer):
|
||||
address_family = socket.AF_INET6
|
||||
address_family = socket.AF_INET6
|
||||
|
||||
|
||||
def start_server(ip, port):
|
||||
|
||||
if(':' in ip):
|
||||
http_server = HTTPServerV6((ip, port), TestHTTPHandle)
|
||||
else:
|
||||
http_server = http.server.HTTPServer((ip, int(port)), TestHTTPHandle)
|
||||
|
||||
print('服务器已开启')
|
||||
|
||||
try:
|
||||
http_server.serve_forever() #设置一直监听并接收请求
|
||||
except KeyboardInterrupt:
|
||||
pass
|
||||
http_server.server_close()
|
||||
print('HTTP server closed')
|
||||
|
||||
if(':' in ip):
|
||||
http_server = HTTPServerV6((ip, port), ASRTHTTPHandle)
|
||||
else:
|
||||
http_server = http.server.HTTPServer((ip, int(port)), ASRTHTTPHandle)
|
||||
|
||||
print('服务器已开启')
|
||||
|
||||
try:
|
||||
http_server.serve_forever() #设置一直监听并接收请求
|
||||
except KeyboardInterrupt:
|
||||
pass
|
||||
http_server.server_close()
|
||||
print('HTTP server closed')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
start_server('', 20000) # For IPv4 Network Only
|
||||
#start_server('::', 20000) # For IPv6 Network
|
||||
|
||||
|
||||
|
||||
|
||||
start_server('', 20000) # For IPv4 Network Only
|
||||
#start_server('::', 20000) # For IPv6 Network
|
||||
|
|
|
@ -1,8 +1,27 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
'''
|
||||
获取符号字典列表的程序
|
||||
'''
|
||||
|
||||
import platform as plat
|
||||
|
||||
def GetSymbolList(datapath):
|
||||
|
|
|
@ -1,5 +1,22 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
import os
|
||||
import wave
|
||||
|
|
|
@ -1,5 +1,22 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
'''
|
||||
一些通用函数
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
'''
|
||||
感谢原作者的无私奉献
|
||||
来自:
|
||||
|
|
|
@ -1,5 +1,22 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
import platform as plat
|
||||
import os
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
'''
|
||||
@author: nl8590687
|
||||
一个对于单一音频时间长度不作限制的版本,正在测试
|
||||
|
|
|
@ -1,3 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
import pyaudio
|
||||
import wave
|
||||
|
||||
|
|
22
test.py
22
test.py
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
用于测试整个一套语音识别系统的程序
|
||||
|
@ -16,7 +34,7 @@ modelpath = 'model_speech'
|
|||
|
||||
system_type = plat.system() # 由于不同的系统的文件路径表示不一样,需要进行判断
|
||||
if(system_type == 'Windows'):
|
||||
datapath = 'D:\\语音数据集'
|
||||
datapath = 'Z:\\SpeechData'
|
||||
modelpath = modelpath + '\\'
|
||||
elif(system_type == 'Linux'):
|
||||
datapath = 'dataset'
|
||||
|
@ -29,7 +47,7 @@ else:
|
|||
ms = ModelSpeech(datapath)
|
||||
|
||||
#ms.LoadModel(modelpath + 'm22_2\\0\\speech_model22_e_0_step_257000.model')
|
||||
ms.LoadModel(modelpath + 'm251\\speech_model251_e_0_step_12000.model')
|
||||
ms.LoadModel(modelpath + 'm251\\speech_model251_e_0_step_625000.model')
|
||||
|
||||
#ms.TestModel(datapath, str_dataset='test', data_count = 64, out_report = True)
|
||||
r = ms.RecognizeSpeech_FromFile('D:\\语音数据集\\ST-CMDS-20170001_1-OS\\20170001P00241I0052.wav')
|
||||
|
|
|
@ -1,5 +1,22 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
'''
|
||||
@author: nl8590687
|
||||
|
@ -11,10 +28,9 @@ import requests
|
|||
from general_function.file_wav import *
|
||||
|
||||
url = 'http://127.0.0.1:20000/'
|
||||
|
||||
token = 'qwertasd'
|
||||
|
||||
wavsignal,fs=read_wav_data('D:\\语音数据集\\ST-CMDS-20170001_1-OS\\20170001P00241I0052.wav')
|
||||
wavsignal,fs=read_wav_data('X:\\语音数据集\\data_thchs30\\train\\A11_0.wav')
|
||||
|
||||
#print(wavsignal,fs)
|
||||
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
用于测试语音识别系统语音模型的程序
|
||||
|
|
|
@ -1,5 +1,23 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright 2016-2099 Ailemon.net
|
||||
#
|
||||
# This file is part of ASRT Speech Recognition Tool.
|
||||
#
|
||||
# ASRT is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
# ASRT is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with ASRT. If not, see <https://www.gnu.org/licenses/>.
|
||||
# ============================================================================
|
||||
|
||||
"""
|
||||
@author: nl8590687
|
||||
用于训练语音识别系统语音模型的程序
|
||||
|
|
Loading…
Reference in New Issue