78 lines
2.5 KiB
Python
78 lines
2.5 KiB
Python
#!/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
|
||
|
||
"""
|
||
import platform as plat
|
||
import os
|
||
|
||
import tensorflow as tf
|
||
#from tensorflow.keras.backend.tensorflow_backend import set_session
|
||
|
||
|
||
from SpeechModel251 import ModelSpeech
|
||
|
||
|
||
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
|
||
#进行配置，使用90%的GPU
|
||
config = tf.compat.v1.ConfigProto()
|
||
config.gpu_options.per_process_gpu_memory_fraction = 0.9
|
||
#config.gpu_options.allow_growth=True #不全部占满显存, 按需分配
|
||
sess = tf.compat.v1.Session(config=config)
|
||
tf.compat.v1.keras.backend.set_session(sess)
|
||
|
||
|
||
|
||
datapath = ''
|
||
modelpath = 'model_speech'
|
||
|
||
|
||
if(not os.path.exists(modelpath)): # 判断保存模型的目录是否存在
|
||
os.makedirs(modelpath) # 如果不存在，就新建一个，避免之后保存模型的时候炸掉
|
||
|
||
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:\\SpeechData'
|
||
modelpath = modelpath + '\\'
|
||
elif(system_type == 'Linux'):
|
||
datapath = 'dataset'
|
||
modelpath = modelpath + '/'
|
||
else:
|
||
print('*[Message] Unknown System\n')
|
||
datapath = 'dataset'
|
||
modelpath = modelpath + '/'
|
||
|
||
ms = ModelSpeech(datapath)
|
||
|
||
ms.LoadModel(modelpath + 'm251/speech_model251_e_0_step_42500.model')
|
||
|
||
ms.TestModel(datapath, str_dataset='test', data_count = 128, out_report = True)
|
||
|
||
#r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\ST-CMDS-20170001_1-OS\\20170001P00241I0053.wav')
|
||
#r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\ST-CMDS-20170001_1-OS\\20170001P00020I0087.wav')
|
||
#r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\wav\\train\\A11\\A11_167.WAV')
|
||
#r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\wav\\test\\D4\\D4_750.wav')
|
||
#print('*[提示] 语音识别结果：\n',r)
|
||
|
||
|