def TrainModel(self, datapath, epoch = 2, save_step = 1000, batch_size = 32, filename = 'model_speech/speech_model2'):
'''
训练模型
参数：
datapath: 数据保存的路径
epoch: 迭代轮数
save_step: 每多少步保存一次模型
filename: 默认保存文件名，不含文件后缀名
'''
data=DataSpeech(datapath, 'train')
#data.LoadDataList()
num_data = data.GetDataNum() # 获取数据的数量
for epoch in range(epoch): # 迭代轮数
print('[running] train epoch %d .' % epoch)
n_step = 0 # 迭代数据数
while True:
try:
print('[message] epoch %d . Have train datas %d+'%(epoch, n_step*save_step))
# data_genetator是一个生成器函数
yielddatas = data.data_genetator(batch_size, self.AUDIO_LENGTH)
#self._model.fit_generator(yielddatas, save_step, nb_worker=2)
self._model.fit_generator(yielddatas, save_step)
n_step += 1
except StopIteration:
print('[error] generator error. please check data format.')
break
self.SaveModel(comment='_e_'+str(epoch)+'_step_'+str(n_step * save_step))
self.TestModel(self.datapath, str_dataset='train', data_count = 4)
self.TestModel(self.datapath, str_dataset='dev', data_count = 4)
def TestModel(self, datapath='', str_dataset='dev', data_count=32):
'''
测试检验模型效果
'''
data = DataSpeech(self.datapath, str_dataset)
#data.LoadDataList(str_dataset)
num_data = data.GetDataNum() # 获取数据的数量
if (data_count <= 0 or data_count >
num_data): # 当data_count为小于等于0或者大于测试数据量的值时，则使用全部数据来测试
data_count = num_data
try:
ran_num = random.randint(0, num_data - 1) # 获取一个随机数
words_num = 0
word_error_num = 0
for i in range(data_count):
data_input, data_labels = data.GetData(
(ran_num + i) % num_data) # 从随机数开始连续向后取一定数量数据
pre = self.Predict(data_input, data_input.shape[0] // 4)
words_num += max(data_labels.shape[0], pre.shape[0])
word_error_num += GetEditDistance(data_labels, pre)
print('*[测试结果] 语音识别 ' + str_dataset + ' 集语音单字错误率：',
word_error_num / words_num * 100, '%')
except StopIteration:
print('[Error] Model Test Error. please check data format.')
def TestModel(self,
datapath='',
str_dataset='dev',
data_count=32,
out_report=False):
'''
测试检验模型效果
'''
data = DataSpeech(self.datapath, str_dataset)
#data.LoadDataList(str_dataset)
num_data = data.GetDataNum() # 获取数据的数量
if (data_count <= 0 or data_count >
num_data): # 当data_count为小于等于0或者大于测试数据量的值时，则使用全部数据来测试
data_count = num_data
try:
ran_num = random.randint(0, num_data - 1) # 获取一个随机数
words_num = 0
word_error_num = 0
nowtime = time.strftime('%Y%m%d_%H%M%S',
time.localtime(time.time()))
if (out_report == True):
txt_obj = open('Test_Report_' + str_dataset + '_' + nowtime +
'.txt',
'w',
encoding='UTF-8') # 打开文件并读入
txt = ''
for i in range(data_count):
data_input, data_labels = data.GetData(
(ran_num + i) % num_data) # 从随机数开始连续向后取一定数量数据
pre = self.Predict(data_input, data_input.shape[0] // 4)
words_n = data_labels.shape[0] # 获取每个句子的字数
words_num += words_n # 把句子的总字数加上
edit_distance = GetEditDistance(data_labels, pre) # 获取编辑距离
if (edit_distance <= words_n): # 当编辑距离小于等于句子字数时
word_error_num += edit_distance # 使用编辑距离作为错误字数
else: # 否则肯定是增加了一堆乱七八糟的奇奇怪怪的字
word_error_num += words_n # 就直接加句子本来的总字数就好了
if (out_report == True):
txt += str(i) + '\n'
txt += 'True:\t' + str(data_labels) + '\n'
txt += 'Pred:\t' + str(pre) + '\n'
txt += '\n'
print('*[测试结果] 语音识别 ' + str_dataset + ' 集语音单字错误率：',
word_error_num / words_num * 100, '%')
if (out_report == True):
txt += '*[测试结果] 语音识别 ' + str_dataset + ' 集语音单字错误率： ' + str(
word_error_num / words_num * 100) + ' %'
txt_obj.write(txt)
txt_obj.close()
except StopIteration:
print('[Error] Model Test Error. please check data format.')
def TestModel(self, datapath, str_dataset='dev'):
'''
测试检验模型效果
'''
data = DataSpeech(datapath)
data.LoadDataList(str_dataset)
num_data = DataSpeech.GetDataNum() # 获取数据的数量
try:
gen = data.data_genetator(num_data)
for i in range(1):
X, y = gen
r = self._model.test_on_batch(X, y)
print(r)
except StopIteration:
print('[Error] Model Test Error. please check data format.')