def ctc_cost2(self):
#data = self.data
data = DataSpeech(self.datapath)
data.LoadDataList('dev')
x = next(data.data_genetator(32, self.AUDIO_LENGTH))
[test_input_data, y, test_input_length, label_length], labels = x
xx = [test_input_data, y, test_input_length, label_length]
y_pred2 = self._model.predict(xx)
_mean = sum(y_pred2) / len(y_pred2)
print(y_pred2, _mean)
return _mean
def __init__(self, datapath):
'''
初始化
默认输出的拼音的表示大小是1283，即1282个拼音+1个空白块
'''
MS_OUTPUT_SIZE = 1417
self.MS_OUTPUT_SIZE = MS_OUTPUT_SIZE # 神经网络最终输出的每一个字符向量维度的大小
#self.BATCH_SIZE = BATCH_SIZE # 一次训练的batch
self.label_max_string_length = 64
self.AUDIO_LENGTH = 1600
self.AUDIO_FEATURE_LENGTH = 200
self.datapath = datapath
self.data = DataSpeech(datapath)
self._model = self.CreateModel()
def RecognizeSpeech(self, wavsignal, fs):
'''
最终做语音识别用的函数，识别一个wav序列的语音
不过这里现在还有bug
'''
#data = self.data
data = DataSpeech('E:\\语音数据集')
data.LoadDataList('dev')
# 获取输入特征
#data_input = data.GetMfccFeature(wavsignal, fs)
data_input = data.GetFrequencyFeature(wavsignal, fs)
list_symbol_dic = data.list_symbol # 获取拼音列表
labels = [
'dong1', 'bei3', 'jun1', 'de5', 'yi4', 'xie1', 'ai4', 'guo2',
'jiang4', 'shi4', 'ma3', 'zhan4', 'shan1', 'li3', 'du4', 'tang2',
'ju4', 'wu3', 'su1', 'bing3', 'ai4', 'deng4', 'tie3', 'mei2',
'deng3', 'ye3', 'fen4', 'qi3', 'kang4', 'zhan4'
]
#labels = [ list_symbol_dic[-1] ]
#labels = [ list_symbol_dic[-1] ]
#while(len(labels) < 32):
# labels.append(list_symbol_dic[-1])
feat_out = []
#print("数据编号",n_start,filename)
for i in labels:
if ('' != i):
n = data.SymbolToNum(i)
feat_out.append(n)
print(feat_out)
labels = feat_out
x = next(
self.data_gen(data_input=np.array(data_input),
data_labels=np.array(labels),
input_length=len(data_input),
labels_length=len(labels),
batch_size=2))
[test_input_data, y, test_input_length, label_length], labels = x
xx = [test_input_data, y, test_input_length, label_length]
pred = self._model.predict(x=xx)
print(pred)
shape = pred[:, :].shape
print(shape)
print('test_input_data:', test_input_data)
y_p = self.test_func([test_input_data])
print(type(y_p))
print('y_p:', y_p)
for j in range(0, 0):
mean = sum(y_p[0][0][j]) / len(y_p[0][0][j])
print('max y_p:', max(y_p[0][0][j]), 'min y_p:', min(y_p[0][0][j]),
'mean y_p:', mean, 'mid y_p:', y_p[0][0][j][100])
print('argmin:', np.argmin(y_p[0][0][j]), 'argmax:',
np.argmax(y_p[0][0][j]))
count = 0
for i in y_p[0][0][j]:
if (i < mean):
count += 1
print('count:', count)
print(K.is_sparse(y_p))
#y_p = K.to_dense(y_p)
print(K.is_sparse(y_p))
_list = []
for i in y_p:
list_i = []
for j in i:
list_j = []
for k in j:
list_j.append(np.argmin(k))
list_i.append(list_j)
_list.append(list_i)
#y_p = np.array(_list, dtype = np.float)
y_p = _list
#print(y_p,type(y_p),y_p.shape)
#y_p = tf.sparse_to_dense(y_p,(2,397),1417,0)
print(test_input_length.T)
test_input_length = test_input_length.reshape(2, 1)
func_in_len = self.test_func_input_length([test_input_length])
print(type(func_in_len))
print(func_in_len)
#in_len = np.ones(shape[0]) * shape[1]
ctc_decoded = K.ctc_decode(y_p[0][0],
input_length=tf.squeeze(
func_in_len[0][0][0]))
print(ctc_decoded)
#ctc_decoded = ctc_decoded[0][0]
#out = K.get_value(ctc_decoded)[:,:64]
#pred = self._model.predict_on_batch([data_input, labels_num, input_length, label_length])
return pred[0][0]
pass