def testModel():
import difflib
import tensorflow as tf
import numpy as np
yysb = utils.SpeechRecognition()
# 1. 准备测试所需数据， 不必和训练数据一致，通过设置data_args.data_type测试，
data_args = utils.data_hparams()
data_args.data_type = 'test'
data_args.shuffle = True
data_args.batch_size = 1
test = utils.get_data(data_args)
# 2. 进行测试-------------------------------------------
word_num = 0
word_error_num = 0
for i in range(100):
print('\n 第 ', i, ' 个例子')
label = test.han_lst[i]
pinyin, hanzi = yysb.predict(os.path.join(test.data_path,
test.wav_lst[i]),
test.pny_lst[i],
label,
come_from_file=True)
#hanzi = yysb.testPinyin(' '.join(test.pny_lst[i]))#单独测试语言模型用
word_error_num += min(len(label), utils.GetEditDistance(label, hanzi))
word_num += len(label)
print('词错误率：', word_error_num / word_num)
def testClient():
import requests
import scipy
data_args = utils.data_hparams()
test = utils.get_data(data_args)
_,wav = scipy.io.wavfile.read(os.path.join('/media/yangjinming/DATA/Dataset',test.wav_lst[0]))
datas={'token':'SR', 'data':wav,'pre_type':'H'}
r = requests.post('http://127.0.0.1:20000/', datas)
r.encoding='utf-8'
print(r.text)
#coding=utf-8
import os
import difflib
import tensorflow as tf
import numpy as np
from utils import decode_ctc, GetEditDistance
# 0.准备解码所需字典，参数需和训练一致，也可以将字典保存到本地，直接进行读取
from utils import get_data, data_hparams
data_args = data_hparams()
train_data = get_data(data_args)
# 1.声学模型-----------------------------------
from model_speech.cnn_ctc import Am, am_hparams
am_args = am_hparams() # 參數初始化 EX: learning rate
# am_args.vocab_size = 230
am_args.vocab_size = len(train_data.am_vocab) # 設定單字長度
am = Am(am_args) # 利用設定好的參數，建造出一個model
print('loading acoustic model...')
am.ctc_model.load_weights('logs_am/model.h5')
am.ctc_model.summary()
# 2.语言模型-------------------------------------------
from model_language.transformer import Lm, lm_hparams
lm_args = lm_hparams()
lm_args.input_vocab_size = len(train_data.pny_vocab)
lm_args.label_vocab_size = len(train_data.han_vocab)
from utils import get_data, data_hparams # 0.准备训练所需数据------------------------------ train_data_args = data_hparams() train_data_args.data_type = 'train' train_data_args.data_path = 'E:/data/corpus/' train_data_args.thchs30 = True train_data_args.aishell = True train_data_args.prime = True train_data_args.stcmd = True train_data_args.batch_size = 4 train_data_args.data_length = 500 # data_args.data_length = None train_data_args.shuffle = False train_data = get_data(train_data_args) # 0.准备验证所需数据------------------------------ dev_data_args = data_hparams() dev_data_args.data_type = 'dev' dev_data_args.data_path = 'E:/data/corpus/' dev_data_args.thchs30 = True dev_data_args.aishell = True dev_data_args.prime = False dev_data_args.stcmd = False dev_data_args.batch_size = 4 # data_args.data_length = None dev_data_args.data_length = 100 dev_data_args.shuffle = True dev_data = get_data(dev_data_args)
import tensorflow as tf
import utils
from tqdm import tqdm
import keras
from keras.callbacks import ModelCheckpoint,EarlyStopping,TensorBoard
import numpy as np
config = tf.ConfigProto()
config.gpu_options.allow_growth = True #不全部占满显存, 按需分配
keras.backend.tensorflow_backend.set_session(tf.Session(config=config))
from datetime import datetime
modelVersion = str(datetime.now())[2:10].replace("-", "")
# 0.准备训练所需数据------------------------------
data_args = utils.data_hparams()
data_args.data_type = 'train'
#data_args.thchs30 = True
#data_args.aishell = True
#data_args.prime = True
#data_args.stcmd = True
data_args.batch_size = 16#可以将不一次性训练am和lm，同样显存情况下lm的batch_size可以比am的大许多
train_data = utils.get_data(data_args)
# 0.准备验证所需数据------------------------------
data_args = utils.data_hparams()
data_args.data_type = 'dev'
#data_args.thchs30 = True
#data_args.aishell = True
#data_args.prime = True
#data_args.stcmd = True
