def test_batch():
data_args.data_type = 'test'
data_args.shuffle = False
data_args.batch_size = 1
test_data = get_data(data_args)
am_batch = test_data.get_am_batch()
word_num = 0
word_error_num = 0
for i in range(10):
print('\n the ', i, 'th example.')
# 载入训练好的模型，并进行识别
inputs, _ = next(am_batch)
x = inputs['the_inputs']
y = test_data.pny_lst[i]
result = am.model.predict(x, steps=1)
# 将数字结果转化为文本结果
_, text = decode_ctc(result, train_data.am_vocab)
text = ' '.join(text)
print('文本结果：', text)
print('原文结果：', ' '.join(y))
with sess.as_default():
text = text.strip('\n').split(' ')
x = np.array([train_data.pny_vocab.index(pny) for pny in text])
x = x.reshape(1, -1)
preds = sess.run(lm.preds, {lm.x: x})
label = test_data.han_lst[i]
got = ''.join(train_data.han_vocab[idx] for idx in preds[0])
print('原文汉字：', label)
print('识别结果：', got)
word_error_num += min(len(label), GetEditDistance(label, got))
word_num += len(label)
print('词错误率：', word_error_num / word_num)
sess.close()
# 4. 进行测试-------------------------------------------
am_batch = test_data.get_am_batch()
word_num = 0
word_error_num = 0
for i in range(10):
print('\n the ', i, 'th example.')
# 载入训练好的模型，并进行识别
inputs, _ = next(am_batch)
x = inputs['the_inputs']
y = test_data.pny_lst[i]
result = am.model.predict(x, steps=1)
# 将数字结果转化为文本结果
_, text = decode_ctc(result, train_data.am_vocab)
text = ' '.join(text)
print('文本結果：', text)
print('原文結果：', ' '.join(y))
with sess.as_default():
text = text.strip('\n').split(' ')
x = np.array([train_data.pny_vocab.index(pny) for pny in text])
x = x.reshape(1, -1)
preds = sess.run(lm.preds, {lm.x: x})
label = test_data.han_lst[i]
got = ''.join(train_data.han_vocab[idx] for idx in preds[0])
print('原文漢字：', label)
print('识别結果：', got)
word_error_num += min(len(label), GetEditDistance(label, got))
word_num += len(label)
print('詞错誤率：', word_error_num / word_num)
sess.close()
am_args = am_hparams()
am_args.vocab_size = len(am_vocab)
am = Am(am_args)
print('loading acoustic model...')
am.ctc_model.load_weights(model_save_path)
data_args.data_type = 'test'
data_args.shuffle = False
data_args.batch_size = 1
test_data = get_data(data_args)
# 4. 进行测试-------------------------------------------
am_batch = test_data.get_am_batch()
word_num = 0
word_error_num = 0
for i in range(1):
print('\n the ', i, 'th example.')
# 载入训练好的模型，并进行识别
inputs, _ = next(am_batch)
x = inputs['the_inputs']
y = test_data.pny_lst[i]
result = am.model.predict(x, steps=1)
# 将数字结果转化为文本结果
_, text = decode_ctc(result, am_vocab)
text = ' '.join(text)
print('文本结果：', text)
print('原文结果：', ' '.join(y))
word_error_num += min(len(y), GetEditDistance(y, text.split(' ')))
word_num += len(y)
print('词错误率：', word_error_num / word_num)
def recognize(args):
model, LFR_m, LFR_n = Transformer.load_model(args.model_path)
print(model)
model.eval()
model.cuda()
char_list, sos_id, eos_id = process_dict(args.dict)
assert model.decoder.sos_id == sos_id and model.decoder.eos_id == eos_id
tr_dataset = AudioDataset('test', args.batch_size)
path_list = tr_dataset.path_lst
label_list = tr_dataset.han_lst
num_data = tr_dataset.path_count
ran_num = random.randint(0, num_data - 1)
num = args.count
words_num = 0
word_error_num = 0
seq_error = 0
data = ''
with torch.no_grad():
for index in range(num):
try:
print('\nthe ', index + 1, 'th example.')
data += 'the ' + str(index + 1) + 'th example.\n'
index = (ran_num + index) % num_data
standard_label = label_list[index]
feature, label = get_fbank_and_hanzi_data(
index, args.feature_dim, char_list, path_list, label_list)
if len(feature) > 1600:
continue
input = build_LFR_features(feature, args.LFR_m, args.LFR_n)
input = torch.from_numpy(input).float()
input_length = torch.tensor([input.size(0)], dtype=torch.int)
input = input.cuda()
nbest_hyps = model.recognize(input, input_length, char_list,
args)
pred_label = nbest_hyps[0]['yseq'][1:-1]
pred_res = ''.join([char_list[index] for index in pred_label])
print("stand:", label)
print("pred :", pred_label)
data += "stand:" + str(standard_label) + '\n'
data += "pred :" + str(pred_res) + '\n'
words_n = len(label)
words_num += words_n
word_distance = GetEditDistance(pred_label, label)
if (word_distance <= words_n):
word_error_num += word_distance
else:
word_error_num += words_n
if pred_label != label:
seq_error += 1
except ValueError:
continue
print('WER = ', (1 - word_error_num / words_num) * 100, '%')
print('CER = ', (1 - seq_error / args.count) * 100, '%')
data += 'WER = ' + str((1 - word_error_num / words_num) * 100) + '%'
data += 'CER = ' + str((1 - seq_error / args.count) * 100) + '%'
with open('../../model_log/pred/test_' + str(args.count) + '.txt',
'w',
encoding='utf-8') as f:
f.writelines(data)