Created by: jiaozhusos

使用aishell模型进行中文识别，感觉非常慢，而且效果也不好。 另外，想基于baidu_1.2k_model进行识别，但是模型里没有vocab.text，此外，相应的warmup_manifest也没有，需要怎么进行设置呢? （待识别的数据本来是一条3-5min的，但是实在太慢，就换成aishell的其中一条wav数据了，只有几秒钟，还是非常慢，等了很久也没有最终的结果出来，是我的设置有问题吗还是参数需要调整一下？） ----------- Configuration Arguments ----------- alpha: 2.5 beam_size: 500 beta: 0.3 cutoff_prob: 0.99 cutoff_top_n: 40 decoding_method: ctc_beam_search host_ip: localhost host_port: 8086 lang_model_path: models/lm/zh_giga.no_cna_cmn.prune01244.klm mean_std_path: models/aishell/mean_std.npz model_path: models/aishell/params.tar.gz num_conv_layers: 2 num_rnn_layers: 3 rnn_layer_size: 2048 share_rnn_weights: True specgram_type: linear speech_save_dir: my_data use_gpu: False use_gru: 1 vocab_path: data/aishell/vocab.txt warmup_manifest: data/aishell/manifest.test

I0506 15:04:53.478561 3892 Util.cpp:166] commandline: --use_gpu=False --trainer_count=1 [INFO 2018-05-06 15:04:53,587 layers.py:2689] output for conv_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2018-05-06 15:04:53,588 layers.py:3251] output for batch_norm_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2018-05-06 15:04:53,589 layers.py:7409] output for scale_sub_region_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2018-05-06 15:04:53,590 layers.py:2689] output for conv_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2018-05-06 15:04:53,591 layers.py:3251] output for batch_norm_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2018-05-06 15:04:53,591 layers.py:7409] output for scale_sub_region_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2018-05-06 15:05:00,766 model.py:243] begin to initialize the external scorer for decoding [INFO 2018-05-06 15:05:06,010 model.py:253] language model: is_character_based = 1, max_order = 5, dict_size = 0 [INFO 2018-05-06 15:05:06,010 model.py:254] end initializing scorer

Warming up ... ('Warm-up Test Case %d: %s', 0, u'/home/hwja/.cache/paddle/dataset/speech/Aishell/data_aishell/wav/test/S0913/BAC009S0913W0441.wav') Response Time: 51.677608, Transcript: 篮 ('Warm-up Test Case %d: %s', 1, u'/home/hwja/.cache/paddle/dataset/speech/Aishell/data_aishell/wav/test/S0912/BAC009S0912W0243.wav') Response Time: 46.002436, Transcript: 篮 ('Warm-up Test Case %d: %s', 2, u'/home/hwja/.cache/paddle/dataset/speech/Aishell/data_aishell/wav/test/S0902/BAC009S0902W0189.wav') Response Time: 40.113678, Transcript: 篮

ASR Server Started.