Created by: 18811737901

/data/DeepSpeech2/deploy$ CUDA_VISIBLE_DEVICES=0 python2 demo_server.py --host_ip localhost --host_port 8086 --use_gpu False ----------- Configuration Arguments ----------- alpha: 2.5 beam_size: 500 beta: 0.3 cutoff_prob: 1.0 cutoff_top_n: 40 decoding_method: ctc_beam_search host_ip: localhost host_port: 8086 lang_model_path: /data/DeepSpeech2/models/lm/zh_giga.no_cna_cmn.prune01244.klm mean_std_path: /data/DeepSpeech2/models/aishell/mean_std.npz model_path: /data/DeepSpeech2/checkpoints/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: /data/DeepSpeech2/gintong use_gpu: 0 use_gru: False vocab_path: /data/DeepSpeech2/models/aishell/vocab.txt warmup_manifest: /data/DeepSpeech2/data/aishell/manifest.test

I0927 15:58:18.889097 2591 Util.cpp:166] commandline: --use_gpu=0 --trainer_count=1 W0927 15:58:18.889184 2591 CpuId.h:112] PaddlePaddle wasn't compiled to use avx instructions, but these are available on your machine and could speed up CPU computations via CMAKE .. -DWITH_AVX=ON [INFO 2018-09-27 15:58:18,964 layers.py:2716] output for conv_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2018-09-27 15:58:18,966 layers.py:3361] output for batch_norm_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2018-09-27 15:58:18,967 layers.py:7533] output for scale_sub_region_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2018-09-27 15:58:18,968 layers.py:2716] output for conv_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2018-09-27 15:58:18,969 layers.py:3361] output for batch_norm_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2018-09-27 15:58:18,971 layers.py:7533] output for scale_sub_region_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2018-09-27 15:58:26,537 model.py:243] begin to initialize the external scorer for decoding [INFO 2018-09-27 15:58:26,657 model.py:253] language model: is_character_based = 1, max_order = 5, dict_size = 0 [INFO 2018-09-27 15:58:26,657 model.py:254] end initializing scorer

Warming up ... ('Warm-up Test Case %d: %s', 0, u'/data/.cache/paddle/dataset/speech/Aishell/data_aishell/wav/test/S0913/BAC009S0913W0419.wav') Traceback (most recent call last): File "demo_server.py", line 215, in main() File "demo_server.py", line 211, in main start_server() File "demo_server.py", line 195, in start_server num_test_cases=3) File "demo_server.py", line 135, in warm_up_test transcript = audio_process_handler(sample['audio_filepath']) File "demo_server.py", line 171, in file_to_transcript feeding_dict=data_generator.feeding) File "/data/DeepSpeech2/deploy/../model_utils/model.py", line 193, in infer_batch_probs output_layer=self._log_probs, parameters=self._parameters) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/inference.py", line 64, in init val.copyFromNumpyArray(parameters.get(name).flatten()) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/parameters.py", line 242, in get return self.getitem(key=parameter_name) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/parameters.py", line 186, in getitem return self.__getter_inner(key, api.PARAMETER_VALUE) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/parameters.py", line 153, in __getter_inner shape = self.get_shape(key) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/parameters.py", line 200, in get_shape raise ValueError("No such parameter %s" % key) ValueError: No such parameter _recurrent_layer_0.w0