Created by: tianchaolangzi

----------- Configuration Arguments ----------- alpha: 2.6 batch_size: 128 beam_size: 300 beta: 5.0 cutoff_prob: 0.99 cutoff_top_n: 40 decoding_method: ctc_beam_search error_rate_type: cer lang_model_path: models/lm/zh_giga.no_cna_cmn.prune01244.klm mean_std_path: models/aishell/mean_std.npz model_path: models/aishell num_conv_layers: 2 num_proc_bsearch: 8 num_rnn_layers: 3 rnn_layer_size: 1024 share_rnn_weights: 0 specgram_type: linear test_manifest: data/aishell/manifest.test use_gpu: 1 use_gru: 1 vocab_path: models/aishell/vocab.txt

2020-01-20 01:43:38,386-INFO: begin to initialize the external scorer for decoding 2020-01-20 01:43:38,501-INFO: language model: is_character_based = 1, max_order = 5, dict_size = 0 2020-01-20 01:43:38,501-INFO: end initializing scorer 2020-01-20 01:43:38,502-INFO: start evaluation ... Traceback (most recent call last): File "test.py", line 149, in main() File "test.py", line 145, in main evaluate() File "test.py", line 110, in evaluate for infer_data in batch_reader(): File "/media/zzzzzzk/HDD4T/zk/DeepSpeech/data_utils/data.py", line 206, in batch_reader yield self._padding_batch(batch, padding_to, flatten) File "/media/zzzzzzk/HDD4T/zk/DeepSpeech/data_utils/data.py", line 336, in _padding_batch texts = np.expand_dims(np.array(texts).astype('int32'), axis=-1) UnicodeEncodeError: 'decimal' codec can't encode characters in position 0-11: invalid decimal Unicode string Failed in evaluation!