2023-05-12 19:54:08,395 INFO [decode.py:678] Decoding started
2023-05-12 19:54:08,396 INFO [decode.py:684] Device: cuda:0
2023-05-12 19:54:08,399 INFO [decode.py:694] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '7efe024b23078ffa0bcb5598afff14f356edae7c', 'k2-git-date': 'Mon Jan 30 20:22:57 2023', 'lhotse-version': '1.12.0.dev+git.891bad1.clean', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'zipformer2_from_dan', 'icefall-git-sha1': 'ec211286-clean', 'icefall-git-date': 'Fri May 12 18:45:00 2023', 'icefall-path': '/ceph-zw/workspace/zipformer/icefall_zipformer', 'k2-path': '/ceph-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-zw/workspace/share/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mlpzc', 'IP address': '10.177.22.19'}, 'epoch': 40, 'iter': 0, 'avg': 13, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-small'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 20.0, 'ngram_lm_scale': 0.01, 'max_contexts': 8, 'max_states': 64, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,2,2,2,2,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,768,768,768,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,256,256,256,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,192,192,192,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'res_dir': PosixPath('zipformer/exp-small/fast_beam_search'), 'suffix': 'epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2023-05-12 19:54:08,399 INFO [decode.py:696] About to create model
2023-05-12 19:54:08,717 INFO [decode.py:763] Calculating the averaged model over epoch range from 27 (excluded) to 40
2023-05-12 19:54:17,225 INFO [decode.py:799] Number of model parameters: 23285615
2023-05-12 19:54:17,225 INFO [asr_datamodule.py:465] About to get test-clean cuts
2023-05-12 19:54:17,227 INFO [asr_datamodule.py:472] About to get test-other cuts
2023-05-12 19:54:19,489 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
2023-05-12 19:54:50,250 INFO [decode.py:570] batch 20/?, cuts processed until now is 1430
2023-05-12 19:55:26,411 INFO [decode.py:570] batch 40/?, cuts processed until now is 2574
2023-05-12 19:55:27,646 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/fast_beam_search/recogs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
2023-05-12 19:55:27,719 INFO [utils.py:558] [test-clean-beam_20.0_max_contexts_8_max_states_64] %WER 2.46% [1293 / 52576, 140 ins, 99 del, 1054 sub ]
2023-05-12 19:55:27,901 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/fast_beam_search/errs-test-clean-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
2023-05-12 19:55:27,902 INFO [decode.py:618] 
For test-clean, WER of different settings are:
beam_20.0_max_contexts_8_max_states_64	2.46	best for test-clean

2023-05-12 19:55:30,060 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
2023-05-12 19:55:31,589 INFO [zipformer.py:1655] name=None, attn_weights_entropy = tensor([1.7907, 2.3585, 2.2052, 2.4565, 1.4741, 2.4270, 2.5435, 2.4639],
       device='cuda:0')
2023-05-12 19:55:56,008 INFO [decode.py:570] batch 20/?, cuts processed until now is 1646
2023-05-12 19:56:24,127 INFO [decode.py:570] batch 40/?, cuts processed until now is 2870
2023-05-12 19:56:25,044 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/fast_beam_search/recogs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
2023-05-12 19:56:25,118 INFO [utils.py:558] [test-other-beam_20.0_max_contexts_8_max_states_64] %WER 5.87% [3073 / 52343, 320 ins, 252 del, 2501 sub ]
2023-05-12 19:56:25,296 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/fast_beam_search/errs-test-other-beam_20.0_max_contexts_8_max_states_64-epoch-40-avg-13-beam-20.0-max-contexts-8-max-states-64-use-averaged-model.txt
2023-05-12 19:56:25,297 INFO [decode.py:618] 
For test-other, WER of different settings are:
beam_20.0_max_contexts_8_max_states_64	5.87	best for test-other

2023-05-12 19:56:25,297 INFO [decode.py:830] Done!