decoding_result/modified_beam_search/log-decode-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model-2023-05-16-15-41-47

2023-05-16 15:41:47,629 INFO [decode.py:678] Decoding started
2023-05-16 15:41:47,629 INFO [decode.py:684] Device: cuda:0
2023-05-16 15:41:47,632 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': '1.24.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'c51a0b9684442a88ee37f3ce0af686a04b66855b', 'k2-git-date': 'Mon May 1 21:38:03 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': '85d51991-dirty', 'icefall-git-date': 'Tue May 16 14:39:13 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': 30, 'iter': 0, 'avg': 8, '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': 'modified_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/modified_beam_search'), 'suffix': 'epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2023-05-16 15:41:47,632 INFO [decode.py:696] About to create model
2023-05-16 15:41:48,028 INFO [decode.py:763] Calculating the averaged model over epoch range from 22 (excluded) to 30
2023-05-16 15:41:53,415 INFO [decode.py:799] Number of model parameters: 23285615
2023-05-16 15:41:53,415 INFO [asr_datamodule.py:465] About to get test-clean cuts
2023-05-16 15:41:53,417 INFO [asr_datamodule.py:472] About to get test-other cuts
2023-05-16 15:41:57,779 INFO [decode.py:570] batch 0/?, cuts processed until now is 43
2023-05-16 15:42:59,578 INFO [zipformer.py:1711] name=None, attn_weights_entropy = tensor([2.7639, 3.0905, 3.5930, 3.2426], device='cuda:0')
2023-05-16 15:43:05,973 INFO [decode.py:570] batch 20/?, cuts processed until now is 1430
2023-05-16 15:44:01,839 INFO [decode.py:570] batch 40/?, cuts processed until now is 2574
2023-05-16 15:44:04,161 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/modified_beam_search/recogs-test-clean-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-05-16 15:44:04,241 INFO [utils.py:558] [test-clean-beam_size_4] %WER 2.60% [1366 / 52576, 152 ins, 106 del, 1108 sub ]
2023-05-16 15:44:04,415 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/modified_beam_search/errs-test-clean-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-05-16 15:44:04,416 INFO [decode.py:618] 
For test-clean, WER of different settings are:
beam_size_4	2.6	best for test-clean

2023-05-16 15:44:08,409 INFO [decode.py:570] batch 0/?, cuts processed until now is 52
2023-05-16 15:44:49,023 INFO [zipformer.py:1711] name=None, attn_weights_entropy = tensor([4.9292, 4.6428, 4.1287, 4.5603], device='cuda:0')
2023-05-16 15:45:14,322 INFO [decode.py:570] batch 20/?, cuts processed until now is 1646
2023-05-16 15:46:08,534 INFO [decode.py:570] batch 40/?, cuts processed until now is 2870
2023-05-16 15:46:10,635 INFO [decode.py:588] The transcripts are stored in zipformer/exp-small/modified_beam_search/recogs-test-other-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-05-16 15:46:10,800 INFO [utils.py:558] [test-other-beam_size_4] %WER 6.01% [3146 / 52343, 336 ins, 259 del, 2551 sub ]
2023-05-16 15:46:10,980 INFO [decode.py:601] Wrote detailed error stats to zipformer/exp-small/modified_beam_search/errs-test-other-beam_size_4-epoch-30-avg-8-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-05-16 15:46:10,981 INFO [decode.py:618] 
For test-other, WER of different settings are:
beam_size_4	6.01	best for test-other

2023-05-16 15:46:10,981 INFO [decode.py:830] Done!