decoding_results/ctc-decoding/log-decode-epoch-25-avg-7-use-averaged-model-2022-11-27-20-36-25

2022-11-27 20:36:25,472 INFO [decode.py:772] Decoding started
2022-11-27 20:36:25,472 INFO [decode.py:778] Device: cuda:0
2022-11-27 20:36:25,472 INFO [decode.py:779] {'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, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'beam_size': 10, 'reduction': 'sum', 'use_double_scores': True, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.21', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '409a24f9035df693583f9b3fea17a5934bdb3bbf', 'k2-git-date': 'Wed Nov 2 18:17:39 2022', 'lhotse-version': '1.4.0.dev+git.21b5b3f.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'latency_k2_ctc', 'icefall-git-sha1': '7817199-dirty', 'icefall-git-date': 'Tue Nov 22 20:35:37 2022', 'icefall-path': '/ceph-zw/workspace/latency/icefall_k2_ctc', 'k2-path': '/ceph-zw/workspace/latency/k2_ctc_latency/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-jb/yaozengwei/workspace/rnnt/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-2-0602201035-5fb6d86964-mclm7', 'IP address': '10.177.74.202'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'epoch': 25, 'iter': 0, 'avg': 7, 'use_averaged_model': True, 'exp_dir': PosixPath('conformer_ctc3/exp-full'), 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 0.5, 'lm_dir': PosixPath('data/my_lm'), 'simulate_streaming': False, 'decode_chunk_size': 32, 'left_context': 128, 'dynamic_chunk_training': False, 'causal_convolution': False, 'short_chunk_size': 25, 'num_left_chunks': 4, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank_ali'), 'max_duration': 300, '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('conformer_ctc3/exp-full/ctc-decoding'), 'suffix': 'epoch-25-avg-7-use-averaged-model'}
2022-11-27 20:36:25,805 INFO [lexicon.py:176] Loading pre-compiled data/lang_bpe_500/Linv.pt
2022-11-27 20:36:30,362 INFO [decode.py:865] About to create model
2022-11-27 20:36:30,752 INFO [decode.py:932] Calculating the averaged model over epoch range from 18 (excluded) to 25
2022-11-27 20:36:32,993 INFO [decode.py:949] Number of model parameters: 77352694
2022-11-27 20:36:32,993 INFO [asr_datamodule.py:444] About to get test-clean cuts
2022-11-27 20:36:32,996 INFO [asr_datamodule.py:451] About to get test-other cuts
2022-11-27 20:36:34,812 INFO [decode.py:651] batch 0/?, cuts processed until now is 23
2022-11-27 20:37:10,536 INFO [decode.py:673] The transcripts are stored in conformer_ctc3/exp-full/ctc-decoding/recogs-test-clean-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
2022-11-27 20:37:10,659 INFO [utils.py:731] [test-clean-ctc-decoding] %WER 3.09% [1624 / 52576, 182 ins, 111 del, 1331 sub ]
2022-11-27 20:37:10,659 INFO [utils.py:736] [test-clean-ctc-decoding] %symbol-delay mean: 0.029s, variance: 0.003 computed on 51134 correct words
2022-11-27 20:37:10,875 INFO [decode.py:687] Wrote detailed error stats to conformer_ctc3/exp-full/ctc-decoding/errs-test-clean-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
2022-11-27 20:37:10,877 INFO [decode.py:717] 
For test-clean, WER of different settings are:
ctc-decoding	3.09	best for test-clean

2022-11-27 20:37:10,877 INFO [decode.py:726] 
For test-clean, symbol-delay of different settings are:
ctc-decoding	mean: 0.029s, variance: 0.003	best for test-clean

2022-11-27 20:37:12,170 INFO [decode.py:651] batch 0/?, cuts processed until now is 29
2022-11-27 20:37:48,013 INFO [decode.py:673] The transcripts are stored in conformer_ctc3/exp-full/ctc-decoding/recogs-test-other-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
2022-11-27 20:37:48,122 INFO [utils.py:731] [test-other-ctc-decoding] %WER 7.62% [3986 / 52343, 361 ins, 327 del, 3298 sub ]
2022-11-27 20:37:48,123 INFO [utils.py:736] [test-other-ctc-decoding] %symbol-delay mean: 0.026s, variance: 0.003 computed on 48700 correct words
2022-11-27 20:37:48,320 INFO [decode.py:687] Wrote detailed error stats to conformer_ctc3/exp-full/ctc-decoding/errs-test-other-ctc-decoding-epoch-25-avg-7-use-averaged-model.txt
2022-11-27 20:37:48,321 INFO [decode.py:717] 
For test-other, WER of different settings are:
ctc-decoding	7.62	best for test-other

2022-11-27 20:37:48,321 INFO [decode.py:726] 
For test-other, symbol-delay of different settings are:
ctc-decoding	mean: 0.026s, variance: 0.003	best for test-other

2022-11-27 20:37:48,321 INFO [decode.py:984] Done!