icefall_asr_wenetspeech_pruned_transducer_stateless5_offline
/
log
/greedy_search
/log-decode-epoch-4-avg-1-context-2-max-sym-per-frame-1-2022-07-22-18-01-40
| 2022-07-22 18:01:40,312 INFO [decode.py:523] Decoding started | |
| 2022-07-22 18:01:40,313 INFO [decode.py:529] Device: cuda:0 | |
| 2022-07-22 18:01:41,538 INFO [lexicon.py:176] Loading pre-compiled data/lang_char/Linv.pt | |
| 2022-07-22 18:01:41,629 INFO [decode.py:540] {'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, 'feature_dim': 80, 'subsampling_factor': 4, 'env_info': {'k2-version': '1.17', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '6f8de3096401edbaeae0714b04ab9adc2277b706', 'k2-git-date': 'Mon Jul 4 17:50:26 2022', 'lhotse-version': '1.5.0.dev+git.7cce647.dirty', 'torch-version': '1.11.0', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'pruned-rnnt5-for-wenetspeech', 'icefall-git-sha1': 'bd043b0-dirty', 'icefall-git-date': 'Fri Jul 22 10:26:19 2022', 'icefall-path': '/ceph-meixu/luomingshuang/icefall', 'k2-path': '/ceph-ms/luomingshuang/k2_sherpa/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-meixu/luomingshuang/anaconda3/envs/k2-python/lib/python3.8/site-packages/lhotse-1.5.0.dev0+git.7cce647.dirty-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0616225511-78bf4545d8-tv52r', 'IP address': '10.177.77.9'}, 'epoch': 4, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp_L_offline'), 'lang_dir': 'data/lang_char', 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'simulate_streaming': False, 'decode_chunk_size': 16, 'left_context': 64, 'num_encoder_layers': 24, 'dim_feedforward': 1536, 'nhead': 8, 'encoder_dim': 384, 'decoder_dim': 512, 'joiner_dim': 512, 'dynamic_chunk_training': False, 'causal_convolution': False, 'short_chunk_size': 25, 'num_left_chunks': 4, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 300, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'training_subset': 'L', 'res_dir': PosixPath('pruned_transducer_stateless5/exp_L_offline/greedy_search'), 'suffix': 'epoch-4-avg-1-context-2-max-sym-per-frame-1', 'blank_id': 0, 'vocab_size': 5537} | |
| 2022-07-22 18:01:41,629 INFO [decode.py:542] About to create model | |
| 2022-07-22 18:01:42,189 INFO [decode.py:609] Calculating the averaged model over epoch range from 3 (excluded) to 4 | |
| 2022-07-22 18:01:56,454 INFO [decode.py:632] Number of model parameters: 97487351 | |
| 2022-07-22 18:01:56,460 INFO [asr_datamodule.py:347] About to create dev dataset | |
| 2022-07-22 18:02:00,756 INFO [asr_datamodule.py:368] About to create dev dataloader | |
| 2022-07-22 18:02:14,887 INFO [decode.py:443] batch 0/?, cuts processed until now is 79 | |
| 2022-07-22 18:03:28,625 INFO [decode.py:443] batch 100/?, cuts processed until now is 9966 | |
| 2022-07-22 18:03:52,701 INFO [decode.py:460] The transcripts are stored in pruned_transducer_stateless5/exp_L_offline/greedy_search/recogs-DEV-greedy_search-epoch-4-avg-1-context-2-max-sym-per-frame-1.txt | |
| 2022-07-22 18:03:53,155 INFO [utils.py:410] [DEV-greedy_search] %WER 8.22% [27157 / 330498, 2884 ins, 10257 del, 14016 sub ] | |
| 2022-07-22 18:03:54,331 INFO [decode.py:473] Wrote detailed error stats to pruned_transducer_stateless5/exp_L_offline/greedy_search/errs-DEV-greedy_search-epoch-4-avg-1-context-2-max-sym-per-frame-1.txt | |
| 2022-07-22 18:03:54,332 INFO [decode.py:490] | |
| For DEV, WER of different settings are: | |
| greedy_search 8.22 best for DEV | |
| 2022-07-22 18:04:01,104 INFO [decode.py:443] batch 0/?, cuts processed until now is 87 | |
| 2022-07-22 18:05:17,466 INFO [decode.py:443] batch 100/?, cuts processed until now is 14012 | |
| 2022-07-22 18:06:11,277 INFO [decode.py:460] The transcripts are stored in pruned_transducer_stateless5/exp_L_offline/greedy_search/recogs-TEST_NET-greedy_search-epoch-4-avg-1-context-2-max-sym-per-frame-1.txt | |
| 2022-07-22 18:06:11,882 INFO [utils.py:410] [TEST_NET-greedy_search] %WER 9.03% [37557 / 415747, 4139 ins, 8162 del, 25256 sub ] | |
| 2022-07-22 18:06:13,422 INFO [decode.py:473] Wrote detailed error stats to pruned_transducer_stateless5/exp_L_offline/greedy_search/errs-TEST_NET-greedy_search-epoch-4-avg-1-context-2-max-sym-per-frame-1.txt | |
| 2022-07-22 18:06:13,423 INFO [decode.py:490] | |
| For TEST_NET, WER of different settings are: | |
| greedy_search 9.03 best for TEST_NET | |
| 2022-07-22 18:06:17,684 INFO [decode.py:443] batch 0/?, cuts processed until now is 56 | |
| 2022-07-22 18:07:34,603 INFO [decode.py:443] batch 100/?, cuts processed until now is 7928 | |
| 2022-07-22 18:07:42,086 INFO [decode.py:460] The transcripts are stored in pruned_transducer_stateless5/exp_L_offline/greedy_search/recogs-TEST_MEETING-greedy_search-epoch-4-avg-1-context-2-max-sym-per-frame-1.txt | |
| 2022-07-22 18:07:42,392 INFO [utils.py:410] [TEST_MEETING-greedy_search] %WER 14.54% [32052 / 220385, 2489 ins, 16073 del, 13490 sub ] | |
| 2022-07-22 18:07:43,199 INFO [decode.py:473] Wrote detailed error stats to pruned_transducer_stateless5/exp_L_offline/greedy_search/errs-TEST_MEETING-greedy_search-epoch-4-avg-1-context-2-max-sym-per-frame-1.txt | |
| 2022-07-22 18:07:43,200 INFO [decode.py:490] | |
| For TEST_MEETING, WER of different settings are: | |
| greedy_search 14.54 best for TEST_MEETING | |
| 2022-07-22 18:07:43,200 INFO [decode.py:731] Done! | |