icefall-asr-librispeech-pruned-transducer-stateless-2022-03-12 / log /log-decode-epoch-42-avg-11-context-2-max-sym-per-frame-3-2022-03-11-18-36-33
csukuangfj's picture
Add decoding logs.
26d87f8
2022-03-11 18:36:33,290 INFO [decode.py:405] Decoding started
2022-03-11 18:36:33,290 INFO [decode.py:411] Device: cuda:0
2022-03-11 18:36:33,292 INFO [decode.py:420] {'feature_dim': 80, 'subsampling_factor': 4, 'attention_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'vgg_frontend': False, 'embedding_dim': 512, 'env_info': {'k2-version': '1.13', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '5ee082ea55f50e8bd42203ba266945ea5a236ab8', 'k2-git-date': 'Sun Feb 27 09:00:48 2022', 'lhotse-version': '1.0.0.dev+missing.version.file', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'ad62981-clean', 'icefall-git-date': 'Fri Mar 4 15:38:23 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-pruned-rnnt', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-rnnt-ali/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-rnnt-ali/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-3-0307202051-57dc848959-8tmmp', 'IP address': '10.177.24.138'}, 'epoch': 42, 'avg': 11, 'exp_dir': PosixPath('pruned_transducer_stateless/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'greedy_search', 'beam_size': 4, 'context_size': 2, 'max_sym_per_frame': 3, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 100, 'bucketing_sampler': True, 'num_buckets': 30, '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, 'res_dir': PosixPath('pruned_transducer_stateless/exp/greedy_search'), 'suffix': 'epoch-42-avg-11-context-2-max-sym-per-frame-3', 'blank_id': 0, 'vocab_size': 500}
2022-03-11 18:36:33,292 INFO [decode.py:422] About to create model
2022-03-11 18:36:33,827 INFO [decode.py:433] averaging ['pruned_transducer_stateless/exp/epoch-32.pt', 'pruned_transducer_stateless/exp/epoch-33.pt', 'pruned_transducer_stateless/exp/epoch-34.pt', 'pruned_transducer_stateless/exp/epoch-35.pt', 'pruned_transducer_stateless/exp/epoch-36.pt', 'pruned_transducer_stateless/exp/epoch-37.pt', 'pruned_transducer_stateless/exp/epoch-38.pt', 'pruned_transducer_stateless/exp/epoch-39.pt', 'pruned_transducer_stateless/exp/epoch-40.pt', 'pruned_transducer_stateless/exp/epoch-41.pt', 'pruned_transducer_stateless/exp/epoch-42.pt']
2022-03-11 18:36:48,445 INFO [decode.py:442] Number of model parameters: 84514780
2022-03-11 18:36:48,445 INFO [asr_datamodule.py:379] About to get test-clean cuts
2022-03-11 18:36:48,545 INFO [asr_datamodule.py:384] About to get test-other cuts
2022-03-11 18:36:50,037 INFO [decode.py:334] batch 0/?, cuts processed until now is 20
2022-03-11 18:38:27,402 INFO [decode.py:334] batch 100/?, cuts processed until now is 1406
2022-03-11 18:40:10,870 INFO [decode.py:334] batch 200/?, cuts processed until now is 2563
2022-03-11 18:40:20,541 INFO [decode.py:351] The transcripts are stored in pruned_transducer_stateless/exp/greedy_search/recogs-test-clean-greedy_search-epoch-42-avg-11-context-2-max-sym-per-frame-3.txt
2022-03-11 18:40:20,607 INFO [utils.py:406] [test-clean-greedy_search] %WER 2.62% [1380 / 52576, 147 ins, 115 del, 1118 sub ]
2022-03-11 18:40:20,807 INFO [decode.py:364] Wrote detailed error stats to pruned_transducer_stateless/exp/greedy_search/errs-test-clean-greedy_search-epoch-42-avg-11-context-2-max-sym-per-frame-3.txt
2022-03-11 18:40:20,808 INFO [decode.py:381]
For test-clean, WER of different settings are:
greedy_search 2.62 best for test-clean
2022-03-11 18:40:22,118 INFO [decode.py:334] batch 0/?, cuts processed until now is 23
2022-03-11 18:42:07,004 INFO [decode.py:334] batch 100/?, cuts processed until now is 1614
2022-03-11 18:43:49,356 INFO [decode.py:334] batch 200/?, cuts processed until now is 2899
2022-03-11 18:43:55,246 INFO [decode.py:351] The transcripts are stored in pruned_transducer_stateless/exp/greedy_search/recogs-test-other-greedy_search-epoch-42-avg-11-context-2-max-sym-per-frame-3.txt
2022-03-11 18:43:55,319 INFO [utils.py:406] [test-other-greedy_search] %WER 6.37% [3334 / 52343, 326 ins, 326 del, 2682 sub ]
2022-03-11 18:43:55,499 INFO [decode.py:364] Wrote detailed error stats to pruned_transducer_stateless/exp/greedy_search/errs-test-other-greedy_search-epoch-42-avg-11-context-2-max-sym-per-frame-3.txt
2022-03-11 18:43:55,502 INFO [decode.py:381]
For test-other, WER of different settings are:
greedy_search 6.37 best for test-other
2022-03-11 18:43:55,502 INFO [decode.py:469] Done!