2023-01-06 03:52:59,856 INFO [decode.py:565] Decoding started 2023-01-06 03:52:59,856 INFO [decode.py:571] Device: cuda:0 2023-01-06 03:53:00,031 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_500/Linv.pt 2023-01-06 03:53:00,067 INFO [decode.py:588] { 'activation': 'doubleswish', 'avg': 1, 'batch_idx_train': 0, 'beam': 20.0, 'beam_size': 4, 'best_train_epoch': -1, 'best_train_loss': inf, 'best_valid_epoch': -1, 'best_valid_loss': inf, 'blank_id': 0, 'bucketing_sampler': True, 'channels': 256, 'concatenate_cuts': False, 'context_size': 2, 'conv_layers': 10, 'decoder_dim': 256, 'decoding_method': 'greedy_search', 'drop_last': True, 'duration_factor': 1.0, 'enable_musan': True, 'enable_spec_aug': True, 'encoder_dim': 256, 'env_info': { 'IP address': '127.0.1.1', 'hostname': 'kao-dgxa-f12-u17', 'icefall-git-branch': 'tiny', 'icefall-git-date': 'Mon Jan 2 00:08:32 2023', 'icefall-git-sha1': '2fd970b-dirty', 'icefall-path': '/home/jsong/git/icefall', 'k2-build-type': 'Release', 'k2-git-date': 'Fri Nov 25 08:23:51 2022', 'k2-git-sha1': '1feafa064cf3b6c243e6b33b0192601224210937', 'k2-path': '/home/jsong/miniconda3/envs/k2/lib/python3.9/site-packages/k2/__init__.py', 'k2-version': '1.23.2', 'k2-with-cuda': True, 'lhotse-path': '/home/jsong/miniconda3/envs/k2/lib/python3.9/site-packages/lhotse/__init__.py', 'lhotse-version': '1.7.0', 'python-version': '3.9', 'torch-cuda-available': True, 'torch-cuda-version': '11.3', 'torch-version': '1.12.0'}, 'epoch': 30, 'exp_dir': PosixPath('tiny_transducer_ctc/exp_1m_bpe500_halfdelay'), 'feature_dim': 80, 'full_libri': True, 'gap': 1.0, 'input_strategy': 'PrecomputedFeatures', 'iter': 0, 'joiner_dim': 256, 'lang_dir': PosixPath('data/lang_bpe_500'), 'log_interval': 500, 'manifest_dir': PosixPath('data/fbank'), 'max_contexts': 8, 'max_duration': 600, 'max_states': 64, 'max_sym_per_frame': 1, 'nbest_scale': 0.5, 'ngram_lm_scale': 0.1, 'num_buckets': 30, 'num_paths': 100, 'num_workers': 2, 'on_the_fly_feats': False, 'res_dir': PosixPath('tiny_transducer_ctc/exp_1m_bpe500_halfdelay/greedy_search'), 'reset_interval': 200, 'return_cuts': True, 'shuffle': True, 'skip_add': False, 'spec_aug_time_warp_factor': 80, 'subsampling_factor': 4, 'suffix': 'epoch-30-avg-1-context-2-max-sym-per-frame-1-uam', 'unk_id': 2, 'use_averaged_model': True, 'use_double_scores': True, 'use_dscnn': True, 'valid_interval': 9000, 'vocab_size': 500, 'warm_step': 5000} 2023-01-06 03:53:00,068 INFO [decode.py:590] About to create model 2023-01-06 03:53:02,340 INFO [train.py:425] Encoder MAC ops for 10 seconds of audio is 219.86M 2023-01-06 03:53:02,343 INFO [decode.py:659] Calculating the averaged model over epoch range from 29 (excluded) to 30 2023-01-06 03:53:02,551 INFO [decode.py:697] Number of model parameters: 1623264 2023-01-06 03:53:02,551 INFO [decode.py:698] Parameters for transducer decoding: 1237764 2023-01-06 03:53:02,552 INFO [asr_datamodule.py:443] About to get test-clean cuts 2023-01-06 03:53:02,552 INFO [asr_datamodule.py:450] About to get test-other cuts 2023-01-06 03:53:04,479 INFO [decode.py:459] batch 0/?, cuts processed until now is 43 2023-01-06 03:53:17,072 INFO [decode.py:478] The transcripts are stored in tiny_transducer_ctc/exp_1m_bpe500_halfdelay/greedy_search/recogs-test-clean-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-uam.txt 2023-01-06 03:53:17,143 INFO [utils.py:536] [test-clean-greedy_search] %WER 14.47% [7610 / 52576, 868 ins, 906 del, 5836 sub ] 2023-01-06 03:53:17,300 INFO [decode.py:491] Wrote detailed error stats to tiny_transducer_ctc/exp_1m_bpe500_halfdelay/greedy_search/errs-test-clean-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-uam.txt 2023-01-06 03:53:17,300 INFO [decode.py:508] For test-clean, WER of different settings are: greedy_search 14.47 best for test-clean 2023-01-06 03:53:17,848 INFO [decode.py:459] batch 0/?, cuts processed until now is 52 2023-01-06 03:53:28,786 INFO [decode.py:478] The transcripts are stored in tiny_transducer_ctc/exp_1m_bpe500_halfdelay/greedy_search/recogs-test-other-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-uam.txt 2023-01-06 03:53:28,866 INFO [utils.py:536] [test-other-greedy_search] %WER 32.03% [16768 / 52343, 1530 ins, 2748 del, 12490 sub ] 2023-01-06 03:53:29,049 INFO [decode.py:491] Wrote detailed error stats to tiny_transducer_ctc/exp_1m_bpe500_halfdelay/greedy_search/errs-test-other-greedy_search-epoch-30-avg-1-context-2-max-sym-per-frame-1-uam.txt 2023-01-06 03:53:29,049 INFO [decode.py:508] For test-other, WER of different settings are: greedy_search 32.03 best for test-other 2023-01-06 03:53:29,049 INFO [decode.py:730] Done!