decoding-results/greedy_search/log-decode-epoch-30-avg-13-context-2-max-sym-per-frame-1-use-averaged-model-2023-01-29-14-48-00

2023-01-29 14:48:00,161 INFO [ctc_guild_decode_bs.py:698] Decoding started
2023-01-29 14:48:00,161 INFO [ctc_guild_decode_bs.py:704] Device: cuda:0
2023-01-29 14:48:00,165 INFO [ctc_guild_decode_bs.py:719] {'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, 'beam_size': 4, 'use_double_scores': True, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.3', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '02376766cbfc95fe67743e42c053d1ccca20009d', 'k2-git-date': 'Wed Jan 11 20:50:20 2023', 'lhotse-version': '1.11.0', 'torch-version': '1.13.1', 'torch-cuda-available': True, 'torch-cuda-version': '11.6', 'python-version': '3.1', 'icefall-git-branch': 'master', 'icefall-git-sha1': '958dbb3-dirty', 'icefall-git-date': 'Wed Jan 11 20:29:36 2023', 'icefall-path': '/k2-dev/yangyifan/icefall', 'k2-path': '/k2-dev/yangyifan/anaconda3/envs/icefall/lib/python3.10/site-packages/k2-1.23.3.dev20230112+cuda11.6.torch1.13.1-py3.10-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/k2-dev/yangyifan/anaconda3/envs/icefall/lib/python3.10/site-packages/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-3-1220120619-7695ff496b-s9n4w', 'IP address': '10.177.6.147'}, 'epoch': 30, 'iter': 0, 'avg': 13, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_ctc_bs/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'greedy_search', '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, 'simulate_streaming': False, 'decode_chunk_size': 16, 'left_context': 64, 'num_encoder_layers': '2,4,3,2,4', 'feedforward_dims': '1024,1024,2048,2048,1024', 'nhead': '8,8,8,8,8', 'encoder_dims': '384,384,384,384,384', 'attention_dims': '192,192,192,192,192', 'encoder_unmasked_dims': '256,256,256,256,256', 'zipformer_downsampling_factors': '1,2,4,8,2', 'cnn_module_kernels': '31,31,31,31,31', 'decoder_dim': 512, 'joiner_dim': 512, 'full_libri': True, '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('pruned_transducer_stateless7_ctc_bs/exp/greedy_search'), 'suffix': 'epoch-30-avg-13-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2023-01-29 14:48:00,165 INFO [ctc_guild_decode_bs.py:721] About to create model
2023-01-29 14:48:00,718 INFO [zipformer.py:178] At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
2023-01-29 14:48:00,738 INFO [ctc_guild_decode_bs.py:788] Calculating the averaged model over epoch range from 17 (excluded) to 30
2023-01-29 14:48:05,452 INFO [ctc_guild_decode_bs.py:822] Number of model parameters: 71159011
2023-01-29 14:48:05,453 INFO [asr_datamodule.py:443] About to get test-clean cuts
2023-01-29 14:48:05,456 INFO [asr_datamodule.py:450] About to get test-other cuts
2023-01-29 14:48:08,694 INFO [ctc_guild_decode_bs.py:601] batch 0/?, cuts processed until now is 44
2023-01-29 14:48:34,150 INFO [ctc_guild_decode_bs.py:617] The transcripts are stored in pruned_transducer_stateless7_ctc_bs/exp/greedy_search/recogs-test-clean-greedy_search-epoch-30-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
2023-01-29 14:48:34,236 INFO [utils.py:536] [test-clean-greedy_search] %WER 2.28% [1201 / 52576, 142 ins, 103 del, 956 sub ]
2023-01-29 14:48:34,421 INFO [ctc_guild_decode_bs.py:630] Wrote detailed error stats to pruned_transducer_stateless7_ctc_bs/exp/greedy_search/errs-test-clean-greedy_search-epoch-30-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
2023-01-29 14:48:34,421 INFO [ctc_guild_decode_bs.py:646] 
For test-clean, WER of different settings are:
greedy_search	2.28	best for test-clean

2023-01-29 14:48:35,501 INFO [ctc_guild_decode_bs.py:601] batch 0/?, cuts processed until now is 52
2023-01-29 14:49:00,110 INFO [ctc_guild_decode_bs.py:617] The transcripts are stored in pruned_transducer_stateless7_ctc_bs/exp/greedy_search/recogs-test-other-greedy_search-epoch-30-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
2023-01-29 14:49:00,198 INFO [utils.py:536] [test-other-greedy_search] %WER 5.53% [2897 / 52343, 273 ins, 270 del, 2354 sub ]
2023-01-29 14:49:00,387 INFO [ctc_guild_decode_bs.py:630] Wrote detailed error stats to pruned_transducer_stateless7_ctc_bs/exp/greedy_search/errs-test-other-greedy_search-epoch-30-avg-13-context-2-max-sym-per-frame-1-use-averaged-model.txt
2023-01-29 14:49:00,388 INFO [ctc_guild_decode_bs.py:646] 
For test-other, WER of different settings are:
greedy_search	5.53	best for test-other

2023-01-29 14:49:00,388 INFO [ctc_guild_decode_bs.py:853] Done!