decoding_results/greedy_search/log-decode-epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model-2023-04-03-17-20-40

2023-04-03 17:20:40,951 INFO [decode.py:659] Decoding started
2023-04-03 17:20:40,952 INFO [decode.py:665] Device: cuda:0
2023-04-03 17:20:40,953 INFO [decode.py:675] {'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, 'warm_step': 2000, 'env_info': {'k2-version': '1.23.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '62e404dd3f3a811d73e424199b3408e309c06e1a', 'k2-git-date': 'Mon Jan 30 02:26:16 2023', 'lhotse-version': '1.12.0.dev+git.3ccfeb7.clean', 'torch-version': '1.13.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.7', 'python-version': '3.8', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'd74822d-dirty', 'icefall-git-date': 'Tue Mar 21 21:35:32 2023', 'icefall-path': '/home/lishaojie/icefall', 'k2-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/home/lishaojie/.conda/envs/env_lishaojie/lib/python3.8/site-packages/lhotse/__init__.py', 'hostname': 'cnc533', 'IP address': '127.0.1.1'}, 'epoch': 29, 'iter': 0, 'avg': 9, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7_streaming/exp1'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'greedy_search', 'beam_size': 4, '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, '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, 'short_chunk_size': 50, 'num_left_chunks': 4, 'decode_chunk_len': 64, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200, '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_streaming/exp1/greedy_search'), 'suffix': 'epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2023-04-03 17:20:40,954 INFO [decode.py:677] About to create model
2023-04-03 17:20:41,325 INFO [zipformer.py:405] 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.
2023-04-03 17:20:41,332 INFO [decode.py:748] Calculating the averaged model over epoch range from 20 (excluded) to 29
2023-04-03 17:20:43,416 INFO [decode.py:782] Number of model parameters: 70369391
2023-04-03 17:20:43,416 INFO [commonvoice_fr.py:406] About to get test cuts
2023-04-03 17:20:46,076 INFO [decode.py:560] batch 0/?, cuts processed until now is 27
2023-04-03 17:20:56,934 INFO [decode.py:560] batch 50/?, cuts processed until now is 1548
2023-04-03 17:21:07,967 INFO [decode.py:560] batch 100/?, cuts processed until now is 3088
2023-04-03 17:21:11,846 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.1787, 1.8910, 2.4172, 1.6407, 2.1728, 2.3893, 1.7562, 2.5306],
       device='cuda:0'), covar=tensor([0.1221, 0.2071, 0.1560, 0.2019, 0.0944, 0.1410, 0.2892, 0.0782],
       device='cuda:0'), in_proj_covar=tensor([0.0188, 0.0202, 0.0188, 0.0186, 0.0170, 0.0210, 0.0213, 0.0194],
       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
       device='cuda:0')
2023-04-03 17:21:19,943 INFO [decode.py:560] batch 150/?, cuts processed until now is 4693
2023-04-03 17:21:24,480 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.9368, 4.1410, 3.9511, 2.1512, 4.1722, 3.3482, 1.1814, 3.0681],
       device='cuda:0'), covar=tensor([0.1757, 0.1534, 0.1609, 0.2749, 0.0958, 0.0773, 0.3330, 0.1192],
       device='cuda:0'), in_proj_covar=tensor([0.0149, 0.0177, 0.0157, 0.0127, 0.0159, 0.0121, 0.0146, 0.0122],
       device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0003, 0.0003, 0.0002, 0.0003, 0.0002, 0.0003, 0.0002],
       device='cuda:0')
2023-04-03 17:21:30,520 INFO [decode.py:560] batch 200/?, cuts processed until now is 6301
2023-04-03 17:21:38,318 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.2529, 2.0297, 1.8643, 2.1288, 1.9791, 1.9835, 1.9948, 2.7326],
       device='cuda:0'), covar=tensor([0.3832, 0.5126, 0.3710, 0.4009, 0.4766, 0.2687, 0.4275, 0.1859],
       device='cuda:0'), in_proj_covar=tensor([0.0286, 0.0261, 0.0233, 0.0273, 0.0255, 0.0225, 0.0254, 0.0234],
       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
       device='cuda:0')
2023-04-03 17:21:41,318 INFO [decode.py:560] batch 250/?, cuts processed until now is 7825
2023-04-03 17:21:45,845 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.8310, 1.7597, 1.6839, 1.8309, 1.2796, 3.4939, 1.4962, 1.9513],
       device='cuda:0'), covar=tensor([0.3100, 0.2143, 0.1930, 0.2158, 0.1619, 0.0206, 0.2399, 0.1100],
       device='cuda:0'), in_proj_covar=tensor([0.0130, 0.0115, 0.0120, 0.0123, 0.0112, 0.0094, 0.0093, 0.0093],
       device='cuda:0'), out_proj_covar=tensor([0.0006, 0.0005, 0.0005, 0.0006, 0.0005, 0.0004, 0.0005, 0.0004],
       device='cuda:0')
2023-04-03 17:21:51,496 INFO [decode.py:560] batch 300/?, cuts processed until now is 9574
2023-04-03 17:21:53,631 INFO [zipformer.py:2441] attn_weights_entropy = tensor([1.9710, 1.4775, 2.1112, 2.0248, 1.8644, 1.8023, 1.9569, 1.9764],
       device='cuda:0'), covar=tensor([0.4725, 0.4362, 0.3711, 0.4021, 0.5538, 0.4317, 0.5152, 0.3214],
       device='cuda:0'), in_proj_covar=tensor([0.0260, 0.0243, 0.0263, 0.0289, 0.0289, 0.0265, 0.0295, 0.0247],
       device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
       device='cuda:0')
2023-04-03 17:22:02,103 INFO [decode.py:560] batch 350/?, cuts processed until now is 11145
2023-04-03 17:22:12,758 INFO [decode.py:560] batch 400/?, cuts processed until now is 12706
2023-04-03 17:22:23,693 INFO [decode.py:560] batch 450/?, cuts processed until now is 14224
2023-04-03 17:22:34,416 INFO [decode.py:560] batch 500/?, cuts processed until now is 15743
2023-04-03 17:22:35,701 INFO [decode.py:576] The transcripts are stored in pruned_transducer_stateless7_streaming/exp1/greedy_search/recogs-test-cv-greedy_search-epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model.txt
2023-04-03 17:22:35,945 INFO [utils.py:558] [test-cv-greedy_search] %WER 10.57% [16585 / 156915, 1231 ins, 1791 del, 13563 sub ]
2023-04-03 17:22:36,536 INFO [decode.py:589] Wrote detailed error stats to pruned_transducer_stateless7_streaming/exp1/greedy_search/errs-test-cv-greedy_search-epoch-29-avg-9-streaming-chunk-size-64-context-2-max-sym-per-frame-1-use-averaged-model.txt
2023-04-03 17:22:36,536 INFO [decode.py:609] 
For test-cv, WER of different settings are:
greedy_search	10.57	best for test-cv

2023-04-03 17:22:36,537 INFO [decode.py:808] Done!