decoding_results/greedy_search/log-decode-epoch-50_avg-26_context-2_max-sym-per-frame-1_use-averaged-model-2024-10-19-21-51-06

2024-10-19 21:51:06,899 INFO [decode.py:860] Decoding started
2024-10-19 21:51:06,899 INFO [decode.py:866] Device: cuda:0
2024-10-19 21:51:06,957 INFO [decode.py:876] {'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, 'ignore_id': -1, 'label_smoothing': 0.1, 'warm_step': 2000, 'env_info': {'k2-version': '1.24.4', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '44a9d5682af9fd3ef77074777e15278ec6d390eb', 'k2-git-date': 'Wed Sep 27 11:22:55 2023', 'lhotse-version': '1.17.0.dev+git.ccfc5b2c.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'cr-ctc-2', 'icefall-git-sha1': 'ae59e5d6-dirty', 'icefall-git-date': 'Tue Oct 8 00:34:32 2024', 'icefall-path': '/star-zw/workspace/zipformer/icefall_cr_ctc', 'k2-path': '/star-zw/workspace/k2/k2/k2/python/k2/__init__.py', 'lhotse-path': '/star-zw/workspace/lhotse/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-2-0904151501-7d58788f57-7cktm', 'IP address': '10.30.14.169'}, 'epoch': 50, 'iter': 0, 'avg': 26, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-large-ctc-rnnt-ctc-loss-scale-0.1-cr-loss-scale-0.02-time-mask-ratio-2.5-scaled-masked-1'), '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, 'use_shallow_fusion': False, 'lm_type': 'rnn', 'lm_scale': 0.3, 'tokens_ngram': 2, 'backoff_id': 500, 'context_score': 2, 'context_file': '', 'skip_scoring': False, 'num_encoder_layers': '2,2,4,5,4,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,1536,2048,1536,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,512,768,512,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,256,320,256,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'attention_decoder_dim': 512, 'attention_decoder_num_layers': 6, 'attention_decoder_attention_dim': 512, 'attention_decoder_num_heads': 8, 'attention_decoder_feedforward_dim': 2048, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'use_transducer': True, 'use_ctc': True, 'use_attention_decoder': False, 'use_cr_ctc': True, 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300, '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', 'lm_vocab_size': 500, 'lm_epoch': 7, 'lm_avg': 1, 'lm_exp_dir': None, 'rnn_lm_embedding_dim': 2048, 'rnn_lm_hidden_dim': 2048, 'rnn_lm_num_layers': 3, 'rnn_lm_tie_weights': True, 'transformer_lm_exp_dir': None, 'transformer_lm_dim_feedforward': 2048, 'transformer_lm_encoder_dim': 768, 'transformer_lm_embedding_dim': 768, 'transformer_lm_nhead': 8, 'transformer_lm_num_layers': 16, 'transformer_lm_tie_weights': True, 'res_dir': PosixPath('zipformer/exp-large-ctc-rnnt-ctc-loss-scale-0.1-cr-loss-scale-0.02-time-mask-ratio-2.5-scaled-masked-1/greedy_search'), 'has_contexts': False, 'suffix': 'epoch-50_avg-26_context-2_max-sym-per-frame-1_use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2024-10-19 21:51:06,957 INFO [decode.py:878] About to create model
2024-10-19 21:51:07,978 INFO [decode.py:945] Calculating the averaged model over epoch range from 24 (excluded) to 50
2024-10-19 21:51:52,193 INFO [decode.py:1039] Number of model parameters: 148824074
2024-10-19 21:51:52,194 INFO [asr_datamodule.py:467] About to get test-clean cuts
2024-10-19 21:51:52,863 INFO [asr_datamodule.py:474] About to get test-other cuts
2024-10-19 21:51:55,707 INFO [decode.py:718] batch 0/?, cuts processed until now is 21
2024-10-19 21:52:27,821 INFO [decode.py:718] batch 50/?, cuts processed until now is 1662
2024-10-19 21:52:40,442 INFO [decode.py:737] The transcripts are stored in zipformer/exp-large-ctc-rnnt-ctc-loss-scale-0.1-cr-loss-scale-0.02-time-mask-ratio-2.5-scaled-masked-1/greedy_search/recogs-test-clean-epoch-50_avg-26_context-2_max-sym-per-frame-1_use-averaged-model.txt
2024-10-19 21:52:40,538 INFO [utils.py:659] [test-clean-greedy_search] %WER 1.90% [1000 / 52576, 109 ins, 76 del, 815 sub ]
2024-10-19 21:52:40,787 INFO [decode.py:759] Wrote detailed error stats to zipformer/exp-large-ctc-rnnt-ctc-loss-scale-0.1-cr-loss-scale-0.02-time-mask-ratio-2.5-scaled-masked-1/greedy_search/errs-test-clean-epoch-50_avg-26_context-2_max-sym-per-frame-1_use-averaged-model.txt
2024-10-19 21:52:40,791 INFO [decode.py:775] 
For test-clean, WER of different settings are:
greedy_search	1.9	best for test-clean

2024-10-19 21:52:42,428 INFO [decode.py:718] batch 0/?, cuts processed until now is 26
2024-10-19 21:53:10,293 INFO [decode.py:718] batch 50/?, cuts processed until now is 1880
2024-10-19 21:53:22,113 INFO [decode.py:737] The transcripts are stored in zipformer/exp-large-ctc-rnnt-ctc-loss-scale-0.1-cr-loss-scale-0.02-time-mask-ratio-2.5-scaled-masked-1/greedy_search/recogs-test-other-epoch-50_avg-26_context-2_max-sym-per-frame-1_use-averaged-model.txt
2024-10-19 21:53:22,208 INFO [utils.py:659] [test-other-greedy_search] %WER 3.96% [2074 / 52343, 204 ins, 184 del, 1686 sub ]
2024-10-19 21:53:22,423 INFO [decode.py:759] Wrote detailed error stats to zipformer/exp-large-ctc-rnnt-ctc-loss-scale-0.1-cr-loss-scale-0.02-time-mask-ratio-2.5-scaled-masked-1/greedy_search/errs-test-other-epoch-50_avg-26_context-2_max-sym-per-frame-1_use-averaged-model.txt
2024-10-19 21:53:22,428 INFO [decode.py:775] 
For test-other, WER of different settings are:
greedy_search	3.96	best for test-other

2024-10-19 21:53:22,428 INFO [decode.py:1081] Done!