modified_beam_search/log-decode-epoch-90-avg-34-modified_beam_search-beam-size-4-use-averaged-model-2023-12-05-17-55-38

2023-12-05 17:55:38,839 INFO [decode.py:852] Decoding started
2023-12-05 17:55:38,839 INFO [decode.py:858] Device: cuda:0
2023-12-05 17:55:38,849 INFO [decode.py:868] {'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': '1.24.3', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '2b2ac14b326d61d79d04e53fbd69b1ff6d630411', 'k2-git-date': 'Thu Aug 24 05:58:26 2023', 'lhotse-version': '1.16.0', 'torch-version': '2.0.1+cu117', 'torch-cuda-available': True, 'torch-cuda-version': '11.7', 'python-version': '3.1', 'icefall-git-branch': 'zipformer_whisper_mvq', 'icefall-git-sha1': '0d26e9c4-dirty', 'icefall-git-date': 'Tue Oct 24 09:46:03 2023', 'icefall-path': '/star-xy/softwares/icefall_development/icefall_mvq', 'k2-path': '/star-xy/softwares/k2_development/k2/k2/python/k2/__init__.py', 'lhotse-path': '/star-xy/softwares/anaconda3/envs/multi_KD/lib/python3.10/site-packages/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'epoch': 90, 'iter': 0, 'avg': 34, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp_baseline_960h_no_sp_enable_musan0'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_500'), 'decoding_method': 'modified_beam_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': '', 'snr': -1, 'mixed_noise': 'as', 'num_encoder_layers': '2,2,3,4,3,2', 'downsampling_factor': '1,2,4,8,4,2', 'feedforward_dim': '512,768,1024,1536,1024,768', 'num_heads': '4,4,4,8,4,4', 'encoder_dim': '192,256,384,512,384,256', 'query_head_dim': '32', 'value_head_dim': '12', 'pos_head_dim': '4', 'pos_dim': 48, 'encoder_unmasked_dim': '192,192,256,256,256,192', 'cnn_module_kernel': '31,31,15,15,15,31', 'decoder_dim': 512, 'joiner_dim': 512, 'causal': False, 'chunk_size': '16,32,64,-1', 'left_context_frames': '64,128,256,-1', 'use_transducer': True, 'use_ctc': False, 'enable_distillation': False, 'num_codebooks': 32, 'distillation_layer': 3, 'full_libri': True, 'mini_libri': False, 'manifest_dir': PosixPath('data/fbank_test_snr_20'), 'max_duration': 1000, '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_baseline_960h_no_sp_enable_musan0/modified_beam_search'), 'has_contexts': False, 'suffix': 'epoch-90-avg-34-modified_beam_search-beam-size-4-use-averaged-model', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2023-12-05 17:55:38,850 INFO [decode.py:870] About to create model
2023-12-05 17:55:39,683 INFO [decode.py:937] Calculating the averaged model over epoch range from 56 (excluded) to 90
2023-12-05 17:55:49,826 INFO [decode.py:1032] Number of model parameters: 65549011
2023-12-05 17:55:49,826 INFO [asr_datamodule.py:465] About to get test-clean cuts
2023-12-05 17:55:49,851 INFO [asr_datamodule.py:472] About to get test-other cuts
2023-12-05 17:56:14,432 INFO [decode.py:722] batch 0/?, cuts processed until now is 73
2023-12-05 18:02:06,338 INFO [decode.py:722] batch 20/?, cuts processed until now is 2311
2023-12-05 18:02:54,327 INFO [decode.py:738] The transcripts are stored in zipformer/exp_baseline_960h_no_sp_enable_musan0/modified_beam_search/recogs-test-clean-beam_size_4-epoch-90-avg-34-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-12-05 18:02:54,470 INFO [utils.py:641] [test-clean-beam_size_4] %WER 4.60% [2420 / 52576, 1027 ins, 95 del, 1298 sub ]
2023-12-05 18:02:54,727 INFO [decode.py:751] Wrote detailed error stats to zipformer/exp_baseline_960h_no_sp_enable_musan0/modified_beam_search/errs-test-clean-beam_size_4-epoch-90-avg-34-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-12-05 18:02:54,731 INFO [decode.py:767] 
For test-clean, WER of different settings are:
beam_size_4	4.6	best for test-clean

2023-12-05 18:03:14,604 INFO [decode.py:722] batch 0/?, cuts processed until now is 86
2023-12-05 18:09:00,806 INFO [decode.py:722] batch 20/?, cuts processed until now is 2644
2023-12-05 18:09:47,353 INFO [decode.py:738] The transcripts are stored in zipformer/exp_baseline_960h_no_sp_enable_musan0/modified_beam_search/recogs-test-other-beam_size_4-epoch-90-avg-34-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-12-05 18:09:47,475 INFO [utils.py:641] [test-other-beam_size_4] %WER 12.01% [6287 / 52343, 2491 ins, 305 del, 3491 sub ]
2023-12-05 18:09:47,733 INFO [decode.py:751] Wrote detailed error stats to zipformer/exp_baseline_960h_no_sp_enable_musan0/modified_beam_search/errs-test-other-beam_size_4-epoch-90-avg-34-modified_beam_search-beam-size-4-use-averaged-model.txt
2023-12-05 18:09:47,737 INFO [decode.py:767] 
For test-other, WER of different settings are:
beam_size_4	12.01	best for test-other

2023-12-05 18:09:47,737 INFO [decode.py:1067] Done!