icefall_asr_tal-csasr_pruned_transducer_stateless5 / log /greedy_search /log-decode-epoch-30-avg-24-context-2-max-sym-per-frame-1-2022-06-23-14-56-02
luomingshuang's picture
add files for tal-csasr pruned rnnt5 recipe
9f6047e
2022-06-23 14:56:02,155 INFO [decode.py:536] Decoding started
2022-06-23 14:56:02,155 INFO [decode.py:542] Device: cuda:0
2022-06-23 14:56:02,262 INFO [lexicon.py:176] Loading pre-compiled data/lang_char/Linv.pt
2022-06-23 14:56:02,280 INFO [decode.py:552] {'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': 100, 'valid_interval': 2000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 1000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.4.0.dev+git.94e9ed9.clean', 'torch-version': '1.11.0', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'pruned-rnnt5-recipe-for-tal-csasr', 'icefall-git-sha1': 'c1c893b-dirty', 'icefall-git-date': 'Thu Jun 16 19:19:00 2022', 'icefall-path': '/ceph-meixu/luomingshuang/icefall', 'k2-path': '/ceph-ms/luomingshuang/k2_latest/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-meixu/luomingshuang/anaconda3/envs/k2-python/lib/python3.8/site-packages/lhotse-1.4.0.dev0+git.94e9ed9.clean-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-0307195509-54c966b95f-rtpfq', 'IP address': '10.177.22.9'}, 'epoch': 30, 'iter': 0, 'avg': 24, 'use_averaged_model': False, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp'), 'lang_dir': 'data/lang_char', 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'num_encoder_layers': 24, 'dim_feedforward': 1536, 'nhead': 8, 'encoder_dim': 384, 'decoder_dim': 512, 'joiner_dim': 512, 'manifest_dir': PosixPath('data/fbank_new'), 'max_duration': 800, 'bucketing_sampler': True, 'num_buckets': 300, '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_stateless5/exp/greedy_search'), 'suffix': 'epoch-30-avg-24-context-2-max-sym-per-frame-1', 'blank_id': 0, 'vocab_size': 7341}
2022-06-23 14:56:02,280 INFO [decode.py:554] About to create model
2022-06-23 14:56:02,848 INFO [decode.py:583] averaging ['pruned_transducer_stateless5/exp/epoch-7.pt', 'pruned_transducer_stateless5/exp/epoch-8.pt', 'pruned_transducer_stateless5/exp/epoch-9.pt', 'pruned_transducer_stateless5/exp/epoch-10.pt', 'pruned_transducer_stateless5/exp/epoch-11.pt', 'pruned_transducer_stateless5/exp/epoch-12.pt', 'pruned_transducer_stateless5/exp/epoch-13.pt', 'pruned_transducer_stateless5/exp/epoch-14.pt', 'pruned_transducer_stateless5/exp/epoch-15.pt', 'pruned_transducer_stateless5/exp/epoch-16.pt', 'pruned_transducer_stateless5/exp/epoch-17.pt', 'pruned_transducer_stateless5/exp/epoch-18.pt', 'pruned_transducer_stateless5/exp/epoch-19.pt', 'pruned_transducer_stateless5/exp/epoch-20.pt', 'pruned_transducer_stateless5/exp/epoch-21.pt', 'pruned_transducer_stateless5/exp/epoch-22.pt', 'pruned_transducer_stateless5/exp/epoch-23.pt', 'pruned_transducer_stateless5/exp/epoch-24.pt', 'pruned_transducer_stateless5/exp/epoch-25.pt', 'pruned_transducer_stateless5/exp/epoch-26.pt', 'pruned_transducer_stateless5/exp/epoch-27.pt', 'pruned_transducer_stateless5/exp/epoch-28.pt', 'pruned_transducer_stateless5/exp/epoch-29.pt', 'pruned_transducer_stateless5/exp/epoch-30.pt']
2022-06-23 14:59:46,996 INFO [decode.py:643] Number of model parameters: 102139163
2022-06-23 14:59:46,997 INFO [asr_datamodule.py:425] About to get dev cuts
2022-06-23 14:59:47,016 INFO [asr_datamodule.py:360] About to create dev dataset
2022-06-23 14:59:47,313 INFO [asr_datamodule.py:381] About to create dev dataloader
2022-06-23 14:59:47,314 INFO [asr_datamodule.py:432] About to get test cuts
2022-06-23 14:59:47,923 INFO [asr_datamodule.py:407] About to create test dataloader
2022-06-23 14:59:50,343 INFO [decode.py:447] batch 0/?, cuts processed until now is 78
2022-06-23 15:00:18,745 INFO [decode.py:464] The transcripts are stored in pruned_transducer_stateless5/exp/greedy_search/recogs-dev-greedy_search-epoch-30-avg-24-context-2-max-sym-per-frame-1.txt
2022-06-23 15:00:18,876 INFO [utils.py:410] [dev-greedy_search] %WER 7.49% [8536 / 113916, 1426 ins, 1987 del, 5123 sub ]
2022-06-23 15:00:19,220 INFO [decode.py:477] Wrote detailed error stats to pruned_transducer_stateless5/exp/greedy_search/errs-dev-greedy_search-epoch-30-avg-24-context-2-max-sym-per-frame-1.txt
2022-06-23 15:00:19,221 INFO [decode.py:494]
For dev, WER of different settings are:
greedy_search 7.49 best for dev
2022-06-23 15:00:21,538 INFO [decode.py:447] batch 0/?, cuts processed until now is 82
2022-06-23 15:01:02,499 INFO [decode.py:447] batch 50/?, cuts processed until now is 6627
2022-06-23 15:01:42,587 INFO [decode.py:447] batch 100/?, cuts processed until now is 14092
2022-06-23 15:01:47,856 INFO [decode.py:464] The transcripts are stored in pruned_transducer_stateless5/exp/greedy_search/recogs-test-greedy_search-epoch-30-avg-24-context-2-max-sym-per-frame-1.txt
2022-06-23 15:01:48,253 INFO [utils.py:410] [test-greedy_search] %WER 7.58% [25384 / 335012, 4025 ins, 5992 del, 15367 sub ]
2022-06-23 15:01:49,238 INFO [decode.py:477] Wrote detailed error stats to pruned_transducer_stateless5/exp/greedy_search/errs-test-greedy_search-epoch-30-avg-24-context-2-max-sym-per-frame-1.txt
2022-06-23 15:01:49,239 INFO [decode.py:494]
For test, WER of different settings are:
greedy_search 7.58 best for test
2022-06-23 15:01:49,239 INFO [decode.py:680] Done!