jinzr
commited on
Commit
•
fa1b4b4
1
Parent(s):
38b4e64
updated ctc decoding results
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- decoding_results/ctc-decoding/errs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-aishell-4-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-aishell_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/errs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-02-26 +0 -18
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-17-01 +0 -18
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-21-51 +0 -18
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-41-49 +0 -6
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-42-14 +0 -18
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-18-23-09 +0 -57
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-18-27-50 +0 -4
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-18-28-40 +0 -196
- decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-25-16-34-00 +266 -0
- decoding_results/ctc-decoding/log-decode-epoch-22-avg-1-use-averaged-model-2023-10-17-16-37-56 +0 -3
- decoding_results/ctc-decoding/log-decode-epoch-22-avg-1-use-averaged-model-2023-10-17-16-38-08 +0 -18
- decoding_results/ctc-decoding/recogs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-aishell-4-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-aishell_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/recogs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt +0 -0
- decoding_results/ctc-decoding/wer-summary-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt +1 -1
- decoding_results/ctc-decoding/wer-summary-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt +1 -1
- decoding_results/ctc-decoding/wer-summary-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt +1 -1
- decoding_results/ctc-decoding/wer-summary-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt +1 -1
- decoding_results/ctc-decoding/wer-summary-aishell-4-epoch-20-avg-1-use-averaged-model.txt +1 -1
decoding_results/ctc-decoding/errs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-aishell-4-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-aishell_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/errs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-02-26
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:02:26,209 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:02:26,210 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:02:26,210 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-3-0423201227-84b4557756-h4fh6', 'IP address': '10.177.77.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 16:02:28,952 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 16:02:45,974 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 16:02:47,196 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
-
2023-10-17 16:03:07,159 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 16:03:07,161 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 16:03:07,161 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 16:03:07,256 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 16:03:07,322 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 16:03:07,368 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 16:03:07,389 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 16:03:07,436 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 16:03:07,503 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 16:03:07,587 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 16:03:20,149 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 16:03:22,114 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_test
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-17-01
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:17:01,559 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:17:01,560 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:17:01,560 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 16:17:03,333 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 16:17:08,838 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 16:17:09,434 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
-
2023-10-17 16:17:16,852 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 16:17:16,853 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 16:17:16,853 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 16:17:16,919 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 16:17:16,948 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 16:17:16,993 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 16:17:16,997 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 16:17:17,016 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 16:17:17,073 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 16:17:17,139 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 16:17:23,632 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 16:17:24,681 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_test
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-21-51
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:21:51,584 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:21:51,584 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:21:51,584 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 16:21:53,329 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 16:21:58,312 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 16:21:58,877 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
-
2023-10-17 16:22:02,908 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 16:22:02,908 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 16:22:02,908 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 16:22:02,927 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 16:22:02,931 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 16:22:02,935 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 16:22:02,936 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 16:22:02,940 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 16:22:02,943 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 16:22:02,948 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 16:22:08,929 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 16:22:09,902 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_dev
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-41-49
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:41:49,881 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:41:49,881 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:41:49,881 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 16:41:51,627 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 16:41:56,685 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 16:41:57,256 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-16-42-14
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:42:14,818 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:42:14,818 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:42:14,819 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 16:42:16,549 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 16:42:21,387 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 16:42:21,967 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
-
2023-10-17 16:42:25,945 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 16:42:25,945 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 16:42:25,945 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 16:42:25,962 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 16:42:25,966 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 16:42:25,970 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 16:42:25,972 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 16:42:25,975 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 16:42:25,978 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 16:42:25,982 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 16:42:32,311 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 16:42:33,328 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_test
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-18-23-09
DELETED
|
@@ -1,57 +0,0 @@
|
|
| 1 |
-
2023-10-17 18:23:09,112 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 18:23:09,112 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 18:23:09,112 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 18:23:10,868 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 18:23:16,848 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 18:23:17,431 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
-
2023-10-17 18:23:22,164 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 18:23:22,164 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 18:23:22,165 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 18:23:22,182 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 18:23:22,186 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 18:23:22,189 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 18:23:22,191 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 18:23:22,194 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 18:23:22,197 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 18:23:22,202 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 18:23:28,526 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 18:23:29,552 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_test
|
| 19 |
-
2023-10-17 18:23:30,937 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 80
|
| 20 |
-
2023-10-17 18:23:31,149 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([4.3243, 4.1785, 3.8951, 4.4938], device='cuda:0')
|
| 21 |
-
2023-10-17 18:23:32,075 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([4.6184, 3.9753, 4.4056, 4.1082], device='cuda:0')
|
| 22 |
-
2023-10-17 18:23:46,072 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([1.7554, 1.8501, 1.9709, 1.4977], device='cuda:0')
|
| 23 |
-
2023-10-17 18:23:47,852 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([2.0318, 2.9265, 2.8671, 2.9708], device='cuda:0')
|
| 24 |
-
2023-10-17 18:23:49,153 INFO [ctc_decode.py:485] batch 100/?, cuts processed until now is 9084
|
| 25 |
-
2023-10-17 18:23:53,157 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([1.7971, 2.1446, 2.3575, 2.1475, 2.1401, 2.0719, 2.1833, 2.1629],
|
| 26 |
-
device='cuda:0')
|
| 27 |
-
2023-10-17 18:24:07,354 INFO [ctc_decode.py:485] batch 200/?, cuts processed until now is 18516
|
| 28 |
-
2023-10-17 18:24:25,501 INFO [ctc_decode.py:485] batch 300/?, cuts processed until now is 28179
|
| 29 |
-
2023-10-17 18:24:28,319 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.8385, 2.2905, 3.9372, 2.3478], device='cuda:0')
|
| 30 |
-
2023-10-17 18:24:41,962 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([5.3786, 4.9526, 5.2852, 4.9957], device='cuda:0')
|
| 31 |
-
2023-10-17 18:24:43,488 INFO [ctc_decode.py:485] batch 400/?, cuts processed until now is 37667
|
| 32 |
-
2023-10-17 18:24:48,276 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.4047, 2.8120, 1.7099, 2.0791], device='cuda:0')
|
| 33 |
-
2023-10-17 18:24:48,972 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.6806, 3.0397, 2.2822, 2.4676], device='cuda:0')
|
| 34 |
-
2023-10-17 18:25:00,399 INFO [ctc_decode.py:485] batch 500/?, cuts processed until now is 46172
|
| 35 |
-
2023-10-17 18:25:06,922 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
|
| 36 |
-
2023-10-17 18:25:07,811 INFO [utils.py:565] [aidatatang_test-ctc-decoding] %WER 15.26% [43137 / 282666, 7255 ins, 10411 del, 25471 sub ]
|
| 37 |
-
2023-10-17 18:25:09,250 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
|
| 38 |
-
2023-10-17 18:25:09,253 INFO [ctc_decode.py:522]
|
| 39 |
-
For aidatatang_test, WER of different settings are:
|
| 40 |
-
ctc-decoding 15.26 best for aidatatang_test
|
| 41 |
-
|
| 42 |
-
2023-10-17 18:25:09,254 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_dev
|
| 43 |
-
2023-10-17 18:25:10,768 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 81
|
| 44 |
-
2023-10-17 18:25:21,290 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([1.6683, 3.5095, 3.2214, 3.0099], device='cuda:0')
|
| 45 |
-
2023-10-17 18:25:28,677 INFO [ctc_decode.py:485] batch 100/?, cuts processed until now is 9077
|
| 46 |
-
2023-10-17 18:25:45,744 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([5.3476, 5.0039, 5.2630, 5.0075], device='cuda:0')
|
| 47 |
-
2023-10-17 18:25:46,062 INFO [ctc_decode.py:485] batch 200/?, cuts processed until now is 18432
|
| 48 |
-
2023-10-17 18:25:58,007 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 49 |
-
2023-10-17 18:25:58,413 INFO [utils.py:565] [aidatatang_dev-ctc-decoding] %WER 14.58% [20723 / 142150, 3444 ins, 5445 del, 11834 sub ]
|
| 50 |
-
2023-10-17 18:25:59,266 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 51 |
-
2023-10-17 18:25:59,276 INFO [ctc_decode.py:522]
|
| 52 |
-
For aidatatang_dev, WER of different settings are:
|
| 53 |
-
ctc-decoding 14.58 best for aidatatang_dev
|
| 54 |
-
|
| 55 |
-
2023-10-17 18:25:59,277 INFO [ctc_decode.py:695] Start decoding test set: alimeeting_test
|
| 56 |
-
2023-10-17 18:26:01,217 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 44
|
| 57 |
-
2023-10-17 18:26:10,131 WARNING [ctc_decode.py:683] Excluding cut with ID: R8008_M8016-8062-123 from decoding, num_frames: 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-18-27-50
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
2023-10-17 18:27:50,959 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 18:27:50,959 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 18:27:50,959 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 18:27:52,674 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-17-18-28-40
DELETED
|
@@ -1,196 +0,0 @@
|
|
| 1 |
-
2023-10-17 18:28:40,557 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 18:28:40,557 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 18:28:40,557 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 1200, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 18:28:42,268 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 18:28:48,063 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 18:28:48,655 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
-
2023-10-17 18:28:53,461 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 18:28:53,462 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 18:28:53,462 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 18:28:53,480 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 18:28:53,483 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 18:28:53,486 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 18:28:53,488 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 18:28:53,492 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 18:28:53,495 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 18:28:53,500 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 18:28:59,880 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 18:29:00,864 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_test
|
| 19 |
-
2023-10-17 18:29:03,097 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 321
|
| 20 |
-
2023-10-17 18:29:55,906 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([2.2702, 2.7870, 3.1113, 2.7685], device='cuda:0')
|
| 21 |
-
2023-10-17 18:30:06,942 INFO [ctc_decode.py:485] batch 100/?, cuts processed until now is 35376
|
| 22 |
-
2023-10-17 18:30:29,144 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
|
| 23 |
-
2023-10-17 18:30:29,895 INFO [utils.py:565] [aidatatang_test-ctc-decoding] %WER 15.26% [43139 / 282666, 7245 ins, 10406 del, 25488 sub ]
|
| 24 |
-
2023-10-17 18:30:31,523 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
|
| 25 |
-
2023-10-17 18:30:31,526 INFO [ctc_decode.py:522]
|
| 26 |
-
For aidatatang_test, WER of different settings are:
|
| 27 |
-
ctc-decoding 15.26 best for aidatatang_test
|
| 28 |
-
|
| 29 |
-
2023-10-17 18:30:31,527 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_dev
|
| 30 |
-
2023-10-17 18:30:33,562 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 325
|
| 31 |
-
2023-10-17 18:31:02,140 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([4.4563, 4.2981, 3.9703, 4.6275], device='cuda:0')
|
| 32 |
-
2023-10-17 18:31:08,199 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.1070, 2.5969, 1.4553, 1.7578], device='cuda:0')
|
| 33 |
-
2023-10-17 18:31:08,818 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.7113, 3.0239, 2.1108, 2.3879], device='cuda:0')
|
| 34 |
-
2023-10-17 18:31:15,999 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 35 |
-
2023-10-17 18:31:16,380 INFO [utils.py:565] [aidatatang_dev-ctc-decoding] %WER 14.57% [20711 / 142150, 3442 ins, 5435 del, 11834 sub ]
|
| 36 |
-
2023-10-17 18:31:17,106 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 37 |
-
2023-10-17 18:31:17,110 INFO [ctc_decode.py:522]
|
| 38 |
-
For aidatatang_dev, WER of different settings are:
|
| 39 |
-
ctc-decoding 14.57 best for aidatatang_dev
|
| 40 |
-
|
| 41 |
-
2023-10-17 18:31:17,110 INFO [ctc_decode.py:695] Start decoding test set: alimeeting_test
|
| 42 |
-
2023-10-17 18:31:19,674 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 177
|
| 43 |
-
2023-10-17 18:31:25,592 WARNING [ctc_decode.py:683] Excluding cut with ID: R8008_M8016-8062-123 from decoding, num_frames: 6
|
| 44 |
-
2023-10-17 18:31:51,823 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 45 |
-
2023-10-17 18:31:51,924 INFO [utils.py:565] [alimeeting_test-ctc-decoding] %WER 69.70% [11401 / 16357, 1 ins, 2019 del, 9381 sub ]
|
| 46 |
-
2023-10-17 18:31:52,197 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 47 |
-
2023-10-17 18:31:52,201 INFO [ctc_decode.py:522]
|
| 48 |
-
For alimeeting_test, WER of different settings are:
|
| 49 |
-
ctc-decoding 69.7 best for alimeeting_test
|
| 50 |
-
|
| 51 |
-
2023-10-17 18:31:52,201 INFO [ctc_decode.py:695] Start decoding test set: alimeeting_eval
|
| 52 |
-
2023-10-17 18:31:54,746 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 140
|
| 53 |
-
2023-10-17 18:32:06,274 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt
|
| 54 |
-
2023-10-17 18:32:06,314 INFO [utils.py:565] [alimeeting_eval-ctc-decoding] %WER 72.85% [4704 / 6457, 0 ins, 930 del, 3774 sub ]
|
| 55 |
-
2023-10-17 18:32:06,496 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt
|
| 56 |
-
2023-10-17 18:32:06,499 INFO [ctc_decode.py:522]
|
| 57 |
-
For alimeeting_eval, WER of different settings are:
|
| 58 |
-
ctc-decoding 72.85 best for alimeeting_eval
|
| 59 |
-
|
| 60 |
-
2023-10-17 18:32:06,499 INFO [ctc_decode.py:695] Start decoding test set: aishell_test
|
| 61 |
-
2023-10-17 18:32:09,216 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 190
|
| 62 |
-
2023-10-17 18:32:15,951 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.6632, 3.6327, 2.7261, 2.6312], device='cuda:0')
|
| 63 |
-
2023-10-17 18:32:28,588 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell_test-epoch-20-avg-1-use-averaged-model.txt
|
| 64 |
-
2023-10-17 18:32:28,732 INFO [utils.py:565] [aishell_test-ctc-decoding] %WER 13.76% [8867 / 64428, 866 ins, 2091 del, 5910 sub ]
|
| 65 |
-
2023-10-17 18:32:29,114 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell_test-epoch-20-avg-1-use-averaged-model.txt
|
| 66 |
-
2023-10-17 18:32:29,118 INFO [ctc_decode.py:522]
|
| 67 |
-
For aishell_test, WER of different settings are:
|
| 68 |
-
ctc-decoding 13.76 best for aishell_test
|
| 69 |
-
|
| 70 |
-
2023-10-17 18:32:29,119 INFO [ctc_decode.py:695] Start decoding test set: aishell_dev
|
| 71 |
-
2023-10-17 18:32:32,157 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 215
|
| 72 |
-
2023-10-17 18:33:07,311 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 73 |
-
2023-10-17 18:33:07,677 INFO [utils.py:565] [aishell_dev-ctc-decoding] %WER 12.87% [16438 / 127698, 1671 ins, 3693 del, 11074 sub ]
|
| 74 |
-
2023-10-17 18:33:08,275 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 75 |
-
2023-10-17 18:33:08,279 INFO [ctc_decode.py:522]
|
| 76 |
-
For aishell_dev, WER of different settings are:
|
| 77 |
-
ctc-decoding 12.87 best for aishell_dev
|
| 78 |
-
|
| 79 |
-
2023-10-17 18:33:08,279 INFO [ctc_decode.py:695] Start decoding test set: aishell-2_test
|
| 80 |
-
2023-10-17 18:33:10,740 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 334
|
| 81 |
-
2023-10-17 18:33:18,787 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
|
| 82 |
-
2023-10-17 18:33:18,825 INFO [utils.py:565] [aishell-2_test-ctc-decoding] %WER 25.55% [1278 / 5002, 0 ins, 3 del, 1275 sub ]
|
| 83 |
-
2023-10-17 18:33:18,904 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
|
| 84 |
-
2023-10-17 18:33:18,907 INFO [ctc_decode.py:522]
|
| 85 |
-
For aishell-2_test, WER of different settings are:
|
| 86 |
-
ctc-decoding 25.55 best for aishell-2_test
|
| 87 |
-
|
| 88 |
-
2023-10-17 18:33:18,907 INFO [ctc_decode.py:695] Start decoding test set: aishell-2_dev
|
| 89 |
-
2023-10-17 18:33:20,413 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 209
|
| 90 |
-
2023-10-17 18:33:24,585 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 91 |
-
2023-10-17 18:33:24,602 INFO [utils.py:565] [aishell-2_dev-ctc-decoding] %WER 23.56% [589 / 2500, 0 ins, 0 del, 589 sub ]
|
| 92 |
-
2023-10-17 18:33:24,638 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 93 |
-
2023-10-17 18:33:24,642 INFO [ctc_decode.py:522]
|
| 94 |
-
For aishell-2_dev, WER of different settings are:
|
| 95 |
-
ctc-decoding 23.56 best for aishell-2_dev
|
| 96 |
-
|
| 97 |
-
2023-10-17 18:33:24,642 INFO [ctc_decode.py:695] Start decoding test set: aishell-4
|
| 98 |
-
2023-10-17 18:33:28,250 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 132
|
| 99 |
-
2023-10-17 18:33:57,329 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell-4-epoch-20-avg-1-use-averaged-model.txt
|
| 100 |
-
2023-10-17 18:33:57,399 INFO [utils.py:565] [aishell-4-ctc-decoding] %WER 71.75% [7590 / 10579, 47 ins, 534 del, 7009 sub ]
|
| 101 |
-
2023-10-17 18:33:57,590 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell-4-epoch-20-avg-1-use-averaged-model.txt
|
| 102 |
-
2023-10-17 18:33:57,593 INFO [ctc_decode.py:522]
|
| 103 |
-
For aishell-4, WER of different settings are:
|
| 104 |
-
ctc-decoding 71.75 best for aishell-4
|
| 105 |
-
|
| 106 |
-
2023-10-17 18:33:57,594 INFO [ctc_decode.py:695] Start decoding test set: magicdata_test
|
| 107 |
-
2023-10-17 18:34:00,583 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 230
|
| 108 |
-
2023-10-17 18:35:01,490 INFO [ctc_decode.py:485] batch 100/?, cuts processed until now is 23940
|
| 109 |
-
2023-10-17 18:35:02,615 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt
|
| 110 |
-
2023-10-17 18:35:02,855 INFO [utils.py:565] [magicdata_test-ctc-decoding] %WER 19.34% [4698 / 24286, 284 ins, 7 del, 4407 sub ]
|
| 111 |
-
2023-10-17 18:35:03,201 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt
|
| 112 |
-
2023-10-17 18:35:03,205 INFO [ctc_decode.py:522]
|
| 113 |
-
For magicdata_test, WER of different settings are:
|
| 114 |
-
ctc-decoding 19.34 best for magicdata_test
|
| 115 |
-
|
| 116 |
-
2023-10-17 18:35:03,205 INFO [ctc_decode.py:695] Start decoding test set: magicdata_dev
|
| 117 |
-
2023-10-17 18:35:06,237 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 211
|
| 118 |
-
2023-10-17 18:35:24,163 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([2.0037, 2.2850, 2.0049, 3.6487], device='cuda:0')
|
| 119 |
-
2023-10-17 18:35:38,292 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 120 |
-
2023-10-17 18:35:38,366 INFO [utils.py:565] [magicdata_dev-ctc-decoding] %WER 22.35% [2653 / 11872, 22 ins, 79 del, 2552 sub ]
|
| 121 |
-
2023-10-17 18:35:38,552 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 122 |
-
2023-10-17 18:35:38,556 INFO [ctc_decode.py:522]
|
| 123 |
-
For magicdata_dev, WER of different settings are:
|
| 124 |
-
ctc-decoding 22.35 best for magicdata_dev
|
| 125 |
-
|
| 126 |
-
2023-10-17 18:35:38,556 INFO [ctc_decode.py:695] Start decoding test set: kespeech-asr_test
|
| 127 |
-
2023-10-17 18:35:41,963 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 179
|
| 128 |
-
2023-10-17 18:35:48,964 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([2.2457, 2.7709, 3.0159, 2.7526, 2.8671, 2.7205, 3.0313, 2.9588],
|
| 129 |
-
device='cuda:0')
|
| 130 |
-
2023-10-17 18:35:52,190 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([2.1268, 2.6636, 2.8915, 2.6335, 2.7311, 2.5814, 2.9027, 2.8249],
|
| 131 |
-
device='cuda:0')
|
| 132 |
-
2023-10-17 18:36:14,760 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([5.0753, 4.3347, 4.8011, 4.4720], device='cuda:0')
|
| 133 |
-
2023-10-17 18:36:18,629 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.0111, 4.3811, 3.5554, 3.9260], device='cuda:0')
|
| 134 |
-
2023-10-17 18:36:19,830 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([5.0782, 4.3275, 4.7918, 4.4625], device='cuda:0')
|
| 135 |
-
2023-10-17 18:36:45,716 INFO [ctc_decode.py:485] batch 100/?, cuts processed until now is 19455
|
| 136 |
-
2023-10-17 18:36:46,846 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt
|
| 137 |
-
2023-10-17 18:36:46,972 INFO [utils.py:565] [kespeech-asr_test-ctc-decoding] %WER 48.71% [9608 / 19723, 0 ins, 3 del, 9605 sub ]
|
| 138 |
-
2023-10-17 18:36:47,307 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt
|
| 139 |
-
2023-10-17 18:36:47,311 INFO [ctc_decode.py:522]
|
| 140 |
-
For kespeech-asr_test, WER of different settings are:
|
| 141 |
-
ctc-decoding 48.71 best for kespeech-asr_test
|
| 142 |
-
|
| 143 |
-
2023-10-17 18:36:47,312 INFO [ctc_decode.py:695] Start decoding test set: kespeech-asr_dev_phase1
|
| 144 |
-
2023-10-17 18:36:49,451 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 179
|
| 145 |
-
2023-10-17 18:36:56,484 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt
|
| 146 |
-
2023-10-17 18:36:56,499 INFO [utils.py:565] [kespeech-asr_dev_phase1-ctc-decoding] %WER 42.38% [932 / 2199, 0 ins, 0 del, 932 sub ]
|
| 147 |
-
2023-10-17 18:36:56,534 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt
|
| 148 |
-
2023-10-17 18:36:56,537 INFO [ctc_decode.py:522]
|
| 149 |
-
For kespeech-asr_dev_phase1, WER of different settings are:
|
| 150 |
-
ctc-decoding 42.38 best for kespeech-asr_dev_phase1
|
| 151 |
-
|
| 152 |
-
2023-10-17 18:36:56,537 INFO [ctc_decode.py:695] Start decoding test set: kespeech-asr_dev_phase2
|
| 153 |
-
2023-10-17 18:36:58,442 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 175
|
| 154 |
-
2023-10-17 18:37:05,129 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt
|
| 155 |
-
2023-10-17 18:37:05,145 INFO [utils.py:565] [kespeech-asr_dev_phase2-ctc-decoding] %WER 26.90% [594 / 2208, 0 ins, 0 del, 594 sub ]
|
| 156 |
-
2023-10-17 18:37:05,178 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt
|
| 157 |
-
2023-10-17 18:37:05,181 INFO [ctc_decode.py:522]
|
| 158 |
-
For kespeech-asr_dev_phase2, WER of different settings are:
|
| 159 |
-
ctc-decoding 26.9 best for kespeech-asr_dev_phase2
|
| 160 |
-
|
| 161 |
-
2023-10-17 18:37:05,182 INFO [ctc_decode.py:695] Start decoding test set: wenetspeech-meeting_test
|
| 162 |
-
2023-10-17 18:37:07,190 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 112
|
| 163 |
-
2023-10-17 18:37:33,122 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([1.8152, 2.0526, 1.9635, 2.3204, 2.4993, 2.4532, 2.2485, 1.9477],
|
| 164 |
-
device='cuda:0')
|
| 165 |
-
2023-10-17 18:37:41,448 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 166 |
-
2023-10-17 18:37:41,502 INFO [utils.py:565] [wenetspeech-meeting_test-ctc-decoding] %WER 67.29% [5632 / 8370, 2 ins, 0 del, 5630 sub ]
|
| 167 |
-
2023-10-17 18:37:41,673 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 168 |
-
2023-10-17 18:37:41,676 INFO [ctc_decode.py:522]
|
| 169 |
-
For wenetspeech-meeting_test, WER of different settings are:
|
| 170 |
-
ctc-decoding 67.29 best for wenetspeech-meeting_test
|
| 171 |
-
|
| 172 |
-
2023-10-17 18:37:41,676 INFO [ctc_decode.py:695] Start decoding test set: wenetspeech-net_test
|
| 173 |
-
2023-10-17 18:37:41,901 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 174 |
-
2023-10-17 18:37:43,917 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 175
|
| 175 |
-
2023-10-17 18:38:04,564 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([4.2461, 2.2640, 4.2913, 3.8631], device='cuda:0')
|
| 176 |
-
2023-10-17 18:38:08,841 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([3.7114, 3.6090, 3.4062, 3.7334], device='cuda:0')
|
| 177 |
-
2023-10-17 18:38:38,781 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt
|
| 178 |
-
2023-10-17 18:38:39,042 INFO [utils.py:565] [wenetspeech-net_test-ctc-decoding] %WER 54.24% [13438 / 24773, 2 ins, 19 del, 13417 sub ]
|
| 179 |
-
2023-10-17 18:38:39,477 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt
|
| 180 |
-
2023-10-17 18:38:39,480 INFO [ctc_decode.py:522]
|
| 181 |
-
For wenetspeech-net_test, WER of different settings are:
|
| 182 |
-
ctc-decoding 54.24 best for wenetspeech-net_test
|
| 183 |
-
|
| 184 |
-
2023-10-17 18:38:39,481 INFO [ctc_decode.py:695] Start decoding test set: wenetspeech_dev
|
| 185 |
-
2023-10-17 18:38:41,576 INFO [ctc_decode.py:485] batch 0/?, cuts processed until now is 157
|
| 186 |
-
2023-10-17 18:38:51,281 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([4.5085, 2.3355, 4.5779, 4.0812], device='cuda:0')
|
| 187 |
-
2023-10-17 18:39:09,310 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([2.2675, 3.6412, 3.7390, 3.8346], device='cuda:0')
|
| 188 |
-
2023-10-17 18:39:20,015 INFO [zipformer.py:1853] name=None, attn_weights_entropy = tensor([1.0711, 2.5839, 2.5771, 3.9200], device='cuda:0')
|
| 189 |
-
2023-10-17 18:39:24,326 INFO [ctc_decode.py:499] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 190 |
-
2023-10-17 18:39:24,419 INFO [utils.py:565] [wenetspeech_dev-ctc-decoding] %WER 64.88% [8970 / 13825, 1 ins, 1 del, 8968 sub ]
|
| 191 |
-
2023-10-17 18:39:24,662 INFO [ctc_decode.py:508] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 192 |
-
2023-10-17 18:39:24,666 INFO [ctc_decode.py:522]
|
| 193 |
-
For wenetspeech_dev, WER of different settings are:
|
| 194 |
-
ctc-decoding 64.88 best for wenetspeech_dev
|
| 195 |
-
|
| 196 |
-
2023-10-17 18:39:24,666 INFO [ctc_decode.py:714] Done!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-20-avg-1-use-averaged-model-2023-10-25-16-34-00
ADDED
|
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2023-10-25 16:34:00,598 INFO [ctc_decode.py:562] Decoding started
|
| 2 |
+
2023-10-25 16:34:00,599 INFO [ctc_decode.py:568] Device: cuda:0
|
| 3 |
+
2023-10-25 16:34:00,599 INFO [ctc_decode.py:569] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_zipformer_cn', 'icefall-git-sha1': '5b9014f7-clean', 'icefall-git-date': 'Tue Oct 24 16:08:39 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 20, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-20-avg-1-use-averaged-model'}
|
| 4 |
+
2023-10-25 16:34:02,303 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
+
2023-10-25 16:34:06,584 INFO [ctc_decode.py:589] About to create model
|
| 6 |
+
2023-10-25 16:34:07,103 INFO [ctc_decode.py:656] Calculating the averaged model over epoch range from 19 (excluded) to 20
|
| 7 |
+
2023-10-25 16:34:10,515 INFO [ctc_decode.py:673] Number of model parameters: 69651511
|
| 8 |
+
2023-10-25 16:34:10,516 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
+
2023-10-25 16:34:10,516 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
+
2023-10-25 16:34:10,537 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
+
2023-10-25 16:34:10,541 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
+
2023-10-25 16:34:10,544 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
+
2023-10-25 16:34:10,546 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
+
2023-10-25 16:34:10,549 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
+
2023-10-25 16:34:10,553 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
+
2023-10-25 16:34:10,558 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
+
2023-10-25 16:34:16,524 WARNING [ctc_decode.py:685] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
+
2023-10-25 16:34:17,479 INFO [ctc_decode.py:697] Start decoding test set: aidatatang_test
|
| 19 |
+
2023-10-25 16:34:18,685 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 80
|
| 20 |
+
2023-10-25 16:34:21,412 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.0520, 3.1377, 2.0728, 2.0816], device='cuda:0')
|
| 21 |
+
2023-10-25 16:34:30,837 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.5011, 3.0861, 3.4112, 3.0793], device='cuda:0')
|
| 22 |
+
2023-10-25 16:34:36,258 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 9084
|
| 23 |
+
2023-10-25 16:34:53,909 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 18516
|
| 24 |
+
2023-10-25 16:35:05,250 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.4200, 3.4877, 2.4226, 2.5617], device='cuda:0')
|
| 25 |
+
2023-10-25 16:35:11,730 INFO [ctc_decode.py:487] batch 300/?, cuts processed until now is 28179
|
| 26 |
+
2023-10-25 16:35:26,845 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.9498, 2.2983, 2.4953, 2.2775, 2.2739, 2.2083, 2.3184, 2.3589],
|
| 27 |
+
device='cuda:0')
|
| 28 |
+
2023-10-25 16:35:29,566 INFO [ctc_decode.py:487] batch 400/?, cuts processed until now is 37667
|
| 29 |
+
2023-10-25 16:35:46,177 INFO [ctc_decode.py:487] batch 500/?, cuts processed until now is 46172
|
| 30 |
+
2023-10-25 16:35:52,683 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
|
| 31 |
+
2023-10-25 16:35:53,533 INFO [utils.py:565] [aidatatang_test-ctc-decoding] %WER 3.36% [15767 / 468933, 2081 ins, 1924 del, 11762 sub ]
|
| 32 |
+
2023-10-25 16:35:55,168 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
|
| 33 |
+
2023-10-25 16:35:55,171 INFO [ctc_decode.py:524]
|
| 34 |
+
For aidatatang_test, WER of different settings are:
|
| 35 |
+
ctc-decoding 3.36 best for aidatatang_test
|
| 36 |
+
|
| 37 |
+
2023-10-25 16:35:55,172 INFO [ctc_decode.py:697] Start decoding test set: aidatatang_dev
|
| 38 |
+
2023-10-25 16:35:56,437 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 81
|
| 39 |
+
2023-10-25 16:36:14,093 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 9077
|
| 40 |
+
2023-10-25 16:36:14,382 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1796, 2.6064, 2.9965, 2.5505], device='cuda:0')
|
| 41 |
+
2023-10-25 16:36:16,426 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.6213, 2.0994, 2.2801, 2.0023, 2.2536, 2.3341, 1.9518, 2.1787],
|
| 42 |
+
device='cuda:0')
|
| 43 |
+
2023-10-25 16:36:19,104 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1558, 2.5520, 2.9477, 2.5092], device='cuda:0')
|
| 44 |
+
2023-10-25 16:36:24,127 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.8962, 2.4230, 2.6258, 2.3016, 2.5764, 2.6809, 2.2256, 2.4345],
|
| 45 |
+
device='cuda:0')
|
| 46 |
+
2023-10-25 16:36:31,096 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 18432
|
| 47 |
+
2023-10-25 16:36:31,516 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.8450, 2.0634, 2.1508, 1.8092], device='cuda:0')
|
| 48 |
+
2023-10-25 16:36:32,160 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1301, 3.0183, 2.9528, 3.0556], device='cuda:0')
|
| 49 |
+
2023-10-25 16:36:34,442 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1589, 3.0802, 3.0217, 3.1254], device='cuda:0')
|
| 50 |
+
2023-10-25 16:36:42,515 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 51 |
+
2023-10-25 16:36:42,937 INFO [utils.py:565] [aidatatang_dev-ctc-decoding] %WER 2.86% [6716 / 234524, 886 ins, 1013 del, 4817 sub ]
|
| 52 |
+
2023-10-25 16:36:43,764 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 53 |
+
2023-10-25 16:36:43,768 INFO [ctc_decode.py:524]
|
| 54 |
+
For aidatatang_dev, WER of different settings are:
|
| 55 |
+
ctc-decoding 2.86 best for aidatatang_dev
|
| 56 |
+
|
| 57 |
+
2023-10-25 16:36:43,768 INFO [ctc_decode.py:697] Start decoding test set: alimeeting_test
|
| 58 |
+
2023-10-25 16:36:45,313 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 44
|
| 59 |
+
2023-10-25 16:36:48,073 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.4251, 3.2546, 3.0462, 3.0440], device='cuda:0')
|
| 60 |
+
2023-10-25 16:36:50,228 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.9540, 1.9129, 2.0041, 3.1405], device='cuda:0')
|
| 61 |
+
2023-10-25 16:36:53,939 WARNING [ctc_decode.py:685] Excluding cut with ID: R8008_M8016-8062-123 from decoding, num_frames: 6
|
| 62 |
+
2023-10-25 16:37:06,497 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 7625
|
| 63 |
+
2023-10-25 16:37:10,965 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.8114, 2.8180, 1.8182, 1.8959], device='cuda:0')
|
| 64 |
+
2023-10-25 16:37:23,583 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 65 |
+
2023-10-25 16:37:23,991 INFO [utils.py:565] [alimeeting_test-ctc-decoding] %WER 24.28% [50952 / 209845, 4093 ins, 24060 del, 22799 sub ]
|
| 66 |
+
2023-10-25 16:37:24,829 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 67 |
+
2023-10-25 16:37:24,833 INFO [ctc_decode.py:524]
|
| 68 |
+
For alimeeting_test, WER of different settings are:
|
| 69 |
+
ctc-decoding 24.28 best for alimeeting_test
|
| 70 |
+
|
| 71 |
+
2023-10-25 16:37:24,833 INFO [ctc_decode.py:697] Start decoding test set: alimeeting_eval
|
| 72 |
+
2023-10-25 16:37:25,951 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 35
|
| 73 |
+
2023-10-25 16:37:40,611 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt
|
| 74 |
+
2023-10-25 16:37:40,758 INFO [utils.py:565] [alimeeting_eval-ctc-decoding] %WER 22.93% [18597 / 81111, 1605 ins, 8426 del, 8566 sub ]
|
| 75 |
+
2023-10-25 16:37:41,068 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt
|
| 76 |
+
2023-10-25 16:37:41,071 INFO [ctc_decode.py:524]
|
| 77 |
+
For alimeeting_eval, WER of different settings are:
|
| 78 |
+
ctc-decoding 22.93 best for alimeeting_eval
|
| 79 |
+
|
| 80 |
+
2023-10-25 16:37:41,072 INFO [ctc_decode.py:697] Start decoding test set: aishell_test
|
| 81 |
+
2023-10-25 16:37:42,054 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 47
|
| 82 |
+
2023-10-25 16:37:58,933 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 5468
|
| 83 |
+
2023-10-25 16:38:03,464 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.8423, 3.3145, 3.6725, 3.2758, 3.5179, 3.1670, 3.0848, 3.5636],
|
| 84 |
+
device='cuda:0')
|
| 85 |
+
2023-10-25 16:38:04,510 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell_test-epoch-20-avg-1-use-averaged-model.txt
|
| 86 |
+
2023-10-25 16:38:04,686 INFO [utils.py:565] [aishell_test-ctc-decoding] %WER 2.27% [2380 / 104765, 359 ins, 80 del, 1941 sub ]
|
| 87 |
+
2023-10-25 16:38:05,034 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell_test-epoch-20-avg-1-use-averaged-model.txt
|
| 88 |
+
2023-10-25 16:38:05,037 INFO [ctc_decode.py:524]
|
| 89 |
+
For aishell_test, WER of different settings are:
|
| 90 |
+
ctc-decoding 2.27 best for aishell_test
|
| 91 |
+
|
| 92 |
+
2023-10-25 16:38:05,038 INFO [ctc_decode.py:697] Start decoding test set: aishell_dev
|
| 93 |
+
2023-10-25 16:38:06,188 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 53
|
| 94 |
+
2023-10-25 16:38:06,246 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1611, 4.0929, 3.5322, 3.4682], device='cuda:0')
|
| 95 |
+
2023-10-25 16:38:08,335 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.0768, 2.5535, 2.8456, 2.5765, 2.6620, 2.4640, 2.3513, 2.7931],
|
| 96 |
+
device='cuda:0')
|
| 97 |
+
2023-10-25 16:38:10,493 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.4007, 4.5441, 5.0637, 4.6880], device='cuda:0')
|
| 98 |
+
2023-10-25 16:38:11,557 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.7117, 3.1288, 3.5261, 2.2668], device='cuda:0')
|
| 99 |
+
2023-10-25 16:38:14,764 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1489, 3.2889, 3.1936, 3.3052], device='cuda:0')
|
| 100 |
+
2023-10-25 16:38:23,271 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 6034
|
| 101 |
+
2023-10-25 16:38:39,877 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 12198
|
| 102 |
+
2023-10-25 16:38:44,231 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.0977, 2.4464, 2.9487, 1.8454], device='cuda:0')
|
| 103 |
+
2023-10-25 16:38:46,332 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 104 |
+
2023-10-25 16:38:46,686 INFO [utils.py:565] [aishell_dev-ctc-decoding] %WER 2.05% [4219 / 205341, 720 ins, 129 del, 3370 sub ]
|
| 105 |
+
2023-10-25 16:38:47,358 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 106 |
+
2023-10-25 16:38:47,361 INFO [ctc_decode.py:524]
|
| 107 |
+
For aishell_dev, WER of different settings are:
|
| 108 |
+
ctc-decoding 2.05 best for aishell_dev
|
| 109 |
+
|
| 110 |
+
2023-10-25 16:38:47,361 INFO [ctc_decode.py:697] Start decoding test set: aishell-2_test
|
| 111 |
+
2023-10-25 16:38:48,202 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 83
|
| 112 |
+
2023-10-25 16:38:58,110 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
|
| 113 |
+
2023-10-25 16:38:58,203 INFO [utils.py:565] [aishell-2_test-ctc-decoding] %WER 3.82% [1891 / 49532, 220 ins, 106 del, 1565 sub ]
|
| 114 |
+
2023-10-25 16:38:58,387 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
|
| 115 |
+
2023-10-25 16:38:58,390 INFO [ctc_decode.py:524]
|
| 116 |
+
For aishell-2_test, WER of different settings are:
|
| 117 |
+
ctc-decoding 3.82 best for aishell-2_test
|
| 118 |
+
|
| 119 |
+
2023-10-25 16:38:58,390 INFO [ctc_decode.py:697] Start decoding test set: aishell-2_dev
|
| 120 |
+
2023-10-25 16:38:59,005 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 81
|
| 121 |
+
2023-10-25 16:39:03,843 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 122 |
+
2023-10-25 16:39:03,888 INFO [utils.py:565] [aishell-2_dev-ctc-decoding] %WER 3.33% [825 / 24802, 68 ins, 34 del, 723 sub ]
|
| 123 |
+
2023-10-25 16:39:03,981 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 124 |
+
2023-10-25 16:39:03,984 INFO [ctc_decode.py:524]
|
| 125 |
+
For aishell-2_dev, WER of different settings are:
|
| 126 |
+
ctc-decoding 3.33 best for aishell-2_dev
|
| 127 |
+
|
| 128 |
+
2023-10-25 16:39:03,984 INFO [ctc_decode.py:697] Start decoding test set: aishell-4
|
| 129 |
+
2023-10-25 16:39:05,396 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 33
|
| 130 |
+
2023-10-25 16:39:06,514 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.7161, 3.0260, 3.4697, 3.0798, 3.1194, 2.9266, 3.3018, 3.3440],
|
| 131 |
+
device='cuda:0')
|
| 132 |
+
2023-10-25 16:39:13,020 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.4888, 4.7211, 5.2793, 4.8764], device='cuda:0')
|
| 133 |
+
2023-10-25 16:39:25,289 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 5000
|
| 134 |
+
2023-10-25 16:39:37,714 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.4363, 2.2623, 2.1157, 2.1364], device='cuda:0')
|
| 135 |
+
2023-10-25 16:39:39,959 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-aishell-4-epoch-20-avg-1-use-averaged-model.txt
|
| 136 |
+
2023-10-25 16:39:40,276 INFO [utils.py:565] [aishell-4-ctc-decoding] %WER 15.45% [27907 / 180665, 4812 ins, 8373 del, 14722 sub ]
|
| 137 |
+
2023-10-25 16:39:40,915 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-aishell-4-epoch-20-avg-1-use-averaged-model.txt
|
| 138 |
+
2023-10-25 16:39:40,922 INFO [ctc_decode.py:524]
|
| 139 |
+
For aishell-4, WER of different settings are:
|
| 140 |
+
ctc-decoding 15.45 best for aishell-4
|
| 141 |
+
|
| 142 |
+
2023-10-25 16:39:40,923 INFO [ctc_decode.py:697] Start decoding test set: magicdata_test
|
| 143 |
+
2023-10-25 16:39:42,150 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 57
|
| 144 |
+
2023-10-25 16:39:45,980 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.2365, 3.2766, 3.2887, 3.2825], device='cuda:0')
|
| 145 |
+
2023-10-25 16:39:59,489 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.5007, 3.1130, 3.2352, 2.9490, 3.2145, 2.7877, 2.3506, 2.7924],
|
| 146 |
+
device='cuda:0')
|
| 147 |
+
2023-10-25 16:40:00,114 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 6425
|
| 148 |
+
2023-10-25 16:40:01,578 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.3456, 2.5491, 4.3242, 1.8453], device='cuda:0')
|
| 149 |
+
2023-10-25 16:40:01,887 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.3791, 4.0503, 3.3906, 3.4577], device='cuda:0')
|
| 150 |
+
2023-10-25 16:40:18,421 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 13211
|
| 151 |
+
2023-10-25 16:40:20,419 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.2894, 3.1911, 3.2014, 3.2303], device='cuda:0')
|
| 152 |
+
2023-10-25 16:40:35,794 INFO [ctc_decode.py:487] batch 300/?, cuts processed until now is 20136
|
| 153 |
+
2023-10-25 16:40:52,211 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt
|
| 154 |
+
2023-10-25 16:40:52,654 INFO [utils.py:565] [magicdata_test-ctc-decoding] %WER 2.77% [6622 / 239091, 1024 ins, 428 del, 5170 sub ]
|
| 155 |
+
2023-10-25 16:40:53,509 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt
|
| 156 |
+
2023-10-25 16:40:53,512 INFO [ctc_decode.py:524]
|
| 157 |
+
For magicdata_test, WER of different settings are:
|
| 158 |
+
ctc-decoding 2.77 best for magicdata_test
|
| 159 |
+
|
| 160 |
+
2023-10-25 16:40:53,513 INFO [ctc_decode.py:697] Start decoding test set: magicdata_dev
|
| 161 |
+
2023-10-25 16:40:54,770 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 52
|
| 162 |
+
2023-10-25 16:40:54,808 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.1237, 4.6547, 5.0120, 4.7204], device='cuda:0')
|
| 163 |
+
2023-10-25 16:41:10,069 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.4620, 2.6096, 4.3213, 1.8959], device='cuda:0')
|
| 164 |
+
2023-10-25 16:41:11,956 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.0565, 2.5376, 2.6165, 2.4429, 2.4652, 2.3741, 1.8434, 2.0589],
|
| 165 |
+
device='cuda:0')
|
| 166 |
+
2023-10-25 16:41:12,750 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 5919
|
| 167 |
+
2023-10-25 16:41:24,277 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.8365, 2.6056, 3.9032, 2.6469], device='cuda:0')
|
| 168 |
+
2023-10-25 16:41:29,523 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.2491, 3.8004, 4.2328, 4.2613], device='cuda:0')
|
| 169 |
+
2023-10-25 16:41:30,449 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 11646
|
| 170 |
+
2023-10-25 16:41:31,119 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.4962, 2.5740, 2.7954, 3.6154], device='cuda:0')
|
| 171 |
+
2023-10-25 16:41:31,588 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 172 |
+
2023-10-25 16:41:31,804 INFO [utils.py:565] [magicdata_dev-ctc-decoding] %WER 3.49% [4080 / 116800, 645 ins, 274 del, 3161 sub ]
|
| 173 |
+
2023-10-25 16:41:32,228 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 174 |
+
2023-10-25 16:41:32,231 INFO [ctc_decode.py:524]
|
| 175 |
+
For magicdata_dev, WER of different settings are:
|
| 176 |
+
ctc-decoding 3.49 best for magicdata_dev
|
| 177 |
+
|
| 178 |
+
2023-10-25 16:41:32,232 INFO [ctc_decode.py:697] Start decoding test set: kespeech-asr_test
|
| 179 |
+
2023-10-25 16:41:33,489 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 45
|
| 180 |
+
2023-10-25 16:41:38,619 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1330, 2.6924, 2.8790, 2.6249, 2.7502, 2.6020, 2.9186, 2.8276],
|
| 181 |
+
device='cuda:0')
|
| 182 |
+
2023-10-25 16:41:52,367 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 4867
|
| 183 |
+
2023-10-25 16:42:11,157 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 9965
|
| 184 |
+
2023-10-25 16:42:29,384 INFO [ctc_decode.py:487] batch 300/?, cuts processed until now is 15124
|
| 185 |
+
2023-10-25 16:42:47,690 INFO [ctc_decode.py:487] batch 400/?, cuts processed until now is 19643
|
| 186 |
+
2023-10-25 16:42:48,374 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt
|
| 187 |
+
2023-10-25 16:42:48,854 INFO [utils.py:565] [kespeech-asr_test-ctc-decoding] %WER 8.29% [23525 / 283772, 2738 ins, 1869 del, 18918 sub ]
|
| 188 |
+
2023-10-25 16:42:49,821 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt
|
| 189 |
+
2023-10-25 16:42:49,825 INFO [ctc_decode.py:524]
|
| 190 |
+
For kespeech-asr_test, WER of different settings are:
|
| 191 |
+
ctc-decoding 8.29 best for kespeech-asr_test
|
| 192 |
+
|
| 193 |
+
2023-10-25 16:42:49,825 INFO [ctc_decode.py:697] Start decoding test set: kespeech-asr_dev_phase1
|
| 194 |
+
2023-10-25 16:42:50,401 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 44
|
| 195 |
+
2023-10-25 16:42:56,659 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.4923, 4.8152, 5.2681, 4.9011], device='cuda:0')
|
| 196 |
+
2023-10-25 16:42:58,778 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt
|
| 197 |
+
2023-10-25 16:42:58,837 INFO [utils.py:565] [kespeech-asr_dev_phase1-ctc-decoding] %WER 6.90% [2182 / 31634, 293 ins, 184 del, 1705 sub ]
|
| 198 |
+
2023-10-25 16:42:58,950 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt
|
| 199 |
+
2023-10-25 16:42:58,953 INFO [ctc_decode.py:524]
|
| 200 |
+
For kespeech-asr_dev_phase1, WER of different settings are:
|
| 201 |
+
ctc-decoding 6.9 best for kespeech-asr_dev_phase1
|
| 202 |
+
|
| 203 |
+
2023-10-25 16:42:58,953 INFO [ctc_decode.py:697] Start decoding test set: kespeech-asr_dev_phase2
|
| 204 |
+
2023-10-25 16:42:59,835 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 47
|
| 205 |
+
2023-10-25 16:43:06,820 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.6326, 2.9347, 4.1799, 2.9961], device='cuda:0')
|
| 206 |
+
2023-10-25 16:43:07,937 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt
|
| 207 |
+
2023-10-25 16:43:07,995 INFO [utils.py:565] [kespeech-asr_dev_phase2-ctc-decoding] %WER 2.85% [910 / 31928, 133 ins, 58 del, 719 sub ]
|
| 208 |
+
2023-10-25 16:43:08,106 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt
|
| 209 |
+
2023-10-25 16:43:08,109 INFO [ctc_decode.py:524]
|
| 210 |
+
For kespeech-asr_dev_phase2, WER of different settings are:
|
| 211 |
+
ctc-decoding 2.85 best for kespeech-asr_dev_phase2
|
| 212 |
+
|
| 213 |
+
2023-10-25 16:43:08,110 INFO [ctc_decode.py:697] Start decoding test set: wenetspeech-meeting_test
|
| 214 |
+
2023-10-25 16:43:09,586 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 28
|
| 215 |
+
2023-10-25 16:43:22,437 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.8702, 3.0656, 1.9713, 2.1329], device='cuda:0')
|
| 216 |
+
2023-10-25 16:43:23,655 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.9881, 2.5628, 4.7751, 1.8426], device='cuda:0')
|
| 217 |
+
2023-10-25 16:43:25,199 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.5829, 2.5263, 2.3613, 4.8147], device='cuda:0')
|
| 218 |
+
2023-10-25 16:43:30,212 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 3776
|
| 219 |
+
2023-10-25 16:43:48,162 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.2392, 2.2775, 2.1982, 3.4906], device='cuda:0')
|
| 220 |
+
2023-10-25 16:43:49,940 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 8092
|
| 221 |
+
2023-10-25 16:43:51,128 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.1897, 3.7199, 3.5001, 4.8150], device='cuda:0')
|
| 222 |
+
2023-10-25 16:43:51,827 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 223 |
+
2023-10-25 16:43:52,189 INFO [utils.py:565] [wenetspeech-meeting_test-ctc-decoding] %WER 6.92% [15242 / 220385, 1952 ins, 3482 del, 9808 sub ]
|
| 224 |
+
2023-10-25 16:43:52,902 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt
|
| 225 |
+
2023-10-25 16:43:52,906 INFO [ctc_decode.py:524]
|
| 226 |
+
For wenetspeech-meeting_test, WER of different settings are:
|
| 227 |
+
ctc-decoding 6.92 best for wenetspeech-meeting_test
|
| 228 |
+
|
| 229 |
+
2023-10-25 16:43:52,906 INFO [ctc_decode.py:697] Start decoding test set: wenetspeech-net_test
|
| 230 |
+
2023-10-25 16:43:53,117 WARNING [ctc_decode.py:685] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 231 |
+
2023-10-25 16:43:54,558 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 43
|
| 232 |
+
2023-10-25 16:44:04,413 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.0308, 2.1754, 2.2245, 3.5140], device='cuda:0')
|
| 233 |
+
2023-10-25 16:44:11,513 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.8906, 1.8713, 1.7192, 2.6720], device='cuda:0')
|
| 234 |
+
2023-10-25 16:44:12,503 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([0.9986, 1.9138, 1.9920, 2.9444], device='cuda:0')
|
| 235 |
+
2023-10-25 16:44:14,225 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 7009
|
| 236 |
+
2023-10-25 16:44:30,429 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.9908, 2.6090, 2.9691, 2.9051], device='cuda:0')
|
| 237 |
+
2023-10-25 16:44:31,876 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([4.7256, 4.8738, 3.7879, 3.5543], device='cuda:0')
|
| 238 |
+
2023-10-25 16:44:33,966 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 14995
|
| 239 |
+
2023-10-25 16:44:45,561 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.4122, 2.4497, 1.7039, 1.7159], device='cuda:0')
|
| 240 |
+
2023-10-25 16:44:52,612 INFO [ctc_decode.py:487] batch 300/?, cuts processed until now is 22693
|
| 241 |
+
2023-10-25 16:44:58,577 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt
|
| 242 |
+
2023-10-25 16:44:59,335 INFO [utils.py:565] [wenetspeech-net_test-ctc-decoding] %WER 8.57% [35611 / 415746, 2894 ins, 13613 del, 19104 sub ]
|
| 243 |
+
2023-10-25 16:45:00,779 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt
|
| 244 |
+
2023-10-25 16:45:00,782 INFO [ctc_decode.py:524]
|
| 245 |
+
For wenetspeech-net_test, WER of different settings are:
|
| 246 |
+
ctc-decoding 8.57 best for wenetspeech-net_test
|
| 247 |
+
|
| 248 |
+
2023-10-25 16:45:00,783 INFO [ctc_decode.py:697] Start decoding test set: wenetspeech_dev
|
| 249 |
+
2023-10-25 16:45:02,490 INFO [ctc_decode.py:487] batch 0/?, cuts processed until now is 39
|
| 250 |
+
2023-10-25 16:45:07,449 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.3442, 3.0899, 3.7565, 3.7398], device='cuda:0')
|
| 251 |
+
2023-10-25 16:45:19,403 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.4367, 2.7283, 2.6068, 4.3270], device='cuda:0')
|
| 252 |
+
2023-10-25 16:45:20,121 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([1.6771, 3.6862, 3.2837, 3.3905], device='cuda:0')
|
| 253 |
+
2023-10-25 16:45:21,677 INFO [ctc_decode.py:487] batch 100/?, cuts processed until now is 4983
|
| 254 |
+
2023-10-25 16:45:25,334 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([3.9137, 2.1321, 4.0173, 2.2182], device='cuda:0')
|
| 255 |
+
2023-10-25 16:45:35,271 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([5.7926, 5.6763, 5.3816, 5.9253], device='cuda:0')
|
| 256 |
+
2023-10-25 16:45:36,045 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.2507, 4.5774, 3.8076, 4.2477], device='cuda:0')
|
| 257 |
+
2023-10-25 16:45:40,086 INFO [ctc_decode.py:487] batch 200/?, cuts processed until now is 10268
|
| 258 |
+
2023-10-25 16:45:46,450 INFO [zipformer.py:1858] name=None, attn_weights_entropy = tensor([2.2227, 2.1938, 2.0968, 4.2055], device='cuda:0')
|
| 259 |
+
2023-10-25 16:45:51,879 INFO [ctc_decode.py:501] The transcripts are stored in zipformer/exp-w-ctc/ctc-decoding/recogs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 260 |
+
2023-10-25 16:45:52,426 INFO [utils.py:565] [wenetspeech_dev-ctc-decoding] %WER 9.41% [31089 / 330498, 1851 ins, 18854 del, 10384 sub ]
|
| 261 |
+
2023-10-25 16:45:53,512 INFO [ctc_decode.py:510] Wrote detailed error stats to zipformer/exp-w-ctc/ctc-decoding/errs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt
|
| 262 |
+
2023-10-25 16:45:53,516 INFO [ctc_decode.py:524]
|
| 263 |
+
For wenetspeech_dev, WER of different settings are:
|
| 264 |
+
ctc-decoding 9.41 best for wenetspeech_dev
|
| 265 |
+
|
| 266 |
+
2023-10-25 16:45:53,516 INFO [ctc_decode.py:716] Done!
|
decoding_results/ctc-decoding/log-decode-epoch-22-avg-1-use-averaged-model-2023-10-17-16-37-56
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:37:56,505 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:37:56,505 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:37:56,505 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 22, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-22-avg-1-use-averaged-model'}
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/log-decode-epoch-22-avg-1-use-averaged-model-2023-10-17-16-38-08
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
2023-10-17 16:38:08,666 INFO [ctc_decode.py:560] Decoding started
|
| 2 |
-
2023-10-17 16:38:08,666 INFO [ctc_decode.py:566] Device: cuda:0
|
| 3 |
-
2023-10-17 16:38:08,666 INFO [ctc_decode.py:567] {'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': '821ebc378e7fb99b8adc81950227963332821e01', 'k2-git-date': 'Wed Jul 19 15:38:25 2023', 'lhotse-version': '1.16.0.dev+git.1db4d97a.clean', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.9', 'icefall-git-branch': 'dev_multi_zh-hans', 'icefall-git-sha1': '919793d3-dirty', 'icefall-git-date': 'Thu Sep 7 21:06:37 2023', 'icefall-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/icefall-1.0-py3.9.egg', 'k2-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/k2-1.24.3.dev20230721+cuda10.2.torch1.11.0-py3.9-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/star-home/jinzengrui/lib/miniconda3/envs/dev39/lib/python3.9/site-packages/lhotse-1.16.0.dev0+git.1db4d97a.clean-py3.9.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-1220091118-57c4d55446-mvd6x', 'IP address': '10.177.22.19'}, 'frame_shift_ms': 10, 'search_beam': 20, 'output_beam': 8, 'min_active_states': 30, 'max_active_states': 10000, 'use_double_scores': True, 'epoch': 22, 'iter': 0, 'avg': 1, 'use_averaged_model': True, 'exp_dir': PosixPath('zipformer/exp-w-ctc'), 'bpe_model': 'data/lang_bpe_2000/bpe.model', 'lang_dir': PosixPath('data/lang_bpe_2000'), 'context_size': 2, 'decoding_method': 'ctc-decoding', 'num_paths': 100, 'nbest_scale': 1.0, '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': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300.0, '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('zipformer/exp-w-ctc/ctc-decoding'), 'suffix': 'epoch-22-avg-1-use-averaged-model'}
|
| 4 |
-
2023-10-17 16:38:10,507 INFO [lexicon.py:168] Loading pre-compiled data/lang_bpe_2000/Linv.pt
|
| 5 |
-
2023-10-17 16:38:16,142 INFO [ctc_decode.py:587] About to create model
|
| 6 |
-
2023-10-17 16:38:16,733 INFO [ctc_decode.py:654] Calculating the averaged model over epoch range from 21 (excluded) to 22
|
| 7 |
-
2023-10-17 16:38:24,407 INFO [ctc_decode.py:671] Number of model parameters: 69651511
|
| 8 |
-
2023-10-17 16:38:24,407 INFO [multi_dataset.py:221] About to get multidataset test cuts
|
| 9 |
-
2023-10-17 16:38:24,407 INFO [multi_dataset.py:224] Loading Aidatatang_200zh set in lazy mode
|
| 10 |
-
2023-10-17 16:38:24,424 INFO [multi_dataset.py:233] Loading Aishell set in lazy mode
|
| 11 |
-
2023-10-17 16:38:24,428 INFO [multi_dataset.py:242] Loading Aishell-2 set in lazy mode
|
| 12 |
-
2023-10-17 16:38:24,431 INFO [multi_dataset.py:251] Loading Aishell-4 TEST set in lazy mode
|
| 13 |
-
2023-10-17 16:38:24,433 INFO [multi_dataset.py:257] Loading Ali-Meeting set in lazy mode
|
| 14 |
-
2023-10-17 16:38:24,436 INFO [multi_dataset.py:266] Loading MagicData set in lazy mode
|
| 15 |
-
2023-10-17 16:38:24,439 INFO [multi_dataset.py:275] Loading KeSpeech set in lazy mode
|
| 16 |
-
2023-10-17 16:38:24,445 INFO [multi_dataset.py:287] Loading WeNetSpeech set in lazy mode
|
| 17 |
-
2023-10-17 16:38:30,811 WARNING [ctc_decode.py:683] Excluding cut with ID: TEST_NET_Y0000000004_0ub4ZzdHzBc_S00023 from decoding, num_frames: 8
|
| 18 |
-
2023-10-17 16:38:31,821 INFO [ctc_decode.py:695] Start decoding test set: aidatatang_test
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
decoding_results/ctc-decoding/recogs-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-aishell-4-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-aishell_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-aishell_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-alimeeting_eval-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-alimeeting_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-kespeech-asr_dev_phase1-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-kespeech-asr_dev_phase2-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-kespeech-asr_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-magicdata_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-magicdata_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-wenetspeech-meeting_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-wenetspeech-net_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/recogs-wenetspeech_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoding_results/ctc-decoding/wer-summary-aidatatang_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
settings WER
|
| 2 |
-
ctc-decoding
|
|
|
|
| 1 |
settings WER
|
| 2 |
+
ctc-decoding 2.86
|
decoding_results/ctc-decoding/wer-summary-aidatatang_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
settings WER
|
| 2 |
-
ctc-decoding
|
|
|
|
| 1 |
settings WER
|
| 2 |
+
ctc-decoding 3.36
|
decoding_results/ctc-decoding/wer-summary-aishell-2_dev-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
settings WER
|
| 2 |
-
ctc-decoding
|
|
|
|
| 1 |
settings WER
|
| 2 |
+
ctc-decoding 3.33
|
decoding_results/ctc-decoding/wer-summary-aishell-2_test-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
settings WER
|
| 2 |
-
ctc-decoding
|
|
|
|
| 1 |
settings WER
|
| 2 |
+
ctc-decoding 3.82
|
decoding_results/ctc-decoding/wer-summary-aishell-4-epoch-20-avg-1-use-averaged-model.txt
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
settings WER
|
| 2 |
-
ctc-decoding
|
|
|
|
| 1 |
settings WER
|
| 2 |
+
ctc-decoding 15.45
|