Commit
•
c28df58
0
Parent(s):
Duplicate from wgb14/icefall-asr-gigaspeech-pruned-transducer-stateless2
Browse files- .gitattributes +28 -0
- README.md +10 -0
- data/lang_bpe_500/bpe.model +3 -0
- exp/cpu_jit-iter-3488000-avg-15.pt +3 -0
- exp/cpu_jit-iter-3488000-avg-20.pt +3 -0
- exp/pretrained-iter-3488000-avg-15.pt +3 -0
- exp/pretrained-iter-3488000-avg-20.pt +3 -0
- log/fast_beam_search/errs-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt +3 -0
- log/fast_beam_search/errs-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt +3 -0
- log/fast_beam_search/log-decode-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8-2022-05-14-12-01-52 +19 -0
- log/fast_beam_search/log-decode-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8-2022-05-14-14-18-23 +27 -0
- log/fast_beam_search/recogs-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt +3 -0
- log/fast_beam_search/recogs-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt +3 -0
- log/fast_beam_search/wer-summary-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt +3 -0
- log/fast_beam_search/wer-summary-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt +3 -0
- log/greedy_search/errs-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt +3 -0
- log/greedy_search/errs-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt +3 -0
- log/greedy_search/log-decode-iter-3488000-avg-20-context-2-max-sym-per-frame-1-2022-05-14-11-54-14 +19 -0
- log/greedy_search/log-decode-iter-3488000-avg-20-context-2-max-sym-per-frame-1-2022-05-14-13-51-47 +27 -0
- log/greedy_search/recogs-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt +3 -0
- log/greedy_search/recogs-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt +3 -0
- log/greedy_search/wer-summary-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt +3 -0
- log/greedy_search/wer-summary-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt +3 -0
- log/modified_beam_search/errs-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt +3 -0
- log/modified_beam_search/errs-test-beam_size_4-iter-3488000-avg-15-beam-4.txt +3 -0
- log/modified_beam_search/log-decode-iter-3488000-avg-15-beam-4-2022-05-14-12-29-36 +19 -0
- log/modified_beam_search/log-decode-iter-3488000-avg-15-beam-4-2022-05-14-15-57-08 +27 -0
- log/modified_beam_search/recogs-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt +3 -0
- log/modified_beam_search/recogs-test-beam_size_4-iter-3488000-avg-15-beam-4.txt +3 -0
- log/modified_beam_search/wer-summary-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt +3 -0
- log/modified_beam_search/wer-summary-test-beam_size_4-iter-3488000-avg-15-beam-4.txt +3 -0
.gitattributes
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
19 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.txt filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- k2
|
4 |
+
- icefall
|
5 |
+
- audio
|
6 |
+
- automatic-speech-recognition
|
7 |
+
language: en
|
8 |
+
datasets:
|
9 |
+
- speechcolab/gigaspeech
|
10 |
+
---
|
data/lang_bpe_500/bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcae393dbc5611be5ffa4c7ae0841558978a5a4f484008cb9dff3a2cc97ebe01
|
3 |
+
size 244836
|
exp/cpu_jit-iter-3488000-avg-15.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:133b49edcaf843db9a1a85ebafb0a0385ca71683f18b9dd9bb7052aaeb032bfd
|
3 |
+
size 335299904
|
exp/cpu_jit-iter-3488000-avg-20.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a40c03b5e68b5507c6109af976066b5b27254cf6ed9b634240ab27bfdf038b26
|
3 |
+
size 335299904
|
exp/pretrained-iter-3488000-avg-15.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:727d545dba814cede4e69d12531a28b8ff8e999a5f472befa41075eeeee51995
|
3 |
+
size 314791463
|
exp/pretrained-iter-3488000-avg-20.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff18baf34ae632ffed28e687af1fd6850163ca333aa6574975474d2a6abf7aa5
|
3 |
+
size 314791463
|
log/fast_beam_search/errs-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d478fb258960cddc47125bdacef6346e46155096a631b4ae98ce09b8467ca35d
|
3 |
+
size 1035462
|
log/fast_beam_search/errs-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79d3740ad3382d9fed5588b4bdeec760111e911c01377b0d14ba469cfc3a35ac
|
3 |
+
size 2996380
|
log/fast_beam_search/log-decode-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8-2022-05-14-12-01-52
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2022-05-14 12:01:52,182 INFO [decode.py:489] Decoding started
|
2 |
+
2022-05-14 12:01:52,183 INFO [decode.py:495] Device: cuda:0
|
3 |
+
2022-05-14 12:01:52,186 INFO [decode.py:505] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 500, 'reset_interval': 2000, 'valid_interval': 20000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 20000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.2.0.dev+git.a3d7b8e.clean', 'torch-version': '1.10.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.7', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'e30e042-dirty', 'icefall-git-date': 'Fri May 13 13:03:16 2022', 'icefall-path': '/userhome/user/guanbo/icefall_master', 'k2-path': '/opt/conda/lib/python3.7/site-packages/k2-1.15.1.dev20220514+cuda11.1.torch1.10.0-py3.7-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/userhome/user/guanbo/lhotse/lhotse/__init__.py', 'hostname': 'ebbb46e00d32c011ec09cda0e7275cb175f4-chenx8564-0', 'IP address': '10.206.33.71'}, 'epoch': 29, 'iter': 3488000, 'avg': 20, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 4, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'subset': 'XL', 'small_dev': False, 'res_dir': PosixPath('pruned_transducer_stateless2/exp/fast_beam_search'), 'suffix': 'iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
|
4 |
+
2022-05-14 12:01:52,186 INFO [decode.py:507] About to create model
|
5 |
+
2022-05-14 12:01:52,561 INFO [decode.py:524] averaging ['pruned_transducer_stateless2/exp/checkpoint-3488000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3480000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3472000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3464000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3456000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3448000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3440000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3432000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3424000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3416000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3408000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3400000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3392000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3384000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3376000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3368000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3360000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3352000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3344000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3336000.pt']
|
6 |
+
2022-05-14 12:02:11,183 INFO [decode.py:549] Number of model parameters: 78648040
|
7 |
+
2022-05-14 12:02:11,184 INFO [asr_datamodule.py:406] About to get dev cuts
|
8 |
+
2022-05-14 12:02:13,478 INFO [decode.py:401] batch 0/?, cuts processed until now is 99
|
9 |
+
2022-05-14 12:02:29,739 INFO [decode.py:401] batch 20/?, cuts processed until now is 1626
|
10 |
+
2022-05-14 12:02:45,580 INFO [decode.py:401] batch 40/?, cuts processed until now is 3172
|
11 |
+
2022-05-14 12:03:00,035 INFO [decode.py:401] batch 60/?, cuts processed until now is 4929
|
12 |
+
2022-05-14 12:03:10,122 INFO [decode.py:418] The transcripts are stored in pruned_transducer_stateless2/exp/fast_beam_search/recogs-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
|
13 |
+
2022-05-14 12:03:10,247 INFO [utils.py:406] [dev-beam_4_max_contexts_4_max_states_8] %WER 10.50% [13415 / 127790, 2992 ins, 3504 del, 6919 sub ]
|
14 |
+
2022-05-14 12:03:10,558 INFO [decode.py:431] Wrote detailed error stats to pruned_transducer_stateless2/exp/fast_beam_search/errs-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
|
15 |
+
2022-05-14 12:03:10,560 INFO [decode.py:452]
|
16 |
+
For dev, WER of different settings are:
|
17 |
+
beam_4_max_contexts_4_max_states_8 10.5 best for dev
|
18 |
+
|
19 |
+
2022-05-14 12:03:10,566 INFO [decode.py:577] Done!
|
log/fast_beam_search/log-decode-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8-2022-05-14-14-18-23
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2022-05-14 14:18:23,183 INFO [decode_test.py:489] Decoding started
|
2 |
+
2022-05-14 14:18:23,184 INFO [decode_test.py:495] Device: cuda:0
|
3 |
+
2022-05-14 14:18:23,186 INFO [decode_test.py:505] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 500, 'reset_interval': 2000, 'valid_interval': 20000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 20000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.2.0.dev+git.a3d7b8e.clean', 'torch-version': '1.10.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.7', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'e30e042-dirty', 'icefall-git-date': 'Fri May 13 13:03:16 2022', 'icefall-path': '/userhome/user/guanbo/icefall_master', 'k2-path': '/opt/conda/lib/python3.7/site-packages/k2-1.15.1.dev20220514+cuda11.1.torch1.10.0-py3.7-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/userhome/user/guanbo/lhotse/lhotse/__init__.py', 'hostname': 'd5e575e00d344011ec09cda0e7275cb175f4-chenx8564-0', 'IP address': '10.206.33.89'}, 'epoch': 29, 'iter': 3488000, 'avg': 20, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 4, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'subset': 'XL', 'small_dev': False, 'res_dir': PosixPath('pruned_transducer_stateless2/exp/fast_beam_search'), 'suffix': 'iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
|
4 |
+
2022-05-14 14:18:23,186 INFO [decode_test.py:507] About to create model
|
5 |
+
2022-05-14 14:18:23,564 INFO [decode_test.py:524] averaging ['pruned_transducer_stateless2/exp/checkpoint-3488000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3480000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3472000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3464000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3456000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3448000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3440000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3432000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3424000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3416000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3408000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3400000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3392000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3384000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3376000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3368000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3360000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3352000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3344000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3336000.pt']
|
6 |
+
2022-05-14 14:18:42,241 INFO [decode_test.py:549] Number of model parameters: 78648040
|
7 |
+
2022-05-14 14:18:42,243 INFO [asr_datamodule.py:415] About to get test cuts
|
8 |
+
2022-05-14 14:18:45,477 INFO [decode_test.py:401] batch 0/?, cuts processed until now is 118
|
9 |
+
2022-05-14 14:19:01,829 INFO [decode_test.py:401] batch 20/?, cuts processed until now is 1859
|
10 |
+
2022-05-14 14:19:17,730 INFO [decode_test.py:401] batch 40/?, cuts processed until now is 3579
|
11 |
+
2022-05-14 14:19:33,751 INFO [decode_test.py:401] batch 60/?, cuts processed until now is 5872
|
12 |
+
2022-05-14 14:19:48,834 INFO [decode_test.py:401] batch 80/?, cuts processed until now is 8436
|
13 |
+
2022-05-14 14:20:04,170 INFO [decode_test.py:401] batch 100/?, cuts processed until now is 10038
|
14 |
+
2022-05-14 14:20:19,157 INFO [decode_test.py:401] batch 120/?, cuts processed until now is 11949
|
15 |
+
2022-05-14 14:20:34,041 INFO [decode_test.py:401] batch 140/?, cuts processed until now is 14046
|
16 |
+
2022-05-14 14:20:48,688 INFO [decode_test.py:401] batch 160/?, cuts processed until now is 16010
|
17 |
+
2022-05-14 14:21:03,607 INFO [decode_test.py:401] batch 180/?, cuts processed until now is 17567
|
18 |
+
2022-05-14 14:21:18,195 INFO [decode_test.py:401] batch 200/?, cuts processed until now is 18926
|
19 |
+
2022-05-14 14:21:33,733 INFO [decode_test.py:401] batch 220/?, cuts processed until now is 19923
|
20 |
+
2022-05-14 14:21:35,201 INFO [decode_test.py:418] The transcripts are stored in pruned_transducer_stateless2/exp/fast_beam_search/recogs-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
|
21 |
+
2022-05-14 14:21:35,614 INFO [utils.py:406] [test-beam_4_max_contexts_4_max_states_8] %WER 10.69% [41753 / 390744, 6857 ins, 11265 del, 23631 sub ]
|
22 |
+
2022-05-14 14:21:36,564 INFO [decode_test.py:431] Wrote detailed error stats to pruned_transducer_stateless2/exp/fast_beam_search/errs-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
|
23 |
+
2022-05-14 14:21:36,566 INFO [decode_test.py:452]
|
24 |
+
For test, WER of different settings are:
|
25 |
+
beam_4_max_contexts_4_max_states_8 10.69 best for test
|
26 |
+
|
27 |
+
2022-05-14 14:21:36,589 INFO [decode_test.py:577] Done!
|
log/fast_beam_search/recogs-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa29d0c19f9c7cb1b9ea54389a3b5f3a02c9dd8c39a8d4719fe16fb0d4406aa2
|
3 |
+
size 2169744
|
log/fast_beam_search/recogs-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f47bfc751d1738ab9ea55b7bfd9afb72c43e9dfab6602d571bcaab98eaaf71
|
3 |
+
size 6649991
|
log/fast_beam_search/wer-summary-dev-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1092dfc0e168125d034ad8448b0c3673125c3222d29903bf0f2bc6118286821c
|
3 |
+
size 53
|
log/fast_beam_search/wer-summary-test-beam_4_max_contexts_4_max_states_8-iter-3488000-avg-20-beam-4-max-contexts-4-max-states-8.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29d40228073a9f126e1b8df3644a068143c31b435f81a32ff93aa30a22686b59
|
3 |
+
size 54
|
log/greedy_search/errs-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:072fa9a3db85e0d19c3efa83876933929eb64eb7bb6a90ab2c6291f50fc9db4d
|
3 |
+
size 1038376
|
log/greedy_search/errs-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67980b2dc573150ea22b62d0f6a4fbdf92b3a1d8259ad4e00a0a5e9eb0d2d72c
|
3 |
+
size 3003586
|
log/greedy_search/log-decode-iter-3488000-avg-20-context-2-max-sym-per-frame-1-2022-05-14-11-54-14
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2022-05-14 11:54:14,566 INFO [decode.py:489] Decoding started
|
2 |
+
2022-05-14 11:54:14,567 INFO [decode.py:495] Device: cuda:0
|
3 |
+
2022-05-14 11:54:14,569 INFO [decode.py:505] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 500, 'reset_interval': 2000, 'valid_interval': 20000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 20000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.2.0.dev+git.a3d7b8e.clean', 'torch-version': '1.10.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.7', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'e30e042-dirty', 'icefall-git-date': 'Fri May 13 13:03:16 2022', 'icefall-path': '/userhome/user/guanbo/icefall_master', 'k2-path': '/opt/conda/lib/python3.7/site-packages/k2-1.15.1.dev20220514+cuda11.1.torch1.10.0-py3.7-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/userhome/user/guanbo/lhotse/lhotse/__init__.py', 'hostname': 'ebbb46e00d32c011ec09cda0e7275cb175f4-chenx8564-0', 'IP address': '10.206.33.71'}, 'epoch': 29, 'iter': 3488000, 'avg': 20, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 4, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'subset': 'XL', 'small_dev': False, 'res_dir': PosixPath('pruned_transducer_stateless2/exp/greedy_search'), 'suffix': 'iter-3488000-avg-20-context-2-max-sym-per-frame-1', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
|
4 |
+
2022-05-14 11:54:14,569 INFO [decode.py:507] About to create model
|
5 |
+
2022-05-14 11:54:14,982 INFO [decode.py:524] averaging ['pruned_transducer_stateless2/exp/checkpoint-3488000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3480000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3472000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3464000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3456000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3448000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3440000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3432000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3424000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3416000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3408000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3400000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3392000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3384000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3376000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3368000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3360000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3352000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3344000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3336000.pt']
|
6 |
+
2022-05-14 11:54:41,194 INFO [decode.py:549] Number of model parameters: 78648040
|
7 |
+
2022-05-14 11:54:41,194 INFO [asr_datamodule.py:406] About to get dev cuts
|
8 |
+
2022-05-14 11:54:43,278 INFO [decode.py:401] batch 0/?, cuts processed until now is 99
|
9 |
+
2022-05-14 11:54:51,676 INFO [decode.py:401] batch 20/?, cuts processed until now is 1626
|
10 |
+
2022-05-14 11:54:59,884 INFO [decode.py:401] batch 40/?, cuts processed until now is 3172
|
11 |
+
2022-05-14 11:55:07,449 INFO [decode.py:401] batch 60/?, cuts processed until now is 4929
|
12 |
+
2022-05-14 11:55:12,667 INFO [decode.py:418] The transcripts are stored in pruned_transducer_stateless2/exp/greedy_search/recogs-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
|
13 |
+
2022-05-14 11:55:12,797 INFO [utils.py:406] [dev-greedy_search] %WER 10.51% [13435 / 127790, 2972 ins, 3469 del, 6994 sub ]
|
14 |
+
2022-05-14 11:55:13,114 INFO [decode.py:431] Wrote detailed error stats to pruned_transducer_stateless2/exp/greedy_search/errs-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
|
15 |
+
2022-05-14 11:55:13,117 INFO [decode.py:452]
|
16 |
+
For dev, WER of different settings are:
|
17 |
+
greedy_search 10.51 best for dev
|
18 |
+
|
19 |
+
2022-05-14 11:55:13,123 INFO [decode.py:577] Done!
|
log/greedy_search/log-decode-iter-3488000-avg-20-context-2-max-sym-per-frame-1-2022-05-14-13-51-47
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2022-05-14 13:51:47,785 INFO [decode_test.py:489] Decoding started
|
2 |
+
2022-05-14 13:51:47,785 INFO [decode_test.py:495] Device: cuda:0
|
3 |
+
2022-05-14 13:51:47,788 INFO [decode_test.py:505] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 500, 'reset_interval': 2000, 'valid_interval': 20000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 20000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.2.0.dev+git.a3d7b8e.clean', 'torch-version': '1.10.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.7', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'e30e042-dirty', 'icefall-git-date': 'Fri May 13 13:03:16 2022', 'icefall-path': '/userhome/user/guanbo/icefall_master', 'k2-path': '/opt/conda/lib/python3.7/site-packages/k2-1.15.1.dev20220514+cuda11.1.torch1.10.0-py3.7-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/userhome/user/guanbo/lhotse/lhotse/__init__.py', 'hostname': 'd5e575e00d344011ec09cda0e7275cb175f4-chenx8564-0', 'IP address': '10.206.33.89'}, 'epoch': 29, 'iter': 3488000, 'avg': 20, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 4, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'subset': 'XL', 'small_dev': False, 'res_dir': PosixPath('pruned_transducer_stateless2/exp/greedy_search'), 'suffix': 'iter-3488000-avg-20-context-2-max-sym-per-frame-1', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
|
4 |
+
2022-05-14 13:51:47,788 INFO [decode_test.py:507] About to create model
|
5 |
+
2022-05-14 13:51:48,181 INFO [decode_test.py:524] averaging ['pruned_transducer_stateless2/exp/checkpoint-3488000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3480000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3472000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3464000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3456000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3448000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3440000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3432000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3424000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3416000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3408000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3400000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3392000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3384000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3376000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3368000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3360000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3352000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3344000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3336000.pt']
|
6 |
+
2022-05-14 13:52:08,047 INFO [decode_test.py:549] Number of model parameters: 78648040
|
7 |
+
2022-05-14 13:52:08,047 INFO [asr_datamodule.py:415] About to get test cuts
|
8 |
+
2022-05-14 13:52:10,933 INFO [decode_test.py:401] batch 0/?, cuts processed until now is 118
|
9 |
+
2022-05-14 13:52:19,402 INFO [decode_test.py:401] batch 20/?, cuts processed until now is 1859
|
10 |
+
2022-05-14 13:52:27,787 INFO [decode_test.py:401] batch 40/?, cuts processed until now is 3579
|
11 |
+
2022-05-14 13:52:35,965 INFO [decode_test.py:401] batch 60/?, cuts processed until now is 5872
|
12 |
+
2022-05-14 13:52:43,812 INFO [decode_test.py:401] batch 80/?, cuts processed until now is 8436
|
13 |
+
2022-05-14 13:52:51,973 INFO [decode_test.py:401] batch 100/?, cuts processed until now is 10038
|
14 |
+
2022-05-14 13:53:00,210 INFO [decode_test.py:401] batch 120/?, cuts processed until now is 11949
|
15 |
+
2022-05-14 13:53:08,120 INFO [decode_test.py:401] batch 140/?, cuts processed until now is 14046
|
16 |
+
2022-05-14 13:53:15,960 INFO [decode_test.py:401] batch 160/?, cuts processed until now is 16010
|
17 |
+
2022-05-14 13:53:23,835 INFO [decode_test.py:401] batch 180/?, cuts processed until now is 17567
|
18 |
+
2022-05-14 13:53:31,603 INFO [decode_test.py:401] batch 200/?, cuts processed until now is 18926
|
19 |
+
2022-05-14 13:53:39,477 INFO [decode_test.py:401] batch 220/?, cuts processed until now is 19923
|
20 |
+
2022-05-14 13:53:40,572 INFO [decode_test.py:418] The transcripts are stored in pruned_transducer_stateless2/exp/greedy_search/recogs-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
|
21 |
+
2022-05-14 13:53:40,991 INFO [utils.py:406] [test-greedy_search] %WER 10.73% [41944 / 390744, 6729 ins, 11351 del, 23864 sub ]
|
22 |
+
2022-05-14 13:53:41,972 INFO [decode_test.py:431] Wrote detailed error stats to pruned_transducer_stateless2/exp/greedy_search/errs-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
|
23 |
+
2022-05-14 13:53:41,974 INFO [decode_test.py:452]
|
24 |
+
For test, WER of different settings are:
|
25 |
+
greedy_search 10.73 best for test
|
26 |
+
|
27 |
+
2022-05-14 13:53:41,997 INFO [decode_test.py:577] Done!
|
log/greedy_search/recogs-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a2256af529d2999d8e0f8e257082ba5223bcfa8a43ff1bbee5dce6e906a0645
|
3 |
+
size 2170033
|
log/greedy_search/recogs-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d25a884d156e8a7d1eb9208c8aeef98b3be59eb382df37cdbbc823eeb2ab54fa
|
3 |
+
size 6648898
|
log/greedy_search/wer-summary-dev-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee2262b183268a7822f4a6e421c2990d043c1c4833e9a8ecb3aac6a0742c3305
|
3 |
+
size 33
|
log/greedy_search/wer-summary-test-greedy_search-iter-3488000-avg-20-context-2-max-sym-per-frame-1.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03c91da304a100d37f721ac963f5ef3622bac1300a43483b2a72061c9219a4a5
|
3 |
+
size 33
|
log/modified_beam_search/errs-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f16424578dbdd9e13b434c38073dab9174f48ebc83fa2ec4bba6b0a9dabe373
|
3 |
+
size 1038772
|
log/modified_beam_search/errs-test-beam_size_4-iter-3488000-avg-15-beam-4.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bddc6f14cc541c4deb067139948b17143b7c8288c7c4f27613859fc71cd253b3
|
3 |
+
size 3003852
|
log/modified_beam_search/log-decode-iter-3488000-avg-15-beam-4-2022-05-14-12-29-36
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2022-05-14 12:29:36,599 INFO [decode.py:489] Decoding started
|
2 |
+
2022-05-14 12:29:36,601 INFO [decode.py:495] Device: cuda:0
|
3 |
+
2022-05-14 12:29:36,604 INFO [decode.py:505] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 500, 'reset_interval': 2000, 'valid_interval': 20000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 20000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.2.0.dev+git.a3d7b8e.clean', 'torch-version': '1.10.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.7', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'e30e042-dirty', 'icefall-git-date': 'Fri May 13 13:03:16 2022', 'icefall-path': '/userhome/user/guanbo/icefall_master', 'k2-path': '/opt/conda/lib/python3.7/site-packages/k2-1.15.1.dev20220514+cuda11.1.torch1.10.0-py3.7-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/userhome/user/guanbo/lhotse/lhotse/__init__.py', 'hostname': 'ebbb46e00d32c011ec09cda0e7275cb175f4-chenx8564-0', 'IP address': '10.206.33.71'}, 'epoch': 29, 'iter': 3488000, 'avg': 15, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'modified_beam_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 4, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'subset': 'XL', 'small_dev': False, 'res_dir': PosixPath('pruned_transducer_stateless2/exp/modified_beam_search'), 'suffix': 'iter-3488000-avg-15-beam-4', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
|
4 |
+
2022-05-14 12:29:36,604 INFO [decode.py:507] About to create model
|
5 |
+
2022-05-14 12:29:37,006 INFO [decode.py:524] averaging ['pruned_transducer_stateless2/exp/checkpoint-3488000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3480000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3472000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3464000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3456000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3448000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3440000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3432000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3424000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3416000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3408000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3400000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3392000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3384000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3376000.pt']
|
6 |
+
2022-05-14 12:29:52,476 INFO [decode.py:549] Number of model parameters: 78648040
|
7 |
+
2022-05-14 12:29:52,476 INFO [asr_datamodule.py:406] About to get dev cuts
|
8 |
+
2022-05-14 12:29:56,881 INFO [decode.py:401] batch 0/?, cuts processed until now is 99
|
9 |
+
2022-05-14 12:30:55,111 INFO [decode.py:401] batch 20/?, cuts processed until now is 1626
|
10 |
+
2022-05-14 12:31:52,924 INFO [decode.py:401] batch 40/?, cuts processed until now is 3172
|
11 |
+
2022-05-14 12:32:44,252 INFO [decode.py:401] batch 60/?, cuts processed until now is 4929
|
12 |
+
2022-05-14 12:33:17,275 INFO [decode.py:418] The transcripts are stored in pruned_transducer_stateless2/exp/modified_beam_search/recogs-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt
|
13 |
+
2022-05-14 12:33:17,394 INFO [utils.py:406] [dev-beam_size_4] %WER 10.40% [13292 / 127790, 3378 ins, 2828 del, 7086 sub ]
|
14 |
+
2022-05-14 12:33:17,784 INFO [decode.py:431] Wrote detailed error stats to pruned_transducer_stateless2/exp/modified_beam_search/errs-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt
|
15 |
+
2022-05-14 12:33:17,787 INFO [decode.py:452]
|
16 |
+
For dev, WER of different settings are:
|
17 |
+
beam_size_4 10.4 best for dev
|
18 |
+
|
19 |
+
2022-05-14 12:33:17,793 INFO [decode.py:577] Done!
|
log/modified_beam_search/log-decode-iter-3488000-avg-15-beam-4-2022-05-14-15-57-08
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2022-05-14 15:57:08,138 INFO [decode_test.py:489] Decoding started
|
2 |
+
2022-05-14 15:57:08,139 INFO [decode_test.py:495] Device: cuda:0
|
3 |
+
2022-05-14 15:57:08,141 INFO [decode_test.py:505] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 500, 'reset_interval': 2000, 'valid_interval': 20000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 20000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'ecfe7bd6d9189964bf3ff043038918d889a43185', 'k2-git-date': 'Tue May 10 10:57:55 2022', 'lhotse-version': '1.2.0.dev+git.a3d7b8e.clean', 'torch-version': '1.10.0', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.7', 'icefall-git-branch': 'master', 'icefall-git-sha1': 'e30e042-dirty', 'icefall-git-date': 'Fri May 13 13:03:16 2022', 'icefall-path': '/userhome/user/guanbo/icefall_master', 'k2-path': '/opt/conda/lib/python3.7/site-packages/k2-1.15.1.dev20220514+cuda11.1.torch1.10.0-py3.7-linux-x86_64.egg/k2/__init__.py', 'lhotse-path': '/userhome/user/guanbo/lhotse/lhotse/__init__.py', 'hostname': 'd5e575e00d344011ec09cda0e7275cb175f4-chenx8564-0', 'IP address': '10.206.33.89'}, 'epoch': 29, 'iter': 3488000, 'avg': 15, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'decoding_method': 'modified_beam_search', 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 600, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 4, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'subset': 'XL', 'small_dev': False, 'res_dir': PosixPath('pruned_transducer_stateless2/exp/modified_beam_search'), 'suffix': 'iter-3488000-avg-15-beam-4', 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
|
4 |
+
2022-05-14 15:57:08,142 INFO [decode_test.py:507] About to create model
|
5 |
+
2022-05-14 15:57:08,525 INFO [decode_test.py:524] averaging ['pruned_transducer_stateless2/exp/checkpoint-3488000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3480000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3472000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3464000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3456000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3448000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3440000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3432000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3424000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3416000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3408000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3400000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3392000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3384000.pt', 'pruned_transducer_stateless2/exp/checkpoint-3376000.pt']
|
6 |
+
2022-05-14 15:57:29,798 INFO [decode_test.py:549] Number of model parameters: 78648040
|
7 |
+
2022-05-14 15:57:29,798 INFO [asr_datamodule.py:415] About to get test cuts
|
8 |
+
2022-05-14 15:57:35,416 INFO [decode_test.py:401] batch 0/?, cuts processed until now is 118
|
9 |
+
2022-05-14 15:58:35,717 INFO [decode_test.py:401] batch 20/?, cuts processed until now is 1859
|
10 |
+
2022-05-14 15:59:35,757 INFO [decode_test.py:401] batch 40/?, cuts processed until now is 3579
|
11 |
+
2022-05-14 16:00:36,442 INFO [decode_test.py:401] batch 60/?, cuts processed until now is 5872
|
12 |
+
2022-05-14 16:01:34,960 INFO [decode_test.py:401] batch 80/?, cuts processed until now is 8436
|
13 |
+
2022-05-14 16:02:35,498 INFO [decode_test.py:401] batch 100/?, cuts processed until now is 10038
|
14 |
+
2022-05-14 16:03:35,274 INFO [decode_test.py:401] batch 120/?, cuts processed until now is 11949
|
15 |
+
2022-05-14 16:04:34,710 INFO [decode_test.py:401] batch 140/?, cuts processed until now is 14046
|
16 |
+
2022-05-14 16:05:32,490 INFO [decode_test.py:401] batch 160/?, cuts processed until now is 16010
|
17 |
+
2022-05-14 16:06:29,256 INFO [decode_test.py:401] batch 180/?, cuts processed until now is 17567
|
18 |
+
2022-05-14 16:07:25,678 INFO [decode_test.py:401] batch 200/?, cuts processed until now is 18926
|
19 |
+
2022-05-14 16:08:19,069 INFO [decode_test.py:401] batch 220/?, cuts processed until now is 19923
|
20 |
+
2022-05-14 16:08:20,359 INFO [decode_test.py:418] The transcripts are stored in pruned_transducer_stateless2/exp/modified_beam_search/recogs-test-beam_size_4-iter-3488000-avg-15-beam-4.txt
|
21 |
+
2022-05-14 16:08:20,745 INFO [utils.py:406] [test-beam_size_4] %WER 10.51% [41060 / 390744, 7449 ins, 9485 del, 24126 sub ]
|
22 |
+
2022-05-14 16:08:21,955 INFO [decode_test.py:431] Wrote detailed error stats to pruned_transducer_stateless2/exp/modified_beam_search/errs-test-beam_size_4-iter-3488000-avg-15-beam-4.txt
|
23 |
+
2022-05-14 16:08:21,966 INFO [decode_test.py:452]
|
24 |
+
For test, WER of different settings are:
|
25 |
+
beam_size_4 10.51 best for test
|
26 |
+
|
27 |
+
2022-05-14 16:08:21,988 INFO [decode_test.py:577] Done!
|
log/modified_beam_search/recogs-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c90134efefc73f13b8b5894a99a2ea2b1d11949ea665928ab74b1bb4bd6e191f
|
3 |
+
size 2177962
|
log/modified_beam_search/recogs-test-beam_size_4-iter-3488000-avg-15-beam-4.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2f04ba5939d5cbd7b6ce5ec0e79effd9563f62a5948f39730a4b3d73421fff1
|
3 |
+
size 6668805
|
log/modified_beam_search/wer-summary-dev-beam_size_4-iter-3488000-avg-15-beam-4.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:697d48a4899230c19e36f10d8478b6a4080e63736ba161fca6a6469861655195
|
3 |
+
size 30
|
log/modified_beam_search/wer-summary-test-beam_size_4-iter-3488000-avg-15-beam-4.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7b1c397136575890c61fe6da5a1db93e18b74a57b15cc572c316b5b69b8b64d
|
3 |
+
size 31
|