Hugging Face's logo

desh2608
/
icefall-asr-alimeeting-pruned-transducer-stateless7

K2
TensorBoard
Chinese
icefall
Model card Files Metrics Community
2
desh2608 commited on
Commit
26cafdd
•
1 Parent(s): d35a7a9

add pretrained model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +48 -0
  2. data/lang_char/L.pt +3 -0
  3. data/lang_char/Linv.pt +3 -0
  4. data/lang_char/tokens.txt +3292 -0
  5. data/lang_char/words.txt +0 -0
  6. exp/cpu_jit.pt +3 -0
  7. exp/pretrained.pt +3 -0
  8. exp/tensorboard/events.out.tfevents.1670405777.r8n04.289848.0 +3 -0
  9. log/fast_beam_search/errs-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  10. log/fast_beam_search/errs-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  11. log/fast_beam_search/errs-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  12. log/fast_beam_search/errs-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  13. log/fast_beam_search/errs-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  14. log/fast_beam_search/errs-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  15. log/fast_beam_search/log-decode-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8-2022-12-09-00-04-39 +350 -0
  16. log/fast_beam_search/recogs-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  17. log/fast_beam_search/recogs-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  18. log/fast_beam_search/recogs-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  19. log/fast_beam_search/recogs-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  20. log/fast_beam_search/recogs-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  21. log/fast_beam_search/recogs-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +0 -0
  22. log/fast_beam_search/wer-summary-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +2 -0
  23. log/fast_beam_search/wer-summary-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +2 -0
  24. log/fast_beam_search/wer-summary-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +2 -0
  25. log/fast_beam_search/wer-summary-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +2 -0
  26. log/fast_beam_search/wer-summary-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +2 -0
  27. log/fast_beam_search/wer-summary-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt +2 -0
  28. log/greedy_search/errs-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  29. log/greedy_search/errs-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  30. log/greedy_search/errs-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  31. log/greedy_search/errs-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  32. log/greedy_search/errs-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  33. log/greedy_search/errs-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  34. log/greedy_search/log-decode-epoch-15-avg-8-context-2-max-sym-per-frame-1-2022-12-08-23-52-09 +137 -0
  35. log/greedy_search/recogs-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  36. log/greedy_search/recogs-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  37. log/greedy_search/recogs-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  38. log/greedy_search/recogs-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  39. log/greedy_search/recogs-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  40. log/greedy_search/recogs-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +0 -0
  41. log/greedy_search/wer-summary-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +2 -0
  42. log/greedy_search/wer-summary-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +2 -0
  43. log/greedy_search/wer-summary-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +2 -0
  44. log/greedy_search/wer-summary-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +2 -0
  45. log/greedy_search/wer-summary-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +2 -0
  46. log/greedy_search/wer-summary-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt +2 -0
  47. log/log-train-2022-12-07-04-36-17-0 +0 -0
  48. log/log-train-2022-12-07-04-36-17-1 +0 -0
  49. log/log-train-2022-12-07-04-36-17-2 +0 -0
  50. log/log-train-2022-12-07-04-36-17-3 +0 -0
README.md CHANGED
@@ -1,3 +1,51 @@
1
  ---
 
 
 
 
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ datasets:
3
+ - AliMeeting
4
+ language:
5
+ - zh
6
  license: apache-2.0
7
+ metrics:
8
+ -
9
+ name: "IHM test CER"
10
+ type: cer
11
+ value: 11.53
12
+ -
13
+ name: "SDM test CER"
14
+ type: cer
15
+ value: 25.85
16
+ -
17
+ name: "GSS test CER"
18
+ type: cer
19
+ value: 14.22
20
+ tags:
21
+ - k2
22
+ - icefall
23
  ---
24
+
25
+ # AliMeeting
26
+
27
+ This is an ASR recipe for the AliMeeting corpus. AMI provides recordings from the speaker's
28
+ headset microphones and an 8-channel microphone array.
29
+ We pool data in the following 4 ways and train a single model on the pooled data:
30
+
31
+ (i) individual headset microphone (IHM)
32
+ (ii) IHM with simulated reverb
33
+ (iii) Single distant microphone (SDM)
34
+ (iv) GSS-enhanced array microphones
35
+
36
+ Speed perturbation and MUSAN noise augmentation are additionally performed on the pooled
37
+ data.
38
+
39
+ ## Performance Record
40
+
41
+ ### pruned_transducer_stateless7
42
+
43
+ The following are decoded using `modified_beam_search`:
44
+
45
+ | Evaluation set | eval CER | test CER |
46
+ |--------------------------|------------|---------|
47
+ | IHM | 9.58 | 11.53 |
48
+ | SDM | 23.37 | 25.85 |
49
+ | MDM (GSS-enhanced) | 11.82 | 14.22 |
50
+
51
+ See the [recipe](https://github.com/k2-fsa/icefall/tree/master/egs/alimeeting/ASR_v2) for details.
data/lang_char/L.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590d0e7c1f48d1881206458f826303407c1efb69678d914b1cd44c5b9b61b135
3
+ size 2156647
data/lang_char/Linv.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c1648f90c05de16a2c8784c9c54f295bfd53f39b4f5c406bf1c5feb4ae60f9
3
+ size 2156647
data/lang_char/tokens.txt ADDED
@@ -0,0 +1,3292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <blk> 0
2
+ <sos/eos> 1
3
+ <unk> 2
4
+ 对 3
5
+ 是 4
6
+ 啊 5
7
+ 两 6
8
+ 天 7
9
+ 的 8
10
+ 时 9
11
+ 间 10
12
+ 远 11
13
+ 方 12
14
+ 亲 13
15
+ 戚 14
16
+ 都 15
17
+ 过 16
18
+ 不 17
19
+ 来 18
20
+ 一 19
21
+ 般 20
22
+ 长 21
23
+ 还 22
24
+ 比 23
25
+ 较 24
26
+ 好 25
27
+ 点 26
28
+ 儿 27
29
+ 嗯 28
30
+ 他 29
31
+ 怎 30
32
+ 么 31
33
+ 也 32
34
+ 能 33
35
+ 总 34
36
+ 在 35
37
+ 室 36
38
+ 内 37
39
+ 肯 38
40
+ 定 39
41
+ 出 40
42
+ 去 41
43
+ 就 42
44
+ 稍 43
45
+ 微 44
46
+ 暖 45
47
+ 和 46
48
+ 有 47
49
+ 感 48
50
+ 觉 49
51
+ 如 50
52
+ 说 51
53
+ 呀 52
54
+ 六 53
55
+ 八 54
56
+ 双 55
57
+ 日 56
58
+ 子 57
59
+ 十 58
60
+ 正 59
61
+ 节 60
62
+ 假 61
63
+ 放 62
64
+ 候 63
65
+ 赶 64
66
+ 上 65
67
+ 起 66
68
+ 人 67
69
+ 多 68
70
+ 热 69
71
+ 闹 70
72
+ 然 71
73
+ 后 72
74
+ 期 73
75
+ 行 74
76
+ 到 75
77
+ 看 76
78
+ 让 77
79
+ 们 78
80
+ 自 79
81
+ 己 80
82
+ 吧 81
83
+ 主 82
84
+ 要 83
85
+ 咱 84
86
+ 这 85
87
+ 边 86
88
+ 太 87
89
+ 清 88
90
+ 楚 89
91
+ 家 90
92
+ 请 91
93
+ 宾 92
94
+ 客 93
95
+ 名 94
96
+ 单 95
97
+ 再 96
98
+ 男 97
99
+ 办 98
100
+ 哼 99
101
+ 个 100
102
+ 得 101
103
+ 提 102
104
+ 前 103
105
+ 给 104
106
+ 策 105
107
+ 划 106
108
+ 下 107
109
+ 了 108
110
+ 算 109
111
+ 里 110
112
+ 面 111
113
+ 那 112
114
+ 户 113
115
+ 需 114
116
+ 求 115
117
+ 跟 116
118
+ 吗 117
119
+ 建 118
120
+ 议 119
121
+ 采 120
122
+ 纳 121
123
+ 预 122
124
+ 你 123
125
+ 意 124
126
+ 思 125
127
+ 您 126
128
+ 露 127
129
+ 省 128
130
+ 气 129
131
+ 果 130
132
+ 话 131
133
+ 知 132
134
+ 道 133
135
+ 啥 134
136
+ 万 135
137
+ 遇 136
138
+ 雨 137
139
+ 刮 138
140
+ 风 139
141
+ 做 140
142
+ 准 141
143
+ 备 142
144
+ 全 143
145
+ 部 144
146
+ 包 145
147
+ 括 146
148
+ 报 147
149
+ 它 148
150
+ 当 149
151
+ 挺 150
152
+ 可 151
153
+ 以 152
154
+ 样 153
155
+ 简 154
156
+ 案 155
157
+ 范 156
158
+ 围 157
159
+ 具 158
160
+ 体 159
161
+ 位 160
162
+ 置 161
163
+ 沟 162
164
+ 通 163
165
+ 现 164
166
+ 司 165
167
+ 仪 166
168
+ 几 167
169
+ 种 168
170
+ 呗 169
171
+ 选 170
172
+ 择 171
173
+ 哪 172
174
+ 贵 173
175
+ 超 174
176
+ 够 175
177
+ 助 176
178
+ 小 177
179
+ 孩 178
180
+ 特 179
181
+ 规 180
182
+ 分 181
183
+ 地 182
184
+ 外 183
185
+ 差 184
186
+ 只 185
187
+ 应 186
188
+ 该 187
189
+ 布 188
190
+ 钱 189
191
+ 避 190
192
+ 免 191
193
+ 些 192
194
+ 浪 193
195
+ 费 194
196
+ 车 195
197
+ 队 196
198
+ 接 197
199
+ 女 198
200
+ 或 199
201
+ 盘 200
202
+ 少 201
203
+ 辆 202
204
+ 什 203
205
+ 碰 204
206
+ 属 205
207
+ 像 206
208
+ 订 207
209
+ 呢 208
210
+ 婚 209
211
+ 用 210
212
+ 别 211
213
+ 数 212
214
+ 敞 213
215
+ 篷 214
216
+ 找 215
217
+ 机 216
218
+ 旁 217
219
+ 装 218
220
+ 饰 219
221
+ 座 220
222
+ 先 221
223
+ 打 222
224
+ 穿 223
225
+ 纱 224
226
+ 她 225
227
+ 刚 226
228
+ 陪 227
229
+ 同 228
230
+ 着 229
231
+ 把 230
232
+ 拉 231
233
+ 送 232
234
+ 会 233
235
+ 截 234
236
+ 走 235
237
+ 很 236
238
+ 新 237
239
+ 娘 238
240
+ 咋 239
241
+ 想 240
242
+ 第 241
243
+ 次 242
244
+ 专 243
245
+ 门 244
246
+ 程 245
247
+ 固 246
248
+ 已 247
249
+ 经 248
250
+ 波 249
251
+ 签 250
252
+ 处 251
253
+ 收 252
254
+ 谁 253
255
+ 字 254
256
+ 嘛 255
257
+ 郎 256
258
+ 直 257
259
+ 账 258
260
+ 声 259
261
+ 记 260
262
+ 持 261
263
+ 证 262
264
+ 之 263
265
+ 类 264
266
+ 台 265
267
+ 我 266
268
+ 估 267
269
+ 计 268
270
+ 问 269
271
+ 句 270
272
+ 愿 271
273
+ 嫁 272
274
+ 娶 273
275
+ 戴 274
276
+ 戒 275
277
+ 指 276
278
+ 拿 277
279
+ 中 278
280
+ 白 279
281
+ 色 280
282
+ 场 281
283
+ 花 282
284
+ 为 283
285
+ 鲜 284
286
+ 绿 285
287
+ 植 286
288
+ 乐 287
289
+ 效 288
290
+ 控 289
291
+ 制 290
292
+ 没 291
293
+ 题 292
294
+ 其 293
295
+ 实 294
296
+ 事 295
297
+ 块 296
298
+ 安 297
299
+ 排 298
300
+ 隆 299
301
+ 重 300
302
+ 喜 301
303
+ 庆 302
304
+ 延 303
305
+ 误 304
306
+ 示 305
307
+ 最 306
308
+ 因 307
309
+ 印 308
310
+ 糖 309
311
+ 书 310
312
+ 纸 311
313
+ 袋 312
314
+ 反 313
315
+ 尽 314
316
+ 量 315
317
+ 成 316
318
+ 本 317
319
+ 低 318
320
+ 西 319
321
+ 式 320
322
+ 由 321
323
+ 讲 322
324
+ 交 323
325
+ 手 324
326
+ 礼 325
327
+ 哈 326
328
+ 教 327
329
+ 堂 328
330
+ 草 329
331
+ 坪 330
332
+ 弄 331
333
+ 摆 332
334
+ 院 333
335
+ 底 334
336
+ 大 335
337
+ 供 336
338
+ 酒 337
339
+ 店 338
340
+ 游 339
341
+ 玩 340
342
+ 管 341
343
+ 跑 342
344
+ 丢 343
345
+ 者 344
346
+ 注 345
347
+ 雇 346
348
+ 负 347
349
+ 责 348
350
+ 除 349
351
+ 非 350
352
+ 加 351
353
+ 百 352
354
+ 工 353
355
+ 作 354
356
+ 员 355
357
+ 宣 356
358
+ 誓 357
359
+ 毕 358
360
+ 竟 359
361
+ 散 360
362
+ 爱 361
363
+ 吃 362
364
+ 棒 363
365
+ 冻 364
366
+ 饼 365
367
+ 干 366
368
+ 掺 367
369
+ 服 368
370
+ 庄 369
371
+ 粉 370
372
+ 伴 371
373
+ 见 372
374
+ 欢 373
375
+ 开 374
376
+ 颜 375
377
+ 周 376
378
+ 朋 377
379
+ 友 378
380
+ 怪 379
381
+ 尬 380
382
+ 理 381
383
+ 但 382
384
+ 斥 383
385
+ 结 384
386
+ 撞 385
387
+ 考 386
388
+ 虑 387
389
+ 二 388
390
+ 幺 389
391
+ 四 390
392
+ 否 391
393
+ 冷 392
394
+ 必 393
395
+ 须 394
396
+ 带 395
397
+ 袖 396
398
+ 春 397
399
+ 举 398
400
+ 秋 399
401
+ 物 400
402
+ 整 401
403
+ 画 402
404
+ 偏 403
405
+ 森 404
406
+ 系 405
407
+ 逢 406
408
+ 叶 407
409
+ 黄 408
410
+ 金 409
411
+ 老 410
412
+ 师 411
413
+ 月 412
414
+ 号 413
415
+ 束 414
416
+ 班 415
417
+ 参 416
418
+ 资 417
419
+ 扣 418
420
+ 又 419
421
+ 赔 420
422
+ 国 421
423
+ 受 422
424
+ 更 423
425
+ 按 424
426
+ 照 425
427
+ 至 426
428
+ 七 427
429
+ 呃 428
430
+ 妈 429
431
+ 爸 430
432
+ 学 431
433
+ 坐 432
434
+ 桌 433
435
+ 矮 434
436
+ 兜 435
437
+ 椅 436
438
+ 哎 437
439
+ 搁 438
440
+ 丁 439
441
+ 领 440
442
+ 导 441
443
+ 拨 442
444
+ 汉 443
445
+ 合 444
446
+ 并 445
447
+ 显 446
448
+ 俗 447
449
+ 哦 448
450
+ 唉 449
451
+ 支 450
452
+ 红 451
453
+ 砖 452
454
+ 美 453
455
+ 术 454
456
+ 馆 455
457
+ 设 456
458
+ 刨 457
459
+ 半 458
460
+ 饭 459
461
+ 而 460
462
+ 且 461
463
+ 餐 462
464
+ 形 463
465
+ 情 464
466
+ 况 465
467
+ 纯 466
468
+ 概 467
469
+ 虽 468
470
+ 麻 469
471
+ 烦 470
472
+ 质 471
473
+ 东 472
474
+ 辈 473
475
+ 强 474
476
+ 烈 475
477
+ 推 476
478
+ 荐 477
479
+ 真 478
480
+ 高 479
481
+ 兴 480
482
+ 区 481
483
+ 帮 482
484
+ 许 483
485
+ 久 484
486
+ 未 485
487
+ 唠 486
488
+ 嗑 487
489
+ 空 488
490
+ 级 489
491
+ 园 490
492
+ 呐 491
493
+ 流 492
494
+ 常 493
495
+ 站 494
496
+ 头 495
497
+ 笑 496
498
+ 抖 497
499
+ 袱 498
500
+ 另 499
501
+ 某 500
502
+ 妻 501
503
+ 向 502
504
+ 洋 503
505
+ 神 504
506
+ 父 505
507
+ 营 506
508
+ 造 507
509
+ 足 508
510
+ 无 509
511
+ 所 510
512
+ 从 511
513
+ 进 512
514
+ 始 513
515
+ 首 514
516
+ 突 515
517
+ 阴 516
518
+ 改 517
519
+ 挑 518
520
+ 晴 519
521
+ 搬 520
522
+ 拱 521
523
+ 球 522
524
+ 格 523
525
+ 写 524
526
+ 完 525
527
+ 赛 526
528
+ 克 527
529
+ 便 528
530
+ 确 529
531
+ 沉 530
532
+ 厚 531
533
+ 背 532
534
+ 裤 533
535
+ 裙 534
536
+ 翅 535
537
+ 膀 536
538
+ 年 537
539
+ 轻 538
540
+ 听 539
541
+ 啪 540
542
+ 信 541
543
+ 发 542
544
+ 转 543
545
+ 既 544
546
+ 璧 545
547
+ 害 546
548
+ 怕 547
549
+ 变 548
550
+ 论 549
551
+ 贫 550
552
+ 穷 551
553
+ 派 552
554
+ 往 553
555
+ 相 554
556
+ 似 555
557
+ 壁 556
558
+ 电 557
559
+ 影 558
560
+ 夫 559
561
+ Y 560
562
+ E 561
563
+ S 562
564
+ L 563
565
+ D 564
566
+ O 565
567
+ 套 566
568
+ 哟 567
569
+ 各 568
570
+ 环 569
571
+ 传 570
572
+ 销 571
573
+ 千 572
574
+ 心 573
575
+ 挥 574
576
+ 验 575
577
+ 元 576
578
+ 素 577
579
+ 杂 578
580
+ ��� 579
581
+ 贴 580
582
+ 胸 581
583
+ 口 582
584
+ 哇 583
585
+ 噻 584
586
+ 搭 585
587
+ 调 586
588
+ 越 587
589
+ 德 588
590
+ 尔 589
591
+ 松 590
592
+ 曲 591
593
+ 瓦 592
594
+ 业 593
595
+ 修 594
596
+ 音 595
597
+ 圣 596
598
+ 洁 597
599
+ 箱 598
600
+ 聘 599
601
+ 模 600
602
+ 琴 601
603
+ 奏 602
604
+ 响 603
605
+ W 604
606
+ 钢 605
607
+ 息 606
608
+ 缺 607
609
+ 贝 608
610
+ 共 609
611
+ 三 610
612
+ 五 611
613
+ 生 612
614
+ 宜 613
615
+ 器 614
616
+ 公 615
617
+ 淘 616
618
+ 宝 617
619
+ 续 618
620
+ 午 619
621
+ 乎 620
622
+ 严 621
623
+ 每 622
624
+ 份 623
625
+ 盒 624
626
+ 齐 625
627
+ 档 626
628
+ 腻 627
629
+ 难 628
630
+ 聊 629
631
+ 母 630
632
+ 牵 631
633
+ 言 632
634
+ 语 633
635
+ 含 634
636
+ 动 635
637
+ 租 636
638
+ 搞 637
639
+ 混 638
640
+ 早 639
641
+ 保 640
642
+ 温 641
643
+ 利 642
644
+ 畅 643
645
+ 幼 644
646
+ 校 645
647
+ 兼 646
648
+ 职 647
649
+ 贼 648
650
+ 熟 649
651
+ 秩 650
652
+ 序 651
653
+ 彩 652
654
+ 等 653
655
+ 留 654
656
+ 组 655
657
+ 巧 656
658
+ 力 657
659
+ 列 658
660
+ 罗 659
661
+ 颗 660
662
+ 熊 661
663
+ 偶 662
664
+ 叫 663
665
+ 丹 664
666
+ 麦 665
667
+ 蓝 666
668
+ 罐 667
669
+ 牌 668
670
+ 奶 669
671
+ 酪 670
672
+ 呛 671
673
+ 牛 672
674
+ 啦 673
675
+ 捧 674
676
+ 华 675
677
+ 丽 676
678
+ 值 677
679
+ 今 678
680
+ 雏 679
681
+ 继 680
682
+ 叉 681
683
+ 明 682
684
+ 稿 683
685
+ K 684
686
+ 嘞 685
687
+ 南 686
688
+ 北 687
689
+ 路 688
690
+ 充 689
691
+ 零 690
692
+ 夕 691
693
+ 俩 692
694
+ 取 693
695
+ 决 694
696
+ 于 695
697
+ P 696
698
+ A 697
699
+ 掉 698
700
+ 识 699
701
+ 吉 700
702
+ 拟 701
703
+ 童 702
704
+ 根 703
705
+ 据 704
706
+ 龄 705
707
+ 段 706
708
+ 翻 707
709
+ 统 708
710
+ 拖 709
711
+ 尾 710
712
+ T 711
713
+ 入 712
714
+ 护 713
715
+ 措 714
716
+ 施 715
717
+ 率 716
718
+ 呈 717
719
+ 象 718
720
+ 厅 719
721
+ 乱 720
722
+ 糟 721
723
+ 回 722
724
+ 价 723
725
+ 线 724
726
+ 查 725
727
+ 玫 726
728
+ 瑰 727
729
+ 住 728
730
+ 宿 729
731
+ 剩 730
732
+ 补 731
733
+ 换 732
734
+ 秀 733
735
+ 禾 734
736
+ 典 735
737
+ 法 736
738
+ 呦 737
739
+ 堵 738
740
+ 录 739
741
+ 平 740
742
+ 塞 741
743
+ 帐 742
744
+ 世 743
745
+ 故 744
746
+ 脸 745
747
+ 皮 746
748
+ 土 747
749
+ 薅 748
750
+ 托 749
751
+ 赚 750
752
+ 眼 751
753
+ 泪 752
754
+ G 753
755
+ 满 754
756
+ 敲 755
757
+ 片 756
758
+ 透 757
759
+ 创 758
760
+ 买 759
761
+ 堆 760
762
+ 约 761
763
+ 蝴 762
764
+ 蝶 763
765
+ 味 764
766
+ 甜 765
767
+ 宫 766
768
+ 爆 767
769
+ 鸡 768
770
+ 忙 769
771
+ 众 770
772
+ 食 771
773
+ 岗 772
774
+ 随 773
775
+ 援 774
776
+ 兔 775
777
+ 衣 776
778
+ 裸 777
779
+ 副 778
780
+ 商 779
781
+ 近 780
782
+ 希 781
783
+ 望 782
784
+ 纪 783
785
+ 念 784
786
+ 义 785
787
+ 表 786
788
+ 恩 787
789
+ 终 788
790
+ 左 789
791
+ 右 790
792
+ 星 791
793
+ 香 792
794
+ 解 793
795
+ 征 794
796
+ 恋 795
797
+ 史 796
798
+ 雅 797
799
+ 馨 798
800
+ 谐 799
801
+ 劲 800
802
+ 综 801
803
+ 基 802
804
+ 善 803
805
+ 境 804
806
+ 尤 805
807
+ 卫 806
808
+ 存 807
809
+ 净 808
810
+ 厨 809
811
+ 抢 810
812
+ 晚 811
813
+ 刷 812
814
+ 卡 813
815
+ 隔 814
816
+ 板 815
817
+ 疫 816
818
+ 待 817
819
+ 初 818
820
+ 达 819
821
+ 标 820
822
+ 才 821
823
+ 普 822
824
+ 倒 823
825
+ 菜 824
826
+ 市 825
827
+ 认 826
828
+ 油 827
829
+ 图 828
830
+ 关 829
831
+ 性 830
832
+ 帽 831
833
+ 罩 832
834
+ 武 833
835
+ 肉 834
836
+ 苛 835
837
+ 刻 836
838
+ 涨 837
839
+ 光 838
840
+ 身 839
841
+ 抠 840
842
+ 房 841
843
+ 笔 842
844
+ 杜 843
845
+ 绝 844
846
+ 消 845
847
+ 检 846
848
+ 积 847
849
+ 卖 848
850
+ 姑 849
851
+ 喝 850
852
+ 咖 851
853
+ 啡 852
854
+ 落 853
855
+ 窗 854
856
+ 亮 855
857
+ 批 856
858
+ 务 857
859
+ 紧 858
860
+ 敢 859
861
+ 水 860
862
+ 易 861
863
+ 增 862
864
+ 益 863
865
+ 伙 864
866
+ 优 865
867
+ 惠 866
868
+ 衡 867
869
+ 材 868
870
+ 料 869
871
+ 甲 870
872
+ 醛 871
873
+ 玻 872
874
+ 璃 873
875
+ 抽 874
876
+ 烟 875
877
+ 锈 876
878
+ 容 877
879
+ 引 878
880
+ 火 879
881
+ 灾 880
882
+ 橱 881
883
+ 柜 882
884
+ 执 883
885
+ 扩 884
886
+ 适 885
887
+ 占 886
888
+ 快 887
889
+ 晾 888
890
+ 歇 889
891
+ 忍 890
892
+ 码 891
893
+ 顿 892
894
+ 糊 893
895
+ 坏 894
896
+ 铁 895
897
+ 木 896
898
+ 际 897
899
+ 异 898
900
+ 品 899
901
+ 谱 900
902
+ 减 901
903
+ 凑 902
904
+ 化 903
905
+ 投 904
906
+ 诉 905
907
+ 楼 906
908
+ 哥 907
909
+ 拦 908
910
+ 劳 909
911
+ 牢 910
912
+ 炒 911
913
+ 茄 912
914
+ 饮 913
915
+ 盛 914
916
+ 扔 915
917
+ 局 916
918
+ 代 917
919
+ 民 918
920
+ 社 919
921
+ 棕 920
922
+ 铺 921
923
+ 层 922
924
+ 吸 923
925
+ 圆 924
926
+ 挡 925
927
+ 撤 926
928
+ 烹 927
929
+ 饪 928
930
+ 健 929
931
+ 康 930
932
+ 养 931
933
+ 嘴 932
934
+ 映 933
935
+ 懂 934
936
+ 擦 935
937
+ 升 936
938
+ 旦 937
939
+ 槽 938
940
+ 猫 939
941
+ 蔬 940
942
+ 累 941
943
+ 喔 942
944
+ 埋 943
945
+ 怨 944
946
+ 破 945
947
+ 悄 946
948
+ 披 947
949
+ 萨 948
950
+ 骨 949
951
+ 连 950
952
+ 烤 951
953
+ 煮 952
954
+ 炖 953
955
+ 试 954
956
+ 称 955
957
+ 戳 956
958
+ 视 957
959
+ 屏 958
960
+ 青 959
961
+ 例 960
962
+ 独 961
963
+ 距 962
964
+ 离 963
965
+ 售 964
966
+ 凌 965
967
+ 晨 966
968
+ 侣 967
969
+ 折 968
970
+ 停 969
971
+ 逼 970
972
+ 辞 971
973
+ 阿 972
974
+ 姨 973
975
+ 招 974
976
+ 茶 975
977
+ 汁 976
978
+ 冲 977
979
+ 熬 978
980
+ 珍 979
981
+ 珠 980
982
+ 贩 981
983
+ 摁 982
984
+ 杯 983
985
+ 钟 984
986
+ 血 985
987
+ 盟 986
988
+ 稳 987
989
+ 挖 988
990
+ 巴 989
991
+ 羊 990
992
+ 附 991
993
+ 厉 992
994
+ 摊 993
995
+ 堡 994
996
+ 脆 995
997
+ 冰 996
998
+ 米 997
999
+ 林 998
1000
+ 挣 999
1001
+ 漆 1000
1002
+ 胶 1001
1003
+ 晒 1002
1004
+ 潢 1003
1005
+ 脏 1004
1006
+ 烂 1005
1007
+ 墙 1006
1008
+ 艺 1007
1009
+ 被 1008
1010
+ 泡 1009
1011
+ 裂 1010
1012
+ 污 1011
1013
+ 洗 1012
1014
+ 涤 1013
1015
+ 灵 1014
1016
+ 立 1015
1017
+ 型 1016
1018
+ 海 1017
1019
+ 股 1018
1020
+ 团 1019
1021
+ 联 1020
1022
+ 塑 1021
1023
+ 辣 1022
1024
+ 淡 1023
1025
+ 沙 1024
1026
+ 汤 1025
1027
+ 粥 1026
1028
+ 嗐 1027
1029
+ 条 1028
1030
+ 款 1029
1031
+ 培 1030
1032
+ 训 1031
1033
+ 摘 1032
1034
+ 域 1033
1035
+ 捷 1034
1036
+ 噢 1035
1037
+ 姗 1036
1038
+ 肥 1037
1039
+ 田 1038
1040
+ 舍 1039
1041
+ 涂 1040
1042
+ 磁 1041
1043
+ 炉 1042
1044
+ 洞 1043
1045
+ 谓 1044
1046
+ 肴 1045
1047
+ 缓 1046
1048
+ 兵 1047
1049
+ 防 1048
1050
+ 止 1049
1051
+ 燃 1050
1052
+ 活 1051
1053
+ 嫌 1052
1054
+ 谈 1053
1055
+ 捋 1054
1056
+ 键 1055
1057
+ 涉 1056
1058
+ 盈 1057
1059
+ 目 1058
1060
+ 顶 1059
1061
+ 甚 1060
1062
+ 退 1061
1063
+ 勤 1062
1064
+ 挂 1063
1065
+ 帅 1064
1066
+ 将 1065
1067
+ 汇 1066
1068
+ 缩 1067
1069
+ 短 1068
1070
+ ！ 1069
1071
+ 炊 1070
1072
+ 件 1071
1073
+ 使 1072
1074
+ 凝 1073
1075
+ 聚 1074
1076
+ 旅 1075
1077
+ 恐 1076
1078
+ 辅 1077
1079
+ 云 1078
1080
+ 错 1079
1081
+ 盹 1080
1082
+ 休 1081
1083
+ 替 1082
1084
+ 项 1083
1085
+ 网 1084
1086
+ 景 1085
1087
+ 版 1086
1088
+ 孔 1087
1089
+ 雀 1088
1090
+ 频 1089
1091
+ 傣 1090
1092
+ 族 1091
1093
+ 拍 1092
1094
+ 驾 1093
1095
+ 限 1094
1096
+ 寻 1095
1097
+ 仨 1096
1098
+ 困 1097
1099
+ 银 1098
1100
+ 忘 1099
1101
+ 姐 1100
1102
+ 旗 1101
1103
+ 袍 1102
1104
+ 山 1103
1105
+ 度 1104
1106
+ 弟 1105
1107
+ 界 1106
1108
+ 季 1107
1109
+ 睡 1108
1110
+ 任 1109
1111
+ 瑞 1110
1112
+ 城 1111
1113
+ 镯 1112
1114
+ 翡 1113
1115
+ 翠 1114
1116
+ 玉 1115
1117
+ 石 1116
1118
+ 硬 1117
1119
+ 碎 1118
1120
+ 婆 1119
1121
+ 缅 1120
1122
+ 甸 1121
1123
+ 产 1122
1124
+ 忽 1123
1125
+ 悠 1124
1126
+ 精 1125
1127
+ 极 1126
1128
+ 宽 1127
1129
+ 致 1128
1130
+ 垫 1129
1131
+ 习 1130
1132
+ 惯 1131
1133
+ 告 1132
1134
+ 张 1133
1135
+ 添 1134
1136
+ 俺 1135
1137
+ 闺 1136
1138
+ 群 1137
1139
+ 飞 1138
1140
+ 险 1139
1141
+ 京 1140
1142
+ 寿 1141
1143
+ 靠 1142
1144
+ 九 1143
1145
+ 呼 1144
1146
+ 悉 1145
1147
+ 练 1146
1148
+ 暂 1147
1149
+ 妥 1148
1150
+ 趟 1149
1151
+ 逛 1150
1152
+ 咳 1151
1153
+ 骑 1152
1154
+ 抛 1153
1155
+ 摔 1154
1156
+ 付 1155
1157
+ 夏 1156
1158
+ 顺 1157
1159
+ 票 1158
1160
+ 原 1159
1161
+ 街 1160
1162
+ 坊 1161
1163
+ 链 1162
1164
+ 悔 1163
1165
+ 织 1164
1166
+ 港 1165
1167
+ 澳 1166
1168
+ 遍 1167
1169
+ 谢 1168
1170
+ 测 1169
1171
+ 屋 1170
1172
+ 集 1171
1173
+ 妹 1172
1174
+ 攒 1173
1175
+ 蚊 1174
1176
+ 滴 1175
1177
+ 赢 1176
1178
+ 掌 1177
1179
+ 插 1178
1180
+ 串 1179
1181
+ 粒 1180
1182
+ 咯 1181
1183
+ 辛 1182
1184
+ 苦 1183
1185
+ 亏 1184
1186
+ 速 1185
1187
+ 溜 1186
1188
+ 逸 1187
1189
+ 郊 1188
1190
+ 耽 1189
1191
+ 则 1190
1192
+ 抗 1191
1193
+ C 1192
1194
+ 农 1193
1195
+ 与 1194
1196
+ 歌 1195
1197
+ 擅 1196
1198
+ 志 1197
1199
+ 唱 1198
1200
+ V 1199
1201
+ 篝 1200
1202
+ 殊 1201
1203
+ 县 1202
1204
+ 鉴 1203
1205
+ 政 1204
1206
+ 戏 1205
1207
+ 拘 1206
1208
+ 虹 1207
1209
+ 鳟 1208
1210
+ 鱼 1209
1211
+ 奋 1210
1212
+ 斗 1211
1213
+ 融 1212
1214
+ 激 1213
1215
+ 冒 1214
1216
+ 丰 1215
1217
+ 富 1216
1218
+ 匮 1217
1219
+ 乏 1218
1220
+ 静 1219
1221
+ 闲 1220
1222
+ 倾 1221
1223
+ 士 1222
1224
+ 阵 1223
1225
+ 压 1224
1226
+ 腾 1225
1227
+ 荷 1226
1228
+ 战 1227
1229
+ 庭 1228
1230
+ 夜 1229
1231
+ 彻 1230
1232
+ 医 1231
1233
+ 危 1232
1234
+ 怀 1233
1235
+ 柔 1234
1236
+ 密 1235
1237
+ 村 1236
1238
+ 索 1237
1239
+ 爬 1238
1240
+ 侧 1239
1241
+ 湖 1240
1242
+ 拔 1241
1243
+ 河 1242
1244
+ 运 1243
1245
+ 互 1244
1246
+ 配 1245
1247
+ 抱 1246
1248
+ 拓 1247
1249
+ 展 1248
1250
+ 唯 1249
1251
+ 彼 1250
1252
+ 此 1251
1253
+ 矛 1252
1254
+ 盾 1253
1255
+ 失 1254
1256
+ 瞎 1255
1257
+ 陡 1256
1258
+ 探 1257
1259
+ 军 1258
1260
+ 余 1259
1261
+ 操 1260
1262
+ 烧 1261
1263
+ 酱 1262
1264
+ 丝 1263
1265
+ 野 1264
1266
+ 锅 1265
1267
+ 馄 1266
1268
+ 饨 1267
1269
+ 货 1268
1270
+ 王 1269
1271
+ 荣 1270
1272
+ 耀 1271
1273
+ 轰 1272
1274
+ 趴 1273
1275
+ 饱 1274
1276
+ 豆 1275
1277
+ 腐 1276
1278
+ 宴 1277
1279
+ 廊 1278
1280
+ 躺 1279
1281
+ 阶 1280
1282
+ 搜 1281
1283
+ 谊 1282
1284
+ 谷 1283
1285
+ 喂 1284
1286
+ 鸭 1285
1287
+ 朴 1286
1288
+ 课 1287
1289
+ 读 1288
1290
+ 皆 1289
1291
+ 锄 1290
1292
+ 汗 1291
1293
+ 演 1292
1294
+ 瑕 1293
1295
+ 趋 1294
1296
+ 疯 1295
1297
+ 舟 1296
1298
+ 甭 1297
1299
+ 奔 1298
1300
+ 私 1299
1301
+ 担 1300
1302
+ 猜 1301
1303
+ 谜 1302
1304
+ 胃 1303
1305
+ 幸 1304
1306
+ 福 1305
1307
+ 追 1306
1308
+ 梦 1307
1309
+ 切 1308
1310
+ 拾 1309
1311
+ 柴 1310
1312
+ 究 1311
1313
+ 娱 1312
1314
+ 州 1313
1315
+ 昌 1314
1316
+ 慢 1315
1317
+ 恨 1316
1318
+ 遛 1317
1319
+ 弯 1318
1320
+ 澡 1319
1321
+ 氛 1320
1322
+ 飘 1321
1323
+ 顾 1322
1324
+ 泉 1323
1325
+ 蹦 1324
1326
+ 螺 1325
1327
+ 寺 1326
1328
+ 拜 1327
1329
+ 即 1328
1330
+ 申 1329
1331
+ 篇 1330
1332
+ 律 1331
1333
+ 漂 1332
1334
+ 状 1333
1335
+ 态 1334
1336
+ 协 1335
1337
+ 萝 1336
1338
+ 卜 1337
1339
+ 坑 1338
1340
+ 官 1339
1341
+ 竞 1340
1342
+ 技 1341
1343
+ 迪 1342
1344
+ U 1343
1345
+ 储 1344
1346
+ 删 1345
1347
+ 载 1346
1348
+ 伍 1347
1349
+ 骁 1348
1350
+ 龙 1349
1351
+ 卓 1350
1352
+ I 1351
1353
+ 广 1352
1354
+ 摄 1353
1355
+ 功 1354
1356
+ 赞 1355
1357
+ 观 1356
1358
+ 闪 1357
1359
+ 税 1358
1360
+ 角 1359
1361
+ 居 1360
1362
+ 苹 1361
1363
+ 狱 1362
1364
+ X 1363
1365
+ R 1364
1366
+ 烊 1365
1367
+ 玺 1366
1368
+ 俊 1367
1369
+ 凯 1368
1370
+ 斜 1369
1371
+ 纹 1370
1372
+ 池 1371
1373
+ 脑 1372
1374
+ 杀 1373
1375
+ 毒 1374
1376
+ 软 1375
1377
+ 讨 1376
1378
+ 厌 1377
1379
+ 科 1378
1380
+ 步 1379
1381
+ 芯 1380
1382
+ 敏 1381
1383
+ 刘 1382
1384
+ 购 1383
1385
+ 诸 1384
1386
+ 维 1385
1387
+ 返 1386
1388
+ 厂 1387
1389
+ 恢 1388
1390
+ 复 1389
1391
+ 舰 1390
1392
+ 拼 1391
1393
+ 评 1392
1394
+ 针 1393
1395
+ 企 1394
1396
+ 弃 1395
1397
+ M 1396
1398
+ 悬 1397
1399
+ 封 1398
1400
+ 闭 1399
1401
+ 研 1400
1402
+ 睛 1401
1403
+ 答 1402
1404
+ 雷 1403
1405
+ 斯 1404
1406
+ 仇 1405
1407
+ 酷 1406
1408
+ 漏 1407
1409
+ 液 1408
1410
+ 源 1409
1411
+ 垃 1410
1412
+ 圾 1411
1413
+ 繁 1412
1414
+ 邮 1413
1415
+ 令 1414
1416
+ 踪 1415
1417
+ 输 1416
1418
+ 监 1417
1419
+ 麒 1418
1420
+ 麟 1419
1421
+ 权 1420
1422
+ 威 1421
1423
+ 础 1422
1424
+ 拢 1423
1425
+ 却 1424
1426
+ 船 1425
1427
+ Q 1426
1428
+ 幕 1427
1429
+ 额 1428
1430
+ 盖 1429
1431
+ 抒 1430
1432
+ 冈 1431
1433
+ 窟 1432
1434
+ 祁 1433
1435
+ 乔 1434
1436
+ 晋 1435
1437
+ 祠 1436
1438
+ 祈 1437
1439
+ 踊 1438
1440
+ 跃 1439
1441
+ 憋 1440
1442
+ 郁 1441
1443
+ 闷 1442
1444
+ 势 1443
1445
+ 绵 1444
1446
+ 恒 1445
1447
+ 遥 1446
1448
+ 古 1447
1449
+ 汽 1448
1450
+ 醋 1449
1451
+ 降 1450
1452
+ 陈 1451
1453
+ 杏 1452
1454
+ 岭 1453
1455
+ 冬 1454
1456
+ 煤 1455
1457
+ 断 1456
1458
+ 深 1457
1459
+ 桶 1458
1460
+ 斤 1459
1461
+ 缸 1460
1462
+ 镇 1461
1463
+ 栅 1462
1464
+ 栏 1463
1465
+ 壶 1464
1466
+ 瀑 1465
1467
+ 羽 1466
1468
+ 绒 1467
1469
+ 文 1468
1470
+ 菩 1469
1471
+ 攻 1470
1472
+ 略 1471
1473
+ 介 1472
1474
+ 绍 1473
1475
+ 炷 1474
1476
+ 佛 1475
1477
+ 巩 1476
1478
+ 俐 1477
1479
+ 享 1478
1480
+ 揽 1479
1481
+ 江 1480
1482
+ 婺 1481
1483
+ 庐 1482
1484
+ 径 1483
1485
+ 仙 1484
1486
+ 览 1485
1487
+ 涧 1486
1488
+ 树 1487
1489
+ 阔 1488
1490
+ 毛 1489
1491
+ 席 1490
1492
+ 址 1491
1493
+ 井 1492
1494
+ 末 1493
1495
+ 叠 1494
1496
+ 磕 1495
1497
+ 允 1496
1498
+ 承 1497
1499
+ 育 1498
1500
+ 雾 1499
1501
+ 缭 1500
1502
+ 绕 1501
1503
+ 梯 1502
1504
+ 朝 1503
1505
+ 喽 1504
1506
+ 胖 1505
1507
+ 圈 1506
1508
+ 薄 1507
1509
+ 趁 1508
1510
+ 借 1509
1511
+ 触 1510
1512
+ 跳 1511
1513
+ 酸 1512
1514
+ 吼 1513
1515
+ 惦 1514
1516
+ 及 1515
1517
+ 残 1516
1518
+ 疾 1517
1519
+ 楞 1518
1520
+ 拽 1519
1521
+ 缆 1520
1522
+ 嗨 1521
1523
+ 陆 1522
1524
+ 登 1523
1525
+ 痛 1524
1526
+ 掏 1525
1527
+ 旺 1526
1528
+ 踏 1527
1529
+ 寄 1528
1530
+ 抓 1529
1531
+ 灰 1530
1532
+ 架 1531
1533
+ 命 1532
1534
+ 汾 1533
1535
+ 挨 1534
1536
+ 构 1535
1537
+ 蜡 1536
1538
+ 遗 1537
1539
+ 憾 1538
1540
+ 震 1539
1541
+ 撼 1540
1542
+ 赋 1541
1543
+ 浆 1542
1544
+ 滑 1543
1545
+ 竿 1544
1546
+ 释 1545
1547
+ 岛 1546
1548
+ 邻 1547
1549
+ 毁 1548
1550
+ 膝 1549
1551
+ 皇 1550
1552
+ 府 1551
1553
+ 雪 1552
1554
+ 舞 1553
1555
+ 络 1554
1556
+ 帘 1555
1557
+ 马 1556
1558
+ 咆 1557
1559
+ 哮 1558
1560
+ 杆 1559
1561
+ 抬 1560
1562
+ 播 1561
1563
+ 何 1562
1564
+ 哺 1563
1565
+ 乳 1564
1566
+ 弥 1565
1567
+ 凳 1566
1568
+ 归 1567
1569
+ 旧 1568
1570
+ 细 1569
1571
+ 扯 1570
1572
+ 财 1571
1573
+ 锋 1572
1574
+ 咨 1573
1575
+ 询 1574
1576
+ 扫 1575
1577
+ 辐 1576
1578
+ 射 1577
1579
+ 鞋 1578
1580
+ 伤 1579
1581
+ 裕 1580
1582
+ 阳 1581
1583
+ 歹 1582
1584
+ 旷 1583
1585
+ 李 1584
1586
+ 瓶 1585
1587
+ 历 1586
1588
+ 屉 1587
1589
+ 撑 1588
1590
+ 冠 1589
1591
+ 舒 1590
1592
+ 涵 1591
1593
+ 击 1592
1594
+ 扰 1593
1595
+ 循 1594
1596
+ 誉 1595
1597
+ 革 1596
1598
+ 良 1597
1599
+ 拆 1598
1600
+ 耗 1599
1601
+ 携 1600
1602
+ 济 1601
1603
+ 摩 1602
1604
+ 锻 1603
1605
+ 炼 1604
1606
+ 呆 1605
1607
+ 趣 1606
1608
+ 乒 1607
1609
+ 乓 1608
1610
+ 疑 1609
1611
+ 筐 1610
1612
+ 尴 1611
1613
+ 绳 1612
1614
+ 邀 1613
1615
+ 钻 1614
1616
+ 轮 1615
1617
+ 滚 1616
1618
+ 踩 1617
1619
+ 虫 1618
1620
+ 棍 1619
1621
+ 拎 1620
1622
+ 踢 1621
1623
+ 毽 1622
1624
+ 鼓 1623
1625
+ 筛 1624
1626
+ 奖 1625
1627
+ 脚 1626
1628
+ 枸 1627
1629
+ 杞 1628
1630
+ 迟 1629
1631
+ 篮 1630
1632
+ 芥 1631
1633
+ 蒂 1632
1634
+ 肠 1633
1635
+ 筹 1634
1636
+ 仅 1635
1637
+ 旬 1636
1638
+ 霾 1637
1639
+ 扎 1638
1640
+ 词 1639
1641
+ 箭 1640
1642
+ 吹 1641
1643
+ 岂 1642
1644
+ 死 1643
1645
+ 惊 1644
1646
+ 吓 1645
1647
+ 察 1646
1648
+ 核 1647
1649
+ 疗 1648
1650
+ 救 1649
1651
+ 促 1650
1652
+ 默 1651
1653
+ 契 1652
1654
+ 拒 1653
1655
+ 励 1654
1656
+ 咦 1655
1657
+ 获 1656
1658
+ 刺 1657
1659
+ 盆 1658
1660
+ 坚 1659
1661
+ 乘 1660
1662
+ 杵 1661
1663
+ 峰 1662
1664
+ 蒙 1663
1665
+ 啃 1664
1666
+ 滨 1665
1667
+ 鹅 1666
1668
+ 嘿 1667
1669
+ 呵 1668
1670
+ 骗 1669
1671
+ 豪 1670
1672
+ 涠 1671
1673
+ 洲 1672
1674
+ 厦 1673
1675
+ 漠 1674
1676
+ 炕 1675
1677
+ 诞 1676
1678
+ 辩 1677
1679
+ 亚 1678
1680
+ 沿 1679
1681
+ 琼 1680
1682
+ 驻 1681
1683
+ 守 1682
1684
+ 橇 1683
1685
+ 兄 1684
1686
+ 卦 1685
1687
+ 沧 1686
1688
+ 茫 1687
1689
+ 坡 1688
1690
+ 驰 1689
1691
+ 宁 1690
1692
+ 川 1691
1693
+ 甘 1692
1694
+ 孜 1693
1695
+ 床 1694
1696
+ 扑 1695
1697
+ 欣 1696
1698
+ 赏 1697
1699
+ 途 1698
1700
+ 迷 1699
1701
+ 刀 1700
1702
+ 刃 1701
1703
+ 宰 1702
1704
+ 杨 1703
1705
+ 猴 1704
1706
+ 瘦 1705
1707
+ 瞅 1706
1708
+ 亭 1707
1709
+ 润 1708
1710
+ 漫 1709
1711
+ 访 1710
1712
+ 剪 1711
1713
+ 忆 1712
1714
+ 撬 1713
1715
+ 扭 1714
1716
+ 横 1715
1717
+ 粗 1716
1718
+ 爷 1717
1719
+ 岁 1718
1720
+ 罚 1719
1721
+ 绪 1720
1722
+ 盯 1721
1723
+ 叔 1722
1724
+ 揣 1723
1725
+ 舅 1724
1726
+ 孕 1725
1727
+ 妆 1726
1728
+ 嘱 1727
1729
+ 咐 1728
1730
+ 媳 1729
1731
+ 妇 1730
1732
+ 璐 1731
1733
+ 矩 1732
1734
+ 晶 1733
1735
+ 芭 1734
1736
+ 蕾 1735
1737
+ 崩 1736
1738
+ 夸 1737
1739
+ 绩 1738
1740
+ 蹭 1739
1741
+ 符 1740
1742
+ 乡 1741
1743
+ 均 1742
1744
+ 吵 1743
1745
+ 苏 1744
1746
+ 臭 1745
1747
+ 病 1746
1748
+ 喊 1747
1749
+ 毯 1748
1750
+ 轿 1749
1751
+ 迎 1750
1752
+ 绣 1751
1753
+ 鞍 1752
1754
+ 唐 1753
1755
+ 迈 1754
1756
+ 扇 1755
1757
+ 撒 1756
1758
+ 瓣 1757
1759
+ 摞 1758
1760
+ 狠 1759
1761
+ 枯 1760
1762
+ 秃 1761
1763
+ 幻 1762
1764
+ 忒 1763
1765
+ 蜜 1764
1766
+ 砸 1765
1767
+ 嗓 1766
1768
+ 耳 1767
1769
+ 敬 1768
1770
+ 肤 1769
1771
+ 争 1770
1772
+ 努 1771
1773
+ 绑 1772
1774
+ 暗 1773
1775
+ 怼 1774
1776
+ 祖 1775
1777
+ 宗 1776
1778
+ 逮 1777
1779
+ 遮 1778
1780
+ 曼 1779
1781
+ 勾 1780
1782
+ 灯 1781
1783
+ 躁 1782
1784
+ 搂 1783
1785
+ 津 1784
1786
+ 淀 1785
1787
+ 仔 1786
1788
+ 疵 1787
1789
+ 兑 1788
1790
+ 绎 1789
1791
+ 颖 1790
1792
+ 貌 1791
1793
+ 晕 1792
1794
+ 障 1793
1795
+ 寨 1794
1796
+ 氧 1795
1797
+ 幅 1796
1798
+ 赘 1797
1799
+ 药 1798
1800
+ 判 1799
1801
+ ( 1800
1802
+ ) 1801
1803
+ 吐 1802
1804
+ 媛 1803
1805
+ 勉 1804
1806
+ 尝 1805
1807
+ 凉 1806
1808
+ 谅 1807
1809
+ 谦 1808
1810
+ 碗 1809
1811
+ 端 1810
1812
+ 召 1811
1813
+ 欲 1812
1814
+ 胞 1813
1815
+ 胎 1814
1816
+ 凡 1815
1817
+ 挎 1816
1818
+ 赴 1817
1819
+ 歉 1818
1820
+ 肢 1819
1821
+ 急 1820
1822
+ 遵 1821
1823
+ 章 1822
1824
+ 仗 1823
1825
+ 述 1824
1826
+ 勋 1825
1827
+ 彰 1826
1828
+ 煎 1827
1829
+ 馅 1828
1830
+ 烙 1829
1831
+ 傅 1830
1832
+ 蒜 1831
1833
+ 筷 1832
1834
+ 染 1833
1835
+ 赤 1834
1836
+ 虚 1835
1837
+ 懒 1836
1838
+ 督 1837
1839
+ 灶 1838
1840
+ 巾 1839
1841
+ 糕 1840
1842
+ 眉 1841
1843
+ 坨 1842
1844
+ 馈 1843
1845
+ 馒 1844
1846
+ 橘 1845
1847
+ 葱 1846
1848
+ 椒 1847
1849
+ 蘑 1848
1850
+ 菇 1849
1851
+ 勺 1850
1852
+ 紫 1851
1853
+ 蛋 1852
1854
+ 审 1853
1855
+ 猪 1854
1856
+ 蒸 1855
1857
+ 卷 1856
1858
+ 笼 1857
1859
+ 掀 1858
1860
+ 荤 1859
1861
+ 喇 1860
1862
+ 叭 1861
1863
+ 扁 1862
1864
+ 棚 1863
1865
+ 蘸 1864
1866
+ 凭 1865
1867
+ 耐 1866
1868
+ 临 1867
1869
+ 禁 1868
1870
+ 警 1869
1871
+ 握 1870
1872
+ 瓜 1871
1873
+ 淇 1872
1874
+ 淋 1873
1875
+ 杭 1874
1876
+ 浙 1875
1877
+ 滩 1876
1878
+ 徽 1877
1879
+ 夷 1878
1880
+ 库 1879
1881
+ 磊 1880
1882
+ 彭 1881
1883
+ 昱 1882
1884
+ 曾 1883
1885
+ 湾 1884
1886
+ 航 1885
1887
+ 册 1886
1888
+ 贺 1887
1889
+ 洽 1888
1890
+ 锁 1889
1891
+ 浦 1890
1892
+ 尼 1891
1893
+ 仓 1892
1894
+ 艾 1893
1895
+ 拥 1894
1896
+ F 1895
1897
+ 挤 1896
1898
+ 予 1897
1899
+ 赌 1898
1900
+ 孙 1899
1901
+ 损 1900
1902
+ 泰 1901
1903
+ 棉 1902
1904
+ 袄 1903
1905
+ 肚 1904
1906
+ 圳 1905
1907
+ 姓 1906
1908
+ 耍 1907
1909
+ 贷 1908
1910
+ 赡 1909
1911
+ 曙 1910
1912
+ 迁 1911
1913
+ 捡 1912
1914
+ 羡 1913
1915
+ 慕 1914
1916
+ 窿 1915
1917
+ 填 1916
1918
+ 债 1917
1919
+ 抄 1918
1920
+ 挪 1919
1921
+ 钩 1920
1922
+ 睁 1921
1923
+ 辑 1922
1924
+ 爹 1923
1925
+ 仿 1924
1926
+ 姻 1925
1927
+ 澄 1926
1928
+ 娲 1927
1929
+ 莱 1928
1930
+ 镜 1929
1931
+ 贸 1930
1932
+ 弱 1931
1933
+ 廖 1932
1934
+ 吆 1933
1935
+ H 1934
1936
+ 亿 1935
1937
+ 媒 1936
1938
+ 惨 1937
1939
+ 丈 1938
1940
+ 霜 1939
1941
+ 详 1940
1942
+ 递 1941
1943
+ 眠 1942
1944
+ 盐 1943
1945
+ 哑 1944
1946
+ 铃 1945
1947
+ 饿 1946
1948
+ 饥 1947
1949
+ 敷 1948
1950
+ 俭 1949
1951
+ 抑 1950
1952
+ 剔 1951
1953
+ 跨 1952
1954
+ 疲 1953
1955
+ 惫 1954
1956
+ 迫 1955
1957
+ 刹 1956
1958
+ 奇 1957
1959
+ 废 1958
1960
+ 贯 1959
1961
+ 衍 1960
1962
+ 裁 1961
1963
+ 浮 1962
1964
+ 汰 1963
1965
+ 肺 1964
1966
+ 疼 1965
1967
+ 罢 1966
1968
+ 腿 1967
1969
+ 噌 1968
1970
+ 腹 1969
1971
+ 摇 1970
1972
+ 捆 1971
1973
+ 渲 1972
1974
+ 匀 1973
1975
+ 胜 1974
1976
+ 牺 1975
1977
+ 牲 1976
1978
+ 靴 1977
1979
+ 衷 1978
1980
+ 墅 1979
1981
+ 栋 1980
1982
+ 撕 1981
1983
+ 贡 1982
1984
+ 献 1983
1985
+ 寒 1984
1986
+ 颁 1985
1987
+ 佳 1986
1988
+ 缘 1987
1989
+ 癖 1988
1990
+ 董 1989
1991
+ 魅 1990
1992
+ N 1991
1993
+ 博 1992
1994
+ 肘 1993
1995
+ 遂 1994
1996
+ 腰 1995
1997
+ 祝 1996
1998
+ 簧 1997
1999
+ 藏 1998
2000
+ 诚 1999
2001
+ 勿 2000
2002
+ 嘉 2001
2003
+ 委 2002
2004
+ 燥 2003
2005
+ 诺 2004
2006
+ 筒 2005
2007
+ 狼 2006
2008
+ 编 2007
2009
+ 碜 2008
2010
+ 棋 2009
2011
+ 雁 2010
2012
+ 栖 2011
2013
+ 赁 2012
2014
+ 衔 2013
2015
+ 逐 2014
2016
+ 渐 2015
2017
+ 砍 2016
2018
+ 琐 2017
2019
+ 败 2018
2020
+ 骤 2019
2021
+ 若 2020
2022
+ 兰 2021
2023
+ 犹 2022
2024
+ 豫 2023
2025
+ 奢 2024
2026
+ 侈 2025
2027
+ 辨 2026
2028
+ 慎 2027
2029
+ 暴 2028
2030
+ 廉 2029
2031
+ B 2030
2032
+ 依 2031
2033
+ 赖 2032
2034
+ 券 2033
2035
+ 劵 2034
2036
+ 棵 2035
2037
+ 晰 2036
2038
+ 智 2037
2039
+ 咸 2038
2040
+ 谨 2039
2041
+ 摸 2040
2042
+ 哩 2041
2043
+ 欺 2042
2044
+ 瞒 2043
2045
+ 缚 2044
2046
+ 覆 2045
2047
+ 阻 2046
2048
+ 碍 2047
2049
+ 柿 2048
2050
+ 渠 2049
2051
+ 匆 2050
2052
+ 稀 2051
2053
+ 榨 2052
2054
+ 羹 2053
2055
+ 蜂 2054
2056
+ 陕 2055
2057
+ 酬 2056
2058
+ 央 2057
2059
+ 塔 2058
2060
+ 奈 2059
2061
+ 俏 2060
2062
+ 赠 2061
2063
+ 沫 2062
2064
+ 裳 2063
2065
+ 催 2064
2066
+ 蟹 2065
2067
+ 伪 2066
2068
+ 劣 2067
2069
+ 茅 2068
2070
+ 抹 2069
2071
+ 泥 2070
2072
+ 搪 2071
2073
+ 昨 2072
2074
+ 弊 2073
2075
+ 姜 2074
2076
+ 铛 2075
2077
+ 肩 2076
2078
+ 捕 2077
2079
+ 捉 2078
2080
+ 悦 2079
2081
+ 削 2080
2082
+ 萧 2081
2083
+ 琢 2082
2084
+ 磨 2083
2085
+ 析 2084
2086
+ 咬 2085
2087
+ 扒 2086
2088
+ 闸 2087
2089
+ 愉 2088
2090
+ 譬 2089
2091
+ 粘 2090
2092
+ 栗 2091
2093
+ 拐 2092
2094
+ 蛮 2093
2095
+ 衬 2094
2096
+ 衫 2095
2097
+ 恤 2096
2098
+ 牙 2097
2099
+ 械 2098
2100
+ 蓄 2099
2101
+ 尺 2100
2102
+ 臀 2101
2103
+ 墨 2102
2104
+ 狗 2103
2105
+ 授 2104
2106
+ 皂 2105
2107
+ 褥 2106
2108
+ 袜 2107
2109
+ 雕 2108
2110
+ 嚯 2109
2111
+ 贱 2110
2112
+ 熨 2111
2113
+ 烘 2112
2114
+ 剜 2113
2115
+ 夹 2114
2116
+ 俱 2115
2117
+ 菌 2116
2118
+ 倍 2117
2119
+ 浑 2118
2120
+ 哗 2119
2121
+ 纺 2120
2122
+ 哐 2121
2123
+ 叽 2122
2124
+ 扬 2123
2125
+ 稠 2124
2126
+ 晃 2125
2127
+ 奥 2126
2128
+ 妙 2127
2129
+ 渍 2128
2130
+ 氯 2129
2131
+ 闻 2130
2132
+ 蹿 2131
2133
+ 恶 2132
2134
+ 矿 2133
2135
+ 剂 2134
2136
+ 沏 2135
2137
+ 湿 2136
2138
+ 歪 2137
2139
+ 纤 2138
2140
+ 浅 2139
2141
+ 潮 2140
2142
+ 胰 2141
2143
+ 沾 2142
2144
+ 芳 2143
2145
+ 褶 2144
2146
+ 碧 2145
2147
+ 搓 2146
2148
+ 硫 2147
2149
+ 磺 2148
2150
+ 酶 2149
2151
+ 浓 2150
2152
+ 溶 2151
2153
+ 屯 2152
2154
+ 螨 2153
2155
+ 膏 2154
2156
+ 浴 2155
2157
+ 灌 2156
2158
+ 灭 2157
2159
+ 脱 2158
2160
+ 脂 2159
2161
+ 滤 2160
2162
+ �� 2161
2163
+ 烫 2162
2164
+ 鼻 2163
2165
+ 鼠 2164
2166
+ 啤 2165
2167
+ 尘 2166
2168
+ 赫 2167
2169
+ 琳 2168
2170
+ 逗 2169
2171
+ 桑 2170
2172
+ 哭 2171
2173
+ 伏 2172
2174
+ 豁 2173
2175
+ 钳 2174
2176
+ 胡 2175
2177
+ 跌 2176
2178
+ 挝 2177
2179
+ 柬 2178
2180
+ 埔 2179
2181
+ 颠 2180
2182
+ 履 2181
2183
+ 桥 2182
2184
+ 永 2183
2185
+ 鸽 2184
2186
+ 玛 2185
2187
+ 辉 2186
2188
+ 诱 2187
2189
+ 疆 2188
2190
+ 粮 2189
2191
+ 仕 2190
2192
+ 斐 2191
2193
+ 鲁 2192
2194
+ 沃 2193
2195
+ 妃 2194
2196
+ 轴 2195
2197
+ 扶 2196
2198
+ 莉 2197
2199
+ 寸 2198
2200
+ 钥 2199
2201
+ 匙 2200
2202
+ 旨 2201
2203
+ 乌 2202
2204
+ 蓬 2203
2205
+ 寓 2204
2206
+ 爽 2205
2207
+ 泳 2206
2208
+ 眯 2207
2209
+ 瞪 2208
2210
+ 骂 2209
2211
+ 奉 2210
2212
+ 赵 2211
2213
+ 著 2212
2214
+ 慰 2213
2215
+ 犒 2214
2216
+ 番 2215
2217
+ 英 2216
2218
+ 聪 2217
2219
+ 贪 2218
2220
+ 蹈 2219
2221
+ 橡 2220
2222
+ 捏 2221
2223
+ 叛 2222
2224
+ 逆 2223
2225
+ 尖 2224
2226
+ 朗 2225
2227
+ 弹 2226
2228
+ 孤 2227
2229
+ 毅 2228
2230
+ 挫 2229
2231
+ 诗 2230
2232
+ 窍 2231
2233
+ 傻 2232
2234
+ 庸 2233
2235
+ 骄 2234
2236
+ 傲 2235
2237
+ 灿 2236
2238
+ 弛 2237
2239
+ 怜 2238
2240
+ 尊 2239
2241
+ 伯 2240
2242
+ 掘 2241
2243
+ 坠 2242
2244
+ 溃 2243
2245
+ 揠 2244
2246
+ 苗 2245
2247
+ 霍 2246
2248
+ 胆 2247
2249
+ 捞 2248
2250
+ 逻 2249
2251
+ 痞 2250
2252
+ 凤 2251
2253
+ 潜 2252
2254
+ 移 2253
2255
+ 姥 2254
2256
+ 宇 2255
2257
+ 愣 2256
2258
+ 蒋 2257
2259
+ 劝 2258
2260
+ 译 2259
2261
+ 掰 2260
2262
+ 撅 2261
2263
+ 钓 2262
2264
+ 磋 2263
2265
+ 艮 2264
2266
+ 啾 2265
2267
+ 犯 2266
2268
+ 杰 2267
2269
+ 伦 2268
2270
+ 笨 2269
2271
+ 韧 2270
2272
+ 噱 2271
2273
+ 帕 2272
2274
+ 伟 2273
2275
+ 渗 2274
2276
+ 剑 2275
2277
+ 迹 2276
2278
+ 醒 2277
2279
+ 幌 2278
2280
+ 薪 2279
2281
+ 岔 2280
2282
+ 锦 2281
2283
+ 掐 2282
2284
+ 苔 2283
2285
+ 娇 2284
2286
+ 镀 2285
2287
+ 碳 2286
2288
+ 驱 2287
2289
+ 籍 2288
2290
+ 欠 2289
2291
+ 粕 2290
2292
+ 柠 2291
2293
+ 檬 2292
2294
+ 呱 2293
2295
+ 瘴 2294
2296
+ 咕 2295
2297
+ 勃 2296
2298
+ 隐 2297
2299
+ 擂 2298
2300
+ 噗 2299
2301
+ 嚓 2300
2302
+ 叮 2301
2303
+ 尚 2302
2304
+ 畴 2303
2305
+ 辟 2304
2306
+ 噪 2305
2307
+ 芙 2306
2308
+ 逾 2307
2309
+ 勒 2308
2310
+ 迭 2309
2311
+ 潘 2310
2312
+ 钉 2311
2313
+ 猕 2312
2314
+ 桃 2313
2315
+ 捂 2314
2316
+ 薯 2315
2317
+ 鸳 2316
2318
+ 鸯 2317
2319
+ 逊 2318
2320
+ 琦 2319
2321
+ 薇 2320
2322
+ 娅 2321
2323
+ 宠 2322
2324
+ 韩 2323
2325
+ 亡 2324
2326
+ 榴 2325
2327
+ 莲 2326
2328
+ 桔 2327
2329
+ 丑 2328
2330
+ 盗 2329
2331
+ 剧 2330
2332
+ 膜 2331
2333
+ 骚 2332
2334
+ 哨 2333
2335
+ 抵 2334
2336
+ 盼 2335
2337
+ 寝 2336
2338
+ 页 2337
2339
+ 浏 2338
2340
+ 侵 2339
2341
+ 簸 2340
2342
+ 糙 2341
2343
+ 偿 2342
2344
+ 冤 2343
2345
+ 框 2344
2346
+ 吊 2345
2347
+ 怖 2346
2348
+ 巢 2347
2349
+ 亦 2348
2350
+ 瑟 2349
2351
+ 垄 2350
2352
+ 遭 2351
2353
+ 劫 2352
2354
+ 蕉 2353
2355
+ 韵 2354
2356
+ 懵 2355
2357
+ 罕 2356
2358
+ 卧 2357
2359
+ 莫 2358
2360
+ 押 2359
2361
+ 啰 2360
2362
+ 偷 2361
2363
+ 楠 2362
2364
+ 瞧 2363
2365
+ 脖 2364
2366
+ 扳 2365
2367
+ 盔 2366
2368
+ 卸 2367
2369
+ 逃 2368
2370
+ 黏 2369
2371
+ 唧 2370
2372
+ 启 2371
2373
+ 违 2372
2374
+ 惩 2373
2375
+ 驶 2374
2376
+ 盲 2375
2377
+ 沛 2376
2378
+ 垮 2377
2379
+ 斧 2378
2380
+ 挞 2379
2381
+ 惑 2380
2382
+ 饺 2381
2383
+ 掂 2382
2384
+ 宵 2383
2385
+ 粤 2384
2386
+ 睫 2385
2387
+ 裹 2386
2388
+ 躲 2387
2389
+ 眨 2388
2390
+ J 2389
2391
+ 蔽 2390
2392
+ 蹲 2391
2393
+ 症 2392
2394
+ 描 2393
2395
+ 驳 2394
2396
+ 泄 2395
2397
+ 洼 2396
2398
+ 槛 2397
2399
+ 陌 2398
2400
+ 蠢 2399
2401
+ 泛 2400
2402
+ 腕 2401
2403
+ 榜 2402
2404
+ 诊 2403
2405
+ 嫩 2404
2406
+ 凹 2405
2407
+ 凸 2406
2408
+ 虎 2407
2409
+ 雄 2408
2410
+ 葛 2409
2411
+ 滋 2410
2412
+ 匹 2411
2413
+ 毫 2412
2414
+ 虐 2413
2415
+ 铜 2414
2416
+ 堕 2415
2417
+ 娜 2416
2418
+ 治 2417
2419
+ 愈 2418
2420
+ 酋 2419
2421
+ 撸 2420
2422
+ 浸 2421
2423
+ 蔡 2422
2424
+ 姬 2423
2425
+ 昭 2424
2426
+ 君 2425
2427
+ 币 2426
2428
+ 壳 2427
2429
+ 漱 2428
2430
+ 垠 2429
2431
+ 鬼 2430
2432
+ 鲍 2431
2433
+ 椰 2432
2434
+ 邂 2433
2435
+ 逅 2434
2436
+ 伞 2435
2437
+ 渡 2436
2438
+ 沈 2437
2439
+ 慈 2438
2440
+ 疮 2439
2441
+ 巨 2440
2442
+ 崇 2441
2443
+ 晤 2442
2444
+ 芒 2443
2445
+ 梨 2444
2446
+ 浇 2445
2447
+ 蜈 2446
2448
+ 寂 2447
2449
+ 寞 2448
2450
+ 蹬 2449
2451
+ 耶 2450
2452
+ 袁 2451
2453
+ 慧 2452
2454
+ 樱 2453
2455
+ 釜 2454
2456
+ 欧 2455
2457
+ 拌 2456
2458
+ 炸 2457
2459
+ 鹭 2458
2460
+ 梁 2459
2461
+ 哄 2460
2462
+ 镐 2461
2463
+ 蹄 2462
2464
+ 讪 2463
2465
+ 帝 2464
2466
+ 殿 2465
2467
+ 荫 2466
2468
+ 弘 2467
2469
+ 仁 2468
2470
+ 邦 2469
2471
+ 礁 2470
2472
+ 怂 2471
2473
+ 壮 2472
2474
+ 宏 2473
2475
+ 妖 2474
2476
+ 践 2475
2477
+ 囊 2476
2478
+ 鱿 2477
2479
+ 旱 2478
2480
+ 悚 2479
2481
+ 憨 2480
2482
+ 芝 2481
2483
+ 驼 2482
2484
+ 纬 2483
2485
+ 捎 2484
2486
+ 患 2485
2487
+ 舱 2486
2488
+ 帆 2487
2489
+ 屁 2488
2490
+ 苍 2489
2491
+ 蝇 2490
2492
+ 汀 2491
2493
+ 霞 2492
2494
+ 艇 2493
2495
+ 呸 2494
2496
+ 嫖 2495
2497
+ 割 2496
2498
+ 勇 2497
2499
+ 搏 2498
2500
+ 茸 2499
2501
+ 咪 2500
2502
+ 薰 2501
2503
+ 檀 2502
2504
+ 喱 2503
2505
+ 笤 2504
2506
+ 帚 2505
2507
+ 蟑 2506
2508
+ 螂 2507
2509
+ 徒 2508
2510
+ 樟 2509
2511
+ 丸 2510
2512
+ 烛 2511
2513
+ 瓢 2512
2514
+ 垢 2513
2515
+ 涮 2514
2516
+ 厕 2515
2517
+ 疹 2516
2518
+ 甩 2517
2519
+ 喷 2518
2520
+ 檫 2519
2521
+ 炭 2520
2522
+ 胀 2521
2523
+ 诧 2522
2524
+ 娃 2523
2525
+ 孚 2524
2526
+ 梳 2525
2527
+ 慌 2526
2528
+ 坎 2527
2529
+ 溯 2528
2530
+ 焦 2529
2531
+ 癌 2530
2532
+ 沪 2531
2533
+ 荟 2532
2534
+ 拣 2533
2535
+ 脾 2534
2536
+ 枪 2535
2537
+ 炮 2536
2538
+ 瘾 2537
2539
+ 咔 2538
2540
+ 剁 2539
2541
+ 犄 2540
2542
+ 旮 2541
2543
+ 旯 2542
2544
+ 碑 2543
2545
+ 曝 2544
2546
+ 迅 2545
2547
+ 砂 2546
2548
+ 爪 2547
2549
+ 秒 2548
2550
+ 膨 2549
2551
+ 洒 2550
2552
+ 芽 2551
2553
+ 窝 2552
2554
+ 炝 2553
2555
+ 韭 2554
2556
+ 疏 2555
2557
+ 唰 2556
2558
+ 溢 2557
2559
+ 蛳 2558
2560
+ 旋 2559
2561
+ 虾 2560
2562
+ 煲 2561
2563
+ 纠 2562
2564
+ 髦 2563
2565
+ 劈 2564
2566
+ 炫 2565
2567
+ 锤 2566
2568
+ 堪 2567
2569
+ 辜 2568
2570
+ 魔 2569
2571
+ 缝 2570
2572
+ 讯 2571
2573
+ 鸣 2572
2574
+ 渣 2573
2575
+ 捐 2574
2576
+ 婴 2575
2577
+ 褒 2576
2578
+ 贬 2577
2579
+ 浩 2578
2580
+ Z 2579
2581
+ 哆 2580
2582
+ 宅 2581
2583
+ 枣 2582
2584
+ 屈 2583
2585
+ 伸 2584
2586
+ 莓 2585
2587
+ 佬 2586
2588
+ 嚷 2587
2589
+ 剃 2588
2590
+ 唤 2589
2591
+ 颇 2590
2592
+ 仍 2591
2593
+ 铄 2592
2594
+ 卤 2593
2595
+ 骛 2594
2596
+ 耙 2595
2597
+ 匿 2596
2598
+ 鸠 2597
2599
+ 鹊 2598
2600
+ 颈 2599
2601
+ 镶 2600
2602
+ 杠 2601
2603
+ 坛 2602
2604
+ 滞 2603
2605
+ 揉 2604
2606
+ 壤 2605
2607
+ 槌 2606
2608
+ 倡 2607
2609
+ 狮 2608
2610
+ 鹜 2609
2611
+ 俪 2610
2612
+ 贾 2611
2613
+ 玲 2612
2614
+ 雯 2613
2615
+ 晓 2614
2616
+ 彤 2615
2617
+ 皱 2616
2618
+ 孝 2617
2619
+ 酵 2618
2620
+ 赃 2619
2621
+ 磷 2620
2622
+ 艰 2621
2623
+ 囤 2622
2624
+ 芦 2623
2625
+ 痒 2624
2626
+ 侍 2625
2627
+ 呕 2626
2628
+ 矣 2627
2629
+ 腑 2628
2630
+ 滥 2629
2631
+ 忧 2630
2632
+ 捣 2631
2633
+ 厢 2632
2634
+ 朵 2633
2635
+ 蛇 2634
2636
+ 荧 2635
2637
+ 嘟 2636
2638
+ 淹 2637
2639
+ 振 2638
2640
+ 窥 2639
2641
+ 撇 2640
2642
+ 铝 2641
2643
+ 倩 2642
2644
+ 惧 2643
2645
+ 彪 2644
2646
+ 侥 2645
2647
+ 玖 2646
2648
+ 姿 2647
2649
+ 蔻 2648
2650
+ 疙 2649
2651
+ 瘩 2650
2652
+ 棺 2651
2653
+ 昂 2652
2654
+ 欸 2653
2655
+ 痘 2654
2656
+ 拧 2655
2657
+ 剥 2656
2658
+ 酿 2657
2659
+ 咣 2658
2660
+ 瓷 2659
2661
+ 褪 2660
2662
+ 俑 2661
2663
+ 坞 2662
2664
+ 拳 2663
2665
+ 洛 2664
2666
+ 杉 2665
2667
+ 矶 2666
2668
+ 俄 2667
2669
+ 渤 2668
2670
+ 鳄 2669
2671
+ 鲨 2670
2672
+ 埃 2671
2673
+ 筑 2672
2674
+ 侦 2673
2675
+ 鹿 2674
2676
+ 恭 2675
2677
+ 嗦 2676
2678
+ 绷 2677
2679
+ 僻 2678
2680
+ 丛 2679
2681
+ 蕴 2680
2682
+ 渊 2681
2683
+ 囧 2682
2684
+ 悟 2683
2685
+ 垂 2684
2686
+ 涎 2685
2687
+ 匠 2686
2688
+ 逝 2687
2689
+ 肿 2688
2690
+ 暑 2689
2691
+ 狂 2690
2692
+ 恙 2691
2693
+ 邪 2692
2694
+ 秘 2693
2695
+ 庙 2694
2696
+ 肃 2695
2697
+ 蜘 2696
2698
+ 蛛 2697
2699
+ 侠 2698
2700
+ 夺 2699
2701
+ 募 2700
2702
+ 翔 2701
2703
+ 佩 2702
2704
+ 衩 2703
2705
+ 秦 2704
2706
+ 绸 2705
2707
+ 猎 2706
2708
+ 瞬 2707
2709
+ 殆 2708
2710
+ 缀 2709
2711
+ 腥 2710
2712
+ 艳 2711
2713
+ 牧 2712
2714
+ 佣 2713
2715
+ 尿 2714
2716
+ 遣 2715
2717
+ 忠 2716
2718
+ 铅 2717
2719
+ 侬 2718
2720
+ 掷 2719
2721
+ 肌 2720
2722
+ 茴 2721
2723
+ 吶 2722
2724
+ 嘚 2723
2725
+ 抡 2724
2726
+ 脉 2725
2727
+ 秤 2726
2728
+ 拷 2727
2729
+ 蛙 2728
2730
+ 舀 2729
2731
+ 仰 2730
2732
+ 函 2731
2733
+ 槟 2732
2734
+ 幽 2733
2735
+ 哏 2734
2736
+ 霸 2735
2737
+ 唔 2736
2738
+ 凰 2737
2739
+ 柱 2738
2740
+ 葡 2739
2741
+ 萄 2740
2742
+ 陶 2741
2743
+ 昆 2742
2744
+ 郭 2743
2745
+ 纲 2744
2746
+ 绢 2745
2747
+ 菲 2746
2748
+ 咚 2747
2749
+ 肋 2748
2750
+ 芬 2749
2751
+ 茬 2750
2752
+ 咵 2751
2753
+ 潍 2752
2754
+ 绞 2753
2755
+ 枕 2754
2756
+ 掸 2755
2757
+ 蚂 2756
2758
+ 蚁 2757
2759
+ 饵 2758
2760
+ 墩 2759
2761
+ 腈 2760
2762
+ 纶 2761
2763
+ 荞 2762
2764
+ 齿 2763
2765
+ 蚀 2764
2766
+ 肆 2765
2767
+ 忌 2766
2768
+ 惮 2767
2769
+ 绊 2768
2770
+ 伺 2769
2771
+ 惜 2770
2772
+ 卵 2771
2773
+ 阅 2772
2774
+ 跆 2773
2775
+ 绘 2774
2776
+ 喧 2775
2777
+ 淑 2776
2778
+ 扛 2777
2779
+ 伶 2778
2780
+ 仃 2779
2781
+ 卑 2780
2782
+ 擀 2781
2783
+ 杖 2782
2784
+ 乖 2783
2785
+ 闯 2784
2786
+ 轨 2785
2787
+ 溺 2786
2788
+ 痰 2787
2789
+ 恰 2788
2790
+ 朱 2789
2791
+ 泊 2790
2792
+ 斑 2791
2793
+ 膈 2792
2794
+ 剌 2793
2795
+ 斟 2794
2796
+ 酌 2795
2797
+ 枝 2796
2798
+ 橙 2797
2799
+ 拙 2798
2800
+ 噶 2799
2801
+ 罪 2800
2802
+ 咧 2801
2803
+ 篓 2802
2804
+ 蔫 2803
2805
+ 喻 2804
2806
+ 锐 2805
2807
+ 屛 2806
2808
+ 愁 2807
2809
+ 幂 2808
2810
+ 噎 2809
2811
+ 呲 2810
2812
+ 窒 2811
2813
+ 硌 2812
2814
+ 帜 2813
2815
+ 嘶 2814
2816
+ 昏 2815
2817
+ 氏 2816
2818
+ 焙 2817
2819
+ 缴 2818
2820
+ 爵 2819
2821
+ 粹 2820
2822
+ 卢 2821
2823
+ 摒 2822
2824
+ 缕 2823
2825
+ 鸟 2824
2826
+ 驿 2825
2827
+ 枉 2826
2828
+ 泼 2827
2829
+ 梗 2828
2830
+ 屡 2829
2831
+ 锡 2830
2832
+ 哔 2831
2833
+ 诈 2832
2834
+ 惕 2833
2835
+ 傍 2834
2836
+ 琪 2835
2837
+ 昊 2836
2838
+ 臣 2837
2839
+ 涛 2838
2840
+ 燕 2839
2841
+ 湘 2840
2842
+ 婷 2841
2843
+ 匪 2842
2844
+ 驴 2843
2845
+ 刊 2844
2846
+ 伊 2845
2847
+ 吞 2846
2848
+ 兽 2847
2849
+ 猿 2848
2850
+ 玄 2849
2851
+ 攀 2850
2852
+ 丫 2851
2853
+ 谋 2852
2854
+ 禅 2853
2855
+ 纵 2854
2856
+ 魄 2855
2857
+ 濡 2856
2858
+ 吏 2857
2859
+ 跤 2858
2860
+ 萃 2859
2861
+ 骼 2860
2862
+ 胳 2861
2863
+ 膊 2862
2864
+ 坦 2863
2865
+ 曹 2864
2866
+ 芹 2865
2867
+ 噜 2866
2868
+ 碱 2867
2869
+ 痕 2868
2870
+ 嘎 2869
2871
+ 飙 2870
2872
+ 蔗 2871
2873
+ 署 2872
2874
+ 刁 2873
2875
+ 嚼 2874
2876
+ 酥 2875
2877
+ 吻 2876
2878
+ 菱 2877
2879
+ 撂 2878
2880
+ 泻 2879
2881
+ 祛 2880
2882
+ 牦 2881
2883
+ 馍 2882
2884
+ 葬 2883
2885
+ 稞 2884
2886
+ 砥 2885
2887
+ 祥 2886
2888
+ 阁 2887
2889
+ 迦 2888
2890
+ 袭 2889
2891
+ 暇 2890
2892
+ 胯 2891
2893
+ 畜 2892
2894
+ 稻 2893
2895
+ 峨 2894
2896
+ 洪 2895
2897
+ 崖 2896
2898
+ 喀 2897
2899
+ 柳 2898
2900
+ 膻 2899
2901
+ 吾 2900
2902
+ 荒 2901
2903
+ 骆 2902
2904
+ 昼 2903
2905
+ 岸 2904
2906
+ 滓 2905
2907
+ 夙 2906
2908
+ 汶 2907
2909
+ 戈 2908
2910
+ 扈 2909
2911
+ 窑 2910
2912
+ 涌 2911
2913
+ 犬 2912
2914
+ 魂 2913
2915
+ 窜 2914
2916
+ 啧 2915
2917
+ 阉 2916
2918
+ 昵 2917
2919
+ 帖 2918
2920
+ 噔 2919
2921
+ 枢 2920
2922
+ 熄 2921
2923
+ 翘 2922
2924
+ 溪 2923
2925
+ 抨 2924
2926
+ 锂 2925
2927
+ 猛 2926
2928
+ 兆 2927
2929
+ 呷 2928
2930
+ 翁 2929
2931
+ 恼 2930
2932
+ 妮 2931
2933
+ 甫 2932
2934
+ 卒 2933
2935
+ 肾 2934
2936
+ 陷 2935
2937
+ 窃 2936
2938
+ 聋 2937
2939
+ 党 2938
2940
+ 巫 2939
2941
+ 醉 2940
2942
+ 叼 2941
2943
+ 迸 2942
2944
+ 蝙 2943
2945
+ 蝠 2944
2946
+ 萎 2945
2947
+ 瘫 2946
2948
+ 铸 2947
2949
+ 橄 2948
2950
+ 榄 2949
2951
+ 岳 2950
2952
+ 瑜 2951
2953
+ 伽 2952
2954
+ 哒 2953
2955
+ 旳 2954
2956
+ 冗 2955
2957
+ 纰 2956
2958
+ 扼 2957
2959
+ 晖 2958
2960
+ 届 2959
2961
+ 役 2960
2962
+ 磅 2961
2963
+ 抉 2962
2964
+ 茉 2963
2965
+ 湛 2964
2966
+ 泵 2965
2967
+ 棱 2966
2968
+ 霉 2967
2969
+ 尧 2968
2970
+ 姚 2969
2971
+ 诵 2970
2972
+ 渴 2971
2973
+ 臂 2972
2974
+ 哧 2973
2975
+ 唢 2974
2976
+ 腌 2975
2977
+ 竹 2976
2978
+ 蛊 2977
2979
+ 瘆 2978
2980
+ 柄 2979
2981
+ 悲 2980
2982
+ 筝 2981
2983
+ 哀 2982
2984
+ 愧 2983
2985
+ 兮 2984
2986
+ 崛 2985
2987
+ 煌 2986
2988
+ 嗤 2987
2989
+ 靡 2988
2990
+ 陨 2989
2991
+ 硕 2990
2992
+ 敛 2991
2993
+ 傀 2992
2994
+ 儡 2993
2995
+ 辍 2994
2996
+ 茨 2995
2997
+ 歧 2996
2998
+ 揍 2997
2999
+ 垒 2998
3000
+ 扮 2999
3001
+ 诋 3000
3002
+ 魏 3001
3003
+ 蔼 3002
3004
+ 婉 3003
3005
+ 焯 3004
3006
+ 皖 3005
3007
+ 酝 3006
3008
+ 锣 3007
3009
+ 巷 3008
3010
+ 桂 3009
3011
+ 笛 3010
3012
+ 鲑 3011
3013
+ 碟 3012
3014
+ 羞 3013
3015
+ 涩 3014
3016
+ 穆 3015
3017
+ 鞭 3016
3018
+ 妨 3017
3019
+ 巡 3018
3020
+ 栓 3019
3021
+ 纽 3020
3022
+ 吁 3021
3023
+ 肇 3022
3024
+ 苑 3023
3025
+ 脊 3024
3026
+ 哲 3025
3027
+ 拄 3026
3028
+ 铲 3027
3029
+ 匡 3028
3030
+ 丧 3029
3031
+ 懈 3030
3032
+ 怠 3031
3033
+ 稽 3032
3034
+ 吱 3033
3035
+ 螃 3034
3036
+ 鲈 3035
3037
+ 犁 3036
3038
+ 鑫 3037
3039
+ 嫂 3038
3040
+ 鼎 3039
3041
+ 轩 3040
3042
+ 焖 3041
3043
+ 馋 3042
3044
+ 籽 3043
3045
+ 辽 3044
3046
+ 齁 3045
3047
+ 梅 3046
3048
+ 朔 3047
3049
+ 藤 3048
3050
+ 纷 3049
3051
+ 腼 3050
3052
+ 腆 3051
3053
+ 暮 3052
3054
+ 叨 3053
3055
+ 沦 3054
3056
+ 痊 3055
3057
+ 烩 3056
3058
+ 吴 3057
3059
+ 匾 3058
3060
+ 簋 3059
3061
+ 辰 3060
3062
+ 霓 3061
3063
+ 怒 3062
3064
+ 椎 3063
3065
+ 寡 3064
3066
+ 濒 3065
3067
+ 昙 3066
3068
+ 沥 3067
3069
+ 萌 3068
3070
+ 寥 3069
3071
+ 镖 3070
3072
+ 跪 3071
3073
+ 瞄 3072
3074
+ 吝 3073
3075
+ 啬 3074
3076
+ 兢 3075
3077
+ 徐 3076
3078
+ 捻 3077
3079
+ 氟 3078
3080
+ 窖 3079
3081
+ 嘀 3080
3082
+ 轱 3081
3083
+ 辘 3082
3084
+ 坟 3083
3085
+ 窄 3084
3086
+ 愤 3085
3087
+ 嗒 3086
3088
+ 肖 3087
3089
+ 缠 3088
3090
+ 瑶 3089
3091
+ 沓 3090
3092
+ 讳 3091
3093
+ 陵 3092
3094
+ 怵 3093
3095
+ 刑 3094
3096
+ 酣 3095
3097
+ 漓 3096
3098
+ 竭 3097
3099
+ 挽 3098
3100
+ 贤 3099
3101
+ 吟 3100
3102
+ 搅 3101
3103
+ 歘 3102
3104
+ 宋 3103
3105
+ 凶 3104
3106
+ 萍 3105
3107
+ 衙 3106
3108
+ 妍 3107
3109
+ 瘪 3108
3110
+ 冯 3109
3111
+ 撮 3110
3112
+ 吩 3111
3113
+ 诟 3112
3114
+ 蛀 3113
3115
+ 鲅 3114
3116
+ 汪 3115
3117
+ 矫 3116
3118
+ 鳞 3117
3119
+ 崭 3118
3120
+ 粪 3119
3121
+ 屎 3120
3122
+ 棠 3121
3123
+ 拴 3122
3124
+ 庇 3123
3125
+ 茂 3124
3126
+ 辖 3125
3127
+ 篦 3126
3128
+ 鸦 3127
3129
+ 靶 3128
3130
+ 癣 3129
3131
+ 钮 3130
3132
+ 蚕 3131
3133
+ 冶 3132
3134
+ 撵 3133
3135
+ 嗷 3134
3136
+ 枚 3135
3137
+ 牡 3136
3138
+ 楂 3137
3139
+ 焕 3138
3140
+ 栽 3139
3141
+ 絮 3140
3142
+ 砌 3141
3143
+ 淆 3142
3144
+ 惰 3143
3145
+ 顽 3144
3146
+ 诀 3145
3147
+ 亩 3146
3148
+ 搀 3147
3149
+ 狡 3148
3150
+ 芮 3149
3151
+ 甄 3150
3152
+ 荀 3151
3153
+ 塘 3152
3154
+ 薛 3153
3155
+ 堰 3154
3156
+ 睹 3155
3157
+ 塌 3156
3158
+ 邓 3157
3159
+ 渔 3158
3160
+ 蜀 3159
3161
+ 缔 3160
3162
+ 诙 3161
3163
+ 藿 3162
3164
+ 怡 3163
3165
+ 栈 3164
3166
+ 筋 3165
3167
+ 璇 3166
3168
+ 奠 3167
3169
+ 滔 3168
3170
+ 谯 3169
3171
+ 翼 3170
3172
+ 髓 3171
3173
+ 骏 3172
3174
+ 乃 3173
3175
+ 睦 3174
3176
+ 峻 3175
3177
+ 廓 3176
3178
+ 榷 3177
3179
+ 狭 3178
3180
+ 隘 3179
3181
+ 孵 3180
3182
+ 郫 3181
3183
+ 猝 3182
3184
+ 炎 3183
3185
+ 喉 3184
3186
+ 咙 3185
3187
+ 柑 3186
3188
+ 奸 3187
3189
+ 隙 3188
3190
+ 凋 3189
3191
+ 熙 3190
3192
+ 衅 3191
3193
+ 缪 3192
3194
+ 坝 3193
3195
+ 乞 3194
3196
+ 丐 3195
3197
+ 觑 3196
3198
+ 嗬 3197
3199
+ 淌 3198
3200
+ 镂 3199
3201
+ 秉 3200
3202
+ 臆 3201
3203
+ 阐 3202
3204
+ 怯 3203
3205
+ 陋 3204
3206
+ 绰 3205
3207
+ 庞 3206
3208
+ 郑 3207
3209
+ 叹 3208
3210
+ 箍 3209
3211
+ 钞 3210
3212
+ 咽 3211
3213
+ 粽 3212
3214
+ 撘 3213
3215
+ 侯 3214
3216
+ 糯 3215
3217
+ 鹏 3216
3218
+ 蔑 3217
3219
+ 秽 3218
3220
+ 慨 3219
3221
+ 僵 3220
3222
+ 潭 3221
3223
+ 耕 3222
3224
+ 耘 3223
3225
+ 簪 3224
3226
+ 诠 3225
3227
+ 涯 3226
3228
+ 煽 3227
3229
+ 伐 3228
3230
+ 跶 3229
3231
+ 敦 3230
3232
+ 谚 3231
3233
+ 媚 3232
3234
+ 绅 3233
3235
+ 辫 3234
3236
+ 侄 3235
3237
+ 桩 3236
3238
+ 碌 3237
3239
+ 御 3238
3240
+ 嵋 3239
3241
+ 彗 3240
3242
+ 憩 3241
3243
+ 嘻 3242
3244
+ 惹 3243
3245
+ 腺 3244
3246
+ 阄 3245
3247
+ 屑 3246
3248
+ 禽 3247
3249
+ 彷 3248
3250
+ 徨 3249
3251
+ 揭 3250
3252
+ 飒 3251
3253
+ 殷 3252
3254
+ 佐 3253
3255
+ 俘 3254
3256
+ 菊 3255
3257
+ 钙 3256
3258
+ 饲 3257
3259
+ 嘈 3258
3260
+ 瞟 3259
3261
+ 抚 3260
3262
+ 惭 3261
3263
+ 珑 3262
3264
+ 瑗 3263
3265
+ 诶 3264
3266
+ 惶 3265
3267
+ 崴 3266
3268
+ 绽 3267
3269
+ 貂 3268
3270
+ 蜕 3269
3271
+ 卉 3270
3272
+ 诅 3271
3273
+ 咒 3272
3274
+ 稚 3273
3275
+ 宙 3274
3276
+ 舌 3275
3277
+ 炙 3276
3278
+ 衢 3277
3279
+ 炽 3278
3280
+ 唇 3279
3281
+ 釉 3280
3282
+ 拭 3281
3283
+ 乙 3282
3284
+ 丙 3283
3285
+ 龈 3284
3286
+ 阂 3285
3287
+ 赣 3286
3288
+ 仆 3287
3289
+ 嘣 3288
3290
+ 叙 3289
3291
+ #0 3290
3292
+ #1 3291
data/lang_char/words.txt ADDED
The diff for this file is too large to render. See raw diff
 
exp/cpu_jit.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db76391235619898952dd3511cecbdb5af5fd29498b889f1dbfc597eaebbe975
3
+ size 303201598
exp/pretrained.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd7e84c584d517e5557f9d485499e2136bf0ba07dc81c843299a362f1862585
3
+ size 303226861
exp/tensorboard/events.out.tfevents.1670405777.r8n04.289848.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d22b3a4e2dfb6019da6a21adb69feee9f020b434370defbed3c6ed4c7368de
3
+ size 738694
log/fast_beam_search/errs-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/errs-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/errs-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/errs-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/errs-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/errs-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/log-decode-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8-2022-12-09-00-04-39 ADDED
@@ -0,0 +1,350 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-12-09 00:04:39,800 INFO [decode.py:551] Decoding started
2
+ 2022-12-09 00:04:39,801 INFO [decode.py:557] Device: cuda:0
3
+ 2022-12-09 00:04:39,862 INFO [lexicon.py:168] Loading pre-compiled data/lang_char/Linv.pt
4
+ 2022-12-09 00:04:39,872 INFO [decode.py:563] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 100, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'b2ce63f3940018e7b433c43fd802fc50ab006a76', 'k2-git-date': 'Wed Nov 23 08:43:43 2022', 'lhotse-version': '1.9.0.dev+git.97bf4b0.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'ali_meeting', 'icefall-git-sha1': 'f13cf61-dirty', 'icefall-git-date': 'Tue Dec 6 03:34:27 2022', 'icefall-path': '/exp/draj/mini_scale_2022/icefall', 'k2-path': '/exp/draj/mini_scale_2022/k2/k2/python/k2/__init__.py', 'lhotse-path': '/exp/draj/mini_scale_2022/lhotse/lhotse/__init__.py', 'hostname': 'r7n08', 'IP address': '10.1.7.8'}, 'epoch': 15, 'iter': 0, 'avg': 8, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7/exp/v1'), 'lang_dir': 'data/lang_char', 'decoding_method': 'fast_beam_search', 'beam_size': 4, 'beam': 4, 'ngram_lm_scale': 0.01, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,4,3,2,4', 'feedforward_dims': '1024,1024,2048,2048,1024', 'nhead': '8,8,8,8,8', 'encoder_dims': '384,384,384,384,384', 'attention_dims': '192,192,192,192,192', 'encoder_unmasked_dims': '256,256,256,256,256', 'zipformer_downsampling_factors': '1,2,4,8,2', 'cnn_module_kernels': '31,31,31,31,31', 'decoder_dim': 512, 'joiner_dim': 512, 'manifest_dir': PosixPath('data/manifests'), 'enable_musan': True, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'max_duration': 500, 'max_cuts': None, 'num_buckets': 50, 'on_the_fly_feats': False, 'shuffle': True, 'num_workers': 8, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'res_dir': PosixPath('pruned_transducer_stateless7/exp/v1/fast_beam_search'), 'suffix': 'epoch-15-avg-8-beam-4-max-contexts-4-max-states-8', 'blank_id': 0, 'vocab_size': 3290}
5
+ 2022-12-09 00:04:39,872 INFO [decode.py:565] About to create model
6
+ 2022-12-09 00:04:40,318 INFO [zipformer.py:179] At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
7
+ 2022-12-09 00:04:40,367 INFO [decode.py:632] Calculating the averaged model over epoch range from 7 (excluded) to 15
8
+ 2022-12-09 00:04:56,153 INFO [decode.py:655] Number of model parameters: 75734561
9
+ 2022-12-09 00:04:56,153 INFO [asr_datamodule.py:381] About to get AliMeeting IHM eval cuts
10
+ 2022-12-09 00:04:56,156 INFO [asr_datamodule.py:402] About to get AliMeeting IHM test cuts
11
+ 2022-12-09 00:04:56,158 INFO [asr_datamodule.py:387] About to get AliMeeting SDM eval cuts
12
+ 2022-12-09 00:04:56,159 INFO [asr_datamodule.py:408] About to get AliMeeting SDM test cuts
13
+ 2022-12-09 00:04:56,161 INFO [asr_datamodule.py:396] About to get AliMeeting GSS-enhanced eval cuts
14
+ 2022-12-09 00:04:56,163 INFO [asr_datamodule.py:417] About to get AliMeeting GSS-enhanced test cuts
15
+ 2022-12-09 00:04:57,914 INFO [decode.py:687] Decoding eval_ihm
16
+ 2022-12-09 00:05:00,542 INFO [decode.py:463] batch 0/?, cuts processed until now is 58
17
+ 2022-12-09 00:05:02,549 INFO [zipformer.py:1414] attn_weights_entropy = tensor([3.0737, 1.5896, 3.0429, 1.9527, 3.1868, 3.0717, 2.1364, 3.2050],
18
+ device='cuda:0'), covar=tensor([0.0130, 0.1163, 0.0235, 0.0949, 0.0167, 0.0218, 0.0828, 0.0144],
19
+ device='cuda:0'), in_proj_covar=tensor([0.0160, 0.0151, 0.0146, 0.0161, 0.0155, 0.0161, 0.0120, 0.0130],
20
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0003, 0.0004, 0.0004, 0.0004, 0.0003, 0.0003],
21
+ device='cuda:0')
22
+ 2022-12-09 00:05:03,160 INFO [decode.py:463] batch 2/?, cuts processed until now is 512
23
+ 2022-12-09 00:05:05,612 INFO [decode.py:463] batch 4/?, cuts processed until now is 645
24
+ 2022-12-09 00:05:08,007 INFO [decode.py:463] batch 6/?, cuts processed until now is 750
25
+ 2022-12-09 00:05:10,443 INFO [decode.py:463] batch 8/?, cuts processed until now is 883
26
+ 2022-12-09 00:05:13,132 INFO [decode.py:463] batch 10/?, cuts processed until now is 1082
27
+ 2022-12-09 00:05:15,399 INFO [decode.py:463] batch 12/?, cuts processed until now is 1279
28
+ 2022-12-09 00:05:17,544 INFO [decode.py:463] batch 14/?, cuts processed until now is 1538
29
+ 2022-12-09 00:05:19,807 INFO [decode.py:463] batch 16/?, cuts processed until now is 1845
30
+ 2022-12-09 00:05:22,396 INFO [decode.py:463] batch 18/?, cuts processed until now is 2084
31
+ 2022-12-09 00:05:24,347 INFO [decode.py:463] batch 20/?, cuts processed until now is 2523
32
+ 2022-12-09 00:05:26,412 INFO [decode.py:463] batch 22/?, cuts processed until now is 2949
33
+ 2022-12-09 00:05:28,474 INFO [decode.py:463] batch 24/?, cuts processed until now is 3160
34
+ 2022-12-09 00:05:30,832 INFO [decode.py:463] batch 26/?, cuts processed until now is 3586
35
+ 2022-12-09 00:05:32,989 INFO [decode.py:463] batch 28/?, cuts processed until now is 3758
36
+ 2022-12-09 00:05:34,898 INFO [decode.py:463] batch 30/?, cuts processed until now is 4116
37
+ 2022-12-09 00:05:36,464 INFO [decode.py:463] batch 32/?, cuts processed until now is 4742
38
+ 2022-12-09 00:05:38,170 INFO [decode.py:463] batch 34/?, cuts processed until now is 5368
39
+ 2022-12-09 00:05:40,030 INFO [decode.py:463] batch 36/?, cuts processed until now is 5796
40
+ 2022-12-09 00:05:40,607 INFO [decode.py:463] batch 38/?, cuts processed until now is 5908
41
+ 2022-12-09 00:05:43,001 INFO [decode.py:463] batch 40/?, cuts processed until now is 6026
42
+ 2022-12-09 00:05:44,872 INFO [decode.py:463] batch 42/?, cuts processed until now is 6171
43
+ 2022-12-09 00:05:47,165 INFO [decode.py:463] batch 44/?, cuts processed until now is 6390
44
+ 2022-12-09 00:05:48,661 INFO [decode.py:463] batch 46/?, cuts processed until now is 6456
45
+ 2022-12-09 00:05:49,043 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/fast_beam_search/recogs-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
46
+ 2022-12-09 00:05:49,145 INFO [utils.py:536] [eval_ihm-beam_4_max_contexts_4_max_states_8] %WER 9.92% [8049 / 81111, 835 ins, 2146 del, 5068 sub ]
47
+ 2022-12-09 00:05:49,383 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/fast_beam_search/errs-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
48
+ 2022-12-09 00:05:49,386 INFO [decode.py:508]
49
+ For eval_ihm, WER of different settings are:
50
+ beam_4_max_contexts_4_max_states_8 9.92 best for eval_ihm
51
+
52
+ 2022-12-09 00:05:49,386 INFO [decode.py:687] Decoding test_ihm
53
+ 2022-12-09 00:05:52,047 INFO [decode.py:463] batch 0/?, cuts processed until now is 49
54
+ 2022-12-09 00:05:54,386 INFO [decode.py:463] batch 2/?, cuts processed until now is 433
55
+ 2022-12-09 00:05:57,029 INFO [decode.py:463] batch 4/?, cuts processed until now is 545
56
+ 2022-12-09 00:05:59,525 INFO [decode.py:463] batch 6/?, cuts processed until now is 637
57
+ 2022-12-09 00:06:02,173 INFO [decode.py:463] batch 8/?, cuts processed until now is 754
58
+ 2022-12-09 00:06:04,845 INFO [decode.py:463] batch 10/?, cuts processed until now is 845
59
+ 2022-12-09 00:06:07,294 INFO [decode.py:463] batch 12/?, cuts processed until now is 976
60
+ 2022-12-09 00:06:09,802 INFO [decode.py:463] batch 14/?, cuts processed until now is 1175
61
+ 2022-12-09 00:06:11,772 INFO [decode.py:463] batch 16/?, cuts processed until now is 1483
62
+ 2022-12-09 00:06:14,661 INFO [decode.py:463] batch 18/?, cuts processed until now is 1590
63
+ 2022-12-09 00:06:17,229 INFO [decode.py:463] batch 20/?, cuts processed until now is 1658
64
+ 2022-12-09 00:06:19,732 INFO [decode.py:463] batch 22/?, cuts processed until now is 1856
65
+ 2022-12-09 00:06:21,553 INFO [decode.py:463] batch 24/?, cuts processed until now is 2224
66
+ 2022-12-09 00:06:24,742 INFO [decode.py:463] batch 26/?, cuts processed until now is 2325
67
+ 2022-12-09 00:06:26,248 INFO [zipformer.py:1414] attn_weights_entropy = tensor([1.7884, 1.7374, 1.7931, 1.6476, 1.5451, 1.3756, 1.2392, 0.9835],
68
+ device='cuda:0'), covar=tensor([0.0257, 0.0477, 0.0302, 0.0285, 0.0391, 0.0372, 0.0391, 0.0706],
69
+ device='cuda:0'), in_proj_covar=tensor([0.0013, 0.0014, 0.0012, 0.0013, 0.0013, 0.0022, 0.0018, 0.0023],
70
+ device='cuda:0'), out_proj_covar=tensor([1.0210e-04, 1.1124e-04, 9.6061e-05, 1.0387e-04, 1.0128e-04, 1.6022e-04,
71
+ 1.3170e-04, 1.5378e-04], device='cuda:0')
72
+ 2022-12-09 00:06:26,881 INFO [decode.py:463] batch 28/?, cuts processed until now is 2546
73
+ 2022-12-09 00:06:29,637 INFO [decode.py:463] batch 30/?, cuts processed until now is 2653
74
+ 2022-12-09 00:06:32,547 INFO [decode.py:463] batch 32/?, cuts processed until now is 2744
75
+ 2022-12-09 00:06:35,176 INFO [decode.py:463] batch 34/?, cuts processed until now is 2875
76
+ 2022-12-09 00:06:37,477 INFO [decode.py:463] batch 36/?, cuts processed until now is 2961
77
+ 2022-12-09 00:06:40,111 INFO [decode.py:463] batch 38/?, cuts processed until now is 3072
78
+ 2022-12-09 00:06:42,224 INFO [decode.py:463] batch 40/?, cuts processed until now is 3440
79
+ 2022-12-09 00:06:44,157 INFO [decode.py:463] batch 42/?, cuts processed until now is 3956
80
+ 2022-12-09 00:06:46,278 INFO [decode.py:463] batch 44/?, cuts processed until now is 4342
81
+ 2022-12-09 00:06:49,059 INFO [decode.py:463] batch 46/?, cuts processed until now is 4443
82
+ 2022-12-09 00:06:51,695 INFO [decode.py:463] batch 48/?, cuts processed until now is 4595
83
+ 2022-12-09 00:06:54,151 INFO [decode.py:463] batch 50/?, cuts processed until now is 4872
84
+ 2022-12-09 00:06:56,640 INFO [decode.py:463] batch 52/?, cuts processed until now is 5061
85
+ 2022-12-09 00:06:59,037 INFO [decode.py:463] batch 54/?, cuts processed until now is 5219
86
+ 2022-12-09 00:06:59,308 INFO [zipformer.py:1414] attn_weights_entropy = tensor([3.0441, 2.9961, 2.5706, 3.2930, 3.2433, 3.2067, 2.9979, 2.6837],
87
+ device='cuda:0'), covar=tensor([0.0658, 0.0330, 0.1699, 0.0248, 0.0410, 0.0486, 0.0532, 0.0554],
88
+ device='cuda:0'), in_proj_covar=tensor([0.0237, 0.0272, 0.0252, 0.0220, 0.0279, 0.0268, 0.0232, 0.0237],
89
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0004, 0.0003, 0.0004, 0.0003, 0.0003, 0.0003],
90
+ device='cuda:0')
91
+ 2022-12-09 00:07:00,786 INFO [decode.py:463] batch 56/?, cuts processed until now is 5892
92
+ 2022-12-09 00:07:03,557 INFO [decode.py:463] batch 58/?, cuts processed until now is 6090
93
+ 2022-12-09 00:07:05,565 INFO [decode.py:463] batch 60/?, cuts processed until now is 6517
94
+ 2022-12-09 00:07:08,044 INFO [decode.py:463] batch 62/?, cuts processed until now is 6715
95
+ 2022-12-09 00:07:10,550 INFO [decode.py:463] batch 64/?, cuts processed until now is 6897
96
+ 2022-12-09 00:07:12,918 INFO [decode.py:463] batch 66/?, cuts processed until now is 7304
97
+ 2022-12-09 00:07:15,211 INFO [decode.py:463] batch 68/?, cuts processed until now is 7488
98
+ 2022-12-09 00:07:17,291 INFO [decode.py:463] batch 70/?, cuts processed until now is 7720
99
+ 2022-12-09 00:07:19,822 INFO [decode.py:463] batch 72/?, cuts processed until now is 7938
100
+ 2022-12-09 00:07:22,356 INFO [decode.py:463] batch 74/?, cuts processed until now is 8367
101
+ 2022-12-09 00:07:24,483 INFO [decode.py:463] batch 76/?, cuts processed until now is 8674
102
+ 2022-12-09 00:07:26,624 INFO [decode.py:463] batch 78/?, cuts processed until now is 8982
103
+ 2022-12-09 00:07:28,566 INFO [decode.py:463] batch 80/?, cuts processed until now is 9350
104
+ 2022-12-09 00:07:31,094 INFO [decode.py:463] batch 82/?, cuts processed until now is 9810
105
+ 2022-12-09 00:07:33,293 INFO [decode.py:463] batch 84/?, cuts processed until now is 10237
106
+ 2022-12-09 00:07:35,118 INFO [decode.py:463] batch 86/?, cuts processed until now is 10755
107
+ 2022-12-09 00:07:36,950 INFO [decode.py:463] batch 88/?, cuts processed until now is 11278
108
+ 2022-12-09 00:07:39,502 INFO [decode.py:463] batch 90/?, cuts processed until now is 11705
109
+ 2022-12-09 00:07:41,666 INFO [decode.py:463] batch 92/?, cuts processed until now is 12013
110
+ 2022-12-09 00:07:43,998 INFO [decode.py:463] batch 94/?, cuts processed until now is 12290
111
+ 2022-12-09 00:07:46,153 INFO [decode.py:463] batch 96/?, cuts processed until now is 12597
112
+ 2022-12-09 00:07:48,323 INFO [decode.py:463] batch 98/?, cuts processed until now is 12963
113
+ 2022-12-09 00:07:50,305 INFO [decode.py:463] batch 100/?, cuts processed until now is 13420
114
+ 2022-12-09 00:07:52,320 INFO [decode.py:463] batch 102/?, cuts processed until now is 13877
115
+ 2022-12-09 00:07:53,978 INFO [decode.py:463] batch 104/?, cuts processed until now is 14543
116
+ 2022-12-09 00:07:55,982 INFO [decode.py:463] batch 106/?, cuts processed until now is 15209
117
+ 2022-12-09 00:07:57,729 INFO [decode.py:463] batch 108/?, cuts processed until now is 15599
118
+ 2022-12-09 00:07:59,309 INFO [decode.py:463] batch 110/?, cuts processed until now is 15787
119
+ 2022-12-09 00:08:00,476 INFO [decode.py:463] batch 112/?, cuts processed until now is 15881
120
+ 2022-12-09 00:08:02,663 INFO [decode.py:463] batch 114/?, cuts processed until now is 15926
121
+ 2022-12-09 00:08:03,600 INFO [decode.py:463] batch 116/?, cuts processed until now is 16287
122
+ 2022-12-09 00:08:05,650 INFO [decode.py:463] batch 118/?, cuts processed until now is 16357
123
+ 2022-12-09 00:08:05,950 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/fast_beam_search/recogs-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
124
+ 2022-12-09 00:08:06,244 INFO [utils.py:536] [test_ihm-beam_4_max_contexts_4_max_states_8] %WER 12.07% [25334 / 209845, 2035 ins, 7940 del, 15359 sub ]
125
+ 2022-12-09 00:08:06,874 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/fast_beam_search/errs-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
126
+ 2022-12-09 00:08:06,875 INFO [decode.py:508]
127
+ For test_ihm, WER of different settings are:
128
+ beam_4_max_contexts_4_max_states_8 12.07 best for test_ihm
129
+
130
+ 2022-12-09 00:08:06,876 INFO [decode.py:687] Decoding eval_sdm
131
+ 2022-12-09 00:08:09,951 INFO [decode.py:463] batch 0/?, cuts processed until now is 58
132
+ 2022-12-09 00:08:12,839 INFO [decode.py:463] batch 2/?, cuts processed until now is 512
133
+ 2022-12-09 00:08:15,558 INFO [decode.py:463] batch 4/?, cuts processed until now is 645
134
+ 2022-12-09 00:08:19,252 INFO [decode.py:463] batch 6/?, cuts processed until now is 750
135
+ 2022-12-09 00:08:21,932 INFO [decode.py:463] batch 8/?, cuts processed until now is 883
136
+ 2022-12-09 00:08:24,663 INFO [decode.py:463] batch 10/?, cuts processed until now is 1082
137
+ 2022-12-09 00:08:26,962 INFO [decode.py:463] batch 12/?, cuts processed until now is 1279
138
+ 2022-12-09 00:08:29,136 INFO [decode.py:463] batch 14/?, cuts processed until now is 1538
139
+ 2022-12-09 00:08:31,430 INFO [decode.py:463] batch 16/?, cuts processed until now is 1845
140
+ 2022-12-09 00:08:34,125 INFO [decode.py:463] batch 18/?, cuts processed until now is 2084
141
+ 2022-12-09 00:08:36,099 INFO [decode.py:463] batch 20/?, cuts processed until now is 2523
142
+ 2022-12-09 00:08:38,223 INFO [decode.py:463] batch 22/?, cuts processed until now is 2949
143
+ 2022-12-09 00:08:40,617 INFO [decode.py:463] batch 24/?, cuts processed until now is 3160
144
+ 2022-12-09 00:08:42,897 INFO [decode.py:463] batch 26/?, cuts processed until now is 3586
145
+ 2022-12-09 00:08:45,251 INFO [decode.py:463] batch 28/?, cuts processed until now is 3758
146
+ 2022-12-09 00:08:47,170 INFO [decode.py:463] batch 30/?, cuts processed until now is 4116
147
+ 2022-12-09 00:08:48,754 INFO [decode.py:463] batch 32/?, cuts processed until now is 4742
148
+ 2022-12-09 00:08:50,490 INFO [decode.py:463] batch 34/?, cuts processed until now is 5368
149
+ 2022-12-09 00:08:52,388 INFO [decode.py:463] batch 36/?, cuts processed until now is 5796
150
+ 2022-12-09 00:08:52,966 INFO [decode.py:463] batch 38/?, cuts processed until now is 5908
151
+ 2022-12-09 00:08:55,520 INFO [decode.py:463] batch 40/?, cuts processed until now is 6026
152
+ 2022-12-09 00:08:57,418 INFO [decode.py:463] batch 42/?, cuts processed until now is 6171
153
+ 2022-12-09 00:08:59,744 INFO [decode.py:463] batch 44/?, cuts processed until now is 6390
154
+ 2022-12-09 00:09:01,542 INFO [decode.py:463] batch 46/?, cuts processed until now is 6456
155
+ 2022-12-09 00:09:01,956 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/fast_beam_search/recogs-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
156
+ 2022-12-09 00:09:02,058 INFO [utils.py:536] [eval_sdm-beam_4_max_contexts_4_max_states_8] %WER 23.60% [19139 / 81111, 1582 ins, 6591 del, 10966 sub ]
157
+ 2022-12-09 00:09:02,314 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/fast_beam_search/errs-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
158
+ 2022-12-09 00:09:02,315 INFO [decode.py:508]
159
+ For eval_sdm, WER of different settings are:
160
+ beam_4_max_contexts_4_max_states_8 23.6 best for eval_sdm
161
+
162
+ 2022-12-09 00:09:02,315 INFO [decode.py:687] Decoding test_sdm
163
+ 2022-12-09 00:09:05,263 INFO [decode.py:463] batch 0/?, cuts processed until now is 49
164
+ 2022-12-09 00:09:08,151 INFO [decode.py:463] batch 2/?, cuts processed until now is 433
165
+ 2022-12-09 00:09:11,022 INFO [decode.py:463] batch 4/?, cuts processed until now is 545
166
+ 2022-12-09 00:09:14,432 INFO [decode.py:463] batch 6/?, cuts processed until now is 637
167
+ 2022-12-09 00:09:18,065 INFO [decode.py:463] batch 8/?, cuts processed until now is 754
168
+ 2022-12-09 00:09:21,737 INFO [decode.py:463] batch 10/?, cuts processed until now is 845
169
+ 2022-12-09 00:09:24,463 INFO [decode.py:463] batch 12/?, cuts processed until now is 976
170
+ 2022-12-09 00:09:27,235 INFO [decode.py:463] batch 14/?, cuts processed until now is 1175
171
+ 2022-12-09 00:09:29,431 INFO [decode.py:463] batch 16/?, cuts processed until now is 1483
172
+ 2022-12-09 00:09:32,640 INFO [decode.py:463] batch 18/?, cuts processed until now is 1590
173
+ 2022-12-09 00:09:35,555 INFO [decode.py:463] batch 20/?, cuts processed until now is 1658
174
+ 2022-12-09 00:09:38,331 INFO [decode.py:463] batch 22/?, cuts processed until now is 1856
175
+ 2022-12-09 00:09:40,406 INFO [decode.py:463] batch 24/?, cuts processed until now is 2224
176
+ 2022-12-09 00:09:44,139 INFO [decode.py:463] batch 26/?, cuts processed until now is 2325
177
+ 2022-12-09 00:09:46,730 INFO [decode.py:463] batch 28/?, cuts processed until now is 2546
178
+ 2022-12-09 00:09:50,522 INFO [decode.py:463] batch 30/?, cuts processed until now is 2653
179
+ 2022-12-09 00:09:53,962 INFO [decode.py:463] batch 32/?, cuts processed until now is 2744
180
+ 2022-12-09 00:09:54,241 INFO [zipformer.py:1414] attn_weights_entropy = tensor([2.7396, 3.1001, 3.0621, 3.0092, 2.4846, 3.1160, 2.9203, 1.5742],
181
+ device='cuda:0'), covar=tensor([0.3222, 0.1240, 0.1216, 0.1279, 0.1173, 0.0968, 0.1290, 0.3379],
182
+ device='cuda:0'), in_proj_covar=tensor([0.0138, 0.0066, 0.0052, 0.0054, 0.0082, 0.0064, 0.0085, 0.0091],
183
+ device='cuda:0'), out_proj_covar=tensor([0.0007, 0.0004, 0.0004, 0.0004, 0.0005, 0.0004, 0.0005, 0.0005],
184
+ device='cuda:0')
185
+ 2022-12-09 00:09:56,816 INFO [decode.py:463] batch 34/?, cuts processed until now is 2875
186
+ 2022-12-09 00:10:00,313 INFO [decode.py:463] batch 36/?, cuts processed until now is 2961
187
+ 2022-12-09 00:10:03,278 INFO [decode.py:463] batch 38/?, cuts processed until now is 3072
188
+ 2022-12-09 00:10:05,621 INFO [decode.py:463] batch 40/?, cuts processed until now is 3440
189
+ 2022-12-09 00:10:07,739 INFO [decode.py:463] batch 42/?, cuts processed until now is 3956
190
+ 2022-12-09 00:10:10,439 INFO [decode.py:463] batch 44/?, cuts processed until now is 4342
191
+ 2022-12-09 00:10:13,586 INFO [decode.py:463] batch 46/?, cuts processed until now is 4443
192
+ 2022-12-09 00:10:16,678 INFO [decode.py:463] batch 48/?, cuts processed until now is 4595
193
+ 2022-12-09 00:10:18,979 INFO [decode.py:463] batch 50/?, cuts processed until now is 4872
194
+ 2022-12-09 00:10:21,564 INFO [decode.py:463] batch 52/?, cuts processed until now is 5061
195
+ 2022-12-09 00:10:24,051 INFO [decode.py:463] batch 54/?, cuts processed until now is 5219
196
+ 2022-12-09 00:10:25,799 INFO [decode.py:463] batch 56/?, cuts processed until now is 5892
197
+ 2022-12-09 00:10:28,484 INFO [decode.py:463] batch 58/?, cuts processed until now is 6090
198
+ 2022-12-09 00:10:30,576 INFO [decode.py:463] batch 60/?, cuts processed until now is 6517
199
+ 2022-12-09 00:10:33,227 INFO [decode.py:463] batch 62/?, cuts processed until now is 6715
200
+ 2022-12-09 00:10:36,188 INFO [decode.py:463] batch 64/?, cuts processed until now is 6897
201
+ 2022-12-09 00:10:38,500 INFO [decode.py:463] batch 66/?, cuts processed until now is 7304
202
+ 2022-12-09 00:10:40,913 INFO [decode.py:463] batch 68/?, cuts processed until now is 7488
203
+ 2022-12-09 00:10:43,631 INFO [decode.py:463] batch 70/?, cuts processed until now is 7720
204
+ 2022-12-09 00:10:46,216 INFO [decode.py:463] batch 72/?, cuts processed until now is 7938
205
+ 2022-12-09 00:10:48,352 INFO [decode.py:463] batch 74/?, cuts processed until now is 8367
206
+ 2022-12-09 00:10:50,400 INFO [decode.py:463] batch 76/?, cuts processed until now is 8674
207
+ 2022-12-09 00:10:52,491 INFO [decode.py:463] batch 78/?, cuts processed until now is 8982
208
+ 2022-12-09 00:10:54,521 INFO [decode.py:463] batch 80/?, cuts processed until now is 9350
209
+ 2022-12-09 00:10:56,482 INFO [decode.py:463] batch 82/?, cuts processed until now is 9810
210
+ 2022-12-09 00:10:58,784 INFO [decode.py:463] batch 84/?, cuts processed until now is 10237
211
+ 2022-12-09 00:11:00,569 INFO [decode.py:463] batch 86/?, cuts processed until now is 10755
212
+ 2022-12-09 00:11:02,454 INFO [decode.py:463] batch 88/?, cuts processed until now is 11278
213
+ 2022-12-09 00:11:04,558 INFO [decode.py:463] batch 90/?, cuts processed until now is 11705
214
+ 2022-12-09 00:11:06,662 INFO [decode.py:463] batch 92/?, cuts processed until now is 12013
215
+ 2022-12-09 00:11:08,880 INFO [decode.py:463] batch 94/?, cuts processed until now is 12290
216
+ 2022-12-09 00:11:11,115 INFO [decode.py:463] batch 96/?, cuts processed until now is 12597
217
+ 2022-12-09 00:11:13,001 INFO [decode.py:463] batch 98/?, cuts processed until now is 12963
218
+ 2022-12-09 00:11:14,951 INFO [decode.py:463] batch 100/?, cuts processed until now is 13420
219
+ 2022-12-09 00:11:16,891 INFO [decode.py:463] batch 102/?, cuts processed until now is 13877
220
+ 2022-12-09 00:11:18,751 INFO [decode.py:463] batch 104/?, cuts processed until now is 14543
221
+ 2022-12-09 00:11:20,406 INFO [decode.py:463] batch 106/?, cuts processed until now is 15209
222
+ 2022-12-09 00:11:22,213 INFO [decode.py:463] batch 108/?, cuts processed until now is 15599
223
+ 2022-12-09 00:11:23,831 INFO [decode.py:463] batch 110/?, cuts processed until now is 15787
224
+ 2022-12-09 00:11:24,660 INFO [zipformer.py:1414] attn_weights_entropy = tensor([4.0644, 3.4893, 2.6910, 4.0270, 4.0221, 3.9192, 3.2926, 2.7434],
225
+ device='cuda:0'), covar=tensor([0.0469, 0.1215, 0.3648, 0.0498, 0.0629, 0.1124, 0.1476, 0.4299],
226
+ device='cuda:0'), in_proj_covar=tensor([0.0237, 0.0272, 0.0252, 0.0220, 0.0279, 0.0268, 0.0232, 0.0237],
227
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0004, 0.0003, 0.0004, 0.0003, 0.0003, 0.0003],
228
+ device='cuda:0')
229
+ 2022-12-09 00:11:24,993 INFO [decode.py:463] batch 112/?, cuts processed until now is 15881
230
+ 2022-12-09 00:11:27,253 INFO [decode.py:463] batch 114/?, cuts processed until now is 15926
231
+ 2022-12-09 00:11:28,278 INFO [decode.py:463] batch 116/?, cuts processed until now is 16287
232
+ 2022-12-09 00:11:30,637 INFO [decode.py:463] batch 118/?, cuts processed until now is 16357
233
+ 2022-12-09 00:11:30,938 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/fast_beam_search/recogs-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
234
+ 2022-12-09 00:11:31,232 INFO [utils.py:536] [test_sdm-beam_4_max_contexts_4_max_states_8] %WER 26.38% [55365 / 209845, 4187 ins, 20994 del, 30184 sub ]
235
+ 2022-12-09 00:11:31,895 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/fast_beam_search/errs-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
236
+ 2022-12-09 00:11:31,896 INFO [decode.py:508]
237
+ For test_sdm, WER of different settings are:
238
+ beam_4_max_contexts_4_max_states_8 26.38 best for test_sdm
239
+
240
+ 2022-12-09 00:11:31,896 INFO [decode.py:687] Decoding eval_gss
241
+ 2022-12-09 00:11:34,643 INFO [decode.py:463] batch 0/?, cuts processed until now is 58
242
+ 2022-12-09 00:11:37,265 INFO [decode.py:463] batch 2/?, cuts processed until now is 512
243
+ 2022-12-09 00:11:39,788 INFO [decode.py:463] batch 4/?, cuts processed until now is 645
244
+ 2022-12-09 00:11:42,519 INFO [decode.py:463] batch 6/?, cuts processed until now is 750
245
+ 2022-12-09 00:11:45,087 INFO [decode.py:463] batch 8/?, cuts processed until now is 883
246
+ 2022-12-09 00:11:45,431 INFO [zipformer.py:1414] attn_weights_entropy = tensor([4.4707, 2.5249, 4.5708, 2.7089, 4.2849, 2.1961, 3.3505, 4.2979],
247
+ device='cuda:0'), covar=tensor([0.0574, 0.4876, 0.0310, 1.1301, 0.0766, 0.4357, 0.1456, 0.0313],
248
+ device='cuda:0'), in_proj_covar=tensor([0.0221, 0.0205, 0.0174, 0.0283, 0.0196, 0.0207, 0.0197, 0.0178],
249
+ device='cuda:0'), out_proj_covar=tensor([0.0004, 0.0004, 0.0003, 0.0005, 0.0004, 0.0004, 0.0004, 0.0004],
250
+ device='cuda:0')
251
+ 2022-12-09 00:11:48,123 INFO [decode.py:463] batch 10/?, cuts processed until now is 1082
252
+ 2022-12-09 00:11:48,459 INFO [zipformer.py:1414] attn_weights_entropy = tensor([5.2040, 2.9190, 5.3102, 3.1520, 4.9151, 2.4271, 3.8951, 4.8336],
253
+ device='cuda:0'), covar=tensor([0.0427, 0.4875, 0.0264, 1.0490, 0.0479, 0.4513, 0.1411, 0.0262],
254
+ device='cuda:0'), in_proj_covar=tensor([0.0221, 0.0205, 0.0174, 0.0283, 0.0196, 0.0207, 0.0197, 0.0178],
255
+ device='cuda:0'), out_proj_covar=tensor([0.0004, 0.0004, 0.0003, 0.0005, 0.0004, 0.0004, 0.0004, 0.0004],
256
+ device='cuda:0')
257
+ 2022-12-09 00:11:50,504 INFO [decode.py:463] batch 12/?, cuts processed until now is 1279
258
+ 2022-12-09 00:11:52,727 INFO [decode.py:463] batch 14/?, cuts processed until now is 1538
259
+ 2022-12-09 00:11:55,047 INFO [decode.py:463] batch 16/?, cuts processed until now is 1845
260
+ 2022-12-09 00:11:57,873 INFO [decode.py:463] batch 18/?, cuts processed until now is 2084
261
+ 2022-12-09 00:11:59,885 INFO [decode.py:463] batch 20/?, cuts processed until now is 2523
262
+ 2022-12-09 00:12:02,047 INFO [decode.py:463] batch 22/?, cuts processed until now is 2949
263
+ 2022-12-09 00:12:04,385 INFO [decode.py:463] batch 24/?, cuts processed until now is 3160
264
+ 2022-12-09 00:12:06,707 INFO [decode.py:463] batch 26/?, cuts processed until now is 3586
265
+ 2022-12-09 00:12:09,309 INFO [decode.py:463] batch 28/?, cuts processed until now is 3758
266
+ 2022-12-09 00:12:11,407 INFO [decode.py:463] batch 30/?, cuts processed until now is 4116
267
+ 2022-12-09 00:12:13,136 INFO [decode.py:463] batch 32/?, cuts processed until now is 4742
268
+ 2022-12-09 00:12:14,909 INFO [decode.py:463] batch 34/?, cuts processed until now is 5368
269
+ 2022-12-09 00:12:16,897 INFO [decode.py:463] batch 36/?, cuts processed until now is 5796
270
+ 2022-12-09 00:12:17,494 INFO [decode.py:463] batch 38/?, cuts processed until now is 5908
271
+ 2022-12-09 00:12:20,025 INFO [decode.py:463] batch 40/?, cuts processed until now is 6026
272
+ 2022-12-09 00:12:21,986 INFO [decode.py:463] batch 42/?, cuts processed until now is 6171
273
+ 2022-12-09 00:12:24,359 INFO [decode.py:463] batch 44/?, cuts processed until now is 6390
274
+ 2022-12-09 00:12:25,982 INFO [decode.py:463] batch 46/?, cuts processed until now is 6456
275
+ 2022-12-09 00:12:26,413 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/fast_beam_search/recogs-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
276
+ 2022-12-09 00:12:26,516 INFO [utils.py:536] [eval_gss-beam_4_max_contexts_4_max_states_8] %WER 12.30% [9980 / 81111, 904 ins, 2805 del, 6271 sub ]
277
+ 2022-12-09 00:12:26,761 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/fast_beam_search/errs-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
278
+ 2022-12-09 00:12:26,762 INFO [decode.py:508]
279
+ For eval_gss, WER of different settings are:
280
+ beam_4_max_contexts_4_max_states_8 12.3 best for eval_gss
281
+
282
+ 2022-12-09 00:12:26,763 INFO [decode.py:687] Decoding test_gss
283
+ 2022-12-09 00:12:29,434 INFO [decode.py:463] batch 0/?, cuts processed until now is 49
284
+ 2022-12-09 00:12:31,943 INFO [decode.py:463] batch 2/?, cuts processed until now is 433
285
+ 2022-12-09 00:12:34,693 INFO [decode.py:463] batch 4/?, cuts processed until now is 545
286
+ 2022-12-09 00:12:37,478 INFO [decode.py:463] batch 6/?, cuts processed until now is 637
287
+ 2022-12-09 00:12:40,171 INFO [decode.py:463] batch 8/?, cuts processed until now is 754
288
+ 2022-12-09 00:12:43,222 INFO [decode.py:463] batch 10/?, cuts processed until now is 845
289
+ 2022-12-09 00:12:45,929 INFO [decode.py:463] batch 12/?, cuts processed until now is 976
290
+ 2022-12-09 00:12:48,699 INFO [decode.py:463] batch 14/?, cuts processed until now is 1175
291
+ 2022-12-09 00:12:50,887 INFO [decode.py:463] batch 16/?, cuts processed until now is 1483
292
+ 2022-12-09 00:12:54,090 INFO [decode.py:463] batch 18/?, cuts processed until now is 1590
293
+ 2022-12-09 00:12:56,948 INFO [decode.py:463] batch 20/?, cuts processed until now is 1658
294
+ 2022-12-09 00:12:59,715 INFO [decode.py:463] batch 22/?, cuts processed until now is 1856
295
+ 2022-12-09 00:13:01,765 INFO [decode.py:463] batch 24/?, cuts processed until now is 2224
296
+ 2022-12-09 00:13:05,033 INFO [decode.py:463] batch 26/?, cuts processed until now is 2325
297
+ 2022-12-09 00:13:07,441 INFO [decode.py:463] batch 28/?, cuts processed until now is 2546
298
+ 2022-12-09 00:13:10,575 INFO [decode.py:463] batch 30/?, cuts processed until now is 2653
299
+ 2022-12-09 00:13:13,637 INFO [decode.py:463] batch 32/?, cuts processed until now is 2744
300
+ 2022-12-09 00:13:16,282 INFO [decode.py:463] batch 34/?, cuts processed until now is 2875
301
+ 2022-12-09 00:13:18,734 INFO [decode.py:463] batch 36/?, cuts processed until now is 2961
302
+ 2022-12-09 00:13:21,537 INFO [decode.py:463] batch 38/?, cuts processed until now is 3072
303
+ 2022-12-09 00:13:23,898 INFO [decode.py:463] batch 40/?, cuts processed until now is 3440
304
+ 2022-12-09 00:13:26,091 INFO [decode.py:463] batch 42/?, cuts processed until now is 3956
305
+ 2022-12-09 00:13:28,620 INFO [decode.py:463] batch 44/?, cuts processed until now is 4342
306
+ 2022-12-09 00:13:31,701 INFO [decode.py:463] batch 46/?, cuts processed until now is 4443
307
+ 2022-12-09 00:13:34,892 INFO [decode.py:463] batch 48/?, cuts processed until now is 4595
308
+ 2022-12-09 00:13:37,348 INFO [decode.py:463] batch 50/?, cuts processed until now is 4872
309
+ 2022-12-09 00:13:40,042 INFO [decode.py:463] batch 52/?, cuts processed until now is 5061
310
+ 2022-12-09 00:13:42,670 INFO [decode.py:463] batch 54/?, cuts processed until now is 5219
311
+ 2022-12-09 00:13:44,416 INFO [decode.py:463] batch 56/?, cuts processed until now is 5892
312
+ 2022-12-09 00:13:47,372 INFO [decode.py:463] batch 58/?, cuts processed until now is 6090
313
+ 2022-12-09 00:13:49,548 INFO [decode.py:463] batch 60/?, cuts processed until now is 6517
314
+ 2022-12-09 00:13:52,266 INFO [decode.py:463] batch 62/?, cuts processed until now is 6715
315
+ 2022-12-09 00:13:55,249 INFO [decode.py:463] batch 64/?, cuts processed until now is 6897
316
+ 2022-12-09 00:13:57,716 INFO [decode.py:463] batch 66/?, cuts processed until now is 7304
317
+ 2022-12-09 00:14:00,289 INFO [decode.py:463] batch 68/?, cuts processed until now is 7488
318
+ 2022-12-09 00:14:02,611 INFO [decode.py:463] batch 70/?, cuts processed until now is 7720
319
+ 2022-12-09 00:14:05,168 INFO [decode.py:463] batch 72/?, cuts processed until now is 7938
320
+ 2022-12-09 00:14:07,503 INFO [decode.py:463] batch 74/?, cuts processed until now is 8367
321
+ 2022-12-09 00:14:09,647 INFO [decode.py:463] batch 76/?, cuts processed until now is 8674
322
+ 2022-12-09 00:14:11,923 INFO [decode.py:463] batch 78/?, cuts processed until now is 8982
323
+ 2022-12-09 00:14:14,092 INFO [decode.py:463] batch 80/?, cuts processed until now is 9350
324
+ 2022-12-09 00:14:16,181 INFO [decode.py:463] batch 82/?, cuts processed until now is 9810
325
+ 2022-12-09 00:14:18,361 INFO [decode.py:463] batch 84/?, cuts processed until now is 10237
326
+ 2022-12-09 00:14:20,381 INFO [decode.py:463] batch 86/?, cuts processed until now is 10755
327
+ 2022-12-09 00:14:22,209 INFO [decode.py:463] batch 88/?, cuts processed until now is 11278
328
+ 2022-12-09 00:14:24,483 INFO [decode.py:463] batch 90/?, cuts processed until now is 11705
329
+ 2022-12-09 00:14:26,641 INFO [decode.py:463] batch 92/?, cuts processed until now is 12013
330
+ 2022-12-09 00:14:29,060 INFO [decode.py:463] batch 94/?, cuts processed until now is 12290
331
+ 2022-12-09 00:14:31,239 INFO [decode.py:463] batch 96/?, cuts processed until now is 12597
332
+ 2022-12-09 00:14:33,271 INFO [decode.py:463] batch 98/?, cuts processed until now is 12963
333
+ 2022-12-09 00:14:35,307 INFO [decode.py:463] batch 100/?, cuts processed until now is 13420
334
+ 2022-12-09 00:14:37,571 INFO [decode.py:463] batch 102/?, cuts processed until now is 13877
335
+ 2022-12-09 00:14:39,261 INFO [decode.py:463] batch 104/?, cuts processed until now is 14543
336
+ 2022-12-09 00:14:40,975 INFO [decode.py:463] batch 106/?, cuts processed until now is 15209
337
+ 2022-12-09 00:14:42,696 INFO [decode.py:463] batch 108/?, cuts processed until now is 15599
338
+ 2022-12-09 00:14:44,299 INFO [decode.py:463] batch 110/?, cuts processed until now is 15787
339
+ 2022-12-09 00:14:45,434 INFO [decode.py:463] batch 112/?, cuts processed until now is 15881
340
+ 2022-12-09 00:14:47,672 INFO [decode.py:463] batch 114/?, cuts processed until now is 15926
341
+ 2022-12-09 00:14:48,671 INFO [decode.py:463] batch 116/?, cuts processed until now is 16287
342
+ 2022-12-09 00:14:50,930 INFO [decode.py:463] batch 118/?, cuts processed until now is 16357
343
+ 2022-12-09 00:14:51,229 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/fast_beam_search/recogs-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
344
+ 2022-12-09 00:14:51,493 INFO [utils.py:536] [test_gss-beam_4_max_contexts_4_max_states_8] %WER 14.98% [31430 / 209845, 2279 ins, 10211 del, 18940 sub ]
345
+ 2022-12-09 00:14:52,136 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/fast_beam_search/errs-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt
346
+ 2022-12-09 00:14:52,138 INFO [decode.py:508]
347
+ For test_gss, WER of different settings are:
348
+ beam_4_max_contexts_4_max_states_8 14.98 best for test_gss
349
+
350
+ 2022-12-09 00:14:52,138 INFO [decode.py:703] Done!
log/fast_beam_search/recogs-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/recogs-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/recogs-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/recogs-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/recogs-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/recogs-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/fast_beam_search/wer-summary-eval_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ beam_4_max_contexts_4_max_states_8 12.3
log/fast_beam_search/wer-summary-eval_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ beam_4_max_contexts_4_max_states_8 9.92
log/fast_beam_search/wer-summary-eval_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ beam_4_max_contexts_4_max_states_8 23.6
log/fast_beam_search/wer-summary-test_gss-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ beam_4_max_contexts_4_max_states_8 14.98
log/fast_beam_search/wer-summary-test_ihm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ beam_4_max_contexts_4_max_states_8 12.07
log/fast_beam_search/wer-summary-test_sdm-beam_4_max_contexts_4_max_states_8-epoch-15-avg-8-beam-4-max-contexts-4-max-states-8.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ beam_4_max_contexts_4_max_states_8 26.38
log/greedy_search/errs-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/errs-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/errs-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/errs-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/errs-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/errs-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/log-decode-epoch-15-avg-8-context-2-max-sym-per-frame-1-2022-12-08-23-52-09 ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-12-08 23:52:09,512 INFO [decode.py:551] Decoding started
2
+ 2022-12-08 23:52:09,513 INFO [decode.py:557] Device: cuda:0
3
+ 2022-12-08 23:52:09,579 INFO [lexicon.py:168] Loading pre-compiled data/lang_char/Linv.pt
4
+ 2022-12-08 23:52:09,589 INFO [decode.py:563] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 100, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'warm_step': 2000, 'env_info': {'k2-version': '1.23', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'b2ce63f3940018e7b433c43fd802fc50ab006a76', 'k2-git-date': 'Wed Nov 23 08:43:43 2022', 'lhotse-version': '1.9.0.dev+git.97bf4b0.dirty', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'ali_meeting', 'icefall-git-sha1': 'f13cf61-dirty', 'icefall-git-date': 'Tue Dec 6 03:34:27 2022', 'icefall-path': '/exp/draj/mini_scale_2022/icefall', 'k2-path': '/exp/draj/mini_scale_2022/k2/k2/python/k2/__init__.py', 'lhotse-path': '/exp/draj/mini_scale_2022/lhotse/lhotse/__init__.py', 'hostname': 'r2n06', 'IP address': '10.1.2.6'}, 'epoch': 15, 'iter': 0, 'avg': 8, 'use_averaged_model': True, 'exp_dir': PosixPath('pruned_transducer_stateless7/exp/v1'), 'lang_dir': 'data/lang_char', 'decoding_method': 'greedy_search', 'beam_size': 4, 'beam': 4, 'ngram_lm_scale': 0.01, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'num_paths': 200, 'nbest_scale': 0.5, 'num_encoder_layers': '2,4,3,2,4', 'feedforward_dims': '1024,1024,2048,2048,1024', 'nhead': '8,8,8,8,8', 'encoder_dims': '384,384,384,384,384', 'attention_dims': '192,192,192,192,192', 'encoder_unmasked_dims': '256,256,256,256,256', 'zipformer_downsampling_factors': '1,2,4,8,2', 'cnn_module_kernels': '31,31,31,31,31', 'decoder_dim': 512, 'joiner_dim': 512, 'manifest_dir': PosixPath('data/manifests'), 'enable_musan': True, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'max_duration': 500, 'max_cuts': None, 'num_buckets': 50, 'on_the_fly_feats': False, 'shuffle': True, 'num_workers': 8, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'res_dir': PosixPath('pruned_transducer_stateless7/exp/v1/greedy_search'), 'suffix': 'epoch-15-avg-8-context-2-max-sym-per-frame-1', 'blank_id': 0, 'vocab_size': 3290}
5
+ 2022-12-08 23:52:09,589 INFO [decode.py:565] About to create model
6
+ 2022-12-08 23:52:10,047 INFO [zipformer.py:179] At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
7
+ 2022-12-08 23:52:10,093 INFO [decode.py:632] Calculating the averaged model over epoch range from 7 (excluded) to 15
8
+ 2022-12-08 23:52:26,211 INFO [decode.py:655] Number of model parameters: 75734561
9
+ 2022-12-08 23:52:26,212 INFO [asr_datamodule.py:381] About to get AliMeeting IHM eval cuts
10
+ 2022-12-08 23:52:26,214 INFO [asr_datamodule.py:402] About to get AliMeeting IHM test cuts
11
+ 2022-12-08 23:52:26,216 INFO [asr_datamodule.py:387] About to get AliMeeting SDM eval cuts
12
+ 2022-12-08 23:52:26,217 INFO [asr_datamodule.py:408] About to get AliMeeting SDM test cuts
13
+ 2022-12-08 23:52:26,219 INFO [asr_datamodule.py:396] About to get AliMeeting GSS-enhanced eval cuts
14
+ 2022-12-08 23:52:26,221 INFO [asr_datamodule.py:417] About to get AliMeeting GSS-enhanced test cuts
15
+ 2022-12-08 23:52:27,975 INFO [decode.py:687] Decoding eval_ihm
16
+ 2022-12-08 23:52:29,438 INFO [decode.py:463] batch 0/?, cuts processed until now is 58
17
+ 2022-12-08 23:52:52,862 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/greedy_search/recogs-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
18
+ 2022-12-08 23:52:52,958 INFO [utils.py:536] [eval_ihm-greedy_search] %WER 10.13% [8216 / 81111, 831 ins, 2185 del, 5200 sub ]
19
+ 2022-12-08 23:52:53,196 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/greedy_search/errs-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
20
+ 2022-12-08 23:52:53,197 INFO [decode.py:508]
21
+ For eval_ihm, WER of different settings are:
22
+ greedy_search 10.13 best for eval_ihm
23
+
24
+ 2022-12-08 23:52:53,197 INFO [decode.py:687] Decoding test_ihm
25
+ 2022-12-08 23:52:54,874 INFO [decode.py:463] batch 0/?, cuts processed until now is 49
26
+ 2022-12-08 23:53:30,263 INFO [zipformer.py:1414] attn_weights_entropy = tensor([4.5696, 4.6696, 4.8707, 4.0575, 4.6745, 4.9781, 2.0707, 4.4098],
27
+ device='cuda:0'), covar=tensor([0.0117, 0.0196, 0.0221, 0.0396, 0.0183, 0.0096, 0.3094, 0.0230],
28
+ device='cuda:0'), in_proj_covar=tensor([0.0143, 0.0153, 0.0125, 0.0123, 0.0184, 0.0118, 0.0149, 0.0172],
29
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0003, 0.0003, 0.0003, 0.0004, 0.0003, 0.0003, 0.0003],
30
+ device='cuda:0')
31
+ 2022-12-08 23:53:49,853 INFO [zipformer.py:1414] attn_weights_entropy = tensor([2.0649, 1.6505, 4.0800, 3.8988, 3.9109, 4.0868, 3.2733, 4.1840],
32
+ device='cuda:0'), covar=tensor([0.1251, 0.1291, 0.0081, 0.0142, 0.0145, 0.0086, 0.0117, 0.0077],
33
+ device='cuda:0'), in_proj_covar=tensor([0.0139, 0.0150, 0.0113, 0.0156, 0.0131, 0.0125, 0.0105, 0.0106],
34
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0003, 0.0003, 0.0003, 0.0003, 0.0003, 0.0002],
35
+ device='cuda:0')
36
+ 2022-12-08 23:53:50,687 INFO [decode.py:463] batch 100/?, cuts processed until now is 13420
37
+ 2022-12-08 23:53:55,847 INFO [zipformer.py:1414] attn_weights_entropy = tensor([4.9753, 2.8328, 4.9959, 2.8165, 4.7903, 2.2568, 3.6416, 4.6590],
38
+ device='cuda:0'), covar=tensor([0.0528, 0.5202, 0.0432, 1.3318, 0.0421, 0.5119, 0.1614, 0.0291],
39
+ device='cuda:0'), in_proj_covar=tensor([0.0221, 0.0205, 0.0174, 0.0283, 0.0196, 0.0207, 0.0197, 0.0178],
40
+ device='cuda:0'), out_proj_covar=tensor([0.0004, 0.0004, 0.0003, 0.0005, 0.0004, 0.0004, 0.0004, 0.0004],
41
+ device='cuda:0')
42
+ 2022-12-08 23:53:58,036 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/greedy_search/recogs-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
43
+ 2022-12-08 23:53:58,352 INFO [utils.py:536] [test_ihm-greedy_search] %WER 12.21% [25615 / 209845, 2007 ins, 7895 del, 15713 sub ]
44
+ 2022-12-08 23:53:58,963 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/greedy_search/errs-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
45
+ 2022-12-08 23:53:58,964 INFO [decode.py:508]
46
+ For test_ihm, WER of different settings are:
47
+ greedy_search 12.21 best for test_ihm
48
+
49
+ 2022-12-08 23:53:58,964 INFO [decode.py:687] Decoding eval_sdm
50
+ 2022-12-08 23:54:00,431 INFO [decode.py:463] batch 0/?, cuts processed until now is 58
51
+ 2022-12-08 23:54:09,011 INFO [zipformer.py:1414] attn_weights_entropy = tensor([2.9497, 2.8796, 3.7148, 2.5176, 2.4075, 2.9990, 1.6958, 2.9434],
52
+ device='cuda:0'), covar=tensor([0.1004, 0.0976, 0.0427, 0.2647, 0.2157, 0.0924, 0.3887, 0.0774],
53
+ device='cuda:0'), in_proj_covar=tensor([0.0070, 0.0085, 0.0077, 0.0085, 0.0104, 0.0072, 0.0116, 0.0077],
54
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0003, 0.0004, 0.0004, 0.0003, 0.0004, 0.0003],
55
+ device='cuda:0')
56
+ 2022-12-08 23:54:21,106 INFO [zipformer.py:1414] attn_weights_entropy = tensor([4.0325, 3.8665, 3.9421, 3.9902, 3.6039, 3.2852, 4.1056, 3.8995],
57
+ device='cuda:0'), covar=tensor([0.0388, 0.0286, 0.0419, 0.0433, 0.0408, 0.0515, 0.0381, 0.0510],
58
+ device='cuda:0'), in_proj_covar=tensor([0.0122, 0.0118, 0.0125, 0.0134, 0.0129, 0.0102, 0.0145, 0.0125],
59
+ device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
60
+ device='cuda:0')
61
+ 2022-12-08 23:54:23,976 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/greedy_search/recogs-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
62
+ 2022-12-08 23:54:24,077 INFO [utils.py:536] [eval_sdm-greedy_search] %WER 23.70% [19222 / 81111, 1683 ins, 6073 del, 11466 sub ]
63
+ 2022-12-08 23:54:24,332 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/greedy_search/errs-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
64
+ 2022-12-08 23:54:24,333 INFO [decode.py:508]
65
+ For eval_sdm, WER of different settings are:
66
+ greedy_search 23.7 best for eval_sdm
67
+
68
+ 2022-12-08 23:54:24,333 INFO [decode.py:687] Decoding test_sdm
69
+ 2022-12-08 23:54:26,054 INFO [decode.py:463] batch 0/?, cuts processed until now is 49
70
+ 2022-12-08 23:54:27,800 INFO [zipformer.py:1414] attn_weights_entropy = tensor([5.8932, 5.8649, 5.7222, 5.8181, 5.3845, 5.4143, 5.9574, 5.6303],
71
+ device='cuda:0'), covar=tensor([0.0422, 0.0200, 0.0364, 0.0455, 0.0434, 0.0144, 0.0327, 0.0613],
72
+ device='cuda:0'), in_proj_covar=tensor([0.0122, 0.0118, 0.0125, 0.0134, 0.0129, 0.0102, 0.0145, 0.0125],
73
+ device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002, 0.0002],
74
+ device='cuda:0')
75
+ 2022-12-08 23:54:31,870 INFO [zipformer.py:1414] attn_weights_entropy = tensor([5.0367, 4.5032, 4.6101, 4.9917, 4.5509, 4.6262, 4.8931, 4.4161],
76
+ device='cuda:0'), covar=tensor([0.0253, 0.1510, 0.0270, 0.0302, 0.0832, 0.0292, 0.0559, 0.0433],
77
+ device='cuda:0'), in_proj_covar=tensor([0.0149, 0.0248, 0.0167, 0.0163, 0.0160, 0.0127, 0.0252, 0.0145],
78
+ device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0003, 0.0002, 0.0002, 0.0002, 0.0002, 0.0003, 0.0002],
79
+ device='cuda:0')
80
+ 2022-12-08 23:54:36,104 INFO [zipformer.py:1414] attn_weights_entropy = tensor([3.5049, 3.0396, 3.1109, 2.3003, 2.9128, 3.3196, 3.3253, 2.8653],
81
+ device='cuda:0'), covar=tensor([0.0876, 0.2228, 0.1388, 0.2084, 0.1478, 0.0834, 0.1264, 0.1702],
82
+ device='cuda:0'), in_proj_covar=tensor([0.0124, 0.0170, 0.0124, 0.0117, 0.0121, 0.0128, 0.0106, 0.0128],
83
+ device='cuda:0'), out_proj_covar=tensor([0.0005, 0.0006, 0.0005, 0.0005, 0.0005, 0.0005, 0.0005, 0.0005],
84
+ device='cuda:0')
85
+ 2022-12-08 23:54:47,951 INFO [zipformer.py:1414] attn_weights_entropy = tensor([2.9691, 2.6751, 2.9312, 3.1152, 2.8372, 2.3588, 2.9794, 3.0298],
86
+ device='cuda:0'), covar=tensor([0.0107, 0.0177, 0.0195, 0.0116, 0.0141, 0.0331, 0.0139, 0.0184],
87
+ device='cuda:0'), in_proj_covar=tensor([0.0258, 0.0233, 0.0347, 0.0293, 0.0235, 0.0280, 0.0265, 0.0260],
88
+ device='cuda:0'), out_proj_covar=tensor([0.0002, 0.0002, 0.0003, 0.0003, 0.0002, 0.0003, 0.0003, 0.0002],
89
+ device='cuda:0')
90
+ 2022-12-08 23:55:21,831 INFO [decode.py:463] batch 100/?, cuts processed until now is 13420
91
+ 2022-12-08 23:55:29,332 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/greedy_search/recogs-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
92
+ 2022-12-08 23:55:29,621 INFO [utils.py:536] [test_sdm-greedy_search] %WER 26.41% [55414 / 209845, 4503 ins, 19379 del, 31532 sub ]
93
+ 2022-12-08 23:55:30,282 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/greedy_search/errs-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
94
+ 2022-12-08 23:55:30,283 INFO [decode.py:508]
95
+ For test_sdm, WER of different settings are:
96
+ greedy_search 26.41 best for test_sdm
97
+
98
+ 2022-12-08 23:55:30,283 INFO [decode.py:687] Decoding eval_gss
99
+ 2022-12-08 23:55:31,773 INFO [decode.py:463] batch 0/?, cuts processed until now is 58
100
+ 2022-12-08 23:55:34,158 INFO [zipformer.py:1414] attn_weights_entropy = tensor([3.2471, 3.7230, 3.3454, 2.8730, 2.7644, 3.7741, 3.4475, 1.8443],
101
+ device='cuda:0'), covar=tensor([0.3240, 0.0695, 0.1965, 0.1750, 0.1144, 0.0470, 0.1355, 0.3201],
102
+ device='cuda:0'), in_proj_covar=tensor([0.0138, 0.0066, 0.0052, 0.0054, 0.0082, 0.0064, 0.0085, 0.0091],
103
+ device='cuda:0'), out_proj_covar=tensor([0.0007, 0.0004, 0.0004, 0.0004, 0.0005, 0.0004, 0.0005, 0.0005],
104
+ device='cuda:0')
105
+ 2022-12-08 23:55:37,669 INFO [zipformer.py:1414] attn_weights_entropy = tensor([3.7584, 3.8680, 4.3876, 3.2812, 2.7117, 3.5261, 2.1305, 3.5684],
106
+ device='cuda:0'), covar=tensor([0.0716, 0.0548, 0.0428, 0.2018, 0.2384, 0.0745, 0.3972, 0.0912],
107
+ device='cuda:0'), in_proj_covar=tensor([0.0070, 0.0085, 0.0077, 0.0085, 0.0104, 0.0072, 0.0116, 0.0077],
108
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0003, 0.0004, 0.0004, 0.0003, 0.0004, 0.0003],
109
+ device='cuda:0')
110
+ 2022-12-08 23:55:41,813 INFO [zipformer.py:1414] attn_weights_entropy = tensor([4.2555, 3.7707, 3.0407, 4.4182, 4.2751, 4.2557, 3.6943, 2.9354],
111
+ device='cuda:0'), covar=tensor([0.0750, 0.1279, 0.4109, 0.0665, 0.0696, 0.1311, 0.1328, 0.4549],
112
+ device='cuda:0'), in_proj_covar=tensor([0.0237, 0.0272, 0.0252, 0.0220, 0.0279, 0.0268, 0.0232, 0.0237],
113
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0004, 0.0003, 0.0004, 0.0003, 0.0003, 0.0003],
114
+ device='cuda:0')
115
+ 2022-12-08 23:55:55,409 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/greedy_search/recogs-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
116
+ 2022-12-08 23:55:55,506 INFO [utils.py:536] [eval_gss-greedy_search] %WER 12.24% [9930 / 81111, 915 ins, 2606 del, 6409 sub ]
117
+ 2022-12-08 23:55:55,743 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/greedy_search/errs-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
118
+ 2022-12-08 23:55:55,744 INFO [decode.py:508]
119
+ For eval_gss, WER of different settings are:
120
+ greedy_search 12.24 best for eval_gss
121
+
122
+ 2022-12-08 23:55:55,744 INFO [decode.py:687] Decoding test_gss
123
+ 2022-12-08 23:55:57,430 INFO [decode.py:463] batch 0/?, cuts processed until now is 49
124
+ 2022-12-08 23:56:44,408 INFO [zipformer.py:1414] attn_weights_entropy = tensor([2.0077, 1.3975, 3.4059, 2.9515, 3.0863, 3.3663, 2.8472, 3.3858],
125
+ device='cuda:0'), covar=tensor([0.0407, 0.0664, 0.0061, 0.0240, 0.0239, 0.0078, 0.0193, 0.0094],
126
+ device='cuda:0'), in_proj_covar=tensor([0.0139, 0.0150, 0.0113, 0.0156, 0.0131, 0.0125, 0.0105, 0.0106],
127
+ device='cuda:0'), out_proj_covar=tensor([0.0003, 0.0004, 0.0003, 0.0003, 0.0003, 0.0003, 0.0003, 0.0002],
128
+ device='cuda:0')
129
+ 2022-12-08 23:56:53,454 INFO [decode.py:463] batch 100/?, cuts processed until now is 13420
130
+ 2022-12-08 23:57:00,993 INFO [decode.py:479] The transcripts are stored in pruned_transducer_stateless7/exp/v1/greedy_search/recogs-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
131
+ 2022-12-08 23:57:01,279 INFO [utils.py:536] [test_gss-greedy_search] %WER 14.99% [31450 / 209845, 2293 ins, 9720 del, 19437 sub ]
132
+ 2022-12-08 23:57:01,910 INFO [decode.py:492] Wrote detailed error stats to pruned_transducer_stateless7/exp/v1/greedy_search/errs-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt
133
+ 2022-12-08 23:57:01,911 INFO [decode.py:508]
134
+ For test_gss, WER of different settings are:
135
+ greedy_search 14.99 best for test_gss
136
+
137
+ 2022-12-08 23:57:01,912 INFO [decode.py:703] Done!
log/greedy_search/recogs-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/recogs-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/recogs-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/recogs-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/recogs-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/recogs-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
The diff for this file is too large to render. See raw diff
 
log/greedy_search/wer-summary-eval_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ greedy_search 12.24
log/greedy_search/wer-summary-eval_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ greedy_search 10.13
log/greedy_search/wer-summary-eval_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ greedy_search 23.7
log/greedy_search/wer-summary-test_gss-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ greedy_search 14.99
log/greedy_search/wer-summary-test_ihm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ greedy_search 12.21
log/greedy_search/wer-summary-test_sdm-greedy_search-epoch-15-avg-8-context-2-max-sym-per-frame-1.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ settings WER
2
+ greedy_search 26.41
log/log-train-2022-12-07-04-36-17-0 ADDED
The diff for this file is too large to render. See raw diff
 
log/log-train-2022-12-07-04-36-17-1 ADDED
The diff for this file is too large to render. See raw diff
 
log/log-train-2022-12-07-04-36-17-2 ADDED
The diff for this file is too large to render. See raw diff
 
log/log-train-2022-12-07-04-36-17-3 ADDED
The diff for this file is too large to render. See raw diff