danielizham commited on
Commit
b5a6d94
1 Parent(s): 33cfe8b

Training in progress, step 1000

Browse files
Files changed (38) hide show
  1. .gitattributes +2 -0
  2. .gitignore +1 -0
  3. added_tokens.json +108 -0
  4. config.json +50 -0
  5. merges.txt +0 -0
  6. normalizer.json +1742 -0
  7. preprocessor_config.json +14 -0
  8. pytorch_model.bin +3 -0
  9. run.sh +40 -0
  10. run_speech_recognition_seq2seq_streaming.py +629 -0
  11. special_tokens_map.json +133 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +35 -0
  14. training.log +0 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
  17. wandb/debug-cli.dizham.log +0 -0
  18. wandb/debug-internal.log +1 -0
  19. wandb/debug.log +1 -0
  20. wandb/latest-run +1 -0
  21. wandb/run-20230506_113337-ysywp688/files/conda-environment.yaml +133 -0
  22. wandb/run-20230506_113337-ysywp688/files/config.yaml +688 -0
  23. wandb/run-20230506_113337-ysywp688/files/output.log +1101 -0
  24. wandb/run-20230506_113337-ysywp688/files/requirements.txt +107 -0
  25. wandb/run-20230506_113337-ysywp688/files/wandb-metadata.json +369 -0
  26. wandb/run-20230506_113337-ysywp688/files/wandb-summary.json +1 -0
  27. wandb/run-20230506_113337-ysywp688/logs/debug-internal.log +0 -0
  28. wandb/run-20230506_113337-ysywp688/logs/debug.log +28 -0
  29. wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb +3 -0
  30. wandb/run-20230507_103405-9zf5xxpu/files/conda-environment.yaml +133 -0
  31. wandb/run-20230507_103405-9zf5xxpu/files/config.yaml +688 -0
  32. wandb/run-20230507_103405-9zf5xxpu/files/output.log +1079 -0
  33. wandb/run-20230507_103405-9zf5xxpu/files/requirements.txt +107 -0
  34. wandb/run-20230507_103405-9zf5xxpu/files/wandb-metadata.json +369 -0
  35. wandb/run-20230507_103405-9zf5xxpu/files/wandb-summary.json +1 -0
  36. wandb/run-20230507_103405-9zf5xxpu/logs/debug-internal.log +0 -0
  37. wandb/run-20230507_103405-9zf5xxpu/logs/debug.log +27 -0
  38. wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb +3 -0
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb filter=lfs diff=lfs merge=lfs -text
36
+ wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|af|>": 50327,
3
+ "<|am|>": 50334,
4
+ "<|ar|>": 50272,
5
+ "<|as|>": 50350,
6
+ "<|az|>": 50304,
7
+ "<|ba|>": 50355,
8
+ "<|be|>": 50330,
9
+ "<|bg|>": 50292,
10
+ "<|bn|>": 50302,
11
+ "<|bo|>": 50347,
12
+ "<|br|>": 50309,
13
+ "<|bs|>": 50315,
14
+ "<|ca|>": 50270,
15
+ "<|cs|>": 50283,
16
+ "<|cy|>": 50297,
17
+ "<|da|>": 50285,
18
+ "<|de|>": 50261,
19
+ "<|el|>": 50281,
20
+ "<|en|>": 50259,
21
+ "<|es|>": 50262,
22
+ "<|et|>": 50307,
23
+ "<|eu|>": 50310,
24
+ "<|fa|>": 50300,
25
+ "<|fi|>": 50277,
26
+ "<|fo|>": 50338,
27
+ "<|fr|>": 50265,
28
+ "<|gl|>": 50319,
29
+ "<|gu|>": 50333,
30
+ "<|haw|>": 50352,
31
+ "<|ha|>": 50354,
32
+ "<|he|>": 50279,
33
+ "<|hi|>": 50276,
34
+ "<|hr|>": 50291,
35
+ "<|ht|>": 50339,
36
+ "<|hu|>": 50286,
37
+ "<|hy|>": 50312,
38
+ "<|id|>": 50275,
39
+ "<|is|>": 50311,
40
+ "<|it|>": 50274,
41
+ "<|ja|>": 50266,
42
+ "<|jw|>": 50356,
43
+ "<|ka|>": 50329,
44
+ "<|kk|>": 50316,
45
+ "<|km|>": 50323,
46
+ "<|kn|>": 50306,
47
+ "<|ko|>": 50264,
48
+ "<|la|>": 50294,
49
+ "<|lb|>": 50345,
50
+ "<|ln|>": 50353,
51
+ "<|lo|>": 50336,
52
+ "<|lt|>": 50293,
53
+ "<|lv|>": 50301,
54
+ "<|mg|>": 50349,
55
+ "<|mi|>": 50295,
56
+ "<|mk|>": 50308,
57
+ "<|ml|>": 50296,
58
+ "<|mn|>": 50314,
59
+ "<|mr|>": 50320,
60
+ "<|ms|>": 50282,
61
+ "<|mt|>": 50343,
62
+ "<|my|>": 50346,
63
+ "<|ne|>": 50313,
64
+ "<|nl|>": 50271,
65
+ "<|nn|>": 50342,
66
+ "<|nocaptions|>": 50362,
67
+ "<|notimestamps|>": 50363,
68
+ "<|no|>": 50288,
69
+ "<|oc|>": 50328,
70
+ "<|pa|>": 50321,
71
+ "<|pl|>": 50269,
72
+ "<|ps|>": 50340,
73
+ "<|pt|>": 50267,
74
+ "<|ro|>": 50284,
75
+ "<|ru|>": 50263,
76
+ "<|sa|>": 50344,
77
+ "<|sd|>": 50332,
78
+ "<|si|>": 50322,
79
+ "<|sk|>": 50298,
80
+ "<|sl|>": 50305,
81
+ "<|sn|>": 50324,
82
+ "<|so|>": 50326,
83
+ "<|sq|>": 50317,
84
+ "<|sr|>": 50303,
85
+ "<|startoflm|>": 50360,
86
+ "<|startofprev|>": 50361,
87
+ "<|startoftranscript|>": 50258,
88
+ "<|su|>": 50357,
89
+ "<|sv|>": 50273,
90
+ "<|sw|>": 50318,
91
+ "<|ta|>": 50287,
92
+ "<|te|>": 50299,
93
+ "<|tg|>": 50331,
94
+ "<|th|>": 50289,
95
+ "<|tk|>": 50341,
96
+ "<|tl|>": 50348,
97
+ "<|transcribe|>": 50359,
98
+ "<|translate|>": 50358,
99
+ "<|tr|>": 50268,
100
+ "<|tt|>": 50351,
101
+ "<|uk|>": 50280,
102
+ "<|ur|>": 50290,
103
+ "<|uz|>": 50337,
104
+ "<|vi|>": 50278,
105
+ "<|yi|>": 50335,
106
+ "<|yo|>": 50325,
107
+ "<|zh|>": 50260
108
+ }
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 448,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "model_type": "whisper",
41
+ "num_hidden_layers": 12,
42
+ "num_mel_bins": 80,
43
+ "pad_token_id": 50257,
44
+ "scale_embedding": false,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.29.0.dev0",
47
+ "use_cache": false,
48
+ "use_weighted_layer_sum": false,
49
+ "vocab_size": 51865
50
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
normalizer.json ADDED
@@ -0,0 +1,1742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "accessorise": "accessorize",
3
+ "accessorised": "accessorized",
4
+ "accessorises": "accessorizes",
5
+ "accessorising": "accessorizing",
6
+ "acclimatisation": "acclimatization",
7
+ "acclimatise": "acclimatize",
8
+ "acclimatised": "acclimatized",
9
+ "acclimatises": "acclimatizes",
10
+ "acclimatising": "acclimatizing",
11
+ "accoutrements": "accouterments",
12
+ "aeon": "eon",
13
+ "aeons": "eons",
14
+ "aerogramme": "aerogram",
15
+ "aerogrammes": "aerograms",
16
+ "aeroplane": "airplane",
17
+ "aeroplanes": "airplanes",
18
+ "aesthete": "esthete",
19
+ "aesthetes": "esthetes",
20
+ "aesthetic": "esthetic",
21
+ "aesthetically": "esthetically",
22
+ "aesthetics": "esthetics",
23
+ "aetiology": "etiology",
24
+ "ageing": "aging",
25
+ "aggrandisement": "aggrandizement",
26
+ "agonise": "agonize",
27
+ "agonised": "agonized",
28
+ "agonises": "agonizes",
29
+ "agonising": "agonizing",
30
+ "agonisingly": "agonizingly",
31
+ "almanack": "almanac",
32
+ "almanacks": "almanacs",
33
+ "aluminium": "aluminum",
34
+ "amortisable": "amortizable",
35
+ "amortisation": "amortization",
36
+ "amortisations": "amortizations",
37
+ "amortise": "amortize",
38
+ "amortised": "amortized",
39
+ "amortises": "amortizes",
40
+ "amortising": "amortizing",
41
+ "amphitheatre": "amphitheater",
42
+ "amphitheatres": "amphitheaters",
43
+ "anaemia": "anemia",
44
+ "anaemic": "anemic",
45
+ "anaesthesia": "anesthesia",
46
+ "anaesthetic": "anesthetic",
47
+ "anaesthetics": "anesthetics",
48
+ "anaesthetise": "anesthetize",
49
+ "anaesthetised": "anesthetized",
50
+ "anaesthetises": "anesthetizes",
51
+ "anaesthetising": "anesthetizing",
52
+ "anaesthetist": "anesthetist",
53
+ "anaesthetists": "anesthetists",
54
+ "anaesthetize": "anesthetize",
55
+ "anaesthetized": "anesthetized",
56
+ "anaesthetizes": "anesthetizes",
57
+ "anaesthetizing": "anesthetizing",
58
+ "analogue": "analog",
59
+ "analogues": "analogs",
60
+ "analyse": "analyze",
61
+ "analysed": "analyzed",
62
+ "analyses": "analyzes",
63
+ "analysing": "analyzing",
64
+ "anglicise": "anglicize",
65
+ "anglicised": "anglicized",
66
+ "anglicises": "anglicizes",
67
+ "anglicising": "anglicizing",
68
+ "annualised": "annualized",
69
+ "antagonise": "antagonize",
70
+ "antagonised": "antagonized",
71
+ "antagonises": "antagonizes",
72
+ "antagonising": "antagonizing",
73
+ "apologise": "apologize",
74
+ "apologised": "apologized",
75
+ "apologises": "apologizes",
76
+ "apologising": "apologizing",
77
+ "appal": "appall",
78
+ "appals": "appalls",
79
+ "appetiser": "appetizer",
80
+ "appetisers": "appetizers",
81
+ "appetising": "appetizing",
82
+ "appetisingly": "appetizingly",
83
+ "arbour": "arbor",
84
+ "arbours": "arbors",
85
+ "archaeologically": "archeologically",
86
+ "archaeologist": "archeologist",
87
+ "archaeologists": "archeologists",
88
+ "archaeology": "archeology</span>",
89
+ "archeological": "archaeological",
90
+ "ardour": "ardor",
91
+ "armour": "armor",
92
+ "armoured": "armored",
93
+ "armourer": "armorer",
94
+ "armourers": "armorers",
95
+ "armouries": "armories",
96
+ "armoury": "armory",
97
+ "artefact": "artifact",
98
+ "artefacts": "artifacts",
99
+ "authorise": "authorize",
100
+ "authorised": "authorized",
101
+ "authorises": "authorizes",
102
+ "authorising": "authorizing",
103
+ "axe": "ax",
104
+ "backpedalled": "backpedaled",
105
+ "backpedalling": "backpedaling",
106
+ "bannister": "banister",
107
+ "bannisters": "banisters",
108
+ "baptise": "baptize",
109
+ "baptised": "baptized",
110
+ "baptises": "baptizes",
111
+ "baptising": "baptizing",
112
+ "bastardise": "bastardize",
113
+ "bastardised": "bastardized",
114
+ "bastardises": "bastardizes",
115
+ "bastardising": "bastardizing",
116
+ "battleax": "battleaxe",
117
+ "baulk": "balk",
118
+ "baulked": "balked",
119
+ "baulking": "balking",
120
+ "baulks": "balks",
121
+ "bedevilled": "bedeviled",
122
+ "bedevilling": "bedeviling",
123
+ "behaviour": "behavior",
124
+ "behavioural": "behavioral",
125
+ "behaviourism": "behaviorism",
126
+ "behaviourist": "behaviorist",
127
+ "behaviourists": "behaviorists",
128
+ "behaviours": "behaviors",
129
+ "behove": "behoove",
130
+ "behoved": "behooved",
131
+ "behoves": "behooves",
132
+ "bejewelled": "bejeweled",
133
+ "belabour": "belabor",
134
+ "belaboured": "belabored",
135
+ "belabouring": "belaboring",
136
+ "belabours": "belabors",
137
+ "bevelled": "beveled",
138
+ "bevvies": "bevies",
139
+ "bevvy": "bevy",
140
+ "biassed": "biased",
141
+ "biassing": "biasing",
142
+ "bingeing": "binging",
143
+ "bougainvillaea": "bougainvillea",
144
+ "bougainvillaeas": "bougainvilleas",
145
+ "bowdlerise": "bowdlerize",
146
+ "bowdlerised": "bowdlerized",
147
+ "bowdlerises": "bowdlerizes",
148
+ "bowdlerising": "bowdlerizing",
149
+ "breathalyse": "breathalyze",
150
+ "breathalysed": "breathalyzed",
151
+ "breathalyser": "breathalyzer",
152
+ "breathalysers": "breathalyzers",
153
+ "breathalyses": "breathalyzes",
154
+ "breathalysing": "breathalyzing",
155
+ "brutalise": "brutalize",
156
+ "brutalised": "brutalized",
157
+ "brutalises": "brutalizes",
158
+ "brutalising": "brutalizing",
159
+ "busses": "buses",
160
+ "bussing": "busing",
161
+ "caesarean": "cesarean",
162
+ "caesareans": "cesareans",
163
+ "calibre": "caliber",
164
+ "calibres": "calibers",
165
+ "calliper": "caliper",
166
+ "callipers": "calipers",
167
+ "callisthenics": "calisthenics",
168
+ "canalise": "canalize",
169
+ "canalised": "canalized",
170
+ "canalises": "canalizes",
171
+ "canalising": "canalizing",
172
+ "cancelation": "cancellation",
173
+ "cancelations": "cancellations",
174
+ "cancelled": "canceled",
175
+ "cancelling": "canceling",
176
+ "candour": "candor",
177
+ "cannibalise": "cannibalize",
178
+ "cannibalised": "cannibalized",
179
+ "cannibalises": "cannibalizes",
180
+ "cannibalising": "cannibalizing",
181
+ "canonise": "canonize",
182
+ "canonised": "canonized",
183
+ "canonises": "canonizes",
184
+ "canonising": "canonizing",
185
+ "capitalise": "capitalize",
186
+ "capitalised": "capitalized",
187
+ "capitalises": "capitalizes",
188
+ "capitalising": "capitalizing",
189
+ "caramelise": "caramelize",
190
+ "caramelised": "caramelized",
191
+ "caramelises": "caramelizes",
192
+ "caramelising": "caramelizing",
193
+ "carbonise": "carbonize",
194
+ "carbonised": "carbonized",
195
+ "carbonises": "carbonizes",
196
+ "carbonising": "carbonizing",
197
+ "carolled": "caroled",
198
+ "carolling": "caroling",
199
+ "catalogue": "catalog",
200
+ "catalogued": "cataloged",
201
+ "catalogues": "catalogs",
202
+ "cataloguing": "cataloging",
203
+ "catalyse": "catalyze",
204
+ "catalysed": "catalyzed",
205
+ "catalyses": "catalyzes",
206
+ "catalysing": "catalyzing",
207
+ "categorise": "categorize",
208
+ "categorised": "categorized",
209
+ "categorises": "categorizes",
210
+ "categorising": "categorizing",
211
+ "cauterise": "cauterize",
212
+ "cauterised": "cauterized",
213
+ "cauterises": "cauterizes",
214
+ "cauterising": "cauterizing",
215
+ "cavilled": "caviled",
216
+ "cavilling": "caviling",
217
+ "centigramme": "centigram",
218
+ "centigrammes": "centigrams",
219
+ "centilitre": "centiliter",
220
+ "centilitres": "centiliters",
221
+ "centimetre": "centimeter",
222
+ "centimetres": "centimeters",
223
+ "centralise": "centralize",
224
+ "centralised": "centralized",
225
+ "centralises": "centralizes",
226
+ "centralising": "centralizing",
227
+ "centre": "center",
228
+ "centred": "centered",
229
+ "centrefold": "centerfold",
230
+ "centrefolds": "centerfolds",
231
+ "centrepiece": "centerpiece",
232
+ "centrepieces": "centerpieces",
233
+ "centres": "centers",
234
+ "channelled": "channeled",
235
+ "channelling": "channeling",
236
+ "characterise": "characterize",
237
+ "characterised": "characterized",
238
+ "characterises": "characterizes",
239
+ "characterising": "characterizing",
240
+ "cheque": "check",
241
+ "chequebook": "checkbook",
242
+ "chequebooks": "checkbooks",
243
+ "chequered": "checkered",
244
+ "cheques": "checks",
245
+ "chilli": "chili",
246
+ "chimaera": "chimera",
247
+ "chimaeras": "chimeras",
248
+ "chiselled": "chiseled",
249
+ "chiselling": "chiseling",
250
+ "circularise": "circularize",
251
+ "circularised": "circularized",
252
+ "circularises": "circularizes",
253
+ "circularising": "circularizing",
254
+ "civilise": "civilize",
255
+ "civilised": "civilized",
256
+ "civilises": "civilizes",
257
+ "civilising": "civilizing",
258
+ "clamour": "clamor",
259
+ "clamoured": "clamored",
260
+ "clamouring": "clamoring",
261
+ "clamours": "clamors",
262
+ "clangour": "clangor",
263
+ "clarinettist": "clarinetist",
264
+ "clarinettists": "clarinetists",
265
+ "collectivise": "collectivize",
266
+ "collectivised": "collectivized",
267
+ "collectivises": "collectivizes",
268
+ "collectivising": "collectivizing",
269
+ "colonisation": "colonization",
270
+ "colonise": "colonize",
271
+ "colonised": "colonized",
272
+ "coloniser": "colonizer",
273
+ "colonisers": "colonizers",
274
+ "colonises": "colonizes",
275
+ "colonising": "colonizing",
276
+ "colour": "color",
277
+ "colourant": "colorant",
278
+ "colourants": "colorants",
279
+ "coloured": "colored",
280
+ "coloureds": "coloreds",
281
+ "colourful": "colorful",
282
+ "colourfully": "colorfully",
283
+ "colouring": "coloring",
284
+ "colourize": "colorize",
285
+ "colourized": "colorized",
286
+ "colourizes": "colorizes",
287
+ "colourizing": "colorizing",
288
+ "colourless": "colorless",
289
+ "colours": "colors",
290
+ "commercialise": "commercialize",
291
+ "commercialised": "commercialized",
292
+ "commercialises": "commercializes",
293
+ "commercialising": "commercializing",
294
+ "compartmentalise": "compartmentalize",
295
+ "compartmentalised": "compartmentalized",
296
+ "compartmentalises": "compartmentalizes",
297
+ "compartmentalising": "compartmentalizing",
298
+ "computerise": "computerize",
299
+ "computerised": "computerized",
300
+ "computerises": "computerizes",
301
+ "computerising": "computerizing",
302
+ "conceptualise": "conceptualize",
303
+ "conceptualised": "conceptualized",
304
+ "conceptualises": "conceptualizes",
305
+ "conceptualising": "conceptualizing",
306
+ "connexion": "connection",
307
+ "connexions": "connections",
308
+ "contextualise": "contextualize",
309
+ "contextualised": "contextualized",
310
+ "contextualises": "contextualizes",
311
+ "contextualising": "contextualizing",
312
+ "cosier": "cozier",
313
+ "cosies": "cozies",
314
+ "cosiest": "coziest",
315
+ "cosily": "cozily",
316
+ "cosiness": "coziness",
317
+ "cosy": "cozy",
318
+ "councillor": "councilor",
319
+ "councillors": "councilors",
320
+ "counselled": "counseled",
321
+ "counselling": "counseling",
322
+ "counsellor": "counselor",
323
+ "counsellors": "counselors",
324
+ "crenelated": "crenellated",
325
+ "criminalise": "criminalize",
326
+ "criminalised": "criminalized",
327
+ "criminalises": "criminalizes",
328
+ "criminalising": "criminalizing",
329
+ "criticise": "criticize",
330
+ "criticised": "criticized",
331
+ "criticises": "criticizes",
332
+ "criticising": "criticizing",
333
+ "crueller": "crueler",
334
+ "cruellest": "cruelest",
335
+ "crystallisation": "crystallization",
336
+ "crystallise": "crystallize",
337
+ "crystallised": "crystallized",
338
+ "crystallises": "crystallizes",
339
+ "crystallising": "crystallizing",
340
+ "cudgelled": "cudgeled",
341
+ "cudgelling": "cudgeling",
342
+ "customise": "customize",
343
+ "customised": "customized",
344
+ "customises": "customizes",
345
+ "customising": "customizing",
346
+ "cypher": "cipher",
347
+ "cyphers": "ciphers",
348
+ "decentralisation": "decentralization",
349
+ "decentralise": "decentralize",
350
+ "decentralised": "decentralized",
351
+ "decentralises": "decentralizes",
352
+ "decentralising": "decentralizing",
353
+ "decriminalisation": "decriminalization",
354
+ "decriminalise": "decriminalize",
355
+ "decriminalised": "decriminalized",
356
+ "decriminalises": "decriminalizes",
357
+ "decriminalising": "decriminalizing",
358
+ "defence": "defense",
359
+ "defenceless": "defenseless",
360
+ "defences": "defenses",
361
+ "dehumanisation": "dehumanization",
362
+ "dehumanise": "dehumanize",
363
+ "dehumanised": "dehumanized",
364
+ "dehumanises": "dehumanizes",
365
+ "dehumanising": "dehumanizing",
366
+ "demeanour": "demeanor",
367
+ "demilitarisation": "demilitarization",
368
+ "demilitarise": "demilitarize",
369
+ "demilitarised": "demilitarized",
370
+ "demilitarises": "demilitarizes",
371
+ "demilitarising": "demilitarizing",
372
+ "demobilisation": "demobilization",
373
+ "demobilise": "demobilize",
374
+ "demobilised": "demobilized",
375
+ "demobilises": "demobilizes",
376
+ "demobilising": "demobilizing",
377
+ "democratisation": "democratization",
378
+ "democratise": "democratize",
379
+ "democratised": "democratized",
380
+ "democratises": "democratizes",
381
+ "democratising": "democratizing",
382
+ "demonise": "demonize",
383
+ "demonised": "demonized",
384
+ "demonises": "demonizes",
385
+ "demonising": "demonizing",
386
+ "demoralisation": "demoralization",
387
+ "demoralise": "demoralize",
388
+ "demoralised": "demoralized",
389
+ "demoralises": "demoralizes",
390
+ "demoralising": "demoralizing",
391
+ "denationalisation": "denationalization",
392
+ "denationalise": "denationalize",
393
+ "denationalised": "denationalized",
394
+ "denationalises": "denationalizes",
395
+ "denationalising": "denationalizing",
396
+ "deodorise": "deodorize",
397
+ "deodorised": "deodorized",
398
+ "deodorises": "deodorizes",
399
+ "deodorising": "deodorizing",
400
+ "depersonalise": "depersonalize",
401
+ "depersonalised": "depersonalized",
402
+ "depersonalises": "depersonalizes",
403
+ "depersonalising": "depersonalizing",
404
+ "deputise": "deputize",
405
+ "deputised": "deputized",
406
+ "deputises": "deputizes",
407
+ "deputising": "deputizing",
408
+ "desensitisation": "desensitization",
409
+ "desensitise": "desensitize",
410
+ "desensitised": "desensitized",
411
+ "desensitises": "desensitizes",
412
+ "desensitising": "desensitizing",
413
+ "destabilisation": "destabilization",
414
+ "destabilise": "destabilize",
415
+ "destabilised": "destabilized",
416
+ "destabilises": "destabilizes",
417
+ "destabilising": "destabilizing",
418
+ "dialled": "dialed",
419
+ "dialling": "dialing",
420
+ "dialogue": "dialog",
421
+ "dialogues": "dialogs",
422
+ "diarrhoea": "diarrhea",
423
+ "digitise": "digitize",
424
+ "digitised": "digitized",
425
+ "digitises": "digitizes",
426
+ "digitising": "digitizing",
427
+ "disc": "disk",
428
+ "discolour": "discolor",
429
+ "discoloured": "discolored",
430
+ "discolouring": "discoloring",
431
+ "discolours": "discolors",
432
+ "discs": "disks",
433
+ "disembowelled": "disemboweled",
434
+ "disembowelling": "disemboweling",
435
+ "disfavour": "disfavor",
436
+ "dishevelled": "disheveled",
437
+ "dishonour": "dishonor",
438
+ "dishonourable": "dishonorable",
439
+ "dishonourably": "dishonorably",
440
+ "dishonoured": "dishonored",
441
+ "dishonouring": "dishonoring",
442
+ "dishonours": "dishonors",
443
+ "disorganisation": "disorganization",
444
+ "disorganised": "disorganized",
445
+ "distil": "distill",
446
+ "distils": "distills",
447
+ "dramatisation": "dramatization",
448
+ "dramatisations": "dramatizations",
449
+ "dramatise": "dramatize",
450
+ "dramatised": "dramatized",
451
+ "dramatises": "dramatizes",
452
+ "dramatising": "dramatizing",
453
+ "draught": "draft",
454
+ "draughtboard": "draftboard",
455
+ "draughtboards": "draftboards",
456
+ "draughtier": "draftier",
457
+ "draughtiest": "draftiest",
458
+ "draughts": "drafts",
459
+ "draughtsman": "draftsman",
460
+ "draughtsmanship": "draftsmanship",
461
+ "draughtsmen": "draftsmen",
462
+ "draughtswoman": "draftswoman",
463
+ "draughtswomen": "draftswomen",
464
+ "draughty": "drafty",
465
+ "drivelled": "driveled",
466
+ "drivelling": "driveling",
467
+ "duelled": "dueled",
468
+ "duelling": "dueling",
469
+ "economise": "economize",
470
+ "economised": "economized",
471
+ "economises": "economizes",
472
+ "economising": "economizing",
473
+ "editorialise": "editorialize",
474
+ "editorialised": "editorialized",
475
+ "editorialises": "editorializes",
476
+ "editorialising": "editorializing",
477
+ "edoema": "edema",
478
+ "empathise": "empathize",
479
+ "empathised": "empathized",
480
+ "empathises": "empathizes",
481
+ "empathising": "empathizing",
482
+ "emphasise": "emphasize",
483
+ "emphasised": "emphasized",
484
+ "emphasises": "emphasizes",
485
+ "emphasising": "emphasizing",
486
+ "enamelled": "enameled",
487
+ "enamelling": "enameling",
488
+ "enamoured": "enamored",
489
+ "encyclopaedia": "encyclopedia",
490
+ "encyclopaedias": "encyclopedias",
491
+ "encyclopaedic": "encyclopedic",
492
+ "endeavour": "endeavor",
493
+ "endeavoured": "endeavored",
494
+ "endeavouring": "endeavoring",
495
+ "endeavours": "endeavors",
496
+ "energise": "energize",
497
+ "energised": "energized",
498
+ "energises": "energizes",
499
+ "energising": "energizing",
500
+ "enrol": "enroll",
501
+ "enrols": "enrolls",
502
+ "enthral": "enthrall",
503
+ "enthrals": "enthralls",
504
+ "epaulette": "epaulet",
505
+ "epaulettes": "epaulets",
506
+ "epicentre": "epicenter",
507
+ "epicentres": "epicenters",
508
+ "epilogue": "epilog",
509
+ "epilogues": "epilogs",
510
+ "epitomise": "epitomize",
511
+ "epitomised": "epitomized",
512
+ "epitomises": "epitomizes",
513
+ "epitomising": "epitomizing",
514
+ "equalisation": "equalization",
515
+ "equalise": "equalize",
516
+ "equalised": "equalized",
517
+ "equaliser": "equalizer",
518
+ "equalisers": "equalizers",
519
+ "equalises": "equalizes",
520
+ "equalising": "equalizing",
521
+ "eulogise": "eulogize",
522
+ "eulogised": "eulogized",
523
+ "eulogises": "eulogizes",
524
+ "eulogising": "eulogizing",
525
+ "evangelise": "evangelize",
526
+ "evangelised": "evangelized",
527
+ "evangelises": "evangelizes",
528
+ "evangelising": "evangelizing",
529
+ "exorcise": "exorcize",
530
+ "exorcised": "exorcized",
531
+ "exorcises": "exorcizes",
532
+ "exorcising": "exorcizing",
533
+ "extemporisation": "extemporization",
534
+ "extemporise": "extemporize",
535
+ "extemporised": "extemporized",
536
+ "extemporises": "extemporizes",
537
+ "extemporising": "extemporizing",
538
+ "externalisation": "externalization",
539
+ "externalisations": "externalizations",
540
+ "externalise": "externalize",
541
+ "externalised": "externalized",
542
+ "externalises": "externalizes",
543
+ "externalising": "externalizing",
544
+ "factorise": "factorize",
545
+ "factorised": "factorized",
546
+ "factorises": "factorizes",
547
+ "factorising": "factorizing",
548
+ "faecal": "fecal",
549
+ "faeces": "feces",
550
+ "familiarisation": "familiarization",
551
+ "familiarise": "familiarize",
552
+ "familiarised": "familiarized",
553
+ "familiarises": "familiarizes",
554
+ "familiarising": "familiarizing",
555
+ "fantasise": "fantasize",
556
+ "fantasised": "fantasized",
557
+ "fantasises": "fantasizes",
558
+ "fantasising": "fantasizing",
559
+ "favour": "favor",
560
+ "favourable": "favorable",
561
+ "favourably": "favorably",
562
+ "favoured": "favored",
563
+ "favouring": "favoring",
564
+ "favourite": "favorite",
565
+ "favourites": "favorites",
566
+ "favouritism": "favoritism",
567
+ "favours": "favors",
568
+ "feminise": "feminize",
569
+ "feminised": "feminized",
570
+ "feminises": "feminizes",
571
+ "feminising": "feminizing",
572
+ "fertilisation": "fertilization",
573
+ "fertilise": "fertilize",
574
+ "fertilised": "fertilized",
575
+ "fertiliser": "fertilizer",
576
+ "fertilisers": "fertilizers",
577
+ "fertilises": "fertilizes",
578
+ "fertilising": "fertilizing",
579
+ "fervour": "fervor",
580
+ "fibre": "fiber",
581
+ "fibreglass": "fiberglass",
582
+ "fibres": "fibers",
583
+ "fictionalisation": "fictionalization",
584
+ "fictionalisations": "fictionalizations",
585
+ "fictionalise": "fictionalize",
586
+ "fictionalised": "fictionalized",
587
+ "fictionalises": "fictionalizes",
588
+ "fictionalising": "fictionalizing",
589
+ "fillet": "filet",
590
+ "filleted": "fileted",
591
+ "filleting": "fileting",
592
+ "fillets": "filets",
593
+ "finalisation": "finalization",
594
+ "finalise": "finalize",
595
+ "finalised": "finalized",
596
+ "finalises": "finalizes",
597
+ "finalising": "finalizing",
598
+ "flautist": "flutist",
599
+ "flautists": "flutists",
600
+ "flavour": "flavor",
601
+ "flavoured": "flavored",
602
+ "flavouring": "flavoring",
603
+ "flavourings": "flavorings",
604
+ "flavourless": "flavorless",
605
+ "flavours": "flavors",
606
+ "flavoursome": "flavorsome",
607
+ "flyer / flier": "flier / flyer",
608
+ "foetal": "fetal",
609
+ "foetid": "fetid",
610
+ "foetus": "fetus",
611
+ "foetuses": "fetuses",
612
+ "formalisation": "formalization",
613
+ "formalise": "formalize",
614
+ "formalised": "formalized",
615
+ "formalises": "formalizes",
616
+ "formalising": "formalizing",
617
+ "fossilisation": "fossilization",
618
+ "fossilise": "fossilize",
619
+ "fossilised": "fossilized",
620
+ "fossilises": "fossilizes",
621
+ "fossilising": "fossilizing",
622
+ "fraternisation": "fraternization",
623
+ "fraternise": "fraternize",
624
+ "fraternised": "fraternized",
625
+ "fraternises": "fraternizes",
626
+ "fraternising": "fraternizing",
627
+ "fulfil": "fulfill",
628
+ "fulfilment": "fulfillment",
629
+ "fulfils": "fulfills",
630
+ "funnelled": "funneled",
631
+ "funnelling": "funneling",
632
+ "gage": "gauge",
633
+ "gaged": "gauged",
634
+ "gages": "gauges",
635
+ "gaging": "gauging",
636
+ "galvanise": "galvanize",
637
+ "galvanised": "galvanized",
638
+ "galvanises": "galvanizes",
639
+ "galvanising": "galvanizing",
640
+ "gambolled": "gamboled",
641
+ "gambolling": "gamboling",
642
+ "gaol": "jail",
643
+ "gaolbird": "jailbird",
644
+ "gaolbirds": "jailbirds",
645
+ "gaolbreak": "jailbreak",
646
+ "gaolbreaks": "jailbreaks",
647
+ "gaoled": "jailed",
648
+ "gaoler": "jailer",
649
+ "gaolers": "jailers",
650
+ "gaoling": "jailing",
651
+ "gaols": "jails",
652
+ "gasses": "gases",
653
+ "generalisation": "generalization",
654
+ "generalisations": "generalizations",
655
+ "generalise": "generalize",
656
+ "generalised": "generalized",
657
+ "generalises": "generalizes",
658
+ "generalising": "generalizing",
659
+ "ghettoise": "ghettoize",
660
+ "ghettoised": "ghettoized",
661
+ "ghettoises": "ghettoizes",
662
+ "ghettoising": "ghettoizing",
663
+ "gipsies": "gypsies",
664
+ "glamor": "glamour",
665
+ "glamorise": "glamorize",
666
+ "glamorised": "glamorized",
667
+ "glamorises": "glamorizes",
668
+ "glamorising": "glamorizing",
669
+ "globalisation": "globalization",
670
+ "globalise": "globalize",
671
+ "globalised": "globalized",
672
+ "globalises": "globalizes",
673
+ "globalising": "globalizing",
674
+ "glueing": "gluing",
675
+ "goitre": "goiter",
676
+ "goitres": "goiters",
677
+ "gonorrhoea": "gonorrhea",
678
+ "gramme": "gram",
679
+ "grammes": "grams",
680
+ "gravelled": "graveled",
681
+ "grey": "gray",
682
+ "greyed": "grayed",
683
+ "greying": "graying",
684
+ "greyish": "grayish",
685
+ "greyness": "grayness",
686
+ "greys": "grays",
687
+ "grovelled": "groveled",
688
+ "grovelling": "groveling",
689
+ "groyne": "groin",
690
+ "groynes": "groins",
691
+ "gruelling": "grueling",
692
+ "gruellingly": "gruelingly",
693
+ "gryphon": "griffin",
694
+ "gryphons": "griffins",
695
+ "gynaecological": "gynecological",
696
+ "gynaecologist": "gynecologist",
697
+ "gynaecologists": "gynecologists",
698
+ "gynaecology": "gynecology",
699
+ "haematological": "hematological",
700
+ "haematologist": "hematologist",
701
+ "haematologists": "hematologists",
702
+ "haematology": "hematology",
703
+ "haemoglobin": "hemoglobin",
704
+ "haemophilia": "hemophilia",
705
+ "haemophiliac": "hemophiliac",
706
+ "haemophiliacs": "hemophiliacs",
707
+ "haemorrhage": "hemorrhage",
708
+ "haemorrhaged": "hemorrhaged",
709
+ "haemorrhages": "hemorrhages",
710
+ "haemorrhaging": "hemorrhaging",
711
+ "haemorrhoids": "hemorrhoids",
712
+ "harbour": "harbor",
713
+ "harboured": "harbored",
714
+ "harbouring": "harboring",
715
+ "harbours": "harbors",
716
+ "harmonisation": "harmonization",
717
+ "harmonise": "harmonize",
718
+ "harmonised": "harmonized",
719
+ "harmonises": "harmonizes",
720
+ "harmonising": "harmonizing",
721
+ "homoeopath": "homeopath",
722
+ "homoeopathic": "homeopathic",
723
+ "homoeopaths": "homeopaths",
724
+ "homoeopathy": "homeopathy",
725
+ "homogenise": "homogenize",
726
+ "homogenised": "homogenized",
727
+ "homogenises": "homogenizes",
728
+ "homogenising": "homogenizing",
729
+ "honour": "honor",
730
+ "honourable": "honorable",
731
+ "honourably": "honorably",
732
+ "honoured": "honored",
733
+ "honouring": "honoring",
734
+ "honours": "honors",
735
+ "hospitalisation": "hospitalization",
736
+ "hospitalise": "hospitalize",
737
+ "hospitalised": "hospitalized",
738
+ "hospitalises": "hospitalizes",
739
+ "hospitalising": "hospitalizing",
740
+ "humanise": "humanize",
741
+ "humanised": "humanized",
742
+ "humanises": "humanizes",
743
+ "humanising": "humanizing",
744
+ "humour": "humor",
745
+ "humoured": "humored",
746
+ "humouring": "humoring",
747
+ "humourless": "humorless",
748
+ "humours": "humors",
749
+ "hybridise": "hybridize",
750
+ "hybridised": "hybridized",
751
+ "hybridises": "hybridizes",
752
+ "hybridising": "hybridizing",
753
+ "hypnotise": "hypnotize",
754
+ "hypnotised": "hypnotized",
755
+ "hypnotises": "hypnotizes",
756
+ "hypnotising": "hypnotizing",
757
+ "hypothesise": "hypothesize",
758
+ "hypothesised": "hypothesized",
759
+ "hypothesises": "hypothesizes",
760
+ "hypothesising": "hypothesizing",
761
+ "idealisation": "idealization",
762
+ "idealise": "idealize",
763
+ "idealised": "idealized",
764
+ "idealises": "idealizes",
765
+ "idealising": "idealizing",
766
+ "idolise": "idolize",
767
+ "idolised": "idolized",
768
+ "idolises": "idolizes",
769
+ "idolising": "idolizing",
770
+ "immobilisation": "immobilization",
771
+ "immobilise": "immobilize",
772
+ "immobilised": "immobilized",
773
+ "immobiliser": "immobilizer",
774
+ "immobilisers": "immobilizers",
775
+ "immobilises": "immobilizes",
776
+ "immobilising": "immobilizing",
777
+ "immortalise": "immortalize",
778
+ "immortalised": "immortalized",
779
+ "immortalises": "immortalizes",
780
+ "immortalising": "immortalizing",
781
+ "immunisation": "immunization",
782
+ "immunise": "immunize",
783
+ "immunised": "immunized",
784
+ "immunises": "immunizes",
785
+ "immunising": "immunizing",
786
+ "impanelled": "impaneled",
787
+ "impanelling": "impaneling",
788
+ "imperilled": "imperiled",
789
+ "imperilling": "imperiling",
790
+ "individualise": "individualize",
791
+ "individualised": "individualized",
792
+ "individualises": "individualizes",
793
+ "individualising": "individualizing",
794
+ "industrialise": "industrialize",
795
+ "industrialised": "industrialized",
796
+ "industrialises": "industrializes",
797
+ "industrialising": "industrializing",
798
+ "inflexion": "inflection",
799
+ "inflexions": "inflections",
800
+ "initialise": "initialize",
801
+ "initialised": "initialized",
802
+ "initialises": "initializes",
803
+ "initialising": "initializing",
804
+ "initialled": "initialed",
805
+ "initialling": "initialing",
806
+ "instal": "install",
807
+ "instalment": "installment",
808
+ "instalments": "installments",
809
+ "instals": "installs",
810
+ "instil": "instill",
811
+ "instils": "instills",
812
+ "institutionalisation": "institutionalization",
813
+ "institutionalise": "institutionalize",
814
+ "institutionalised": "institutionalized",
815
+ "institutionalises": "institutionalizes",
816
+ "institutionalising": "institutionalizing",
817
+ "intellectualise": "intellectualize",
818
+ "intellectualised": "intellectualized",
819
+ "intellectualises": "intellectualizes",
820
+ "intellectualising": "intellectualizing",
821
+ "internalisation": "internalization",
822
+ "internalise": "internalize",
823
+ "internalised": "internalized",
824
+ "internalises": "internalizes",
825
+ "internalising": "internalizing",
826
+ "internationalisation": "internationalization",
827
+ "internationalise": "internationalize",
828
+ "internationalised": "internationalized",
829
+ "internationalises": "internationalizes",
830
+ "internationalising": "internationalizing",
831
+ "ionisation": "ionization",
832
+ "ionise": "ionize",
833
+ "ionised": "ionized",
834
+ "ioniser": "ionizer",
835
+ "ionisers": "ionizers",
836
+ "ionises": "ionizes",
837
+ "ionising": "ionizing",
838
+ "italicise": "italicize",
839
+ "italicised": "italicized",
840
+ "italicises": "italicizes",
841
+ "italicising": "italicizing",
842
+ "itemise": "itemize",
843
+ "itemised": "itemized",
844
+ "itemises": "itemizes",
845
+ "itemising": "itemizing",
846
+ "jeopardise": "jeopardize",
847
+ "jeopardised": "jeopardized",
848
+ "jeopardises": "jeopardizes",
849
+ "jeopardising": "jeopardizing",
850
+ "jewelled": "jeweled",
851
+ "jeweller": "jeweler",
852
+ "jewellers": "jewelers",
853
+ "jewellery": "jewelry",
854
+ "judgement": "judgment",
855
+ "kilogramme": "kilogram",
856
+ "kilogrammes": "kilograms",
857
+ "kilometre": "kilometer",
858
+ "kilometres": "kilometers",
859
+ "labelled": "labeled",
860
+ "labelling": "labeling",
861
+ "labour": "labor",
862
+ "laboured": "labored",
863
+ "labourer": "laborer",
864
+ "labourers": "laborers",
865
+ "labouring": "laboring",
866
+ "labours": "labors",
867
+ "lacklustre": "lackluster",
868
+ "legalisation": "legalization",
869
+ "legalise": "legalize",
870
+ "legalised": "legalized",
871
+ "legalises": "legalizes",
872
+ "legalising": "legalizing",
873
+ "legitimise": "legitimize",
874
+ "legitimised": "legitimized",
875
+ "legitimises": "legitimizes",
876
+ "legitimising": "legitimizing",
877
+ "leukaemia": "leukemia",
878
+ "levelled": "leveled",
879
+ "leveller": "leveler",
880
+ "levellers": "levelers",
881
+ "levelling": "leveling",
882
+ "libelled": "libeled",
883
+ "libelling": "libeling",
884
+ "libellous": "libelous",
885
+ "liberalisation": "liberalization",
886
+ "liberalise": "liberalize",
887
+ "liberalised": "liberalized",
888
+ "liberalises": "liberalizes",
889
+ "liberalising": "liberalizing",
890
+ "licence": "license",
891
+ "licenced": "licensed",
892
+ "licences": "licenses",
893
+ "licencing": "licensing",
894
+ "likeable": "likable",
895
+ "lionisation": "lionization",
896
+ "lionise": "lionize",
897
+ "lionised": "lionized",
898
+ "lionises": "lionizes",
899
+ "lionising": "lionizing",
900
+ "liquidise": "liquidize",
901
+ "liquidised": "liquidized",
902
+ "liquidiser": "liquidizer",
903
+ "liquidisers": "liquidizers",
904
+ "liquidises": "liquidizes",
905
+ "liquidising": "liquidizing",
906
+ "litre": "liter",
907
+ "litres": "liters",
908
+ "localise": "localize",
909
+ "localised": "localized",
910
+ "localises": "localizes",
911
+ "localising": "localizing",
912
+ "louvre": "louver",
913
+ "louvred": "louvered",
914
+ "louvres": "louvers",
915
+ "lustre": "luster",
916
+ "magnetise": "magnetize",
917
+ "magnetised": "magnetized",
918
+ "magnetises": "magnetizes",
919
+ "magnetising": "magnetizing",
920
+ "manoeuvrability": "maneuverability",
921
+ "manoeuvrable": "maneuverable",
922
+ "manoeuvre": "maneuver",
923
+ "manoeuvred": "maneuvered",
924
+ "manoeuvres": "maneuvers",
925
+ "manoeuvring": "maneuvering",
926
+ "manoeuvrings": "maneuverings",
927
+ "marginalisation": "marginalization",
928
+ "marginalise": "marginalize",
929
+ "marginalised": "marginalized",
930
+ "marginalises": "marginalizes",
931
+ "marginalising": "marginalizing",
932
+ "marshalled": "marshaled",
933
+ "marshalling": "marshaling",
934
+ "marvelled": "marveled",
935
+ "marvelling": "marveling",
936
+ "marvellous": "marvelous",
937
+ "marvellously": "marvelously",
938
+ "materialisation": "materialization",
939
+ "materialise": "materialize",
940
+ "materialised": "materialized",
941
+ "materialises": "materializes",
942
+ "materialising": "materializing",
943
+ "maximisation": "maximization",
944
+ "maximise": "maximize",
945
+ "maximised": "maximized",
946
+ "maximises": "maximizes",
947
+ "maximising": "maximizing",
948
+ "meagre": "meager",
949
+ "mechanisation": "mechanization",
950
+ "mechanise": "mechanize",
951
+ "mechanised": "mechanized",
952
+ "mechanises": "mechanizes",
953
+ "mechanising": "mechanizing",
954
+ "mediaeval": "medieval",
955
+ "memorialise": "memorialize",
956
+ "memorialised": "memorialized",
957
+ "memorialises": "memorializes",
958
+ "memorialising": "memorializing",
959
+ "memorise": "memorize",
960
+ "memorised": "memorized",
961
+ "memorises": "memorizes",
962
+ "memorising": "memorizing",
963
+ "mesmerise": "mesmerize",
964
+ "mesmerised": "mesmerized",
965
+ "mesmerises": "mesmerizes",
966
+ "mesmerising": "mesmerizing",
967
+ "metabolise": "metabolize",
968
+ "metabolised": "metabolized",
969
+ "metabolises": "metabolizes",
970
+ "metabolising": "metabolizing",
971
+ "metre": "meter",
972
+ "metres": "meters",
973
+ "mhm": "hmm",
974
+ "micrometre": "micrometer",
975
+ "micrometres": "micrometers",
976
+ "militarise": "militarize",
977
+ "militarised": "militarized",
978
+ "militarises": "militarizes",
979
+ "militarising": "militarizing",
980
+ "milligramme": "milligram",
981
+ "milligrammes": "milligrams",
982
+ "millilitre": "milliliter",
983
+ "millilitres": "milliliters",
984
+ "millimetre": "millimeter",
985
+ "millimetres": "millimeters",
986
+ "miniaturisation": "miniaturization",
987
+ "miniaturise": "miniaturize",
988
+ "miniaturised": "miniaturized",
989
+ "miniaturises": "miniaturizes",
990
+ "miniaturising": "miniaturizing",
991
+ "minibusses": "minibuses",
992
+ "minimise": "minimize",
993
+ "minimised": "minimized",
994
+ "minimises": "minimizes",
995
+ "minimising": "minimizing",
996
+ "misbehaviour": "misbehavior",
997
+ "misdemeanour": "misdemeanor",
998
+ "misdemeanours": "misdemeanors",
999
+ "misspelt": "misspelled",
1000
+ "mitre": "miter",
1001
+ "mitres": "miters",
1002
+ "mm": "hmm",
1003
+ "mmm": "hmm",
1004
+ "mobilisation": "mobilization",
1005
+ "mobilise": "mobilize",
1006
+ "mobilised": "mobilized",
1007
+ "mobilises": "mobilizes",
1008
+ "mobilising": "mobilizing",
1009
+ "modelled": "modeled",
1010
+ "modeller": "modeler",
1011
+ "modellers": "modelers",
1012
+ "modelling": "modeling",
1013
+ "modernise": "modernize",
1014
+ "modernised": "modernized",
1015
+ "modernises": "modernizes",
1016
+ "modernising": "modernizing",
1017
+ "moisturise": "moisturize",
1018
+ "moisturised": "moisturized",
1019
+ "moisturiser": "moisturizer",
1020
+ "moisturisers": "moisturizers",
1021
+ "moisturises": "moisturizes",
1022
+ "moisturising": "moisturizing",
1023
+ "monologue": "monolog",
1024
+ "monologues": "monologs",
1025
+ "monopolisation": "monopolization",
1026
+ "monopolise": "monopolize",
1027
+ "monopolised": "monopolized",
1028
+ "monopolises": "monopolizes",
1029
+ "monopolising": "monopolizing",
1030
+ "moralise": "moralize",
1031
+ "moralised": "moralized",
1032
+ "moralises": "moralizes",
1033
+ "moralising": "moralizing",
1034
+ "motorised": "motorized",
1035
+ "mould": "mold",
1036
+ "moulded": "molded",
1037
+ "moulder": "molder",
1038
+ "mouldered": "moldered",
1039
+ "mouldering": "moldering",
1040
+ "moulders": "molders",
1041
+ "mouldier": "moldier",
1042
+ "mouldiest": "moldiest",
1043
+ "moulding": "molding",
1044
+ "mouldings": "moldings",
1045
+ "moulds": "molds",
1046
+ "mouldy": "moldy",
1047
+ "moult": "molt",
1048
+ "moulted": "molted",
1049
+ "moulting": "molting",
1050
+ "moults": "molts",
1051
+ "moustache": "mustache",
1052
+ "moustached": "mustached",
1053
+ "moustaches": "mustaches",
1054
+ "moustachioed": "mustachioed",
1055
+ "multicoloured": "multicolored",
1056
+ "nationalisation": "nationalization",
1057
+ "nationalisations": "nationalizations",
1058
+ "nationalise": "nationalize",
1059
+ "nationalised": "nationalized",
1060
+ "nationalises": "nationalizes",
1061
+ "nationalising": "nationalizing",
1062
+ "naturalisation": "naturalization",
1063
+ "naturalise": "naturalize",
1064
+ "naturalised": "naturalized",
1065
+ "naturalises": "naturalizes",
1066
+ "naturalising": "naturalizing",
1067
+ "neighbour": "neighbor",
1068
+ "neighbourhood": "neighborhood",
1069
+ "neighbourhoods": "neighborhoods",
1070
+ "neighbouring": "neighboring",
1071
+ "neighbourliness": "neighborliness",
1072
+ "neighbourly": "neighborly",
1073
+ "neighbours": "neighbors",
1074
+ "neutralisation": "neutralization",
1075
+ "neutralise": "neutralize",
1076
+ "neutralised": "neutralized",
1077
+ "neutralises": "neutralizes",
1078
+ "neutralising": "neutralizing",
1079
+ "normalisation": "normalization",
1080
+ "normalise": "normalize",
1081
+ "normalised": "normalized",
1082
+ "normalises": "normalizes",
1083
+ "normalising": "normalizing",
1084
+ "odour": "odor",
1085
+ "odourless": "odorless",
1086
+ "odours": "odors",
1087
+ "oesophagus": "esophagus",
1088
+ "oesophaguses": "esophaguses",
1089
+ "oestrogen": "estrogen",
1090
+ "offence": "offense",
1091
+ "offences": "offenses",
1092
+ "omelette": "omelet",
1093
+ "omelettes": "omelets",
1094
+ "optimise": "optimize",
1095
+ "optimised": "optimized",
1096
+ "optimises": "optimizes",
1097
+ "optimising": "optimizing",
1098
+ "organisation": "organization",
1099
+ "organisational": "organizational",
1100
+ "organisations": "organizations",
1101
+ "organise": "organize",
1102
+ "organised": "organized",
1103
+ "organiser": "organizer",
1104
+ "organisers": "organizers",
1105
+ "organises": "organizes",
1106
+ "organising": "organizing",
1107
+ "orthopaedic": "orthopedic",
1108
+ "orthopaedics": "orthopedics",
1109
+ "ostracise": "ostracize",
1110
+ "ostracised": "ostracized",
1111
+ "ostracises": "ostracizes",
1112
+ "ostracising": "ostracizing",
1113
+ "outmanoeuvre": "outmaneuver",
1114
+ "outmanoeuvred": "outmaneuvered",
1115
+ "outmanoeuvres": "outmaneuvers",
1116
+ "outmanoeuvring": "outmaneuvering",
1117
+ "overemphasise": "overemphasize",
1118
+ "overemphasised": "overemphasized",
1119
+ "overemphasises": "overemphasizes",
1120
+ "overemphasising": "overemphasizing",
1121
+ "oxidisation": "oxidization",
1122
+ "oxidise": "oxidize",
1123
+ "oxidised": "oxidized",
1124
+ "oxidises": "oxidizes",
1125
+ "oxidising": "oxidizing",
1126
+ "paederast": "pederast",
1127
+ "paederasts": "pederasts",
1128
+ "paediatric": "pediatric",
1129
+ "paediatrician": "pediatrician",
1130
+ "paediatricians": "pediatricians",
1131
+ "paediatrics": "pediatrics",
1132
+ "paedophile": "pedophile",
1133
+ "paedophiles": "pedophiles",
1134
+ "paedophilia": "pedophilia",
1135
+ "palaeolithic": "paleolithic",
1136
+ "palaeontologist": "paleontologist",
1137
+ "palaeontologists": "paleontologists",
1138
+ "palaeontology": "paleontology",
1139
+ "panelled": "paneled",
1140
+ "panelling": "paneling",
1141
+ "panellist": "panelist",
1142
+ "panellists": "panelists",
1143
+ "paralyse": "paralyze",
1144
+ "paralysed": "paralyzed",
1145
+ "paralyses": "paralyzes",
1146
+ "paralysing": "paralyzing",
1147
+ "parcelled": "parceled",
1148
+ "parcelling": "parceling",
1149
+ "parlour": "parlor",
1150
+ "parlours": "parlors",
1151
+ "particularise": "particularize",
1152
+ "particularised": "particularized",
1153
+ "particularises": "particularizes",
1154
+ "particularising": "particularizing",
1155
+ "passivisation": "passivization",
1156
+ "passivise": "passivize",
1157
+ "passivised": "passivized",
1158
+ "passivises": "passivizes",
1159
+ "passivising": "passivizing",
1160
+ "pasteurisation": "pasteurization",
1161
+ "pasteurise": "pasteurize",
1162
+ "pasteurised": "pasteurized",
1163
+ "pasteurises": "pasteurizes",
1164
+ "pasteurising": "pasteurizing",
1165
+ "patronise": "patronize",
1166
+ "patronised": "patronized",
1167
+ "patronises": "patronizes",
1168
+ "patronising": "patronizing",
1169
+ "patronisingly": "patronizingly",
1170
+ "pedalled": "pedaled",
1171
+ "pedalling": "pedaling",
1172
+ "pedestrianisation": "pedestrianization",
1173
+ "pedestrianise": "pedestrianize",
1174
+ "pedestrianised": "pedestrianized",
1175
+ "pedestrianises": "pedestrianizes",
1176
+ "pedestrianising": "pedestrianizing",
1177
+ "penalise": "penalize",
1178
+ "penalised": "penalized",
1179
+ "penalises": "penalizes",
1180
+ "penalising": "penalizing",
1181
+ "pencilled": "penciled",
1182
+ "pencilling": "penciling",
1183
+ "personalise": "personalize",
1184
+ "personalised": "personalized",
1185
+ "personalises": "personalizes",
1186
+ "personalising": "personalizing",
1187
+ "pharmacopoeia": "pharmacopeia",
1188
+ "pharmacopoeias": "pharmacopeias",
1189
+ "philosophise": "philosophize",
1190
+ "philosophised": "philosophized",
1191
+ "philosophises": "philosophizes",
1192
+ "philosophising": "philosophizing",
1193
+ "philtre": "filter",
1194
+ "philtres": "filters",
1195
+ "phoney": "phony",
1196
+ "plagiarise": "plagiarize",
1197
+ "plagiarised": "plagiarized",
1198
+ "plagiarises": "plagiarizes",
1199
+ "plagiarising": "plagiarizing",
1200
+ "plough": "plow",
1201
+ "ploughed": "plowed",
1202
+ "ploughing": "plowing",
1203
+ "ploughman": "plowman",
1204
+ "ploughmen": "plowmen",
1205
+ "ploughs": "plows",
1206
+ "ploughshare": "plowshare",
1207
+ "ploughshares": "plowshares",
1208
+ "polarisation": "polarization",
1209
+ "polarise": "polarize",
1210
+ "polarised": "polarized",
1211
+ "polarises": "polarizes",
1212
+ "polarising": "polarizing",
1213
+ "politicisation": "politicization",
1214
+ "politicise": "politicize",
1215
+ "politicised": "politicized",
1216
+ "politicises": "politicizes",
1217
+ "politicising": "politicizing",
1218
+ "popularisation": "popularization",
1219
+ "popularise": "popularize",
1220
+ "popularised": "popularized",
1221
+ "popularises": "popularizes",
1222
+ "popularising": "popularizing",
1223
+ "pouffe": "pouf",
1224
+ "pouffes": "poufs",
1225
+ "practise": "practice",
1226
+ "practised": "practiced",
1227
+ "practises": "practices",
1228
+ "practising": "practicing",
1229
+ "praesidium": "presidium",
1230
+ "praesidiums": "presidiums",
1231
+ "pressurisation": "pressurization",
1232
+ "pressurise": "pressurize",
1233
+ "pressurised": "pressurized",
1234
+ "pressurises": "pressurizes",
1235
+ "pressurising": "pressurizing",
1236
+ "pretence": "pretense",
1237
+ "pretences": "pretenses",
1238
+ "primaeval": "primeval",
1239
+ "prioritisation": "prioritization",
1240
+ "prioritise": "prioritize",
1241
+ "prioritised": "prioritized",
1242
+ "prioritises": "prioritizes",
1243
+ "prioritising": "prioritizing",
1244
+ "privatisation": "privatization",
1245
+ "privatisations": "privatizations",
1246
+ "privatise": "privatize",
1247
+ "privatised": "privatized",
1248
+ "privatises": "privatizes",
1249
+ "privatising": "privatizing",
1250
+ "professionalisation": "professionalization",
1251
+ "professionalise": "professionalize",
1252
+ "professionalised": "professionalized",
1253
+ "professionalises": "professionalizes",
1254
+ "professionalising": "professionalizing",
1255
+ "programme": "program",
1256
+ "programmes": "programs",
1257
+ "prologue": "prolog",
1258
+ "prologues": "prologs",
1259
+ "propagandise": "propagandize",
1260
+ "propagandised": "propagandized",
1261
+ "propagandises": "propagandizes",
1262
+ "propagandising": "propagandizing",
1263
+ "proselytise": "proselytize",
1264
+ "proselytised": "proselytized",
1265
+ "proselytiser": "proselytizer",
1266
+ "proselytisers": "proselytizers",
1267
+ "proselytises": "proselytizes",
1268
+ "proselytising": "proselytizing",
1269
+ "psychoanalyse": "psychoanalyze",
1270
+ "psychoanalysed": "psychoanalyzed",
1271
+ "psychoanalyses": "psychoanalyzes",
1272
+ "psychoanalysing": "psychoanalyzing",
1273
+ "publicise": "publicize",
1274
+ "publicised": "publicized",
1275
+ "publicises": "publicizes",
1276
+ "publicising": "publicizing",
1277
+ "pulverisation": "pulverization",
1278
+ "pulverise": "pulverize",
1279
+ "pulverised": "pulverized",
1280
+ "pulverises": "pulverizes",
1281
+ "pulverising": "pulverizing",
1282
+ "pummelled": "pummel",
1283
+ "pummelling": "pummeled",
1284
+ "pyjama": "pajama",
1285
+ "pyjamas": "pajamas",
1286
+ "pzazz": "pizzazz",
1287
+ "quarrelled": "quarreled",
1288
+ "quarrelling": "quarreling",
1289
+ "radicalise": "radicalize",
1290
+ "radicalised": "radicalized",
1291
+ "radicalises": "radicalizes",
1292
+ "radicalising": "radicalizing",
1293
+ "rancour": "rancor",
1294
+ "randomise": "randomize",
1295
+ "randomised": "randomized",
1296
+ "randomises": "randomizes",
1297
+ "randomising": "randomizing",
1298
+ "rationalisation": "rationalization",
1299
+ "rationalisations": "rationalizations",
1300
+ "rationalise": "rationalize",
1301
+ "rationalised": "rationalized",
1302
+ "rationalises": "rationalizes",
1303
+ "rationalising": "rationalizing",
1304
+ "ravelled": "raveled",
1305
+ "ravelling": "raveling",
1306
+ "realisable": "realizable",
1307
+ "realisation": "realization",
1308
+ "realisations": "realizations",
1309
+ "realise": "realize",
1310
+ "realised": "realized",
1311
+ "realises": "realizes",
1312
+ "realising": "realizing",
1313
+ "recognisable": "recognizable",
1314
+ "recognisably": "recognizably",
1315
+ "recognisance": "recognizance",
1316
+ "recognise": "recognize",
1317
+ "recognised": "recognized",
1318
+ "recognises": "recognizes",
1319
+ "recognising": "recognizing",
1320
+ "reconnoitre": "reconnoiter",
1321
+ "reconnoitred": "reconnoitered",
1322
+ "reconnoitres": "reconnoiters",
1323
+ "reconnoitring": "reconnoitering",
1324
+ "refuelled": "refueled",
1325
+ "refuelling": "refueling",
1326
+ "regularisation": "regularization",
1327
+ "regularise": "regularize",
1328
+ "regularised": "regularized",
1329
+ "regularises": "regularizes",
1330
+ "regularising": "regularizing",
1331
+ "remodelled": "remodeled",
1332
+ "remodelling": "remodeling",
1333
+ "remould": "remold",
1334
+ "remoulded": "remolded",
1335
+ "remoulding": "remolding",
1336
+ "remoulds": "remolds",
1337
+ "reorganisation": "reorganization",
1338
+ "reorganisations": "reorganizations",
1339
+ "reorganise": "reorganize",
1340
+ "reorganised": "reorganized",
1341
+ "reorganises": "reorganizes",
1342
+ "reorganising": "reorganizing",
1343
+ "revelled": "reveled",
1344
+ "reveller": "reveler",
1345
+ "revellers": "revelers",
1346
+ "revelling": "reveling",
1347
+ "revitalise": "revitalize",
1348
+ "revitalised": "revitalized",
1349
+ "revitalises": "revitalizes",
1350
+ "revitalising": "revitalizing",
1351
+ "revolutionise": "revolutionize",
1352
+ "revolutionised": "revolutionized",
1353
+ "revolutionises": "revolutionizes",
1354
+ "revolutionising": "revolutionizing",
1355
+ "rhapsodise": "rhapsodize",
1356
+ "rhapsodised": "rhapsodized",
1357
+ "rhapsodises": "rhapsodizes",
1358
+ "rhapsodising": "rhapsodizing",
1359
+ "rigour": "rigor",
1360
+ "rigours": "rigors",
1361
+ "ritualised": "ritualized",
1362
+ "rivalled": "rivaled",
1363
+ "rivalling": "rivaling",
1364
+ "romanticise": "romanticize",
1365
+ "romanticised": "romanticized",
1366
+ "romanticises": "romanticizes",
1367
+ "romanticising": "romanticizing",
1368
+ "rumour": "rumor",
1369
+ "rumoured": "rumored",
1370
+ "rumours": "rumors",
1371
+ "sabre": "saber",
1372
+ "sabres": "sabers",
1373
+ "saltpetre": "saltpeter",
1374
+ "sanitise": "sanitize",
1375
+ "sanitised": "sanitized",
1376
+ "sanitises": "sanitizes",
1377
+ "sanitising": "sanitizing",
1378
+ "satirise": "satirize",
1379
+ "satirised": "satirized",
1380
+ "satirises": "satirizes",
1381
+ "satirising": "satirizing",
1382
+ "saviour": "savior",
1383
+ "saviours": "saviors",
1384
+ "savour": "savor",
1385
+ "savoured": "savored",
1386
+ "savouries": "savories",
1387
+ "savouring": "savoring",
1388
+ "savours": "savors",
1389
+ "savoury": "savory",
1390
+ "scandalise": "scandalize",
1391
+ "scandalised": "scandalized",
1392
+ "scandalises": "scandalizes",
1393
+ "scandalising": "scandalizing",
1394
+ "sceptic": "skeptic",
1395
+ "sceptical": "skeptical",
1396
+ "sceptically": "skeptically",
1397
+ "scepticism": "skepticism",
1398
+ "sceptics": "skeptics",
1399
+ "sceptre": "scepter",
1400
+ "sceptres": "scepters",
1401
+ "scrutinise": "scrutinize",
1402
+ "scrutinised": "scrutinized",
1403
+ "scrutinises": "scrutinizes",
1404
+ "scrutinising": "scrutinizing",
1405
+ "secularisation": "secularization",
1406
+ "secularise": "secularize",
1407
+ "secularised": "secularized",
1408
+ "secularises": "secularizes",
1409
+ "secularising": "secularizing",
1410
+ "sensationalise": "sensationalize",
1411
+ "sensationalised": "sensationalized",
1412
+ "sensationalises": "sensationalizes",
1413
+ "sensationalising": "sensationalizing",
1414
+ "sensitise": "sensitize",
1415
+ "sensitised": "sensitized",
1416
+ "sensitises": "sensitizes",
1417
+ "sensitising": "sensitizing",
1418
+ "sentimentalise": "sentimentalize",
1419
+ "sentimentalised": "sentimentalized",
1420
+ "sentimentalises": "sentimentalizes",
1421
+ "sentimentalising": "sentimentalizing",
1422
+ "sepulchre": "sepulcher",
1423
+ "sepulchres": "sepulchers",
1424
+ "serialisation": "serialization",
1425
+ "serialisations": "serializations",
1426
+ "serialise": "serialize",
1427
+ "serialised": "serialized",
1428
+ "serialises": "serializes",
1429
+ "serialising": "serializing",
1430
+ "sermonise": "sermonize",
1431
+ "sermonised": "sermonized",
1432
+ "sermonises": "sermonizes",
1433
+ "sermonising": "sermonizing",
1434
+ "sheikh": "sheik",
1435
+ "shovelled": "shoveled",
1436
+ "shovelling": "shoveling",
1437
+ "shrivelled": "shriveled",
1438
+ "shrivelling": "shriveling",
1439
+ "signalise": "signalize",
1440
+ "signalised": "signalized",
1441
+ "signalises": "signalizes",
1442
+ "signalising": "signalizing",
1443
+ "signalled": "signaled",
1444
+ "signalling": "signaling",
1445
+ "smoulder": "smolder",
1446
+ "smouldered": "smoldered",
1447
+ "smouldering": "smoldering",
1448
+ "smoulders": "smolders",
1449
+ "snivelled": "sniveled",
1450
+ "snivelling": "sniveling",
1451
+ "snorkelled": "snorkeled",
1452
+ "snorkelling": "snorkeling",
1453
+ "snowplough": "snowplow",
1454
+ "snowploughs": "snowplow",
1455
+ "socialisation": "socialization",
1456
+ "socialise": "socialize",
1457
+ "socialised": "socialized",
1458
+ "socialises": "socializes",
1459
+ "socialising": "socializing",
1460
+ "sodomise": "sodomize",
1461
+ "sodomised": "sodomized",
1462
+ "sodomises": "sodomizes",
1463
+ "sodomising": "sodomizing",
1464
+ "solemnise": "solemnize",
1465
+ "solemnised": "solemnized",
1466
+ "solemnises": "solemnizes",
1467
+ "solemnising": "solemnizing",
1468
+ "sombre": "somber",
1469
+ "specialisation": "specialization",
1470
+ "specialisations": "specializations",
1471
+ "specialise": "specialize",
1472
+ "specialised": "specialized",
1473
+ "specialises": "specializes",
1474
+ "specialising": "specializing",
1475
+ "spectre": "specter",
1476
+ "spectres": "specters",
1477
+ "spiralled": "spiraled",
1478
+ "spiralling": "spiraling",
1479
+ "splendour": "splendor",
1480
+ "splendours": "splendors",
1481
+ "squirrelled": "squirreled",
1482
+ "squirrelling": "squirreling",
1483
+ "stabilisation": "stabilization",
1484
+ "stabilise": "stabilize",
1485
+ "stabilised": "stabilized",
1486
+ "stabiliser": "stabilizer",
1487
+ "stabilisers": "stabilizers",
1488
+ "stabilises": "stabilizes",
1489
+ "stabilising": "stabilizing",
1490
+ "standardisation": "standardization",
1491
+ "standardise": "standardize",
1492
+ "standardised": "standardized",
1493
+ "standardises": "standardizes",
1494
+ "standardising": "standardizing",
1495
+ "stencilled": "stenciled",
1496
+ "stencilling": "stenciling",
1497
+ "sterilisation": "sterilization",
1498
+ "sterilisations": "sterilizations",
1499
+ "sterilise": "sterilize",
1500
+ "sterilised": "sterilized",
1501
+ "steriliser": "sterilizer",
1502
+ "sterilisers": "sterilizers",
1503
+ "sterilises": "sterilizes",
1504
+ "sterilising": "sterilizing",
1505
+ "stigmatisation": "stigmatization",
1506
+ "stigmatise": "stigmatize",
1507
+ "stigmatised": "stigmatized",
1508
+ "stigmatises": "stigmatizes",
1509
+ "stigmatising": "stigmatizing",
1510
+ "storey": "story",
1511
+ "storeys": "stories",
1512
+ "subsidisation": "subsidization",
1513
+ "subsidise": "subsidize",
1514
+ "subsidised": "subsidized",
1515
+ "subsidiser": "subsidizer",
1516
+ "subsidisers": "subsidizers",
1517
+ "subsidises": "subsidizes",
1518
+ "subsidising": "subsidizing",
1519
+ "succour": "succor",
1520
+ "succoured": "succored",
1521
+ "succouring": "succoring",
1522
+ "succours": "succors",
1523
+ "sulphate": "sulfate",
1524
+ "sulphates": "sulfates",
1525
+ "sulphide": "sulfide",
1526
+ "sulphides": "sulfides",
1527
+ "sulphur": "sulfur",
1528
+ "sulphurous": "sulfurous",
1529
+ "summarise": "summarize",
1530
+ "summarised": "summarized",
1531
+ "summarises": "summarizes",
1532
+ "summarising": "summarizing",
1533
+ "swivelled": "swiveled",
1534
+ "swivelling": "swiveling",
1535
+ "symbolise": "symbolize",
1536
+ "symbolised": "symbolized",
1537
+ "symbolises": "symbolizes",
1538
+ "symbolising": "symbolizing",
1539
+ "sympathise": "sympathize",
1540
+ "sympathised": "sympathized",
1541
+ "sympathiser": "sympathizer",
1542
+ "sympathisers": "sympathizers",
1543
+ "sympathises": "sympathizes",
1544
+ "sympathising": "sympathizing",
1545
+ "synchronisation": "synchronization",
1546
+ "synchronise": "synchronize",
1547
+ "synchronised": "synchronized",
1548
+ "synchronises": "synchronizes",
1549
+ "synchronising": "synchronizing",
1550
+ "synthesise": "synthesize",
1551
+ "synthesised": "synthesized",
1552
+ "synthesiser": "synthesizer",
1553
+ "synthesisers": "synthesizers",
1554
+ "synthesises": "synthesizes",
1555
+ "synthesising": "synthesizing",
1556
+ "syphon": "siphon",
1557
+ "syphoned": "siphoned",
1558
+ "syphoning": "siphoning",
1559
+ "syphons": "siphons",
1560
+ "systematisation": "systematization",
1561
+ "systematise": "systematize",
1562
+ "systematised": "systematized",
1563
+ "systematises": "systematizes",
1564
+ "systematising": "systematizing",
1565
+ "tantalise": "tantalize",
1566
+ "tantalised": "tantalized",
1567
+ "tantalises": "tantalizes",
1568
+ "tantalising": "tantalizing",
1569
+ "tantalisingly": "tantalizingly",
1570
+ "tasselled": "tasseled",
1571
+ "technicolour": "technicolor",
1572
+ "temporise": "temporize",
1573
+ "temporised": "temporized",
1574
+ "temporises": "temporizes",
1575
+ "temporising": "temporizing",
1576
+ "tenderise": "tenderize",
1577
+ "tenderised": "tenderized",
1578
+ "tenderises": "tenderizes",
1579
+ "tenderising": "tenderizing",
1580
+ "terrorise": "terrorize",
1581
+ "terrorised": "terrorized",
1582
+ "terrorises": "terrorizes",
1583
+ "terrorising": "terrorizing",
1584
+ "theatre": "theater",
1585
+ "theatregoer": "theatergoer",
1586
+ "theatregoers": "theatergoers",
1587
+ "theatres": "theaters",
1588
+ "theorise": "theorize",
1589
+ "theorised": "theorized",
1590
+ "theorises": "theorizes",
1591
+ "theorising": "theorizing",
1592
+ "tonne": "ton",
1593
+ "tonnes": "tons",
1594
+ "towelled": "toweled",
1595
+ "towelling": "toweling",
1596
+ "toxaemia": "toxemia",
1597
+ "tranquillise": "tranquilize",
1598
+ "tranquillised": "tranquilized",
1599
+ "tranquilliser": "tranquilizer",
1600
+ "tranquillisers": "tranquilizers",
1601
+ "tranquillises": "tranquilizes",
1602
+ "tranquillising": "tranquilizing",
1603
+ "tranquillity": "tranquility",
1604
+ "tranquillize": "tranquilize",
1605
+ "tranquillized": "tranquilized",
1606
+ "tranquillizer": "tranquilizer",
1607
+ "tranquillizers": "tranquilizers",
1608
+ "tranquillizes": "tranquilizes",
1609
+ "tranquillizing": "tranquilizing",
1610
+ "tranquilly": "tranquility",
1611
+ "transistorised": "transistorized",
1612
+ "traumatise": "traumatize",
1613
+ "traumatised": "traumatized",
1614
+ "traumatises": "traumatizes",
1615
+ "traumatising": "traumatizing",
1616
+ "travelled": "traveled",
1617
+ "traveller": "traveler",
1618
+ "travellers": "travelers",
1619
+ "travelling": "traveling",
1620
+ "travelog": "travelogue",
1621
+ "travelogs": "travelogues",
1622
+ "trialled": "trialed",
1623
+ "trialling": "trialing",
1624
+ "tricolour": "tricolor",
1625
+ "tricolours": "tricolors",
1626
+ "trivialise": "trivialize",
1627
+ "trivialised": "trivialized",
1628
+ "trivialises": "trivializes",
1629
+ "trivialising": "trivializing",
1630
+ "tumour": "tumor",
1631
+ "tumours": "tumors",
1632
+ "tunnelled": "tunneled",
1633
+ "tunnelling": "tunneling",
1634
+ "tyrannise": "tyrannize",
1635
+ "tyrannised": "tyrannized",
1636
+ "tyrannises": "tyrannizes",
1637
+ "tyrannising": "tyrannizing",
1638
+ "tyre": "tire",
1639
+ "tyres": "tires",
1640
+ "unauthorised": "unauthorized",
1641
+ "uncivilised": "uncivilized",
1642
+ "underutilised": "underutilized",
1643
+ "unequalled": "unequaled",
1644
+ "unfavourable": "unfavorable",
1645
+ "unfavourably": "unfavorably",
1646
+ "unionisation": "unionization",
1647
+ "unionise": "unionize",
1648
+ "unionised": "unionized",
1649
+ "unionises": "unionizes",
1650
+ "unionising": "unionizing",
1651
+ "unorganised": "unorganized",
1652
+ "unravelled": "unraveled",
1653
+ "unravelling": "unraveling",
1654
+ "unrecognisable": "unrecognizable",
1655
+ "unrecognised": "unrecognized",
1656
+ "unrivalled": "unrivaled",
1657
+ "unsavoury": "unsavory",
1658
+ "untrammelled": "untrammeled",
1659
+ "urbanisation": "urbanization",
1660
+ "urbanise": "urbanize",
1661
+ "urbanised": "urbanized",
1662
+ "urbanises": "urbanizes",
1663
+ "urbanising": "urbanizing",
1664
+ "utilisable": "utilizable",
1665
+ "utilisation": "utilization",
1666
+ "utilise": "utilize",
1667
+ "utilised": "utilized",
1668
+ "utilises": "utilizes",
1669
+ "utilising": "utilizing",
1670
+ "valour": "valor",
1671
+ "vandalise": "vandalize",
1672
+ "vandalised": "vandalized",
1673
+ "vandalises": "vandalizes",
1674
+ "vandalising": "vandalizing",
1675
+ "vaporisation": "vaporization",
1676
+ "vaporise": "vaporize",
1677
+ "vaporised": "vaporized",
1678
+ "vaporises": "vaporizes",
1679
+ "vaporising": "vaporizing",
1680
+ "vapour": "vapor",
1681
+ "vapours": "vapors",
1682
+ "verbalise": "verbalize",
1683
+ "verbalised": "verbalized",
1684
+ "verbalises": "verbalizes",
1685
+ "verbalising": "verbalizing",
1686
+ "victimisation": "victimization",
1687
+ "victimise": "victimize",
1688
+ "victimised": "victimized",
1689
+ "victimises": "victimizes",
1690
+ "victimising": "victimizing",
1691
+ "videodisc": "videodisk",
1692
+ "videodiscs": "videodisks",
1693
+ "vigour": "vigor",
1694
+ "visualisation": "visualization",
1695
+ "visualisations": "visualizations",
1696
+ "visualise": "visualize",
1697
+ "visualised": "visualized",
1698
+ "visualises": "visualizes",
1699
+ "visualising": "visualizing",
1700
+ "vocalisation": "vocalization",
1701
+ "vocalisations": "vocalizations",
1702
+ "vocalise": "vocalize",
1703
+ "vocalised": "vocalized",
1704
+ "vocalises": "vocalizes",
1705
+ "vocalising": "vocalizing",
1706
+ "vulcanised": "vulcanized",
1707
+ "vulgarisation": "vulgarization",
1708
+ "vulgarise": "vulgarize",
1709
+ "vulgarised": "vulgarized",
1710
+ "vulgarises": "vulgarizes",
1711
+ "vulgarising": "vulgarizing",
1712
+ "waggon": "wagon",
1713
+ "waggons": "wagons",
1714
+ "watercolour": "watercolor",
1715
+ "watercolours": "watercolors",
1716
+ "weaselled": "weaseled",
1717
+ "weaselling": "weaseling",
1718
+ "westernisation": "westernization",
1719
+ "westernise": "westernize",
1720
+ "westernised": "westernized",
1721
+ "westernises": "westernizes",
1722
+ "westernising": "westernizing",
1723
+ "womanise": "womanize",
1724
+ "womanised": "womanized",
1725
+ "womaniser": "womanizer",
1726
+ "womanisers": "womanizers",
1727
+ "womanises": "womanizes",
1728
+ "womanising": "womanizing",
1729
+ "woollen": "woolen",
1730
+ "woollens": "woolens",
1731
+ "woollies": "woolies",
1732
+ "woolly": "wooly",
1733
+ "worshipped": "worshiped",
1734
+ "worshipper": "worshiper",
1735
+ "worshipping": "worshiping",
1736
+ "yodelled": "yodeled",
1737
+ "yodelling": "yodeling",
1738
+ "yoghourt": "yogurt",
1739
+ "yoghourts": "yogurts",
1740
+ "yoghurt": "yogurt",
1741
+ "yoghurts": "yogurts"
1742
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be05096f1055ca0b3022a876a2827ad24ff96a673483fa8886e418ff25d1f07
3
+ size 967102601
run.sh ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python run_speech_recognition_seq2seq_streaming.py \
2
+ --model_name_or_path="openai/whisper-small" \
3
+ --dataset_name="mozilla-foundation/common_voice_11_0" \
4
+ --dataset_config_name="ar" \
5
+ --language="arabic" \
6
+ --train_split_name="train+validation" \
7
+ --eval_split_name="test" \
8
+ --model_index_name="Whisper Small Arabic" \
9
+ --max_steps="5000" \
10
+ --output_dir="./" \
11
+ --per_device_train_batch_size="32" \
12
+ --gradient_accumulation_steps="2" \
13
+ --per_device_eval_batch_size="32" \
14
+ --logging_steps="25" \
15
+ --learning_rate="1e-5" \
16
+ --warmup_steps="500" \
17
+ --evaluation_strategy="steps" \
18
+ --eval_steps="1000" \
19
+ --save_strategy="steps" \
20
+ --save_steps="1000" \
21
+ --generation_max_length="225" \
22
+ --length_column_name="input_length" \
23
+ --max_duration_in_seconds="30" \
24
+ --text_column_name="sentence" \
25
+ --freeze_feature_encoder="False" \
26
+ --report_to="tensorboard" \
27
+ --report_to="wandb" \
28
+ --metric_for_best_model="wer" \
29
+ --greater_is_better="False" \
30
+ --load_best_model_at_end \
31
+ --gradient_checkpointing \
32
+ --fp16 \
33
+ --overwrite_output_dir \
34
+ --do_train \
35
+ --do_eval \
36
+ --predict_with_generate \
37
+ --do_normalize_eval \
38
+ --streaming \
39
+ --use_auth_token \
40
+ --push_to_hub
run_speech_recognition_seq2seq_streaming.py ADDED
@@ -0,0 +1,629 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+ # coding=utf-8
3
+ # Copyright 2022 The HuggingFace Team. All rights reserved.
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+ """
17
+ Fine-tuning the library models for sequence to sequence speech recognition
18
+ with 🤗 Datasets' streaming mode.
19
+ """
20
+ # You can also adapt this script for your own sequence to sequence speech
21
+ # recognition task. Pointers for this are left as comments.
22
+
23
+ import logging
24
+ import os
25
+ import sys
26
+ from dataclasses import dataclass, field
27
+ from typing import Any, Dict, List, Optional, Union
28
+
29
+ import datasets
30
+ import torch
31
+ from datasets import DatasetDict, IterableDatasetDict, interleave_datasets, load_dataset
32
+ from torch.utils.data import IterableDataset
33
+
34
+ import evaluate
35
+ import transformers
36
+ from transformers import (
37
+ AutoConfig,
38
+ AutoFeatureExtractor,
39
+ AutoModelForSpeechSeq2Seq,
40
+ AutoProcessor,
41
+ AutoTokenizer,
42
+ HfArgumentParser,
43
+ Seq2SeqTrainer,
44
+ Seq2SeqTrainingArguments,
45
+ TrainerCallback,
46
+ set_seed,
47
+ )
48
+ from transformers.models.whisper.english_normalizer import BasicTextNormalizer
49
+ from transformers.trainer_pt_utils import IterableDatasetShard
50
+ from transformers.trainer_utils import get_last_checkpoint, is_main_process
51
+ from transformers.utils import check_min_version, send_example_telemetry
52
+ from transformers.utils.versions import require_version
53
+
54
+
55
+ # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
56
+ check_min_version("4.25.0.dev0")
57
+
58
+ require_version("datasets>=1.18.2", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
59
+
60
+ logger = logging.getLogger(__name__)
61
+
62
+
63
+ @dataclass
64
+ class ModelArguments:
65
+ """
66
+ Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
67
+ """
68
+
69
+ model_name_or_path: str = field(
70
+ metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
71
+ )
72
+ config_name: Optional[str] = field(
73
+ default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
74
+ )
75
+ tokenizer_name: Optional[str] = field(
76
+ default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
77
+ )
78
+ feature_extractor_name: Optional[str] = field(
79
+ default=None, metadata={"help": "feature extractor name or path if not the same as model_name"}
80
+ )
81
+ cache_dir: Optional[str] = field(
82
+ default=None,
83
+ metadata={"help": "Where to store the pretrained models downloaded from huggingface.co"},
84
+ )
85
+ use_fast_tokenizer: bool = field(
86
+ default=True,
87
+ metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
88
+ )
89
+ model_revision: str = field(
90
+ default="main",
91
+ metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
92
+ )
93
+ use_auth_token: bool = field(
94
+ default=False,
95
+ metadata={
96
+ "help": (
97
+ "Will use the token generated when running `huggingface-cli login` (necessary to use this script "
98
+ "with private models)."
99
+ )
100
+ },
101
+ )
102
+ freeze_feature_encoder: bool = field(
103
+ default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
104
+ )
105
+ freeze_encoder: bool = field(
106
+ default=False, metadata={"help": "Whether to freeze the entire encoder of the seq2seq model."}
107
+ )
108
+ forced_decoder_ids: List[List[int]] = field(
109
+ default=None,
110
+ metadata={
111
+ "help": (
112
+ "A list of pairs of integers which indicates a mapping from generation indices to token indices "
113
+ "that will be forced before sampling. For example, [[0, 123]] means the first generated token "
114
+ "will always be a token of index 123."
115
+ )
116
+ },
117
+ )
118
+ suppress_tokens: List[int] = field(
119
+ default=None, metadata={"help": "A list of tokens that will be suppressed at generation."}
120
+ )
121
+ model_index_name: str = field(default=None, metadata={"help": "Pretty name for the model card."})
122
+
123
+
124
+ @dataclass
125
+ class DataTrainingArguments:
126
+ """
127
+ Arguments pertaining to what data we are going to input our model for training and eval.
128
+ """
129
+
130
+ dataset_name: str = field(
131
+ default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
132
+ )
133
+ dataset_config_name: Optional[str] = field(
134
+ default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
135
+ )
136
+ text_column: Optional[str] = field(
137
+ default=None,
138
+ metadata={"help": "The name of the column in the datasets containing the full texts (for summarization)."},
139
+ )
140
+ max_train_samples: Optional[int] = field(
141
+ default=None,
142
+ metadata={
143
+ "help": (
144
+ "For debugging purposes or quicker training, truncate the number of training examples to this "
145
+ "value if set."
146
+ )
147
+ },
148
+ )
149
+ max_eval_samples: Optional[int] = field(
150
+ default=None,
151
+ metadata={
152
+ "help": (
153
+ "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
154
+ "value if set."
155
+ )
156
+ },
157
+ )
158
+ audio_column_name: str = field(
159
+ default="audio",
160
+ metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
161
+ )
162
+ text_column_name: str = field(
163
+ default="text",
164
+ metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
165
+ )
166
+ max_duration_in_seconds: float = field(
167
+ default=20.0,
168
+ metadata={
169
+ "help": (
170
+ "Truncate audio files that are longer than `max_duration_in_seconds` seconds to"
171
+ " 'max_duration_in_seconds`"
172
+ )
173
+ },
174
+ )
175
+ min_duration_in_seconds: float = field(
176
+ default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
177
+ )
178
+ train_split_name: str = field(
179
+ default="train",
180
+ metadata={
181
+ "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
182
+ },
183
+ )
184
+ eval_split_name: str = field(
185
+ default="test",
186
+ metadata={
187
+ "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
188
+ },
189
+ )
190
+ do_lower_case: bool = field(
191
+ default=False,
192
+ metadata={"help": "Whether the target text should be lower cased."},
193
+ )
194
+ do_remove_punctuation: bool = field(
195
+ default=False,
196
+ metadata={"help": "Whether the target text should be striped of punctuation."},
197
+ )
198
+ do_normalize_eval: bool = field(
199
+ default=True,
200
+ metadata={"help": "Whether to normalise the references and predictions in the eval WER calculation."},
201
+ )
202
+ language: str = field(
203
+ default=None,
204
+ metadata={
205
+ "help": (
206
+ "Language for multilingual fine-tuning. This argument should be set for multilingual fine-tuning "
207
+ "only. For English speech recognition, it should be set to `None`."
208
+ )
209
+ },
210
+ )
211
+ task: str = field(
212
+ default="transcribe",
213
+ metadata={"help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."},
214
+ )
215
+ shuffle_buffer_size: Optional[int] = field(
216
+ default=500,
217
+ metadata={
218
+ "help": (
219
+ "The number of streamed examples to download before shuffling them. The large the buffer, "
220
+ "the closer it is to real offline shuffling."
221
+ )
222
+ },
223
+ )
224
+ streaming: bool = field(
225
+ default=True,
226
+ metadata={"help": "Whether to use streaming mode to load and pre-process the data."},
227
+ )
228
+
229
+
230
+ @dataclass
231
+ class DataCollatorSpeechSeq2SeqWithPadding:
232
+ """
233
+ Data collator that will dynamically pad the inputs received.
234
+ Args:
235
+ processor ([`WhisperProcessor`])
236
+ The processor used for processing the data.
237
+ decoder_start_token_id (`int`)
238
+ The begin-of-sentence of the decoder.
239
+ """
240
+
241
+ processor: Any
242
+ decoder_start_token_id: int
243
+
244
+ def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
245
+ # split inputs and labels since they have to be of different lengths and need
246
+ # different padding methods
247
+ model_input_name = self.processor.model_input_names[0]
248
+ input_features = [{model_input_name: feature[model_input_name]} for feature in features]
249
+ label_features = [{"input_ids": feature["labels"]} for feature in features]
250
+
251
+ batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
252
+
253
+ labels_batch = self.processor.tokenizer.pad(label_features, return_tensors="pt")
254
+
255
+ # replace padding with -100 to ignore loss correctly
256
+ labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
257
+
258
+ # if bos token is appended in previous tokenization step,
259
+ # cut bos token here as it's append later anyways
260
+ if (labels[:, 0] == self.decoder_start_token_id).all().cpu().item():
261
+ labels = labels[:, 1:]
262
+
263
+ batch["labels"] = labels
264
+
265
+ return batch
266
+
267
+
268
+ def load_maybe_streaming_dataset(dataset_name, dataset_config_name, split="train", streaming=True, **kwargs):
269
+ """
270
+ Utility function to load a dataset in streaming mode. For datasets with multiple splits,
271
+ each split is loaded individually and then splits combined by taking alternating examples from
272
+ each (interleaving).
273
+ """
274
+ if "+" in split:
275
+ # load multiple splits separated by the `+` symbol with streaming mode
276
+ dataset_splits = [
277
+ load_dataset(dataset_name, dataset_config_name, split=split_name, streaming=streaming, **kwargs)
278
+ for split_name in split.split("+")
279
+ ]
280
+ # interleave multiple splits to form one dataset
281
+ interleaved_dataset = interleave_datasets(dataset_splits)
282
+ return interleaved_dataset
283
+ else:
284
+ # load a single split *with* streaming mode
285
+ dataset = load_dataset(dataset_name, dataset_config_name, split=split, streaming=streaming, **kwargs)
286
+ return dataset
287
+
288
+
289
+ def main():
290
+ # 1. Parse input arguments
291
+ # See all possible arguments in src/transformers/training_args.py
292
+ # or by passing the --help flag to this script.
293
+ # We now keep distinct sets of args, for a cleaner separation of concerns.
294
+ parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
295
+
296
+ if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
297
+ # If we pass only one argument to the script and it's the path to a json file,
298
+ # let's parse it to get our arguments.
299
+ model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
300
+ else:
301
+ model_args, data_args, training_args = parser.parse_args_into_dataclasses()
302
+
303
+ # Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
304
+ # information sent is the one passed as arguments along with your Python/PyTorch versions.
305
+ send_example_telemetry("run_speech_recognition_seq2seq_streaming", model_args, data_args)
306
+
307
+ # 2. Setup logging
308
+ logging.basicConfig(
309
+ format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
310
+ datefmt="%m/%d/%Y %H:%M:%S",
311
+ handlers=[logging.StreamHandler(sys.stdout)],
312
+ )
313
+ log_level = training_args.get_process_log_level()
314
+ logger.setLevel(log_level)
315
+ datasets.utils.logging.set_verbosity(log_level)
316
+ transformers.utils.logging.set_verbosity(log_level)
317
+ transformers.utils.logging.enable_default_handler()
318
+ transformers.utils.logging.enable_explicit_format()
319
+
320
+ logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
321
+
322
+ # Log on each process the small summary:
323
+ logger.warning(
324
+ f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
325
+ f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
326
+ )
327
+ logger.info(f"Training/evaluation parameters {training_args}")
328
+
329
+ # Set the verbosity to info of the Transformers logger (on main process only):
330
+ if is_main_process(training_args.local_rank):
331
+ transformers.utils.logging.set_verbosity_info()
332
+ logger.info("Training/evaluation parameters %s", training_args)
333
+
334
+ # 3. Detecting last checkpoint and eventually continue from last checkpoint
335
+ last_checkpoint = None
336
+ if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
337
+ last_checkpoint = get_last_checkpoint(training_args.output_dir)
338
+ if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
339
+ raise ValueError(
340
+ f"Output directory ({training_args.output_dir}) already exists and is not empty. "
341
+ "Use --overwrite_output_dir to overcome."
342
+ )
343
+ elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
344
+ logger.info(
345
+ f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
346
+ "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
347
+ )
348
+
349
+ # Set seed before initializing model.
350
+ set_seed(training_args.seed)
351
+
352
+ # 4. Load dataset
353
+ raw_datasets = IterableDatasetDict() if data_args.streaming else DatasetDict()
354
+
355
+ if training_args.do_train:
356
+ raw_datasets["train"] = load_maybe_streaming_dataset(
357
+ data_args.dataset_name,
358
+ data_args.dataset_config_name,
359
+ split=data_args.train_split_name,
360
+ use_auth_token=True if model_args.use_auth_token else None,
361
+ streaming=data_args.streaming,
362
+ )
363
+
364
+ if training_args.do_eval:
365
+ raw_datasets["eval"] = load_maybe_streaming_dataset(
366
+ data_args.dataset_name,
367
+ data_args.dataset_config_name,
368
+ split=data_args.eval_split_name,
369
+ use_auth_token=True if model_args.use_auth_token else None,
370
+ streaming=data_args.streaming,
371
+ )
372
+
373
+ raw_datasets_features = list(next(iter(raw_datasets.values())).features.keys())
374
+
375
+ if data_args.audio_column_name not in raw_datasets_features:
376
+ raise ValueError(
377
+ f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
378
+ "Make sure to set `--audio_column_name` to the correct audio column - one of "
379
+ f"{', '.join(raw_datasets_features)}."
380
+ )
381
+
382
+ if data_args.text_column_name not in raw_datasets_features:
383
+ raise ValueError(
384
+ f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
385
+ "Make sure to set `--text_column_name` to the correct text column - one of "
386
+ f"{', '.join(raw_datasets_features)}."
387
+ )
388
+
389
+ # 5. Load pretrained model, tokenizer, and feature extractor
390
+ #
391
+ # Distributed training:
392
+ # The .from_pretrained methods guarantee that only one local process can concurrently
393
+ config = AutoConfig.from_pretrained(
394
+ model_args.config_name if model_args.config_name else model_args.model_name_or_path,
395
+ cache_dir=model_args.cache_dir,
396
+ revision=model_args.model_revision,
397
+ use_auth_token=True if model_args.use_auth_token else None,
398
+ )
399
+
400
+ config.update({"forced_decoder_ids": model_args.forced_decoder_ids, "suppress_tokens": model_args.suppress_tokens})
401
+
402
+ if training_args.gradient_checkpointing:
403
+ config.update({"use_cache": False})
404
+
405
+ feature_extractor = AutoFeatureExtractor.from_pretrained(
406
+ model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
407
+ cache_dir=model_args.cache_dir,
408
+ revision=model_args.model_revision,
409
+ use_auth_token=True if model_args.use_auth_token else None,
410
+ )
411
+ tokenizer = AutoTokenizer.from_pretrained(
412
+ model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
413
+ cache_dir=model_args.cache_dir,
414
+ use_fast=model_args.use_fast_tokenizer,
415
+ revision=model_args.model_revision,
416
+ use_auth_token=True if model_args.use_auth_token else None,
417
+ )
418
+ model = AutoModelForSpeechSeq2Seq.from_pretrained(
419
+ model_args.model_name_or_path,
420
+ config=config,
421
+ cache_dir=model_args.cache_dir,
422
+ revision=model_args.model_revision,
423
+ use_auth_token=True if model_args.use_auth_token else None,
424
+ )
425
+
426
+ if model.config.decoder_start_token_id is None:
427
+ raise ValueError("Make sure that `config.decoder_start_token_id` is correctly defined")
428
+
429
+ if model_args.freeze_feature_encoder:
430
+ model.freeze_feature_encoder()
431
+
432
+ if model_args.freeze_encoder:
433
+ model.freeze_encoder()
434
+
435
+ if data_args.language is not None:
436
+ # We only need to set the task id when the language is specified (i.e. in a multilingual setting)
437
+ tokenizer.set_prefix_tokens(language=data_args.language, task=data_args.task)
438
+
439
+ # 6. Resample speech dataset if necessary
440
+ dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
441
+ if dataset_sampling_rate != feature_extractor.sampling_rate:
442
+ raw_datasets = raw_datasets.cast_column(
443
+ data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
444
+ )
445
+
446
+ # 7. Preprocessing the datasets.
447
+ # We need to read the audio files as arrays and tokenize the targets.
448
+ max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
449
+ min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
450
+ audio_column_name = data_args.audio_column_name
451
+ text_column_name = data_args.text_column_name
452
+ model_input_name = feature_extractor.model_input_names[0]
453
+ do_lower_case = data_args.do_lower_case
454
+ do_remove_punctuation = data_args.do_remove_punctuation
455
+ normalizer = BasicTextNormalizer() # 'official' text normalizer from OpenAI
456
+
457
+ if data_args.max_train_samples is not None:
458
+ raw_datasets["train"] = (
459
+ raw_datasets["train"].take(data_args.max_train_samples)
460
+ if data_args.streaming
461
+ else raw_datasets["train"].select(range(data_args.max_train_samples))
462
+ )
463
+
464
+ if data_args.max_eval_samples is not None:
465
+ raw_datasets["eval"] = (
466
+ raw_datasets["eval"].take(data_args.max_eval_samples)
467
+ if data_args.streaming
468
+ else raw_datasets["eval"].select(range(data_args.max_eval_samples))
469
+ )
470
+
471
+ def prepare_dataset(batch):
472
+ # process audio
473
+ sample = batch[audio_column_name]
474
+ inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
475
+ # process audio length
476
+ batch[model_input_name] = inputs.get(model_input_name)[0]
477
+ batch["input_length"] = len(sample["array"])
478
+
479
+ # process targets
480
+ input_str = batch[text_column_name].lower() if do_lower_case else batch[text_column_name]
481
+ if do_remove_punctuation:
482
+ input_str = normalizer(input_str).strip()
483
+ batch["labels"] = tokenizer(input_str).input_ids
484
+ return batch
485
+
486
+ with training_args.main_process_first(desc="dataset map pre-processing"):
487
+ vectorized_datasets = raw_datasets.map(
488
+ prepare_dataset,
489
+ remove_columns=raw_datasets_features,
490
+ ).with_format("torch")
491
+
492
+ if training_args.do_train and data_args.streaming:
493
+ # manually shuffle if streaming (done by the trainer for non-streaming)
494
+ vectorized_datasets["train"] = vectorized_datasets["train"].shuffle(
495
+ buffer_size=data_args.shuffle_buffer_size,
496
+ seed=training_args.seed,
497
+ )
498
+
499
+ # filter training data that is shorter than min_input_length or longer than
500
+ # max_input_length
501
+ def is_audio_in_length_range(length):
502
+ return min_input_length < length < max_input_length
503
+
504
+ if training_args.do_train:
505
+ vectorized_datasets["train"] = vectorized_datasets["train"].filter(
506
+ is_audio_in_length_range,
507
+ input_columns=["input_length"],
508
+ )
509
+
510
+ # 8. Load Metric
511
+ metric = evaluate.load("wer")
512
+ do_normalize_eval = data_args.do_normalize_eval
513
+
514
+ def compute_metrics(pred):
515
+ pred_ids = pred.predictions
516
+
517
+ pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
518
+
519
+ pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
520
+ # we do not want to group tokens when computing the metrics
521
+ label_str = tokenizer.batch_decode(pred.label_ids, skip_special_tokens=True)
522
+
523
+ if do_normalize_eval:
524
+ pred_str = [normalizer(pred) for pred in pred_str]
525
+ label_str = [normalizer(label) for label in label_str]
526
+ # filtering step to only evaluate the samples that correspond to non-zero references:
527
+ pred_str = [pred_str[i] for i in range(len(pred_str)) if len(label_str[i]) > 0]
528
+ label_str = [label_str[i] for i in range(len(label_str)) if len(label_str[i]) > 0]
529
+
530
+ wer = 100 * metric.compute(predictions=pred_str, references=label_str)
531
+
532
+ return {"wer": wer}
533
+
534
+ # 9. Create a single speech processor
535
+ if is_main_process(training_args.local_rank):
536
+ # save feature extractor, tokenizer and config
537
+ feature_extractor.save_pretrained(training_args.output_dir)
538
+ tokenizer.save_pretrained(training_args.output_dir)
539
+ config.save_pretrained(training_args.output_dir)
540
+
541
+ processor = AutoProcessor.from_pretrained(training_args.output_dir)
542
+
543
+ # 10. Define data collator
544
+ data_collator = DataCollatorSpeechSeq2SeqWithPadding(
545
+ processor=processor,
546
+ decoder_start_token_id=model.config.decoder_start_token_id,
547
+ )
548
+
549
+ # 11. Configure Trainer
550
+ # Trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch
551
+ # Only required for streaming: Trainer automatically shuffles non-streaming datasets
552
+ class ShuffleCallback(TrainerCallback):
553
+ def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):
554
+ if isinstance(train_dataloader.dataset, IterableDatasetShard):
555
+ pass # set_epoch() is handled by the Trainer
556
+ elif isinstance(train_dataloader.dataset, IterableDataset):
557
+ train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
558
+
559
+ # Initialize Trainer
560
+ trainer = Seq2SeqTrainer(
561
+ model=model,
562
+ args=training_args,
563
+ train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
564
+ eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
565
+ tokenizer=feature_extractor,
566
+ data_collator=data_collator,
567
+ compute_metrics=compute_metrics if training_args.predict_with_generate else None,
568
+ callbacks=[ShuffleCallback()] if data_args.streaming else None,
569
+ )
570
+
571
+ # 12. Training
572
+ if training_args.do_train:
573
+ checkpoint = None
574
+ if training_args.resume_from_checkpoint is not None:
575
+ checkpoint = training_args.resume_from_checkpoint
576
+ elif last_checkpoint is not None:
577
+ checkpoint = last_checkpoint
578
+ train_result = trainer.train(resume_from_checkpoint=checkpoint)
579
+ trainer.save_model() # Saves the feature extractor too for easy upload
580
+
581
+ metrics = train_result.metrics
582
+ if data_args.max_train_samples:
583
+ metrics["train_samples"] = data_args.max_train_samples
584
+ trainer.log_metrics("train", metrics)
585
+ trainer.save_metrics("train", metrics)
586
+ trainer.save_state()
587
+
588
+ # 13. Evaluation
589
+ results = {}
590
+ if training_args.do_eval:
591
+ logger.info("*** Evaluate ***")
592
+ metrics = trainer.evaluate(
593
+ metric_key_prefix="eval",
594
+ max_length=training_args.generation_max_length,
595
+ num_beams=training_args.generation_num_beams,
596
+ )
597
+ if data_args.max_eval_samples:
598
+ metrics["eval_samples"] = data_args.max_eval_samples
599
+
600
+ trainer.log_metrics("eval", metrics)
601
+ trainer.save_metrics("eval", metrics)
602
+
603
+ # 14. Write Training Stats
604
+ kwargs = {
605
+ "finetuned_from": model_args.model_name_or_path,
606
+ "tasks": "automatic-speech-recognition",
607
+ "tags": "whisper-event",
608
+ }
609
+ if data_args.dataset_name is not None:
610
+ kwargs["dataset_tags"] = data_args.dataset_name
611
+ if data_args.dataset_config_name is not None:
612
+ kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
613
+ else:
614
+ kwargs["dataset"] = data_args.dataset_name
615
+ if "common_voice" in data_args.dataset_name:
616
+ kwargs["language"] = data_args.dataset_config_name.split('-')[0]
617
+ if model_args.model_index_name is not None:
618
+ kwargs["model_name"] = model_args.model_index_name
619
+
620
+ if training_args.push_to_hub:
621
+ trainer.push_to_hub(**kwargs)
622
+ else:
623
+ trainer.create_model_card(**kwargs)
624
+
625
+ return results
626
+
627
+
628
+ if __name__ == "__main__":
629
+ main()
special_tokens_map.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|he|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": "<|endoftext|>",
126
+ "unk_token": {
127
+ "content": "<|endoftext|>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ }
133
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "processor_class": "WhisperProcessor",
25
+ "return_attention_mask": false,
26
+ "tokenizer_class": "WhisperTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
training.log ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41ee1723077d9367104b059cfecdb53a548d49fcfc2a3cd253a6e7408db5fbf
3
+ size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
wandb/debug-cli.dizham.log ADDED
File without changes
wandb/debug-internal.log ADDED
@@ -0,0 +1 @@
 
 
1
+ run-20230507_103405-9zf5xxpu/logs/debug-internal.log
wandb/debug.log ADDED
@@ -0,0 +1 @@
 
 
1
+ run-20230507_103405-9zf5xxpu/logs/debug.log
wandb/latest-run ADDED
@@ -0,0 +1 @@
 
 
1
+ run-20230507_103405-9zf5xxpu
wandb/run-20230506_113337-ysywp688/files/conda-environment.yaml ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: whisper
2
+ channels:
3
+ - conda-forge
4
+ - defaults
5
+ dependencies:
6
+ - _libgcc_mutex=0.1=conda_forge
7
+ - _openmp_mutex=4.5=2_gnu
8
+ - bzip2=1.0.8=h7f98852_4
9
+ - ca-certificates=2022.12.7=ha878542_0
10
+ - git-lfs=3.3.0=ha770c72_0
11
+ - ld_impl_linux-64=2.40=h41732ed_0
12
+ - libffi=3.4.2=h7f98852_5
13
+ - libgcc-ng=12.2.0=h65d4601_19
14
+ - libgomp=12.2.0=h65d4601_19
15
+ - libnsl=2.0.0=h7f98852_0
16
+ - libsqlite=3.40.0=h753d276_1
17
+ - libuuid=2.38.1=h0b41bf4_0
18
+ - libzlib=1.2.13=h166bdaf_4
19
+ - ncurses=6.3=h27087fc_1
20
+ - openssl=3.1.0=hd590300_3
21
+ - pip=23.1.2=pyhd8ed1ab_0
22
+ - python=3.9.16=h2782a2a_0_cpython
23
+ - readline=8.2=h8228510_1
24
+ - setuptools=67.7.2=pyhd8ed1ab_0
25
+ - tk=8.6.12=h27826a3_0
26
+ - wheel=0.40.0=pyhd8ed1ab_0
27
+ - xz=5.2.6=h166bdaf_0
28
+ - pip:
29
+ - absl-py==1.4.0
30
+ - accelerate==0.18.0
31
+ - aiohttp==3.8.4
32
+ - aiosignal==1.3.1
33
+ - appdirs==1.4.4
34
+ - async-timeout==4.0.2
35
+ - attrs==23.1.0
36
+ - audioread==3.0.0
37
+ - cachetools==5.3.0
38
+ - certifi==2022.12.7
39
+ - cffi==1.15.1
40
+ - charset-normalizer==3.1.0
41
+ - click==8.1.3
42
+ - cmake==3.26.3
43
+ - datasets==2.12.1.dev0
44
+ - decorator==5.1.1
45
+ - dill==0.3.6
46
+ - docker-pycreds==0.4.0
47
+ - evaluate==0.4.0
48
+ - filelock==3.12.0
49
+ - frozenlist==1.3.3
50
+ - fsspec==2023.4.0
51
+ - gitdb==4.0.10
52
+ - gitpython==3.1.31
53
+ - google-auth==2.17.3
54
+ - google-auth-oauthlib==1.0.0
55
+ - grpcio==1.54.0
56
+ - huggingface-hub==0.14.1
57
+ - idna==3.4
58
+ - importlib-metadata==6.6.0
59
+ - jinja2==3.1.2
60
+ - jiwer==3.0.1
61
+ - joblib==1.2.0
62
+ - lazy-loader==0.2
63
+ - librosa==0.10.0.post2
64
+ - lit==16.0.2
65
+ - llvmlite==0.40.0
66
+ - markdown==3.4.3
67
+ - markupsafe==2.1.2
68
+ - more-itertools==9.1.0
69
+ - mpmath==1.3.0
70
+ - msgpack==1.0.5
71
+ - multidict==6.0.4
72
+ - multiprocess==0.70.14
73
+ - networkx==3.1
74
+ - numba==0.57.0
75
+ - numpy==1.24.3
76
+ - nvidia-cublas-cu11==11.10.3.66
77
+ - nvidia-cuda-cupti-cu11==11.7.101
78
+ - nvidia-cuda-nvrtc-cu11==11.7.99
79
+ - nvidia-cuda-runtime-cu11==11.7.99
80
+ - nvidia-cudnn-cu11==8.5.0.96
81
+ - nvidia-cufft-cu11==10.9.0.58
82
+ - nvidia-curand-cu11==10.2.10.91
83
+ - nvidia-cusolver-cu11==11.4.0.1
84
+ - nvidia-cusparse-cu11==11.7.4.91
85
+ - nvidia-nccl-cu11==2.14.3
86
+ - nvidia-nvtx-cu11==11.7.91
87
+ - oauthlib==3.2.2
88
+ - packaging==23.1
89
+ - pandas==2.0.1
90
+ - pathtools==0.1.2
91
+ - pooch==1.6.0
92
+ - protobuf==4.22.3
93
+ - psutil==5.9.5
94
+ - pyarrow==12.0.0
95
+ - pyasn1==0.5.0
96
+ - pyasn1-modules==0.3.0
97
+ - pycparser==2.21
98
+ - python-dateutil==2.8.2
99
+ - pytz==2023.3
100
+ - pyyaml==6.0
101
+ - rapidfuzz==2.13.7
102
+ - regex==2023.5.4
103
+ - requests==2.29.0
104
+ - requests-oauthlib==1.3.1
105
+ - responses==0.18.0
106
+ - rsa==4.9
107
+ - scikit-learn==1.2.2
108
+ - scipy==1.10.1
109
+ - sentry-sdk==1.22.1
110
+ - setproctitle==1.3.2
111
+ - six==1.16.0
112
+ - smmap==5.0.0
113
+ - soundfile==0.12.1
114
+ - soxr==0.3.5
115
+ - sympy==1.11.1
116
+ - tensorboard==2.12.3
117
+ - tensorboard-data-server==0.7.0
118
+ - threadpoolctl==3.1.0
119
+ - tokenizers==0.13.3
120
+ - torch==2.0.0
121
+ - torchaudio==2.0.1
122
+ - tqdm==4.65.0
123
+ - transformers==4.29.0.dev0
124
+ - triton==2.0.0
125
+ - typing-extensions==4.5.0
126
+ - tzdata==2023.3
127
+ - urllib3==1.26.15
128
+ - wandb==0.15.2
129
+ - werkzeug==2.3.3
130
+ - xxhash==3.2.0
131
+ - yarl==1.9.2
132
+ - zipp==3.15.0
133
+ prefix: /home/local/QCRI/dizham/miniconda3/envs/whisper
wandb/run-20230506_113337-ysywp688/files/config.yaml ADDED
@@ -0,0 +1,688 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.9.16
7
+ cli_version: 0.15.2
8
+ framework: huggingface
9
+ huggingface_version: 4.29.0.dev0
10
+ is_jupyter_run: false
11
+ is_kaggle_kernel: false
12
+ start_time: 1683362017.131512
13
+ t:
14
+ 1:
15
+ - 1
16
+ - 5
17
+ - 11
18
+ - 49
19
+ - 51
20
+ - 53
21
+ - 55
22
+ - 71
23
+ 2:
24
+ - 1
25
+ - 5
26
+ - 11
27
+ - 49
28
+ - 51
29
+ - 53
30
+ - 55
31
+ - 71
32
+ 3:
33
+ - 7
34
+ - 23
35
+ 4: 3.9.16
36
+ 5: 0.15.2
37
+ 6: 4.29.0.dev0
38
+ 8:
39
+ - 5
40
+ m:
41
+ - 1: train/global_step
42
+ 6:
43
+ - 3
44
+ - 1: train/loss
45
+ 5: 1
46
+ 6:
47
+ - 1
48
+ - 1: train/learning_rate
49
+ 5: 1
50
+ 6:
51
+ - 1
52
+ - 1: train/epoch
53
+ 5: 1
54
+ 6:
55
+ - 1
56
+ - 1: eval/loss
57
+ 5: 1
58
+ 6:
59
+ - 1
60
+ - 1: eval/wer
61
+ 5: 1
62
+ 6:
63
+ - 1
64
+ - 1: eval/runtime
65
+ 5: 1
66
+ 6:
67
+ - 1
68
+ - 1: eval/samples_per_second
69
+ 5: 1
70
+ 6:
71
+ - 1
72
+ - 1: eval/steps_per_second
73
+ 5: 1
74
+ 6:
75
+ - 1
76
+ vocab_size:
77
+ desc: null
78
+ value: 51865
79
+ num_mel_bins:
80
+ desc: null
81
+ value: 80
82
+ d_model:
83
+ desc: null
84
+ value: 768
85
+ encoder_layers:
86
+ desc: null
87
+ value: 12
88
+ encoder_attention_heads:
89
+ desc: null
90
+ value: 12
91
+ decoder_layers:
92
+ desc: null
93
+ value: 12
94
+ decoder_attention_heads:
95
+ desc: null
96
+ value: 12
97
+ decoder_ffn_dim:
98
+ desc: null
99
+ value: 3072
100
+ encoder_ffn_dim:
101
+ desc: null
102
+ value: 3072
103
+ dropout:
104
+ desc: null
105
+ value: 0.0
106
+ attention_dropout:
107
+ desc: null
108
+ value: 0.0
109
+ activation_dropout:
110
+ desc: null
111
+ value: 0.0
112
+ activation_function:
113
+ desc: null
114
+ value: gelu
115
+ init_std:
116
+ desc: null
117
+ value: 0.02
118
+ encoder_layerdrop:
119
+ desc: null
120
+ value: 0.0
121
+ decoder_layerdrop:
122
+ desc: null
123
+ value: 0.0
124
+ use_cache:
125
+ desc: null
126
+ value: false
127
+ num_hidden_layers:
128
+ desc: null
129
+ value: 12
130
+ scale_embedding:
131
+ desc: null
132
+ value: false
133
+ max_source_positions:
134
+ desc: null
135
+ value: 1500
136
+ max_target_positions:
137
+ desc: null
138
+ value: 448
139
+ classifier_proj_size:
140
+ desc: null
141
+ value: 256
142
+ use_weighted_layer_sum:
143
+ desc: null
144
+ value: false
145
+ apply_spec_augment:
146
+ desc: null
147
+ value: false
148
+ mask_time_prob:
149
+ desc: null
150
+ value: 0.05
151
+ mask_time_length:
152
+ desc: null
153
+ value: 10
154
+ mask_time_min_masks:
155
+ desc: null
156
+ value: 2
157
+ mask_feature_prob:
158
+ desc: null
159
+ value: 0.0
160
+ mask_feature_length:
161
+ desc: null
162
+ value: 10
163
+ mask_feature_min_masks:
164
+ desc: null
165
+ value: 0
166
+ return_dict:
167
+ desc: null
168
+ value: true
169
+ output_hidden_states:
170
+ desc: null
171
+ value: false
172
+ output_attentions:
173
+ desc: null
174
+ value: false
175
+ torchscript:
176
+ desc: null
177
+ value: false
178
+ torch_dtype:
179
+ desc: null
180
+ value: float32
181
+ use_bfloat16:
182
+ desc: null
183
+ value: false
184
+ tf_legacy_loss:
185
+ desc: null
186
+ value: false
187
+ pruned_heads:
188
+ desc: null
189
+ value: {}
190
+ tie_word_embeddings:
191
+ desc: null
192
+ value: true
193
+ is_encoder_decoder:
194
+ desc: null
195
+ value: true
196
+ is_decoder:
197
+ desc: null
198
+ value: false
199
+ cross_attention_hidden_size:
200
+ desc: null
201
+ value: null
202
+ add_cross_attention:
203
+ desc: null
204
+ value: false
205
+ tie_encoder_decoder:
206
+ desc: null
207
+ value: false
208
+ max_length:
209
+ desc: null
210
+ value: 448
211
+ min_length:
212
+ desc: null
213
+ value: 0
214
+ do_sample:
215
+ desc: null
216
+ value: false
217
+ early_stopping:
218
+ desc: null
219
+ value: false
220
+ num_beams:
221
+ desc: null
222
+ value: 1
223
+ num_beam_groups:
224
+ desc: null
225
+ value: 1
226
+ diversity_penalty:
227
+ desc: null
228
+ value: 0.0
229
+ temperature:
230
+ desc: null
231
+ value: 1.0
232
+ top_k:
233
+ desc: null
234
+ value: 50
235
+ top_p:
236
+ desc: null
237
+ value: 1.0
238
+ typical_p:
239
+ desc: null
240
+ value: 1.0
241
+ repetition_penalty:
242
+ desc: null
243
+ value: 1.0
244
+ length_penalty:
245
+ desc: null
246
+ value: 1.0
247
+ no_repeat_ngram_size:
248
+ desc: null
249
+ value: 0
250
+ encoder_no_repeat_ngram_size:
251
+ desc: null
252
+ value: 0
253
+ bad_words_ids:
254
+ desc: null
255
+ value: null
256
+ num_return_sequences:
257
+ desc: null
258
+ value: 1
259
+ chunk_size_feed_forward:
260
+ desc: null
261
+ value: 0
262
+ output_scores:
263
+ desc: null
264
+ value: false
265
+ return_dict_in_generate:
266
+ desc: null
267
+ value: false
268
+ forced_bos_token_id:
269
+ desc: null
270
+ value: null
271
+ forced_eos_token_id:
272
+ desc: null
273
+ value: null
274
+ remove_invalid_values:
275
+ desc: null
276
+ value: false
277
+ exponential_decay_length_penalty:
278
+ desc: null
279
+ value: null
280
+ suppress_tokens:
281
+ desc: null
282
+ value: null
283
+ begin_suppress_tokens:
284
+ desc: null
285
+ value:
286
+ - 220
287
+ - 50257
288
+ architectures:
289
+ desc: null
290
+ value:
291
+ - WhisperForConditionalGeneration
292
+ finetuning_task:
293
+ desc: null
294
+ value: null
295
+ id2label:
296
+ desc: null
297
+ value:
298
+ '0': LABEL_0
299
+ '1': LABEL_1
300
+ label2id:
301
+ desc: null
302
+ value:
303
+ LABEL_0: 0
304
+ LABEL_1: 1
305
+ tokenizer_class:
306
+ desc: null
307
+ value: null
308
+ prefix:
309
+ desc: null
310
+ value: null
311
+ bos_token_id:
312
+ desc: null
313
+ value: 50257
314
+ pad_token_id:
315
+ desc: null
316
+ value: 50257
317
+ eos_token_id:
318
+ desc: null
319
+ value: 50257
320
+ sep_token_id:
321
+ desc: null
322
+ value: null
323
+ decoder_start_token_id:
324
+ desc: null
325
+ value: 50258
326
+ task_specific_params:
327
+ desc: null
328
+ value: null
329
+ problem_type:
330
+ desc: null
331
+ value: null
332
+ _name_or_path:
333
+ desc: null
334
+ value: openai/whisper-small
335
+ transformers_version:
336
+ desc: null
337
+ value: 4.29.0.dev0
338
+ forced_decoder_ids:
339
+ desc: null
340
+ value: null
341
+ model_type:
342
+ desc: null
343
+ value: whisper
344
+ output_dir:
345
+ desc: null
346
+ value: ./
347
+ overwrite_output_dir:
348
+ desc: null
349
+ value: true
350
+ do_train:
351
+ desc: null
352
+ value: true
353
+ do_eval:
354
+ desc: null
355
+ value: true
356
+ do_predict:
357
+ desc: null
358
+ value: false
359
+ evaluation_strategy:
360
+ desc: null
361
+ value: steps
362
+ prediction_loss_only:
363
+ desc: null
364
+ value: false
365
+ per_device_train_batch_size:
366
+ desc: null
367
+ value: 32
368
+ per_device_eval_batch_size:
369
+ desc: null
370
+ value: 32
371
+ per_gpu_train_batch_size:
372
+ desc: null
373
+ value: None
374
+ per_gpu_eval_batch_size:
375
+ desc: null
376
+ value: None
377
+ gradient_accumulation_steps:
378
+ desc: null
379
+ value: 2
380
+ eval_accumulation_steps:
381
+ desc: null
382
+ value: None
383
+ eval_delay:
384
+ desc: null
385
+ value: 0
386
+ learning_rate:
387
+ desc: null
388
+ value: 1.0e-05
389
+ weight_decay:
390
+ desc: null
391
+ value: 0.0
392
+ adam_beta1:
393
+ desc: null
394
+ value: 0.9
395
+ adam_beta2:
396
+ desc: null
397
+ value: 0.999
398
+ adam_epsilon:
399
+ desc: null
400
+ value: 1.0e-08
401
+ max_grad_norm:
402
+ desc: null
403
+ value: 1.0
404
+ num_train_epochs:
405
+ desc: null
406
+ value: 3.0
407
+ max_steps:
408
+ desc: null
409
+ value: 5000
410
+ lr_scheduler_type:
411
+ desc: null
412
+ value: linear
413
+ warmup_ratio:
414
+ desc: null
415
+ value: 0.0
416
+ warmup_steps:
417
+ desc: null
418
+ value: 500
419
+ log_level:
420
+ desc: null
421
+ value: passive
422
+ log_level_replica:
423
+ desc: null
424
+ value: warning
425
+ log_on_each_node:
426
+ desc: null
427
+ value: true
428
+ logging_dir:
429
+ desc: null
430
+ value: ./runs/May06_11-33-02_crimv3mgpu025
431
+ logging_strategy:
432
+ desc: null
433
+ value: steps
434
+ logging_first_step:
435
+ desc: null
436
+ value: false
437
+ logging_steps:
438
+ desc: null
439
+ value: 25
440
+ logging_nan_inf_filter:
441
+ desc: null
442
+ value: true
443
+ save_strategy:
444
+ desc: null
445
+ value: steps
446
+ save_steps:
447
+ desc: null
448
+ value: 1000
449
+ save_total_limit:
450
+ desc: null
451
+ value: None
452
+ save_safetensors:
453
+ desc: null
454
+ value: false
455
+ save_on_each_node:
456
+ desc: null
457
+ value: false
458
+ no_cuda:
459
+ desc: null
460
+ value: false
461
+ use_mps_device:
462
+ desc: null
463
+ value: false
464
+ seed:
465
+ desc: null
466
+ value: 42
467
+ data_seed:
468
+ desc: null
469
+ value: None
470
+ jit_mode_eval:
471
+ desc: null
472
+ value: false
473
+ use_ipex:
474
+ desc: null
475
+ value: false
476
+ bf16:
477
+ desc: null
478
+ value: false
479
+ fp16:
480
+ desc: null
481
+ value: true
482
+ fp16_opt_level:
483
+ desc: null
484
+ value: O1
485
+ half_precision_backend:
486
+ desc: null
487
+ value: cuda_amp
488
+ bf16_full_eval:
489
+ desc: null
490
+ value: false
491
+ fp16_full_eval:
492
+ desc: null
493
+ value: false
494
+ tf32:
495
+ desc: null
496
+ value: None
497
+ local_rank:
498
+ desc: null
499
+ value: 0
500
+ ddp_backend:
501
+ desc: null
502
+ value: None
503
+ tpu_num_cores:
504
+ desc: null
505
+ value: None
506
+ tpu_metrics_debug:
507
+ desc: null
508
+ value: false
509
+ debug:
510
+ desc: null
511
+ value: '[]'
512
+ dataloader_drop_last:
513
+ desc: null
514
+ value: false
515
+ eval_steps:
516
+ desc: null
517
+ value: 1000
518
+ dataloader_num_workers:
519
+ desc: null
520
+ value: 0
521
+ past_index:
522
+ desc: null
523
+ value: -1
524
+ run_name:
525
+ desc: null
526
+ value: ./
527
+ disable_tqdm:
528
+ desc: null
529
+ value: false
530
+ remove_unused_columns:
531
+ desc: null
532
+ value: true
533
+ label_names:
534
+ desc: null
535
+ value: None
536
+ load_best_model_at_end:
537
+ desc: null
538
+ value: true
539
+ metric_for_best_model:
540
+ desc: null
541
+ value: wer
542
+ greater_is_better:
543
+ desc: null
544
+ value: false
545
+ ignore_data_skip:
546
+ desc: null
547
+ value: false
548
+ sharded_ddp:
549
+ desc: null
550
+ value: '[]'
551
+ fsdp:
552
+ desc: null
553
+ value: '[]'
554
+ fsdp_min_num_params:
555
+ desc: null
556
+ value: 0
557
+ fsdp_config:
558
+ desc: null
559
+ value: '{''fsdp_min_num_params'': 0, ''xla'': False, ''xla_fsdp_grad_ckpt'': False}'
560
+ fsdp_transformer_layer_cls_to_wrap:
561
+ desc: null
562
+ value: None
563
+ deepspeed:
564
+ desc: null
565
+ value: None
566
+ label_smoothing_factor:
567
+ desc: null
568
+ value: 0.0
569
+ optim:
570
+ desc: null
571
+ value: adamw_hf
572
+ optim_args:
573
+ desc: null
574
+ value: None
575
+ adafactor:
576
+ desc: null
577
+ value: false
578
+ group_by_length:
579
+ desc: null
580
+ value: false
581
+ length_column_name:
582
+ desc: null
583
+ value: input_length
584
+ report_to:
585
+ desc: null
586
+ value: '[''wandb'']'
587
+ ddp_find_unused_parameters:
588
+ desc: null
589
+ value: None
590
+ ddp_bucket_cap_mb:
591
+ desc: null
592
+ value: None
593
+ dataloader_pin_memory:
594
+ desc: null
595
+ value: true
596
+ skip_memory_metrics:
597
+ desc: null
598
+ value: true
599
+ use_legacy_prediction_loop:
600
+ desc: null
601
+ value: false
602
+ push_to_hub:
603
+ desc: null
604
+ value: true
605
+ resume_from_checkpoint:
606
+ desc: null
607
+ value: None
608
+ hub_model_id:
609
+ desc: null
610
+ value: None
611
+ hub_strategy:
612
+ desc: null
613
+ value: every_save
614
+ hub_token:
615
+ desc: null
616
+ value: <HUB_TOKEN>
617
+ hub_private_repo:
618
+ desc: null
619
+ value: false
620
+ gradient_checkpointing:
621
+ desc: null
622
+ value: true
623
+ include_inputs_for_metrics:
624
+ desc: null
625
+ value: false
626
+ fp16_backend:
627
+ desc: null
628
+ value: auto
629
+ push_to_hub_model_id:
630
+ desc: null
631
+ value: None
632
+ push_to_hub_organization:
633
+ desc: null
634
+ value: None
635
+ push_to_hub_token:
636
+ desc: null
637
+ value: <PUSH_TO_HUB_TOKEN>
638
+ mp_parameters:
639
+ desc: null
640
+ value: ''
641
+ auto_find_batch_size:
642
+ desc: null
643
+ value: false
644
+ full_determinism:
645
+ desc: null
646
+ value: false
647
+ torchdynamo:
648
+ desc: null
649
+ value: None
650
+ ray_scope:
651
+ desc: null
652
+ value: last
653
+ ddp_timeout:
654
+ desc: null
655
+ value: 1800
656
+ torch_compile:
657
+ desc: null
658
+ value: false
659
+ torch_compile_backend:
660
+ desc: null
661
+ value: None
662
+ torch_compile_mode:
663
+ desc: null
664
+ value: None
665
+ xpu_backend:
666
+ desc: null
667
+ value: None
668
+ sortish_sampler:
669
+ desc: null
670
+ value: false
671
+ predict_with_generate:
672
+ desc: null
673
+ value: true
674
+ generation_max_length:
675
+ desc: null
676
+ value: 225
677
+ generation_num_beams:
678
+ desc: null
679
+ value: None
680
+ generation_config:
681
+ desc: null
682
+ value: None
683
+ train_batch_size:
684
+ desc: null
685
+ value: 64
686
+ eval_batch_size:
687
+ desc: null
688
+ value: 64
wandb/run-20230506_113337-ysywp688/files/output.log ADDED
@@ -0,0 +1,1101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 0%| | 0/5000 [00:00<?, ?it/s]
2
+
3
+
4
+ Reading metadata...: 23332it [00:04, 5566.60it/s]
5
+
6
+
7
+ [INFO|trainer_utils.py:693] 2023-05-06 11:35:39,880 >> The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.
8
+ /home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
9
+ warnings.warn('Was asked to gather along dimension 0, but all '
10
+
11
+
12
+
13
+
14
+
15
+
16
+
17
+
18
+
19
+
20
+
21
+
22
+
23
+
24
+
25
+
26
+
27
+
28
+
29
+
30
+
31
+
32
+
33
+
34
+ 0%| | 25/5000 [14:20<40:49:08, 29.54s/it]
35
+
36
+
37
+
38
+
39
+
40
+
41
+
42
+
43
+
44
+
45
+
46
+
47
+
48
+
49
+
50
+
51
+
52
+
53
+
54
+
55
+
56
+
57
+
58
+
59
+ 1%| | 49/5000 [25:57<39:52:38, 29.00s/it]
60
+
61
+
62
+
63
+
64
+
65
+
66
+
67
+
68
+
69
+
70
+
71
+
72
+
73
+
74
+
75
+
76
+
77
+
78
+
79
+
80
+
81
+
82
+
83
+
84
+
85
+ 1%|▏ | 74/5000 [38:10<39:26:07, 28.82s/it]
86
+
87
+
88
+
89
+
90
+
91
+
92
+
93
+
94
+
95
+
96
+
97
+
98
+
99
+
100
+
101
+
102
+
103
+
104
+
105
+
106
+
107
+
108
+
109
+
110
+
111
+ 2%|▏ | 99/5000 [50:13<39:03:58, 28.70s/it]
112
+
113
+
114
+
115
+
116
+
117
+
118
+
119
+
120
+
121
+
122
+
123
+
124
+
125
+
126
+
127
+
128
+
129
+
130
+
131
+
132
+
133
+
134
+
135
+
136
+
137
+ 2%|▏ | 124/5000 [1:02:25<38:47:32, 28.64s/it]
138
+
139
+
140
+
141
+
142
+
143
+
144
+
145
+
146
+
147
+
148
+
149
+
150
+
151
+
152
+
153
+
154
+
155
+
156
+
157
+
158
+
159
+
160
+
161
+
162
+
163
+
164
+ 3%|▎ | 150/5000 [1:15:09<40:31:35, 30.08s/it]
165
+
166
+
167
+
168
+
169
+
170
+
171
+
172
+
173
+
174
+
175
+
176
+
177
+
178
+ 3%|▎ | 163/5000 [1:20:20<21:29:00, 15.99s/it]
179
+
180
+ Reading metadata...: 22927it [00:03, 10857.89it/s]
181
+
182
+
183
+
184
+
185
+
186
+
187
+
188
+
189
+
190
+
191
+
192
+
193
+ 3%|▎ | 174/5000 [1:26:45<37:53:20, 28.26s/it]
194
+
195
+
196
+
197
+
198
+
199
+
200
+
201
+
202
+
203
+
204
+
205
+
206
+
207
+
208
+
209
+
210
+
211
+
212
+
213
+
214
+
215
+
216
+
217
+
218
+
219
+
220
+ 4%|▍ | 200/5000 [1:38:49<36:55:58, 27.70s/it]
221
+
222
+
223
+
224
+
225
+
226
+
227
+
228
+
229
+
230
+
231
+
232
+
233
+
234
+
235
+
236
+
237
+
238
+
239
+
240
+
241
+
242
+
243
+
244
+
245
+ 4%|▍ | 224/5000 [1:49:53<36:01:48, 27.16s/it]
246
+
247
+
248
+
249
+
250
+
251
+
252
+
253
+
254
+
255
+
256
+
257
+
258
+
259
+
260
+
261
+
262
+
263
+
264
+
265
+
266
+
267
+
268
+
269
+
270
+
271
+ 5%|▍ | 249/5000 [2:01:25<35:37:24, 26.99s/it]
272
+
273
+
274
+
275
+
276
+
277
+
278
+
279
+
280
+
281
+
282
+
283
+
284
+
285
+
286
+
287
+
288
+
289
+
290
+
291
+
292
+
293
+
294
+
295
+
296
+
297
+ 5%|▌ | 274/5000 [2:12:59<36:06:06, 27.50s/it]
298
+
299
+
300
+
301
+
302
+
303
+
304
+
305
+
306
+
307
+
308
+
309
+
310
+
311
+
312
+
313
+
314
+
315
+
316
+
317
+
318
+
319
+
320
+
321
+
322
+
323
+ 6%|▌ | 299/5000 [2:24:40<37:31:10, 28.73s/it]
324
+
325
+
326
+
327
+
328
+
329
+
330
+
331
+
332
+
333
+
334
+
335
+
336
+
337
+
338
+
339
+
340
+
341
+
342
+
343
+
344
+
345
+
346
+
347
+
348
+
349
+ 6%|▋ | 324/5000 [2:35:58<29:09:59, 22.45s/it]
350
+
351
+
352
+
353
+ 7%|▋ | 327/5000 [2:36:27<18:05:01, 13.93s/it]
354
+
355
+
356
+ Reading metadata...: 24506it [00:05, 5432.25it/s]
357
+
358
+
359
+
360
+
361
+
362
+
363
+
364
+
365
+
366
+
367
+
368
+
369
+
370
+
371
+
372
+
373
+
374
+
375
+
376
+
377
+
378
+
379
+
380
+ 7%|▋ | 349/5000 [2:48:13<35:54:20, 27.79s/it]
381
+
382
+
383
+
384
+
385
+
386
+
387
+
388
+
389
+
390
+
391
+
392
+
393
+
394
+
395
+
396
+
397
+
398
+
399
+
400
+
401
+
402
+
403
+
404
+
405
+
406
+ 7%|▋ | 374/5000 [3:00:12<40:33:48, 31.57s/it]
407
+
408
+
409
+
410
+
411
+
412
+
413
+
414
+
415
+
416
+
417
+
418
+
419
+
420
+
421
+
422
+
423
+
424
+
425
+
426
+
427
+
428
+
429
+
430
+
431
+
432
+
433
+ 8%|▊ | 400/5000 [3:12:45<36:54:59, 28.89s/it]
434
+
435
+
436
+
437
+
438
+
439
+
440
+
441
+
442
+
443
+
444
+
445
+
446
+
447
+
448
+
449
+
450
+
451
+
452
+
453
+
454
+
455
+
456
+
457
+
458
+
459
+ 8%|▊ | 425/5000 [3:24:31<35:49:54, 28.20s/it]
460
+
461
+
462
+
463
+
464
+
465
+
466
+
467
+
468
+
469
+
470
+
471
+
472
+
473
+
474
+
475
+
476
+
477
+
478
+
479
+
480
+
481
+
482
+
483
+
484
+ 9%|▉ | 449/5000 [3:35:37<34:58:52, 27.67s/it]
485
+
486
+
487
+
488
+
489
+
490
+
491
+
492
+
493
+
494
+
495
+
496
+
497
+
498
+
499
+
500
+
501
+
502
+
503
+
504
+
505
+
506
+
507
+
508
+
509
+
510
+
511
+ 10%|▉ | 475/5000 [3:47:38<34:53:17, 27.76s/it]
512
+
513
+
514
+
515
+
516
+
517
+
518
+
519
+
520
+
521
+
522
+
523
+
524
+
525
+
526
+
527
+ 10%|▉ | 490/5000 [3:53:33<19:04:32, 15.23s/it]
528
+
529
+ Reading metadata...: 10438it [00:00, 25934.78it/s]
530
+
531
+
532
+
533
+
534
+
535
+
536
+
537
+
538
+
539
+ 10%|▉ | 499/5000 [3:58:50<37:18:31, 29.84s/it]
540
+
541
+
542
+
543
+
544
+
545
+
546
+
547
+
548
+
549
+
550
+
551
+
552
+
553
+
554
+
555
+
556
+
557
+
558
+
559
+
560
+
561
+
562
+
563
+
564
+
565
+
566
+ 10%|█ | 525/5000 [4:10:52<34:41:42, 27.91s/it]
567
+
568
+
569
+
570
+
571
+
572
+
573
+
574
+
575
+
576
+
577
+
578
+
579
+
580
+
581
+
582
+
583
+
584
+
585
+
586
+
587
+
588
+
589
+
590
+
591
+
592
+ 11%|█ | 550/5000 [4:22:29<34:29:35, 27.90s/it]
593
+
594
+
595
+
596
+
597
+
598
+
599
+
600
+
601
+
602
+
603
+
604
+
605
+
606
+
607
+
608
+
609
+
610
+
611
+
612
+
613
+
614
+
615
+
616
+
617
+
618
+ 12%|█▏ | 575/5000 [4:34:05<34:32:46, 28.11s/it]
619
+
620
+
621
+
622
+
623
+
624
+
625
+
626
+
627
+
628
+
629
+
630
+
631
+
632
+
633
+
634
+
635
+
636
+
637
+
638
+
639
+
640
+
641
+
642
+
643
+
644
+ 12%|█▏ | 600/5000 [4:45:35<34:09:51, 27.95s/it]
645
+
646
+
647
+
648
+
649
+
650
+
651
+
652
+
653
+
654
+
655
+
656
+
657
+
658
+
659
+
660
+
661
+
662
+
663
+
664
+
665
+
666
+
667
+
668
+
669
+
670
+ 12%|█▎ | 625/5000 [4:57:10<33:31:38, 27.59s/it]
671
+
672
+
673
+
674
+
675
+
676
+
677
+
678
+
679
+
680
+
681
+
682
+
683
+
684
+
685
+
686
+
687
+
688
+
689
+
690
+
691
+
692
+
693
+
694
+
695
+
696
+ 13%|█▎ | 650/5000 [5:08:39<31:35:25, 26.14s/it]
697
+
698
+
699
+
700
+ 13%|█▎ | 654/5000 [5:09:19<16:25:57, 13.61s/it]
701
+
702
+ Reading metadata...: 10438it [00:00, 25770.40it/s]
703
+
704
+
705
+
706
+
707
+
708
+
709
+
710
+
711
+
712
+
713
+
714
+
715
+
716
+
717
+
718
+
719
+
720
+
721
+
722
+
723
+ 13%|█▎ | 674/5000 [5:19:54<34:45:47, 28.93s/it]
724
+
725
+
726
+
727
+
728
+
729
+
730
+
731
+
732
+
733
+
734
+
735
+
736
+
737
+
738
+
739
+
740
+
741
+
742
+
743
+
744
+
745
+
746
+
747
+
748
+
749
+
750
+ 14%|█▍ | 700/5000 [5:31:55<32:45:38, 27.43s/it]
751
+
752
+
753
+
754
+
755
+
756
+
757
+
758
+
759
+
760
+
761
+
762
+
763
+
764
+
765
+
766
+
767
+
768
+
769
+
770
+
771
+
772
+
773
+
774
+
775
+ 14%|█▍ | 724/5000 [5:43:03<33:14:52, 27.99s/it]
776
+
777
+
778
+
779
+
780
+
781
+
782
+
783
+
784
+
785
+
786
+
787
+
788
+
789
+
790
+
791
+
792
+
793
+
794
+
795
+
796
+
797
+
798
+
799
+
800
+
801
+
802
+ 15%|█▌ | 750/5000 [5:55:12<34:08:13, 28.92s/it]
803
+
804
+
805
+
806
+
807
+
808
+
809
+
810
+
811
+
812
+
813
+
814
+
815
+
816
+
817
+
818
+
819
+
820
+
821
+
822
+
823
+
824
+
825
+
826
+
827
+
828
+ 16%|█▌ | 775/5000 [6:06:46<32:23:45, 27.60s/it]
829
+
830
+
831
+
832
+
833
+
834
+
835
+
836
+
837
+
838
+
839
+
840
+
841
+
842
+
843
+
844
+
845
+
846
+
847
+
848
+
849
+
850
+
851
+
852
+
853
+
854
+ 16%|█▌ | 800/5000 [6:18:21<32:13:15, 27.62s/it]
855
+
856
+
857
+
858
+
859
+
860
+
861
+
862
+
863
+
864
+
865
+
866
+
867
+
868
+
869
+
870
+
871
+
872
+ Reading metadata...: 28043it [00:01, 19987.99it/s]s/it]
873
+ Reading metadata...: 10438it [00:00, 25735.72it/s]
874
+
875
+
876
+
877
+
878
+
879
+
880
+
881
+
882
+ 16%|█▋ | 825/5000 [6:29:57<33:54:47, 29.24s/it]
883
+
884
+
885
+
886
+
887
+
888
+
889
+
890
+
891
+
892
+
893
+
894
+
895
+
896
+
897
+
898
+
899
+
900
+
901
+
902
+
903
+
904
+
905
+
906
+
907
+
908
+ 17%|█▋ | 850/5000 [6:41:29<31:44:09, 27.53s/it]
909
+
910
+
911
+
912
+
913
+
914
+
915
+
916
+
917
+
918
+
919
+
920
+
921
+
922
+
923
+
924
+
925
+
926
+
927
+
928
+
929
+
930
+
931
+
932
+
933
+
934
+ 18%|█▊ | 875/5000 [6:53:08<31:50:31, 27.79s/it]
935
+
936
+
937
+
938
+
939
+
940
+
941
+
942
+
943
+
944
+
945
+
946
+
947
+
948
+
949
+
950
+
951
+
952
+
953
+
954
+
955
+
956
+
957
+
958
+
959
+
960
+ 18%|█▊ | 900/5000 [7:04:43<31:41:55, 27.83s/it]
961
+
962
+
963
+
964
+
965
+
966
+
967
+
968
+
969
+
970
+
971
+
972
+
973
+
974
+
975
+
976
+
977
+
978
+
979
+
980
+
981
+
982
+
983
+
984
+
985
+
986
+ 18%|█▊ | 925/5000 [7:16:16<31:19:18, 27.67s/it]
987
+
988
+
989
+
990
+
991
+
992
+
993
+
994
+
995
+
996
+
997
+
998
+
999
+
1000
+
1001
+
1002
+
1003
+
1004
+
1005
+
1006
+
1007
+
1008
+
1009
+
1010
+
1011
+ 19%|█▉ | 949/5000 [7:27:24<31:16:42, 27.80s/it]
1012
+
1013
+
1014
+
1015
+
1016
+
1017
+
1018
+
1019
+
1020
+
1021
+
1022
+
1023
+
1024
+
1025
+
1026
+
1027
+
1028
+
1029
+
1030
+
1031
+
1032
+
1033
+
1034
+
1035
+
1036
+
1037
+
1038
+ 20%|█▉ | 975/5000 [7:39:31<30:54:27, 27.64s/it]
1039
+
1040
+
1041
+
1042
+
1043
+
1044
+ Reading metadata...: 28043it [00:00, 28643.05it/s]s/it]
1045
+ Reading metadata...: 10438it [00:00, 24507.54it/s]
1046
+
1047
+
1048
+
1049
+
1050
+
1051
+
1052
+
1053
+
1054
+
1055
+
1056
+
1057
+
1058
+
1059
+
1060
+
1061
+
1062
+
1063
+
1064
+ 20%|██ | 1000/5000 [7:51:12<31:18:37, 28.18s/it][INFO|trainer.py:3138] 2023-05-06 19:25:00,699 >> ***** Running Evaluation *****
1065
+ [INFO|trainer.py:3142] 2023-05-06 19:25:00,699 >> Num examples: Unknown
1066
+ [INFO|trainer.py:3143] 2023-05-06 19:25:00,699 >> Batch size = 64
1067
+ {'loss': 0.0517, 'learning_rate': 8.893333333333333e-06, 'epoch': 6.0}
1068
+
1069
+
1070
+ [INFO|trainer_utils.py:693] 2023-05-06 19:25:16,854 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.
1071
+ {'eval_loss': 0.43406692147254944, 'eval_wer': 54.476, 'eval_runtime': 2259.524, 'eval_samples_per_second': 4.62, 'eval_steps_per_second': 0.073, 'epoch': 6.0}
1072
+ 20%|██ | 1000/5000 [8:28:52<31:18:37, 28.18s/it][INFO|trainer.py:2877] 2023-05-06 20:02:40,234 >> Saving model checkpoint to ./checkpoint-1000
1073
+ [INFO|configuration_utils.py:458] 2023-05-06 20:02:40,239 >> Configuration saved in ./checkpoint-1000/config.json
1074
+ [INFO|configuration_utils.py:364] 2023-05-06 20:02:40,243 >> Configuration saved in ./checkpoint-1000/generation_config.json
1075
+ [INFO|modeling_utils.py:1855] 2023-05-06 20:02:43,051 >> Model weights saved in ./checkpoint-1000/pytorch_model.bin
1076
+ [INFO|feature_extraction_utils.py:369] 2023-05-06 20:02:43,056 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
1077
+ [INFO|feature_extraction_utils.py:369] 2023-05-06 20:02:51,152 >> Feature extractor saved in ./preprocessor_config.json
1078
+ Traceback (most recent call last):
1079
+ File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 629, in <module>
1080
+ main()
1081
+ File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 578, in main
1082
+ train_result = trainer.train(resume_from_checkpoint=checkpoint)
1083
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 1664, in train
1084
+ return inner_training_loop(
1085
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 2011, in _inner_training_loop
1086
+ self._maybe_log_save_evaluate(tr_loss, model, trial, epoch, ignore_keys_for_eval)
1087
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 2300, in _maybe_log_save_evaluate
1088
+ self._save_checkpoint(model, trial, metrics=metrics)
1089
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 2444, in _save_checkpoint
1090
+ self._push_from_checkpoint(output_dir)
1091
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 3622, in _push_from_checkpoint
1092
+ _, self.push_in_progress = self.repo.push_to_hub(
1093
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 1305, in push_to_hub
1094
+ self.git_add(auto_lfs_track=True)
1095
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 1009, in git_add
1096
+ tracked_files.extend(self.auto_track_binary_files(pattern))
1097
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 903, in auto_track_binary_files
1098
+ is_binary = is_binary_file(path_to_file)
1099
+ File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 230, in is_binary_file
1100
+ with open(filename, "rb") as f:
1101
+ IsADirectoryError: [Errno 21] Is a directory: '/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/./wandb/latest-run'
wandb/run-20230506_113337-ysywp688/files/requirements.txt ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==1.4.0
2
+ accelerate==0.18.0
3
+ aiohttp==3.8.4
4
+ aiosignal==1.3.1
5
+ appdirs==1.4.4
6
+ async-timeout==4.0.2
7
+ attrs==23.1.0
8
+ audioread==3.0.0
9
+ cachetools==5.3.0
10
+ certifi==2022.12.7
11
+ cffi==1.15.1
12
+ charset-normalizer==3.1.0
13
+ click==8.1.3
14
+ cmake==3.26.3
15
+ datasets==2.12.1.dev0
16
+ decorator==5.1.1
17
+ dill==0.3.6
18
+ docker-pycreds==0.4.0
19
+ evaluate==0.4.0
20
+ filelock==3.12.0
21
+ frozenlist==1.3.3
22
+ fsspec==2023.4.0
23
+ gitdb==4.0.10
24
+ gitpython==3.1.31
25
+ google-auth-oauthlib==1.0.0
26
+ google-auth==2.17.3
27
+ grpcio==1.54.0
28
+ huggingface-hub==0.14.1
29
+ idna==3.4
30
+ importlib-metadata==6.6.0
31
+ jinja2==3.1.2
32
+ jiwer==3.0.1
33
+ joblib==1.2.0
34
+ lazy-loader==0.2
35
+ librosa==0.10.0.post2
36
+ lit==16.0.2
37
+ llvmlite==0.40.0
38
+ markdown==3.4.3
39
+ markupsafe==2.1.2
40
+ more-itertools==9.1.0
41
+ mpmath==1.3.0
42
+ msgpack==1.0.5
43
+ multidict==6.0.4
44
+ multiprocess==0.70.14
45
+ networkx==3.1
46
+ numba==0.57.0
47
+ numpy==1.24.3
48
+ nvidia-cublas-cu11==11.10.3.66
49
+ nvidia-cuda-cupti-cu11==11.7.101
50
+ nvidia-cuda-nvrtc-cu11==11.7.99
51
+ nvidia-cuda-runtime-cu11==11.7.99
52
+ nvidia-cudnn-cu11==8.5.0.96
53
+ nvidia-cufft-cu11==10.9.0.58
54
+ nvidia-curand-cu11==10.2.10.91
55
+ nvidia-cusolver-cu11==11.4.0.1
56
+ nvidia-cusparse-cu11==11.7.4.91
57
+ nvidia-nccl-cu11==2.14.3
58
+ nvidia-nvtx-cu11==11.7.91
59
+ oauthlib==3.2.2
60
+ packaging==23.1
61
+ pandas==2.0.1
62
+ pathtools==0.1.2
63
+ pip==23.1.2
64
+ pooch==1.6.0
65
+ protobuf==4.22.3
66
+ psutil==5.9.5
67
+ pyarrow==12.0.0
68
+ pyasn1-modules==0.3.0
69
+ pyasn1==0.5.0
70
+ pycparser==2.21
71
+ python-dateutil==2.8.2
72
+ pytz==2023.3
73
+ pyyaml==6.0
74
+ rapidfuzz==2.13.7
75
+ regex==2023.5.4
76
+ requests-oauthlib==1.3.1
77
+ requests==2.29.0
78
+ responses==0.18.0
79
+ rsa==4.9
80
+ scikit-learn==1.2.2
81
+ scipy==1.10.1
82
+ sentry-sdk==1.22.1
83
+ setproctitle==1.3.2
84
+ setuptools==67.7.2
85
+ six==1.16.0
86
+ smmap==5.0.0
87
+ soundfile==0.12.1
88
+ soxr==0.3.5
89
+ sympy==1.11.1
90
+ tensorboard-data-server==0.7.0
91
+ tensorboard==2.12.3
92
+ threadpoolctl==3.1.0
93
+ tokenizers==0.13.3
94
+ torch==2.0.0
95
+ torchaudio==2.0.1
96
+ tqdm==4.65.0
97
+ transformers==4.29.0.dev0
98
+ triton==2.0.0
99
+ typing-extensions==4.5.0
100
+ tzdata==2023.3
101
+ urllib3==1.26.15
102
+ wandb==0.15.2
103
+ werkzeug==2.3.3
104
+ wheel==0.40.0
105
+ xxhash==3.2.0
106
+ yarl==1.9.2
107
+ zipp==3.15.0
wandb/run-20230506_113337-ysywp688/files/wandb-metadata.json ADDED
@@ -0,0 +1,369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-3.10.0-957.27.2.el7.x86_64-x86_64-with-glibc2.17",
3
+ "python": "3.9.16",
4
+ "heartbeatAt": "2023-05-06T08:33:38.114072",
5
+ "startedAt": "2023-05-06T08:33:37.104716",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "--model_name_or_path=openai/whisper-small",
10
+ "--dataset_name=mozilla-foundation/common_voice_11_0",
11
+ "--dataset_config_name=ar",
12
+ "--language=arabic",
13
+ "--train_split_name=train+validation",
14
+ "--eval_split_name=test",
15
+ "--model_index_name=Whisper Small Arabic",
16
+ "--max_steps=5000",
17
+ "--output_dir=./",
18
+ "--per_device_train_batch_size=32",
19
+ "--gradient_accumulation_steps=2",
20
+ "--per_device_eval_batch_size=32",
21
+ "--logging_steps=25",
22
+ "--learning_rate=1e-5",
23
+ "--warmup_steps=500",
24
+ "--evaluation_strategy=steps",
25
+ "--eval_steps=1000",
26
+ "--save_strategy=steps",
27
+ "--save_steps=1000",
28
+ "--generation_max_length=225",
29
+ "--length_column_name=input_length",
30
+ "--max_duration_in_seconds=30",
31
+ "--text_column_name=sentence",
32
+ "--freeze_feature_encoder=False",
33
+ "--report_to=tensorboard",
34
+ "--report_to=wandb",
35
+ "--metric_for_best_model=wer",
36
+ "--greater_is_better=False",
37
+ "--load_best_model_at_end",
38
+ "--gradient_checkpointing",
39
+ "--fp16",
40
+ "--overwrite_output_dir",
41
+ "--do_train",
42
+ "--do_eval",
43
+ "--predict_with_generate",
44
+ "--do_normalize_eval",
45
+ "--streaming",
46
+ "--use_auth_token",
47
+ "--push_to_hub"
48
+ ],
49
+ "state": "running",
50
+ "program": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py",
51
+ "codePath": "run_speech_recognition_seq2seq_streaming.py",
52
+ "git": {
53
+ "remote": "https://huggingface.co/danielizham/whisper-small-ar",
54
+ "commit": "33cfe8b27be49d1904070ffc4339ab1b4075c5b1"
55
+ },
56
+ "email": "[email protected]",
57
+ "root": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar",
58
+ "host": "crimv3mgpu025",
59
+ "username": "dizham",
60
+ "executable": "/home/local/QCRI/dizham/miniconda3/envs/whisper/bin/python",
61
+ "cpu_count": 28,
62
+ "cpu_count_logical": 56,
63
+ "cpu_freq": {
64
+ "current": 2201.0,
65
+ "min": 1000.0,
66
+ "max": 2201.0
67
+ },
68
+ "cpu_freq_per_core": [
69
+ {
70
+ "current": 2201.0,
71
+ "min": 1000.0,
72
+ "max": 2201.0
73
+ },
74
+ {
75
+ "current": 2201.0,
76
+ "min": 1000.0,
77
+ "max": 2201.0
78
+ },
79
+ {
80
+ "current": 2201.0,
81
+ "min": 1000.0,
82
+ "max": 2201.0
83
+ },
84
+ {
85
+ "current": 2201.0,
86
+ "min": 1000.0,
87
+ "max": 2201.0
88
+ },
89
+ {
90
+ "current": 2201.0,
91
+ "min": 1000.0,
92
+ "max": 2201.0
93
+ },
94
+ {
95
+ "current": 2201.0,
96
+ "min": 1000.0,
97
+ "max": 2201.0
98
+ },
99
+ {
100
+ "current": 2201.0,
101
+ "min": 1000.0,
102
+ "max": 2201.0
103
+ },
104
+ {
105
+ "current": 2201.0,
106
+ "min": 1000.0,
107
+ "max": 2201.0
108
+ },
109
+ {
110
+ "current": 2201.0,
111
+ "min": 1000.0,
112
+ "max": 2201.0
113
+ },
114
+ {
115
+ "current": 2201.0,
116
+ "min": 1000.0,
117
+ "max": 2201.0
118
+ },
119
+ {
120
+ "current": 2201.0,
121
+ "min": 1000.0,
122
+ "max": 2201.0
123
+ },
124
+ {
125
+ "current": 2201.0,
126
+ "min": 1000.0,
127
+ "max": 2201.0
128
+ },
129
+ {
130
+ "current": 2201.0,
131
+ "min": 1000.0,
132
+ "max": 2201.0
133
+ },
134
+ {
135
+ "current": 2201.0,
136
+ "min": 1000.0,
137
+ "max": 2201.0
138
+ },
139
+ {
140
+ "current": 2201.0,
141
+ "min": 1000.0,
142
+ "max": 2201.0
143
+ },
144
+ {
145
+ "current": 2201.0,
146
+ "min": 1000.0,
147
+ "max": 2201.0
148
+ },
149
+ {
150
+ "current": 2201.0,
151
+ "min": 1000.0,
152
+ "max": 2201.0
153
+ },
154
+ {
155
+ "current": 2201.0,
156
+ "min": 1000.0,
157
+ "max": 2201.0
158
+ },
159
+ {
160
+ "current": 2201.0,
161
+ "min": 1000.0,
162
+ "max": 2201.0
163
+ },
164
+ {
165
+ "current": 2201.0,
166
+ "min": 1000.0,
167
+ "max": 2201.0
168
+ },
169
+ {
170
+ "current": 2201.0,
171
+ "min": 1000.0,
172
+ "max": 2201.0
173
+ },
174
+ {
175
+ "current": 2201.0,
176
+ "min": 1000.0,
177
+ "max": 2201.0
178
+ },
179
+ {
180
+ "current": 2201.0,
181
+ "min": 1000.0,
182
+ "max": 2201.0
183
+ },
184
+ {
185
+ "current": 2201.0,
186
+ "min": 1000.0,
187
+ "max": 2201.0
188
+ },
189
+ {
190
+ "current": 2201.0,
191
+ "min": 1000.0,
192
+ "max": 2201.0
193
+ },
194
+ {
195
+ "current": 2201.0,
196
+ "min": 1000.0,
197
+ "max": 2201.0
198
+ },
199
+ {
200
+ "current": 2201.0,
201
+ "min": 1000.0,
202
+ "max": 2201.0
203
+ },
204
+ {
205
+ "current": 2201.0,
206
+ "min": 1000.0,
207
+ "max": 2201.0
208
+ },
209
+ {
210
+ "current": 2201.0,
211
+ "min": 1000.0,
212
+ "max": 2201.0
213
+ },
214
+ {
215
+ "current": 2201.0,
216
+ "min": 1000.0,
217
+ "max": 2201.0
218
+ },
219
+ {
220
+ "current": 2201.0,
221
+ "min": 1000.0,
222
+ "max": 2201.0
223
+ },
224
+ {
225
+ "current": 2201.0,
226
+ "min": 1000.0,
227
+ "max": 2201.0
228
+ },
229
+ {
230
+ "current": 2201.0,
231
+ "min": 1000.0,
232
+ "max": 2201.0
233
+ },
234
+ {
235
+ "current": 2201.0,
236
+ "min": 1000.0,
237
+ "max": 2201.0
238
+ },
239
+ {
240
+ "current": 2201.0,
241
+ "min": 1000.0,
242
+ "max": 2201.0
243
+ },
244
+ {
245
+ "current": 2201.0,
246
+ "min": 1000.0,
247
+ "max": 2201.0
248
+ },
249
+ {
250
+ "current": 2201.0,
251
+ "min": 1000.0,
252
+ "max": 2201.0
253
+ },
254
+ {
255
+ "current": 2201.0,
256
+ "min": 1000.0,
257
+ "max": 2201.0
258
+ },
259
+ {
260
+ "current": 2201.0,
261
+ "min": 1000.0,
262
+ "max": 2201.0
263
+ },
264
+ {
265
+ "current": 2201.0,
266
+ "min": 1000.0,
267
+ "max": 2201.0
268
+ },
269
+ {
270
+ "current": 2201.0,
271
+ "min": 1000.0,
272
+ "max": 2201.0
273
+ },
274
+ {
275
+ "current": 2201.0,
276
+ "min": 1000.0,
277
+ "max": 2201.0
278
+ },
279
+ {
280
+ "current": 2201.0,
281
+ "min": 1000.0,
282
+ "max": 2201.0
283
+ },
284
+ {
285
+ "current": 2201.0,
286
+ "min": 1000.0,
287
+ "max": 2201.0
288
+ },
289
+ {
290
+ "current": 2201.0,
291
+ "min": 1000.0,
292
+ "max": 2201.0
293
+ },
294
+ {
295
+ "current": 2201.0,
296
+ "min": 1000.0,
297
+ "max": 2201.0
298
+ },
299
+ {
300
+ "current": 2201.0,
301
+ "min": 1000.0,
302
+ "max": 2201.0
303
+ },
304
+ {
305
+ "current": 2201.0,
306
+ "min": 1000.0,
307
+ "max": 2201.0
308
+ },
309
+ {
310
+ "current": 2201.0,
311
+ "min": 1000.0,
312
+ "max": 2201.0
313
+ },
314
+ {
315
+ "current": 2201.0,
316
+ "min": 1000.0,
317
+ "max": 2201.0
318
+ },
319
+ {
320
+ "current": 2201.0,
321
+ "min": 1000.0,
322
+ "max": 2201.0
323
+ },
324
+ {
325
+ "current": 2201.0,
326
+ "min": 1000.0,
327
+ "max": 2201.0
328
+ },
329
+ {
330
+ "current": 2201.0,
331
+ "min": 1000.0,
332
+ "max": 2201.0
333
+ },
334
+ {
335
+ "current": 2201.0,
336
+ "min": 1000.0,
337
+ "max": 2201.0
338
+ },
339
+ {
340
+ "current": 2201.0,
341
+ "min": 1000.0,
342
+ "max": 2201.0
343
+ },
344
+ {
345
+ "current": 2201.0,
346
+ "min": 1000.0,
347
+ "max": 2201.0
348
+ }
349
+ ],
350
+ "disk": {
351
+ "total": 99.951171875,
352
+ "used": 19.748153686523438
353
+ },
354
+ "gpu": "Tesla V100-SXM2-32GB",
355
+ "gpu_count": 2,
356
+ "gpu_devices": [
357
+ {
358
+ "name": "Tesla V100-SXM2-32GB",
359
+ "memory_total": 34089730048
360
+ },
361
+ {
362
+ "name": "Tesla V100-SXM2-32GB",
363
+ "memory_total": 34089730048
364
+ }
365
+ ],
366
+ "memory": {
367
+ "total": 251.55353164672852
368
+ }
369
+ }
wandb/run-20230506_113337-ysywp688/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/loss": 0.0517, "train/learning_rate": 8.893333333333333e-06, "train/epoch": 6.0, "train/global_step": 1000, "_timestamp": 1683392560.2236953, "_runtime": 30543.092183351517, "_step": 40, "eval/loss": 0.43406692147254944, "eval/wer": 54.476, "eval/runtime": 2259.524, "eval/samples_per_second": 4.62, "eval/steps_per_second": 0.073, "_wandb": {"runtime": 30558}}
wandb/run-20230506_113337-ysywp688/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20230506_113337-ysywp688/logs/debug.log ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Current SDK version is 0.15.2
2
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Configure stats pid to 59902
3
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/.config/wandb/settings
4
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/settings
5
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program': '/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py'}
8
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_init.py:_log_setup():507] Logging user logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230506_113337-ysywp688/logs/debug.log
9
+ 2023-05-06 11:33:37,123 INFO MainThread:59902 [wandb_init.py:_log_setup():508] Logging internal logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230506_113337-ysywp688/logs/debug-internal.log
10
+ 2023-05-06 11:33:37,124 INFO MainThread:59902 [wandb_init.py:init():547] calling init triggers
11
+ 2023-05-06 11:33:37,124 INFO MainThread:59902 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
12
+ config: {}
13
+ 2023-05-06 11:33:37,124 INFO MainThread:59902 [wandb_init.py:init():596] starting backend
14
+ 2023-05-06 11:33:37,124 INFO MainThread:59902 [wandb_init.py:init():600] setting up manager
15
+ 2023-05-06 11:33:37,127 INFO MainThread:59902 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
16
+ 2023-05-06 11:33:37,131 INFO MainThread:59902 [wandb_init.py:init():606] backend started and connected
17
+ 2023-05-06 11:33:37,133 INFO MainThread:59902 [wandb_init.py:init():700] updated telemetry
18
+ 2023-05-06 11:33:37,202 INFO MainThread:59902 [wandb_init.py:init():737] communicating run to backend with 60.0 second timeout
19
+ 2023-05-06 11:33:37,804 INFO MainThread:59902 [wandb_run.py:_on_init():2177] communicating current version
20
+ 2023-05-06 11:33:38,081 INFO MainThread:59902 [wandb_run.py:_on_init():2186] got version response
21
+ 2023-05-06 11:33:38,081 INFO MainThread:59902 [wandb_init.py:init():787] starting run threads in backend
22
+ 2023-05-06 11:33:47,905 INFO MainThread:59902 [wandb_run.py:_console_start():2158] atexit reg
23
+ 2023-05-06 11:33:47,906 INFO MainThread:59902 [wandb_run.py:_redirect():2013] redirect: SettingsConsole.WRAP_RAW
24
+ 2023-05-06 11:33:47,906 INFO MainThread:59902 [wandb_run.py:_redirect():2078] Wrapping output streams.
25
+ 2023-05-06 11:33:47,906 INFO MainThread:59902 [wandb_run.py:_redirect():2103] Redirects installed.
26
+ 2023-05-06 11:33:47,907 INFO MainThread:59902 [wandb_init.py:init():829] run started, returning control to user process
27
+ 2023-05-06 11:33:47,925 INFO MainThread:59902 [wandb_run.py:_config_callback():1286] config_cb None None {'vocab_size': 51865, 'num_mel_bins': 80, 'd_model': 768, 'encoder_layers': 12, 'encoder_attention_heads': 12, 'decoder_layers': 12, 'decoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'encoder_ffn_dim': 3072, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': False, 'num_hidden_layers': 12, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50257, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-small', 'transformers_version': '4.29.0.dev0', 'forced_decoder_ids': None, 'model_type': 'whisper', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 5000, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/May06_11-33-02_crimv3mgpu025', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 'None', 'save_safetensors': False, 'save_on_each_node': False, 'no_cuda': False, 'use_mps_device': False, 'seed': 42, 'data_seed': 'None', 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'cuda_amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': 0, 'ddp_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'fsdp': '[]', 'fsdp_min_num_params': 0, 'fsdp_config': "{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}", 'fsdp_transformer_layer_cls_to_wrap': 'None', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'optim_args': 'None', 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': 'None', 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': 'None', 'torch_compile_mode': 'None', 'xpu_backend': 'None', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': 'None', 'generation_config': 'None', 'train_batch_size': 64, 'eval_batch_size': 64}
28
+ 2023-05-06 20:03:08,523 WARNING MsgRouterThr:59902 [router.py:message_loop():77] message_loop has been closed
wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc04e94097f673d3a51da6ac65952f7e186c90757b4c6e65049e6316ed513737
3
+ size 2828090
wandb/run-20230507_103405-9zf5xxpu/files/conda-environment.yaml ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: whisper
2
+ channels:
3
+ - conda-forge
4
+ - defaults
5
+ dependencies:
6
+ - _libgcc_mutex=0.1=conda_forge
7
+ - _openmp_mutex=4.5=2_gnu
8
+ - bzip2=1.0.8=h7f98852_4
9
+ - ca-certificates=2022.12.7=ha878542_0
10
+ - git-lfs=3.3.0=ha770c72_0
11
+ - ld_impl_linux-64=2.40=h41732ed_0
12
+ - libffi=3.4.2=h7f98852_5
13
+ - libgcc-ng=12.2.0=h65d4601_19
14
+ - libgomp=12.2.0=h65d4601_19
15
+ - libnsl=2.0.0=h7f98852_0
16
+ - libsqlite=3.40.0=h753d276_1
17
+ - libuuid=2.38.1=h0b41bf4_0
18
+ - libzlib=1.2.13=h166bdaf_4
19
+ - ncurses=6.3=h27087fc_1
20
+ - openssl=3.1.0=hd590300_3
21
+ - pip=23.1.2=pyhd8ed1ab_0
22
+ - python=3.9.16=h2782a2a_0_cpython
23
+ - readline=8.2=h8228510_1
24
+ - setuptools=67.7.2=pyhd8ed1ab_0
25
+ - tk=8.6.12=h27826a3_0
26
+ - wheel=0.40.0=pyhd8ed1ab_0
27
+ - xz=5.2.6=h166bdaf_0
28
+ - pip:
29
+ - absl-py==1.4.0
30
+ - accelerate==0.18.0
31
+ - aiohttp==3.8.4
32
+ - aiosignal==1.3.1
33
+ - appdirs==1.4.4
34
+ - async-timeout==4.0.2
35
+ - attrs==23.1.0
36
+ - audioread==3.0.0
37
+ - cachetools==5.3.0
38
+ - certifi==2022.12.7
39
+ - cffi==1.15.1
40
+ - charset-normalizer==3.1.0
41
+ - click==8.1.3
42
+ - cmake==3.26.3
43
+ - datasets==2.12.1.dev0
44
+ - decorator==5.1.1
45
+ - dill==0.3.6
46
+ - docker-pycreds==0.4.0
47
+ - evaluate==0.4.0
48
+ - filelock==3.12.0
49
+ - frozenlist==1.3.3
50
+ - fsspec==2023.4.0
51
+ - gitdb==4.0.10
52
+ - gitpython==3.1.31
53
+ - google-auth==2.17.3
54
+ - google-auth-oauthlib==1.0.0
55
+ - grpcio==1.54.0
56
+ - huggingface-hub==0.14.1
57
+ - idna==3.4
58
+ - importlib-metadata==6.6.0
59
+ - jinja2==3.1.2
60
+ - jiwer==3.0.1
61
+ - joblib==1.2.0
62
+ - lazy-loader==0.2
63
+ - librosa==0.10.0.post2
64
+ - lit==16.0.2
65
+ - llvmlite==0.40.0
66
+ - markdown==3.4.3
67
+ - markupsafe==2.1.2
68
+ - more-itertools==9.1.0
69
+ - mpmath==1.3.0
70
+ - msgpack==1.0.5
71
+ - multidict==6.0.4
72
+ - multiprocess==0.70.14
73
+ - networkx==3.1
74
+ - numba==0.57.0
75
+ - numpy==1.24.3
76
+ - nvidia-cublas-cu11==11.10.3.66
77
+ - nvidia-cuda-cupti-cu11==11.7.101
78
+ - nvidia-cuda-nvrtc-cu11==11.7.99
79
+ - nvidia-cuda-runtime-cu11==11.7.99
80
+ - nvidia-cudnn-cu11==8.5.0.96
81
+ - nvidia-cufft-cu11==10.9.0.58
82
+ - nvidia-curand-cu11==10.2.10.91
83
+ - nvidia-cusolver-cu11==11.4.0.1
84
+ - nvidia-cusparse-cu11==11.7.4.91
85
+ - nvidia-nccl-cu11==2.14.3
86
+ - nvidia-nvtx-cu11==11.7.91
87
+ - oauthlib==3.2.2
88
+ - packaging==23.1
89
+ - pandas==2.0.1
90
+ - pathtools==0.1.2
91
+ - pooch==1.6.0
92
+ - protobuf==4.22.3
93
+ - psutil==5.9.5
94
+ - pyarrow==12.0.0
95
+ - pyasn1==0.5.0
96
+ - pyasn1-modules==0.3.0
97
+ - pycparser==2.21
98
+ - python-dateutil==2.8.2
99
+ - pytz==2023.3
100
+ - pyyaml==6.0
101
+ - rapidfuzz==2.13.7
102
+ - regex==2023.5.4
103
+ - requests==2.29.0
104
+ - requests-oauthlib==1.3.1
105
+ - responses==0.18.0
106
+ - rsa==4.9
107
+ - scikit-learn==1.2.2
108
+ - scipy==1.10.1
109
+ - sentry-sdk==1.22.1
110
+ - setproctitle==1.3.2
111
+ - six==1.16.0
112
+ - smmap==5.0.0
113
+ - soundfile==0.12.1
114
+ - soxr==0.3.5
115
+ - sympy==1.11.1
116
+ - tensorboard==2.12.3
117
+ - tensorboard-data-server==0.7.0
118
+ - threadpoolctl==3.1.0
119
+ - tokenizers==0.13.3
120
+ - torch==2.0.0
121
+ - torchaudio==2.0.1
122
+ - tqdm==4.65.0
123
+ - transformers==4.29.0.dev0
124
+ - triton==2.0.0
125
+ - typing-extensions==4.5.0
126
+ - tzdata==2023.3
127
+ - urllib3==1.26.15
128
+ - wandb==0.15.2
129
+ - werkzeug==2.3.3
130
+ - xxhash==3.2.0
131
+ - yarl==1.9.2
132
+ - zipp==3.15.0
133
+ prefix: /home/local/QCRI/dizham/miniconda3/envs/whisper
wandb/run-20230507_103405-9zf5xxpu/files/config.yaml ADDED
@@ -0,0 +1,688 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.9.16
7
+ cli_version: 0.15.2
8
+ framework: huggingface
9
+ huggingface_version: 4.29.0.dev0
10
+ is_jupyter_run: false
11
+ is_kaggle_kernel: false
12
+ start_time: 1683444845.953953
13
+ t:
14
+ 1:
15
+ - 1
16
+ - 5
17
+ - 11
18
+ - 49
19
+ - 51
20
+ - 53
21
+ - 55
22
+ - 71
23
+ 2:
24
+ - 1
25
+ - 5
26
+ - 11
27
+ - 49
28
+ - 51
29
+ - 53
30
+ - 55
31
+ - 71
32
+ 3:
33
+ - 7
34
+ - 23
35
+ 4: 3.9.16
36
+ 5: 0.15.2
37
+ 6: 4.29.0.dev0
38
+ 8:
39
+ - 5
40
+ m:
41
+ - 1: train/global_step
42
+ 6:
43
+ - 3
44
+ - 1: train/loss
45
+ 5: 1
46
+ 6:
47
+ - 1
48
+ - 1: train/learning_rate
49
+ 5: 1
50
+ 6:
51
+ - 1
52
+ - 1: train/epoch
53
+ 5: 1
54
+ 6:
55
+ - 1
56
+ - 1: eval/loss
57
+ 5: 1
58
+ 6:
59
+ - 1
60
+ - 1: eval/wer
61
+ 5: 1
62
+ 6:
63
+ - 1
64
+ - 1: eval/runtime
65
+ 5: 1
66
+ 6:
67
+ - 1
68
+ - 1: eval/samples_per_second
69
+ 5: 1
70
+ 6:
71
+ - 1
72
+ - 1: eval/steps_per_second
73
+ 5: 1
74
+ 6:
75
+ - 1
76
+ vocab_size:
77
+ desc: null
78
+ value: 51865
79
+ num_mel_bins:
80
+ desc: null
81
+ value: 80
82
+ d_model:
83
+ desc: null
84
+ value: 768
85
+ encoder_layers:
86
+ desc: null
87
+ value: 12
88
+ encoder_attention_heads:
89
+ desc: null
90
+ value: 12
91
+ decoder_layers:
92
+ desc: null
93
+ value: 12
94
+ decoder_attention_heads:
95
+ desc: null
96
+ value: 12
97
+ decoder_ffn_dim:
98
+ desc: null
99
+ value: 3072
100
+ encoder_ffn_dim:
101
+ desc: null
102
+ value: 3072
103
+ dropout:
104
+ desc: null
105
+ value: 0.0
106
+ attention_dropout:
107
+ desc: null
108
+ value: 0.0
109
+ activation_dropout:
110
+ desc: null
111
+ value: 0.0
112
+ activation_function:
113
+ desc: null
114
+ value: gelu
115
+ init_std:
116
+ desc: null
117
+ value: 0.02
118
+ encoder_layerdrop:
119
+ desc: null
120
+ value: 0.0
121
+ decoder_layerdrop:
122
+ desc: null
123
+ value: 0.0
124
+ use_cache:
125
+ desc: null
126
+ value: false
127
+ num_hidden_layers:
128
+ desc: null
129
+ value: 12
130
+ scale_embedding:
131
+ desc: null
132
+ value: false
133
+ max_source_positions:
134
+ desc: null
135
+ value: 1500
136
+ max_target_positions:
137
+ desc: null
138
+ value: 448
139
+ classifier_proj_size:
140
+ desc: null
141
+ value: 256
142
+ use_weighted_layer_sum:
143
+ desc: null
144
+ value: false
145
+ apply_spec_augment:
146
+ desc: null
147
+ value: false
148
+ mask_time_prob:
149
+ desc: null
150
+ value: 0.05
151
+ mask_time_length:
152
+ desc: null
153
+ value: 10
154
+ mask_time_min_masks:
155
+ desc: null
156
+ value: 2
157
+ mask_feature_prob:
158
+ desc: null
159
+ value: 0.0
160
+ mask_feature_length:
161
+ desc: null
162
+ value: 10
163
+ mask_feature_min_masks:
164
+ desc: null
165
+ value: 0
166
+ return_dict:
167
+ desc: null
168
+ value: true
169
+ output_hidden_states:
170
+ desc: null
171
+ value: false
172
+ output_attentions:
173
+ desc: null
174
+ value: false
175
+ torchscript:
176
+ desc: null
177
+ value: false
178
+ torch_dtype:
179
+ desc: null
180
+ value: float32
181
+ use_bfloat16:
182
+ desc: null
183
+ value: false
184
+ tf_legacy_loss:
185
+ desc: null
186
+ value: false
187
+ pruned_heads:
188
+ desc: null
189
+ value: {}
190
+ tie_word_embeddings:
191
+ desc: null
192
+ value: true
193
+ is_encoder_decoder:
194
+ desc: null
195
+ value: true
196
+ is_decoder:
197
+ desc: null
198
+ value: false
199
+ cross_attention_hidden_size:
200
+ desc: null
201
+ value: null
202
+ add_cross_attention:
203
+ desc: null
204
+ value: false
205
+ tie_encoder_decoder:
206
+ desc: null
207
+ value: false
208
+ max_length:
209
+ desc: null
210
+ value: 448
211
+ min_length:
212
+ desc: null
213
+ value: 0
214
+ do_sample:
215
+ desc: null
216
+ value: false
217
+ early_stopping:
218
+ desc: null
219
+ value: false
220
+ num_beams:
221
+ desc: null
222
+ value: 1
223
+ num_beam_groups:
224
+ desc: null
225
+ value: 1
226
+ diversity_penalty:
227
+ desc: null
228
+ value: 0.0
229
+ temperature:
230
+ desc: null
231
+ value: 1.0
232
+ top_k:
233
+ desc: null
234
+ value: 50
235
+ top_p:
236
+ desc: null
237
+ value: 1.0
238
+ typical_p:
239
+ desc: null
240
+ value: 1.0
241
+ repetition_penalty:
242
+ desc: null
243
+ value: 1.0
244
+ length_penalty:
245
+ desc: null
246
+ value: 1.0
247
+ no_repeat_ngram_size:
248
+ desc: null
249
+ value: 0
250
+ encoder_no_repeat_ngram_size:
251
+ desc: null
252
+ value: 0
253
+ bad_words_ids:
254
+ desc: null
255
+ value: null
256
+ num_return_sequences:
257
+ desc: null
258
+ value: 1
259
+ chunk_size_feed_forward:
260
+ desc: null
261
+ value: 0
262
+ output_scores:
263
+ desc: null
264
+ value: false
265
+ return_dict_in_generate:
266
+ desc: null
267
+ value: false
268
+ forced_bos_token_id:
269
+ desc: null
270
+ value: null
271
+ forced_eos_token_id:
272
+ desc: null
273
+ value: null
274
+ remove_invalid_values:
275
+ desc: null
276
+ value: false
277
+ exponential_decay_length_penalty:
278
+ desc: null
279
+ value: null
280
+ suppress_tokens:
281
+ desc: null
282
+ value: null
283
+ begin_suppress_tokens:
284
+ desc: null
285
+ value:
286
+ - 220
287
+ - 50257
288
+ architectures:
289
+ desc: null
290
+ value:
291
+ - WhisperForConditionalGeneration
292
+ finetuning_task:
293
+ desc: null
294
+ value: null
295
+ id2label:
296
+ desc: null
297
+ value:
298
+ '0': LABEL_0
299
+ '1': LABEL_1
300
+ label2id:
301
+ desc: null
302
+ value:
303
+ LABEL_0: 0
304
+ LABEL_1: 1
305
+ tokenizer_class:
306
+ desc: null
307
+ value: null
308
+ prefix:
309
+ desc: null
310
+ value: null
311
+ bos_token_id:
312
+ desc: null
313
+ value: 50257
314
+ pad_token_id:
315
+ desc: null
316
+ value: 50257
317
+ eos_token_id:
318
+ desc: null
319
+ value: 50257
320
+ sep_token_id:
321
+ desc: null
322
+ value: null
323
+ decoder_start_token_id:
324
+ desc: null
325
+ value: 50258
326
+ task_specific_params:
327
+ desc: null
328
+ value: null
329
+ problem_type:
330
+ desc: null
331
+ value: null
332
+ _name_or_path:
333
+ desc: null
334
+ value: openai/whisper-small
335
+ transformers_version:
336
+ desc: null
337
+ value: 4.29.0.dev0
338
+ forced_decoder_ids:
339
+ desc: null
340
+ value: null
341
+ model_type:
342
+ desc: null
343
+ value: whisper
344
+ output_dir:
345
+ desc: null
346
+ value: ./
347
+ overwrite_output_dir:
348
+ desc: null
349
+ value: true
350
+ do_train:
351
+ desc: null
352
+ value: true
353
+ do_eval:
354
+ desc: null
355
+ value: true
356
+ do_predict:
357
+ desc: null
358
+ value: false
359
+ evaluation_strategy:
360
+ desc: null
361
+ value: steps
362
+ prediction_loss_only:
363
+ desc: null
364
+ value: false
365
+ per_device_train_batch_size:
366
+ desc: null
367
+ value: 32
368
+ per_device_eval_batch_size:
369
+ desc: null
370
+ value: 32
371
+ per_gpu_train_batch_size:
372
+ desc: null
373
+ value: None
374
+ per_gpu_eval_batch_size:
375
+ desc: null
376
+ value: None
377
+ gradient_accumulation_steps:
378
+ desc: null
379
+ value: 2
380
+ eval_accumulation_steps:
381
+ desc: null
382
+ value: None
383
+ eval_delay:
384
+ desc: null
385
+ value: 0
386
+ learning_rate:
387
+ desc: null
388
+ value: 1.0e-05
389
+ weight_decay:
390
+ desc: null
391
+ value: 0.0
392
+ adam_beta1:
393
+ desc: null
394
+ value: 0.9
395
+ adam_beta2:
396
+ desc: null
397
+ value: 0.999
398
+ adam_epsilon:
399
+ desc: null
400
+ value: 1.0e-08
401
+ max_grad_norm:
402
+ desc: null
403
+ value: 1.0
404
+ num_train_epochs:
405
+ desc: null
406
+ value: 3.0
407
+ max_steps:
408
+ desc: null
409
+ value: 5000
410
+ lr_scheduler_type:
411
+ desc: null
412
+ value: linear
413
+ warmup_ratio:
414
+ desc: null
415
+ value: 0.0
416
+ warmup_steps:
417
+ desc: null
418
+ value: 500
419
+ log_level:
420
+ desc: null
421
+ value: passive
422
+ log_level_replica:
423
+ desc: null
424
+ value: warning
425
+ log_on_each_node:
426
+ desc: null
427
+ value: true
428
+ logging_dir:
429
+ desc: null
430
+ value: ./runs/May07_10-33-38_crimv3mgpu025
431
+ logging_strategy:
432
+ desc: null
433
+ value: steps
434
+ logging_first_step:
435
+ desc: null
436
+ value: false
437
+ logging_steps:
438
+ desc: null
439
+ value: 25
440
+ logging_nan_inf_filter:
441
+ desc: null
442
+ value: true
443
+ save_strategy:
444
+ desc: null
445
+ value: steps
446
+ save_steps:
447
+ desc: null
448
+ value: 1000
449
+ save_total_limit:
450
+ desc: null
451
+ value: None
452
+ save_safetensors:
453
+ desc: null
454
+ value: false
455
+ save_on_each_node:
456
+ desc: null
457
+ value: false
458
+ no_cuda:
459
+ desc: null
460
+ value: false
461
+ use_mps_device:
462
+ desc: null
463
+ value: false
464
+ seed:
465
+ desc: null
466
+ value: 42
467
+ data_seed:
468
+ desc: null
469
+ value: None
470
+ jit_mode_eval:
471
+ desc: null
472
+ value: false
473
+ use_ipex:
474
+ desc: null
475
+ value: false
476
+ bf16:
477
+ desc: null
478
+ value: false
479
+ fp16:
480
+ desc: null
481
+ value: true
482
+ fp16_opt_level:
483
+ desc: null
484
+ value: O1
485
+ half_precision_backend:
486
+ desc: null
487
+ value: cuda_amp
488
+ bf16_full_eval:
489
+ desc: null
490
+ value: false
491
+ fp16_full_eval:
492
+ desc: null
493
+ value: false
494
+ tf32:
495
+ desc: null
496
+ value: None
497
+ local_rank:
498
+ desc: null
499
+ value: 0
500
+ ddp_backend:
501
+ desc: null
502
+ value: None
503
+ tpu_num_cores:
504
+ desc: null
505
+ value: None
506
+ tpu_metrics_debug:
507
+ desc: null
508
+ value: false
509
+ debug:
510
+ desc: null
511
+ value: '[]'
512
+ dataloader_drop_last:
513
+ desc: null
514
+ value: false
515
+ eval_steps:
516
+ desc: null
517
+ value: 1000
518
+ dataloader_num_workers:
519
+ desc: null
520
+ value: 0
521
+ past_index:
522
+ desc: null
523
+ value: -1
524
+ run_name:
525
+ desc: null
526
+ value: ./
527
+ disable_tqdm:
528
+ desc: null
529
+ value: false
530
+ remove_unused_columns:
531
+ desc: null
532
+ value: true
533
+ label_names:
534
+ desc: null
535
+ value: None
536
+ load_best_model_at_end:
537
+ desc: null
538
+ value: true
539
+ metric_for_best_model:
540
+ desc: null
541
+ value: wer
542
+ greater_is_better:
543
+ desc: null
544
+ value: false
545
+ ignore_data_skip:
546
+ desc: null
547
+ value: false
548
+ sharded_ddp:
549
+ desc: null
550
+ value: '[]'
551
+ fsdp:
552
+ desc: null
553
+ value: '[]'
554
+ fsdp_min_num_params:
555
+ desc: null
556
+ value: 0
557
+ fsdp_config:
558
+ desc: null
559
+ value: '{''fsdp_min_num_params'': 0, ''xla'': False, ''xla_fsdp_grad_ckpt'': False}'
560
+ fsdp_transformer_layer_cls_to_wrap:
561
+ desc: null
562
+ value: None
563
+ deepspeed:
564
+ desc: null
565
+ value: None
566
+ label_smoothing_factor:
567
+ desc: null
568
+ value: 0.0
569
+ optim:
570
+ desc: null
571
+ value: adamw_hf
572
+ optim_args:
573
+ desc: null
574
+ value: None
575
+ adafactor:
576
+ desc: null
577
+ value: false
578
+ group_by_length:
579
+ desc: null
580
+ value: false
581
+ length_column_name:
582
+ desc: null
583
+ value: input_length
584
+ report_to:
585
+ desc: null
586
+ value: '[''wandb'']'
587
+ ddp_find_unused_parameters:
588
+ desc: null
589
+ value: None
590
+ ddp_bucket_cap_mb:
591
+ desc: null
592
+ value: None
593
+ dataloader_pin_memory:
594
+ desc: null
595
+ value: true
596
+ skip_memory_metrics:
597
+ desc: null
598
+ value: true
599
+ use_legacy_prediction_loop:
600
+ desc: null
601
+ value: false
602
+ push_to_hub:
603
+ desc: null
604
+ value: true
605
+ resume_from_checkpoint:
606
+ desc: null
607
+ value: None
608
+ hub_model_id:
609
+ desc: null
610
+ value: None
611
+ hub_strategy:
612
+ desc: null
613
+ value: every_save
614
+ hub_token:
615
+ desc: null
616
+ value: <HUB_TOKEN>
617
+ hub_private_repo:
618
+ desc: null
619
+ value: false
620
+ gradient_checkpointing:
621
+ desc: null
622
+ value: true
623
+ include_inputs_for_metrics:
624
+ desc: null
625
+ value: false
626
+ fp16_backend:
627
+ desc: null
628
+ value: auto
629
+ push_to_hub_model_id:
630
+ desc: null
631
+ value: None
632
+ push_to_hub_organization:
633
+ desc: null
634
+ value: None
635
+ push_to_hub_token:
636
+ desc: null
637
+ value: <PUSH_TO_HUB_TOKEN>
638
+ mp_parameters:
639
+ desc: null
640
+ value: ''
641
+ auto_find_batch_size:
642
+ desc: null
643
+ value: false
644
+ full_determinism:
645
+ desc: null
646
+ value: false
647
+ torchdynamo:
648
+ desc: null
649
+ value: None
650
+ ray_scope:
651
+ desc: null
652
+ value: last
653
+ ddp_timeout:
654
+ desc: null
655
+ value: 1800
656
+ torch_compile:
657
+ desc: null
658
+ value: false
659
+ torch_compile_backend:
660
+ desc: null
661
+ value: None
662
+ torch_compile_mode:
663
+ desc: null
664
+ value: None
665
+ xpu_backend:
666
+ desc: null
667
+ value: None
668
+ sortish_sampler:
669
+ desc: null
670
+ value: false
671
+ predict_with_generate:
672
+ desc: null
673
+ value: true
674
+ generation_max_length:
675
+ desc: null
676
+ value: 225
677
+ generation_num_beams:
678
+ desc: null
679
+ value: None
680
+ generation_config:
681
+ desc: null
682
+ value: None
683
+ train_batch_size:
684
+ desc: null
685
+ value: 64
686
+ eval_batch_size:
687
+ desc: null
688
+ value: 64
wandb/run-20230507_103405-9zf5xxpu/files/output.log ADDED
@@ -0,0 +1,1079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 0%| | 0/5000 [00:00<?, ?it/s]
2
+
3
+ Reading metadata...: 10438it [00:00, 28290.14it/s]
4
+
5
+ [INFO|trainer_utils.py:693] 2023-05-07 10:35:32,760 >> The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.
6
+ /home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
7
+ warnings.warn('Was asked to gather along dimension 0, but all '
8
+
9
+
10
+
11
+
12
+
13
+
14
+
15
+
16
+
17
+
18
+
19
+
20
+
21
+
22
+
23
+
24
+
25
+
26
+
27
+
28
+
29
+
30
+
31
+
32
+ 0%| | 25/5000 [12:57<38:59:22, 28.21s/it]
33
+
34
+
35
+
36
+
37
+
38
+
39
+
40
+
41
+
42
+
43
+
44
+
45
+
46
+
47
+
48
+
49
+
50
+
51
+
52
+
53
+
54
+
55
+
56
+
57
+
58
+ 1%| | 50/5000 [24:31<38:04:45, 27.69s/it]
59
+
60
+
61
+
62
+
63
+
64
+
65
+
66
+
67
+
68
+
69
+
70
+
71
+
72
+
73
+
74
+
75
+
76
+
77
+
78
+
79
+
80
+
81
+
82
+
83
+
84
+ 2%|▏ | 75/5000 [36:10<38:12:36, 27.93s/it]
85
+
86
+
87
+
88
+
89
+
90
+
91
+
92
+
93
+
94
+
95
+
96
+
97
+
98
+
99
+
100
+
101
+
102
+
103
+
104
+
105
+
106
+
107
+
108
+
109
+
110
+ 2%|▏ | 100/5000 [47:46<37:40:02, 27.67s/it]
111
+
112
+
113
+
114
+
115
+
116
+
117
+
118
+
119
+
120
+
121
+
122
+
123
+
124
+
125
+
126
+
127
+
128
+
129
+
130
+
131
+
132
+
133
+
134
+
135
+
136
+ 2%|▎ | 125/5000 [59:17<37:59:12, 28.05s/it]
137
+
138
+
139
+
140
+
141
+
142
+
143
+
144
+
145
+
146
+
147
+
148
+
149
+
150
+
151
+
152
+
153
+
154
+
155
+
156
+
157
+
158
+
159
+
160
+
161
+
162
+ 3%|▎ | 150/5000 [1:10:46<37:32:21, 27.86s/it]
163
+
164
+
165
+
166
+
167
+
168
+
169
+
170
+
171
+
172
+
173
+
174
+
175
+
176
+ 3%|▎ | 163/5000 [1:15:43<20:26:07, 15.21s/it]
177
+ Reading metadata...: 23919it [00:01, 14960.32it/s]
178
+
179
+
180
+
181
+
182
+
183
+
184
+
185
+
186
+
187
+
188
+
189
+
190
+
191
+ 4%|▎ | 175/5000 [1:22:25<38:42:56, 28.89s/it]
192
+
193
+
194
+
195
+
196
+
197
+
198
+
199
+
200
+
201
+
202
+
203
+
204
+
205
+
206
+
207
+
208
+
209
+
210
+
211
+
212
+
213
+
214
+
215
+
216
+
217
+ 4%|▍ | 200/5000 [1:34:15<39:11:58, 29.40s/it]
218
+
219
+
220
+
221
+
222
+
223
+
224
+
225
+
226
+
227
+
228
+
229
+
230
+
231
+
232
+
233
+
234
+
235
+
236
+
237
+
238
+
239
+
240
+
241
+
242
+ 4%|▍ | 224/5000 [1:45:23<36:46:48, 27.72s/it]
243
+
244
+
245
+
246
+
247
+
248
+
249
+
250
+
251
+
252
+
253
+
254
+
255
+
256
+
257
+
258
+
259
+
260
+
261
+
262
+
263
+
264
+
265
+
266
+
267
+
268
+ 5%|▍ | 249/5000 [1:57:07<37:05:48, 28.11s/it]
269
+
270
+
271
+
272
+
273
+
274
+
275
+
276
+
277
+
278
+
279
+
280
+
281
+
282
+
283
+
284
+
285
+
286
+
287
+
288
+
289
+
290
+
291
+
292
+
293
+
294
+ 5%|▌ | 274/5000 [2:08:53<36:42:42, 27.97s/it]
295
+
296
+
297
+
298
+
299
+
300
+
301
+
302
+
303
+
304
+
305
+
306
+
307
+
308
+
309
+
310
+
311
+
312
+
313
+
314
+
315
+
316
+
317
+
318
+
319
+
320
+ 6%|▌ | 299/5000 [2:20:36<36:26:30, 27.91s/it]
321
+
322
+
323
+
324
+
325
+
326
+
327
+
328
+
329
+
330
+
331
+
332
+
333
+
334
+
335
+
336
+
337
+
338
+
339
+
340
+
341
+
342
+
343
+
344
+
345
+
346
+
347
+ 6%|▋ | 325/5000 [2:32:04<23:59:08, 18.47s/it]
348
+
349
+
350
+ 7%|▋ | 327/5000 [2:32:23<17:43:56, 13.66s/it]
351
+
352
+
353
+ Reading metadata...: 23979it [00:02, 8389.85it/s]
354
+
355
+
356
+
357
+
358
+
359
+
360
+
361
+
362
+
363
+
364
+
365
+
366
+
367
+
368
+
369
+
370
+
371
+
372
+
373
+
374
+
375
+
376
+
377
+
378
+ 7%|▋ | 350/5000 [2:45:20<38:18:16, 29.66s/it]
379
+
380
+
381
+
382
+
383
+
384
+
385
+
386
+
387
+
388
+
389
+
390
+
391
+
392
+
393
+
394
+
395
+
396
+
397
+
398
+
399
+
400
+
401
+
402
+
403
+ 7%|▋ | 374/5000 [2:56:51<36:29:03, 28.39s/it]
404
+
405
+
406
+
407
+
408
+
409
+
410
+
411
+
412
+
413
+
414
+
415
+
416
+
417
+
418
+
419
+
420
+
421
+
422
+
423
+
424
+
425
+
426
+
427
+
428
+
429
+
430
+ 8%|▊ | 400/5000 [3:09:27<37:45:36, 29.55s/it]
431
+
432
+
433
+
434
+
435
+
436
+
437
+
438
+
439
+
440
+
441
+
442
+
443
+
444
+
445
+
446
+
447
+
448
+
449
+
450
+
451
+
452
+
453
+
454
+
455
+ 8%|▊ | 424/5000 [3:21:03<36:39:46, 28.84s/it]
456
+
457
+
458
+
459
+
460
+
461
+
462
+
463
+
464
+
465
+
466
+
467
+
468
+
469
+
470
+
471
+
472
+
473
+
474
+
475
+
476
+
477
+
478
+
479
+
480
+
481
+ 9%|▉ | 449/5000 [3:33:05<36:30:32, 28.88s/it]
482
+
483
+
484
+
485
+
486
+
487
+
488
+
489
+
490
+
491
+
492
+
493
+
494
+
495
+
496
+
497
+
498
+
499
+
500
+
501
+
502
+
503
+
504
+
505
+
506
+
507
+ 9%|▉ | 474/5000 [3:44:57<36:23:20, 28.94s/it]
508
+
509
+
510
+
511
+
512
+
513
+
514
+
515
+
516
+
517
+
518
+
519
+
520
+
521
+
522
+
523
+
524
+ 10%|▉ | 490/5000 [3:51:29<19:35:34, 15.64s/it]
525
+
526
+
527
+ Reading metadata...: 23848it [00:02, 13351.04it/s]
528
+
529
+
530
+
531
+
532
+
533
+
534
+
535
+
536
+
537
+
538
+
539
+ 10%|█ | 500/5000 [3:57:20<35:45:29, 28.61s/it]
540
+
541
+
542
+
543
+
544
+
545
+
546
+
547
+
548
+
549
+
550
+
551
+
552
+
553
+
554
+
555
+
556
+
557
+
558
+
559
+
560
+
561
+
562
+
563
+
564
+
565
+ 10%|█ | 525/5000 [4:09:00<34:54:55, 28.09s/it]
566
+
567
+
568
+
569
+
570
+
571
+
572
+
573
+
574
+
575
+
576
+
577
+
578
+
579
+
580
+
581
+
582
+
583
+
584
+
585
+
586
+
587
+
588
+
589
+
590
+
591
+ 11%|█ | 550/5000 [4:20:30<34:27:46, 27.88s/it]
592
+
593
+
594
+
595
+
596
+
597
+
598
+
599
+
600
+
601
+
602
+
603
+
604
+
605
+
606
+
607
+
608
+
609
+
610
+
611
+
612
+
613
+
614
+
615
+
616
+ 11%|█▏ | 574/5000 [4:31:36<34:02:43, 27.69s/it]
617
+
618
+
619
+
620
+
621
+
622
+
623
+
624
+
625
+
626
+
627
+
628
+
629
+
630
+
631
+
632
+
633
+
634
+
635
+
636
+
637
+
638
+
639
+
640
+
641
+
642
+
643
+ 12%|█▏ | 600/5000 [4:43:33<34:06:44, 27.91s/it]
644
+
645
+
646
+
647
+
648
+
649
+
650
+
651
+
652
+
653
+
654
+
655
+
656
+
657
+
658
+
659
+
660
+
661
+
662
+
663
+
664
+
665
+
666
+
667
+
668
+
669
+ 12%|█▎ | 625/5000 [4:55:08<33:43:52, 27.76s/it]
670
+
671
+
672
+
673
+
674
+
675
+
676
+
677
+
678
+
679
+
680
+
681
+
682
+
683
+
684
+
685
+
686
+
687
+
688
+
689
+
690
+
691
+
692
+
693
+
694
+
695
+ 13%|█▎ | 650/5000 [5:06:34<31:39:01, 26.19s/it]
696
+
697
+
698
+
699
+ 13%|█▎ | 654/5000 [5:07:15<16:27:10, 13.63s/it]
700
+ Reading metadata...: 10438it [00:00, 28332.17it/s]
701
+
702
+
703
+
704
+
705
+
706
+
707
+
708
+
709
+
710
+
711
+
712
+
713
+
714
+
715
+
716
+
717
+
718
+
719
+
720
+
721
+
722
+ 14%|█▎ | 675/5000 [5:18:11<33:22:09, 27.78s/it]
723
+
724
+
725
+
726
+
727
+
728
+
729
+
730
+
731
+
732
+
733
+
734
+
735
+
736
+
737
+
738
+
739
+
740
+
741
+
742
+
743
+
744
+
745
+
746
+
747
+ 14%|█▍ | 699/5000 [5:29:08<32:58:14, 27.60s/it]
748
+
749
+
750
+
751
+
752
+
753
+
754
+
755
+
756
+
757
+
758
+
759
+
760
+
761
+
762
+
763
+
764
+
765
+
766
+
767
+
768
+
769
+
770
+
771
+
772
+
773
+
774
+ 14%|█▍ | 725/5000 [5:41:16<32:59:03, 27.78s/it]
775
+
776
+
777
+
778
+
779
+
780
+
781
+
782
+
783
+
784
+
785
+
786
+
787
+
788
+
789
+
790
+
791
+
792
+
793
+
794
+
795
+
796
+
797
+
798
+
799
+ 15%|█▍ | 749/5000 [5:52:28<32:45:54, 27.75s/it]
800
+
801
+
802
+
803
+
804
+
805
+
806
+
807
+
808
+
809
+
810
+
811
+
812
+
813
+
814
+
815
+
816
+
817
+
818
+
819
+
820
+
821
+
822
+
823
+
824
+
825
+
826
+ 16%|█▌ | 775/5000 [6:04:31<32:25:51, 27.63s/it]
827
+
828
+
829
+
830
+
831
+
832
+
833
+
834
+
835
+
836
+
837
+
838
+
839
+
840
+
841
+
842
+
843
+
844
+
845
+
846
+
847
+
848
+
849
+
850
+
851
+
852
+ 16%|█▌ | 800/5000 [6:16:05<31:52:14, 27.32s/it]
853
+
854
+
855
+
856
+
857
+
858
+
859
+
860
+
861
+
862
+
863
+
864
+
865
+
866
+
867
+
868
+
869
+
870
+ 16%|█▋ | 817/5000 [6:22:52<17:40:15, 15.21s/it]
871
+
872
+ Reading metadata...: 10438it [00:00, 26121.88it/s]
873
+
874
+
875
+
876
+
877
+
878
+
879
+
880
+ 16%|█▋ | 824/5000 [6:27:10<33:50:30, 29.17s/it]
881
+
882
+
883
+
884
+
885
+
886
+
887
+
888
+
889
+
890
+
891
+
892
+
893
+
894
+
895
+
896
+
897
+
898
+
899
+
900
+
901
+
902
+
903
+
904
+
905
+
906
+ 17%|█▋ | 849/5000 [6:38:45<32:12:00, 27.93s/it]
907
+
908
+
909
+
910
+
911
+
912
+
913
+
914
+
915
+
916
+
917
+
918
+
919
+
920
+
921
+
922
+
923
+
924
+
925
+
926
+
927
+
928
+
929
+
930
+
931
+
932
+
933
+ 18%|█▊ | 875/5000 [6:50:44<31:43:20, 27.68s/it]
934
+
935
+
936
+
937
+
938
+
939
+
940
+
941
+
942
+
943
+
944
+
945
+
946
+
947
+
948
+
949
+
950
+
951
+
952
+
953
+
954
+
955
+
956
+
957
+
958
+
959
+ 18%|█▊ | 900/5000 [7:02:26<31:53:22, 28.00s/it]
960
+
961
+
962
+
963
+
964
+
965
+
966
+
967
+
968
+
969
+
970
+
971
+
972
+
973
+
974
+
975
+
976
+
977
+
978
+
979
+
980
+
981
+
982
+
983
+
984
+
985
+ 18%|█▊ | 925/5000 [7:14:00<31:27:54, 27.80s/it]
986
+
987
+
988
+
989
+
990
+
991
+
992
+
993
+
994
+
995
+
996
+
997
+
998
+
999
+
1000
+
1001
+
1002
+
1003
+
1004
+
1005
+
1006
+
1007
+
1008
+
1009
+
1010
+
1011
+ 19%|█▉ | 950/5000 [7:25:24<29:51:57, 26.55s/it]
1012
+
1013
+
1014
+
1015
+
1016
+
1017
+
1018
+
1019
+
1020
+
1021
+
1022
+
1023
+
1024
+
1025
+
1026
+
1027
+
1028
+
1029
+
1030
+
1031
+
1032
+
1033
+
1034
+
1035
+
1036
+
1037
+ 20%|█▉ | 975/5000 [7:36:55<31:02:52, 27.77s/it]
1038
+
1039
+
1040
+
1041
+
1042
+
1043
+
1044
+ 20%|█▉ | 981/5000 [7:38:26<15:15:07, 13.66s/it]
1045
+ Reading metadata...: 23329it [00:00, 27403.88it/s]
1046
+
1047
+
1048
+
1049
+
1050
+
1051
+
1052
+
1053
+
1054
+
1055
+
1056
+
1057
+
1058
+
1059
+
1060
+
1061
+
1062
+
1063
+
1064
+
1065
+ 20%|█▉ | 999/5000 [7:48:10<31:41:54, 28.52s/it]
1066
+ 20%|██ | 1000/5000 [7:48:38<31:29:41, 28.35s/it][INFO|trainer.py:3138] 2023-05-07 18:22:49,172 >> ***** Running Evaluation *****
1067
+ [INFO|trainer.py:3142] 2023-05-07 18:22:49,172 >> Num examples: Unknown
1068
+ [INFO|trainer.py:3143] 2023-05-07 18:22:49,172 >> Batch size = 64
1069
+
1070
+
1071
+ [INFO|trainer_utils.py:693] 2023-05-07 18:23:04,305 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.
1072
+ {'eval_loss': 0.43405279517173767, 'eval_wer': 54.25600000000001, 'eval_runtime': 2248.2056, 'eval_samples_per_second': 4.644, 'eval_steps_per_second': 0.073, 'epoch': 6.0}
1073
+ 20%|██ | 1000/5000 [8:26:06<31:29:41, 28.35s/it][INFO|trainer.py:2877] 2023-05-07 19:00:17,386 >> Saving model checkpoint to ./checkpoint-1000
1074
+ [INFO|configuration_utils.py:458] 2023-05-07 19:00:17,393 >> Configuration saved in ./checkpoint-1000/config.json
1075
+ [INFO|configuration_utils.py:364] 2023-05-07 19:00:17,398 >> Configuration saved in ./checkpoint-1000/generation_config.json
1076
+ [INFO|modeling_utils.py:1855] 2023-05-07 19:00:20,753 >> Model weights saved in ./checkpoint-1000/pytorch_model.bin
1077
+ [INFO|feature_extraction_utils.py:369] 2023-05-07 19:00:20,758 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
1078
+ [INFO|feature_extraction_utils.py:369] 2023-05-07 19:00:30,115 >> Feature extractor saved in ./preprocessor_config.json
1079
+ Adding files tracked by Git LFS: ['wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb', 'wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb']. This may take a bit of time if the files are large.
wandb/run-20230507_103405-9zf5xxpu/files/requirements.txt ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==1.4.0
2
+ accelerate==0.18.0
3
+ aiohttp==3.8.4
4
+ aiosignal==1.3.1
5
+ appdirs==1.4.4
6
+ async-timeout==4.0.2
7
+ attrs==23.1.0
8
+ audioread==3.0.0
9
+ cachetools==5.3.0
10
+ certifi==2022.12.7
11
+ cffi==1.15.1
12
+ charset-normalizer==3.1.0
13
+ click==8.1.3
14
+ cmake==3.26.3
15
+ datasets==2.12.1.dev0
16
+ decorator==5.1.1
17
+ dill==0.3.6
18
+ docker-pycreds==0.4.0
19
+ evaluate==0.4.0
20
+ filelock==3.12.0
21
+ frozenlist==1.3.3
22
+ fsspec==2023.4.0
23
+ gitdb==4.0.10
24
+ gitpython==3.1.31
25
+ google-auth-oauthlib==1.0.0
26
+ google-auth==2.17.3
27
+ grpcio==1.54.0
28
+ huggingface-hub==0.14.1
29
+ idna==3.4
30
+ importlib-metadata==6.6.0
31
+ jinja2==3.1.2
32
+ jiwer==3.0.1
33
+ joblib==1.2.0
34
+ lazy-loader==0.2
35
+ librosa==0.10.0.post2
36
+ lit==16.0.2
37
+ llvmlite==0.40.0
38
+ markdown==3.4.3
39
+ markupsafe==2.1.2
40
+ more-itertools==9.1.0
41
+ mpmath==1.3.0
42
+ msgpack==1.0.5
43
+ multidict==6.0.4
44
+ multiprocess==0.70.14
45
+ networkx==3.1
46
+ numba==0.57.0
47
+ numpy==1.24.3
48
+ nvidia-cublas-cu11==11.10.3.66
49
+ nvidia-cuda-cupti-cu11==11.7.101
50
+ nvidia-cuda-nvrtc-cu11==11.7.99
51
+ nvidia-cuda-runtime-cu11==11.7.99
52
+ nvidia-cudnn-cu11==8.5.0.96
53
+ nvidia-cufft-cu11==10.9.0.58
54
+ nvidia-curand-cu11==10.2.10.91
55
+ nvidia-cusolver-cu11==11.4.0.1
56
+ nvidia-cusparse-cu11==11.7.4.91
57
+ nvidia-nccl-cu11==2.14.3
58
+ nvidia-nvtx-cu11==11.7.91
59
+ oauthlib==3.2.2
60
+ packaging==23.1
61
+ pandas==2.0.1
62
+ pathtools==0.1.2
63
+ pip==23.1.2
64
+ pooch==1.6.0
65
+ protobuf==4.22.3
66
+ psutil==5.9.5
67
+ pyarrow==12.0.0
68
+ pyasn1-modules==0.3.0
69
+ pyasn1==0.5.0
70
+ pycparser==2.21
71
+ python-dateutil==2.8.2
72
+ pytz==2023.3
73
+ pyyaml==6.0
74
+ rapidfuzz==2.13.7
75
+ regex==2023.5.4
76
+ requests-oauthlib==1.3.1
77
+ requests==2.29.0
78
+ responses==0.18.0
79
+ rsa==4.9
80
+ scikit-learn==1.2.2
81
+ scipy==1.10.1
82
+ sentry-sdk==1.22.1
83
+ setproctitle==1.3.2
84
+ setuptools==67.7.2
85
+ six==1.16.0
86
+ smmap==5.0.0
87
+ soundfile==0.12.1
88
+ soxr==0.3.5
89
+ sympy==1.11.1
90
+ tensorboard-data-server==0.7.0
91
+ tensorboard==2.12.3
92
+ threadpoolctl==3.1.0
93
+ tokenizers==0.13.3
94
+ torch==2.0.0
95
+ torchaudio==2.0.1
96
+ tqdm==4.65.0
97
+ transformers==4.29.0.dev0
98
+ triton==2.0.0
99
+ typing-extensions==4.5.0
100
+ tzdata==2023.3
101
+ urllib3==1.26.15
102
+ wandb==0.15.2
103
+ werkzeug==2.3.3
104
+ wheel==0.40.0
105
+ xxhash==3.2.0
106
+ yarl==1.9.2
107
+ zipp==3.15.0
wandb/run-20230507_103405-9zf5xxpu/files/wandb-metadata.json ADDED
@@ -0,0 +1,369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-3.10.0-957.27.2.el7.x86_64-x86_64-with-glibc2.17",
3
+ "python": "3.9.16",
4
+ "heartbeatAt": "2023-05-07T07:34:06.720314",
5
+ "startedAt": "2023-05-07T07:34:05.852018",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "--model_name_or_path=openai/whisper-small",
10
+ "--dataset_name=mozilla-foundation/common_voice_11_0",
11
+ "--dataset_config_name=ar",
12
+ "--language=arabic",
13
+ "--train_split_name=train+validation",
14
+ "--eval_split_name=test",
15
+ "--model_index_name=Whisper Small Arabic",
16
+ "--max_steps=5000",
17
+ "--output_dir=./",
18
+ "--per_device_train_batch_size=32",
19
+ "--gradient_accumulation_steps=2",
20
+ "--per_device_eval_batch_size=32",
21
+ "--logging_steps=25",
22
+ "--learning_rate=1e-5",
23
+ "--warmup_steps=500",
24
+ "--evaluation_strategy=steps",
25
+ "--eval_steps=1000",
26
+ "--save_strategy=steps",
27
+ "--save_steps=1000",
28
+ "--generation_max_length=225",
29
+ "--length_column_name=input_length",
30
+ "--max_duration_in_seconds=30",
31
+ "--text_column_name=sentence",
32
+ "--freeze_feature_encoder=False",
33
+ "--report_to=tensorboard",
34
+ "--report_to=wandb",
35
+ "--metric_for_best_model=wer",
36
+ "--greater_is_better=False",
37
+ "--load_best_model_at_end",
38
+ "--gradient_checkpointing",
39
+ "--fp16",
40
+ "--overwrite_output_dir",
41
+ "--do_train",
42
+ "--do_eval",
43
+ "--predict_with_generate",
44
+ "--do_normalize_eval",
45
+ "--streaming",
46
+ "--use_auth_token",
47
+ "--push_to_hub"
48
+ ],
49
+ "state": "running",
50
+ "program": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py",
51
+ "codePath": "run_speech_recognition_seq2seq_streaming.py",
52
+ "git": {
53
+ "remote": "https://huggingface.co/danielizham/whisper-small-ar",
54
+ "commit": "33cfe8b27be49d1904070ffc4339ab1b4075c5b1"
55
+ },
56
+ "email": "[email protected]",
57
+ "root": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar",
58
+ "host": "crimv3mgpu025",
59
+ "username": "dizham",
60
+ "executable": "/home/local/QCRI/dizham/miniconda3/envs/whisper/bin/python",
61
+ "cpu_count": 28,
62
+ "cpu_count_logical": 56,
63
+ "cpu_freq": {
64
+ "current": 2201.0,
65
+ "min": 1000.0,
66
+ "max": 2201.0
67
+ },
68
+ "cpu_freq_per_core": [
69
+ {
70
+ "current": 2201.0,
71
+ "min": 1000.0,
72
+ "max": 2201.0
73
+ },
74
+ {
75
+ "current": 2201.0,
76
+ "min": 1000.0,
77
+ "max": 2201.0
78
+ },
79
+ {
80
+ "current": 2201.0,
81
+ "min": 1000.0,
82
+ "max": 2201.0
83
+ },
84
+ {
85
+ "current": 2201.0,
86
+ "min": 1000.0,
87
+ "max": 2201.0
88
+ },
89
+ {
90
+ "current": 2201.0,
91
+ "min": 1000.0,
92
+ "max": 2201.0
93
+ },
94
+ {
95
+ "current": 2201.0,
96
+ "min": 1000.0,
97
+ "max": 2201.0
98
+ },
99
+ {
100
+ "current": 2201.0,
101
+ "min": 1000.0,
102
+ "max": 2201.0
103
+ },
104
+ {
105
+ "current": 2201.0,
106
+ "min": 1000.0,
107
+ "max": 2201.0
108
+ },
109
+ {
110
+ "current": 2201.0,
111
+ "min": 1000.0,
112
+ "max": 2201.0
113
+ },
114
+ {
115
+ "current": 2201.0,
116
+ "min": 1000.0,
117
+ "max": 2201.0
118
+ },
119
+ {
120
+ "current": 2201.0,
121
+ "min": 1000.0,
122
+ "max": 2201.0
123
+ },
124
+ {
125
+ "current": 2201.0,
126
+ "min": 1000.0,
127
+ "max": 2201.0
128
+ },
129
+ {
130
+ "current": 2201.0,
131
+ "min": 1000.0,
132
+ "max": 2201.0
133
+ },
134
+ {
135
+ "current": 2201.0,
136
+ "min": 1000.0,
137
+ "max": 2201.0
138
+ },
139
+ {
140
+ "current": 2201.0,
141
+ "min": 1000.0,
142
+ "max": 2201.0
143
+ },
144
+ {
145
+ "current": 2201.0,
146
+ "min": 1000.0,
147
+ "max": 2201.0
148
+ },
149
+ {
150
+ "current": 2201.0,
151
+ "min": 1000.0,
152
+ "max": 2201.0
153
+ },
154
+ {
155
+ "current": 2201.0,
156
+ "min": 1000.0,
157
+ "max": 2201.0
158
+ },
159
+ {
160
+ "current": 2201.0,
161
+ "min": 1000.0,
162
+ "max": 2201.0
163
+ },
164
+ {
165
+ "current": 2201.0,
166
+ "min": 1000.0,
167
+ "max": 2201.0
168
+ },
169
+ {
170
+ "current": 2201.0,
171
+ "min": 1000.0,
172
+ "max": 2201.0
173
+ },
174
+ {
175
+ "current": 2201.0,
176
+ "min": 1000.0,
177
+ "max": 2201.0
178
+ },
179
+ {
180
+ "current": 2201.0,
181
+ "min": 1000.0,
182
+ "max": 2201.0
183
+ },
184
+ {
185
+ "current": 2201.0,
186
+ "min": 1000.0,
187
+ "max": 2201.0
188
+ },
189
+ {
190
+ "current": 2201.0,
191
+ "min": 1000.0,
192
+ "max": 2201.0
193
+ },
194
+ {
195
+ "current": 2201.0,
196
+ "min": 1000.0,
197
+ "max": 2201.0
198
+ },
199
+ {
200
+ "current": 2201.0,
201
+ "min": 1000.0,
202
+ "max": 2201.0
203
+ },
204
+ {
205
+ "current": 2201.0,
206
+ "min": 1000.0,
207
+ "max": 2201.0
208
+ },
209
+ {
210
+ "current": 2201.0,
211
+ "min": 1000.0,
212
+ "max": 2201.0
213
+ },
214
+ {
215
+ "current": 2201.0,
216
+ "min": 1000.0,
217
+ "max": 2201.0
218
+ },
219
+ {
220
+ "current": 2201.0,
221
+ "min": 1000.0,
222
+ "max": 2201.0
223
+ },
224
+ {
225
+ "current": 2201.0,
226
+ "min": 1000.0,
227
+ "max": 2201.0
228
+ },
229
+ {
230
+ "current": 2201.0,
231
+ "min": 1000.0,
232
+ "max": 2201.0
233
+ },
234
+ {
235
+ "current": 2201.0,
236
+ "min": 1000.0,
237
+ "max": 2201.0
238
+ },
239
+ {
240
+ "current": 2201.0,
241
+ "min": 1000.0,
242
+ "max": 2201.0
243
+ },
244
+ {
245
+ "current": 2201.0,
246
+ "min": 1000.0,
247
+ "max": 2201.0
248
+ },
249
+ {
250
+ "current": 2201.0,
251
+ "min": 1000.0,
252
+ "max": 2201.0
253
+ },
254
+ {
255
+ "current": 2201.0,
256
+ "min": 1000.0,
257
+ "max": 2201.0
258
+ },
259
+ {
260
+ "current": 2201.0,
261
+ "min": 1000.0,
262
+ "max": 2201.0
263
+ },
264
+ {
265
+ "current": 2201.0,
266
+ "min": 1000.0,
267
+ "max": 2201.0
268
+ },
269
+ {
270
+ "current": 2201.0,
271
+ "min": 1000.0,
272
+ "max": 2201.0
273
+ },
274
+ {
275
+ "current": 2201.0,
276
+ "min": 1000.0,
277
+ "max": 2201.0
278
+ },
279
+ {
280
+ "current": 2201.0,
281
+ "min": 1000.0,
282
+ "max": 2201.0
283
+ },
284
+ {
285
+ "current": 2201.0,
286
+ "min": 1000.0,
287
+ "max": 2201.0
288
+ },
289
+ {
290
+ "current": 2201.0,
291
+ "min": 1000.0,
292
+ "max": 2201.0
293
+ },
294
+ {
295
+ "current": 2201.0,
296
+ "min": 1000.0,
297
+ "max": 2201.0
298
+ },
299
+ {
300
+ "current": 2201.0,
301
+ "min": 1000.0,
302
+ "max": 2201.0
303
+ },
304
+ {
305
+ "current": 2201.0,
306
+ "min": 1000.0,
307
+ "max": 2201.0
308
+ },
309
+ {
310
+ "current": 2201.0,
311
+ "min": 1000.0,
312
+ "max": 2201.0
313
+ },
314
+ {
315
+ "current": 2201.0,
316
+ "min": 1000.0,
317
+ "max": 2201.0
318
+ },
319
+ {
320
+ "current": 2201.0,
321
+ "min": 1000.0,
322
+ "max": 2201.0
323
+ },
324
+ {
325
+ "current": 2201.0,
326
+ "min": 1000.0,
327
+ "max": 2201.0
328
+ },
329
+ {
330
+ "current": 2201.0,
331
+ "min": 1000.0,
332
+ "max": 2201.0
333
+ },
334
+ {
335
+ "current": 2201.0,
336
+ "min": 1000.0,
337
+ "max": 2201.0
338
+ },
339
+ {
340
+ "current": 2201.0,
341
+ "min": 1000.0,
342
+ "max": 2201.0
343
+ },
344
+ {
345
+ "current": 2201.0,
346
+ "min": 1000.0,
347
+ "max": 2201.0
348
+ }
349
+ ],
350
+ "disk": {
351
+ "total": 99.951171875,
352
+ "used": 19.748153686523438
353
+ },
354
+ "gpu": "Tesla V100-SXM2-32GB",
355
+ "gpu_count": 2,
356
+ "gpu_devices": [
357
+ {
358
+ "name": "Tesla V100-SXM2-32GB",
359
+ "memory_total": 34089730048
360
+ },
361
+ {
362
+ "name": "Tesla V100-SXM2-32GB",
363
+ "memory_total": 34089730048
364
+ }
365
+ ],
366
+ "memory": {
367
+ "total": 251.55353164672852
368
+ }
369
+ }
wandb/run-20230507_103405-9zf5xxpu/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval/loss": 0.43405279517173767, "eval/wer": 54.25600000000001, "eval/runtime": 2248.2056, "eval/samples_per_second": 4.644, "eval/steps_per_second": 0.073, "_timestamp": 1683475217.3777876, "_runtime": 30371.4238345623, "_step": 40}
wandb/run-20230507_103405-9zf5xxpu/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20230507_103405-9zf5xxpu/logs/debug.log ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Current SDK version is 0.15.2
2
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Configure stats pid to 12412
3
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/.config/wandb/settings
4
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/settings
5
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program': '/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py'}
8
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_init.py:_log_setup():507] Logging user logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230507_103405-9zf5xxpu/logs/debug.log
9
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_init.py:_log_setup():508] Logging internal logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230507_103405-9zf5xxpu/logs/debug-internal.log
10
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_init.py:init():547] calling init triggers
11
+ 2023-05-07 10:34:05,926 INFO MainThread:12412 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
12
+ config: {}
13
+ 2023-05-07 10:34:05,927 INFO MainThread:12412 [wandb_init.py:init():596] starting backend
14
+ 2023-05-07 10:34:05,927 INFO MainThread:12412 [wandb_init.py:init():600] setting up manager
15
+ 2023-05-07 10:34:05,929 INFO MainThread:12412 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
16
+ 2023-05-07 10:34:05,953 INFO MainThread:12412 [wandb_init.py:init():606] backend started and connected
17
+ 2023-05-07 10:34:05,955 INFO MainThread:12412 [wandb_init.py:init():700] updated telemetry
18
+ 2023-05-07 10:34:06,022 INFO MainThread:12412 [wandb_init.py:init():737] communicating run to backend with 60.0 second timeout
19
+ 2023-05-07 10:34:06,586 INFO MainThread:12412 [wandb_run.py:_on_init():2177] communicating current version
20
+ 2023-05-07 10:34:06,688 INFO MainThread:12412 [wandb_run.py:_on_init():2186] got version response
21
+ 2023-05-07 10:34:06,688 INFO MainThread:12412 [wandb_init.py:init():787] starting run threads in backend
22
+ 2023-05-07 10:34:10,572 INFO MainThread:12412 [wandb_run.py:_console_start():2158] atexit reg
23
+ 2023-05-07 10:34:10,573 INFO MainThread:12412 [wandb_run.py:_redirect():2013] redirect: SettingsConsole.WRAP_RAW
24
+ 2023-05-07 10:34:10,573 INFO MainThread:12412 [wandb_run.py:_redirect():2078] Wrapping output streams.
25
+ 2023-05-07 10:34:10,573 INFO MainThread:12412 [wandb_run.py:_redirect():2103] Redirects installed.
26
+ 2023-05-07 10:34:10,574 INFO MainThread:12412 [wandb_init.py:init():829] run started, returning control to user process
27
+ 2023-05-07 10:34:10,592 INFO MainThread:12412 [wandb_run.py:_config_callback():1286] config_cb None None {'vocab_size': 51865, 'num_mel_bins': 80, 'd_model': 768, 'encoder_layers': 12, 'encoder_attention_heads': 12, 'decoder_layers': 12, 'decoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'encoder_ffn_dim': 3072, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': False, 'num_hidden_layers': 12, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50257, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-small', 'transformers_version': '4.29.0.dev0', 'forced_decoder_ids': None, 'model_type': 'whisper', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 5000, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/May07_10-33-38_crimv3mgpu025', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 'None', 'save_safetensors': False, 'save_on_each_node': False, 'no_cuda': False, 'use_mps_device': False, 'seed': 42, 'data_seed': 'None', 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'cuda_amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': 0, 'ddp_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'fsdp': '[]', 'fsdp_min_num_params': 0, 'fsdp_config': "{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}", 'fsdp_transformer_layer_cls_to_wrap': 'None', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'optim_args': 'None', 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': 'None', 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': 'None', 'torch_compile_mode': 'None', 'xpu_backend': 'None', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': 'None', 'generation_config': 'None', 'train_batch_size': 64, 'eval_batch_size': 64}
wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77d49c926099ac2b0f7a7e3b4e00ce2e9407dda9d529e412727a2fb9b212be2
3
+ size 2787409