Cheng Jed commited on
Commit
05b6e1e
1 Parent(s): 59ef4f0

first model

Browse files
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - mozilla-foundation/common_voice_11_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-large-v2-zh-hk-2gpu
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: mozilla-foundation/common_voice_11_0 zh-HK
17
+ type: mozilla-foundation/common_voice_11_0
18
+ config: None
19
+ split: None
20
+ args: zh-HK
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.45734639358860196
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # whisper-large-v2-zh-hk-2gpu
31
+
32
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the mozilla-foundation/common_voice_11_0 zh-HK dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2237
35
+ - Wer: 0.4573
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 8
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - distributed_type: multi-GPU
59
+ - num_devices: 2
60
+ - total_train_batch_size: 16
61
+ - total_eval_batch_size: 16
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 5000
66
+ - mixed_precision_training: Native AMP
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
71
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
72
+ | 0.1544 | 1.14 | 1000 | 0.2260 | 0.5485 |
73
+ | 0.0745 | 2.28 | 2000 | 0.2132 | 0.4967 |
74
+ | 0.0213 | 3.42 | 3000 | 0.2114 | 0.4718 |
75
+ | 0.0117 | 4.57 | 4000 | 0.2196 | 0.4643 |
76
+ | 0.0014 | 5.71 | 5000 | 0.2237 | 0.4573 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.26.0.dev0
82
+ - Pytorch 1.13.1
83
+ - Datasets 2.8.0
84
+ - Tokenizers 0.13.2
added_tokens.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|endoftext|>": 50257,
21
+ "<|en|>": 50259,
22
+ "<|es|>": 50262,
23
+ "<|et|>": 50307,
24
+ "<|eu|>": 50310,
25
+ "<|fa|>": 50300,
26
+ "<|fi|>": 50277,
27
+ "<|fo|>": 50338,
28
+ "<|fr|>": 50265,
29
+ "<|gl|>": 50319,
30
+ "<|gu|>": 50333,
31
+ "<|haw|>": 50352,
32
+ "<|ha|>": 50354,
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
+ "<|iw|>": 50279,
42
+ "<|ja|>": 50266,
43
+ "<|jw|>": 50356,
44
+ "<|ka|>": 50329,
45
+ "<|kk|>": 50316,
46
+ "<|km|>": 50323,
47
+ "<|kn|>": 50306,
48
+ "<|ko|>": 50264,
49
+ "<|la|>": 50294,
50
+ "<|lb|>": 50345,
51
+ "<|ln|>": 50353,
52
+ "<|lo|>": 50336,
53
+ "<|lt|>": 50293,
54
+ "<|lv|>": 50301,
55
+ "<|mg|>": 50349,
56
+ "<|mi|>": 50295,
57
+ "<|mk|>": 50308,
58
+ "<|ml|>": 50296,
59
+ "<|mn|>": 50314,
60
+ "<|mr|>": 50320,
61
+ "<|ms|>": 50282,
62
+ "<|mt|>": 50343,
63
+ "<|my|>": 50346,
64
+ "<|ne|>": 50313,
65
+ "<|nl|>": 50271,
66
+ "<|nn|>": 50342,
67
+ "<|nocaptions|>": 50362,
68
+ "<|notimestamps|>": 50363,
69
+ "<|no|>": 50288,
70
+ "<|oc|>": 50328,
71
+ "<|pa|>": 50321,
72
+ "<|pl|>": 50269,
73
+ "<|ps|>": 50340,
74
+ "<|pt|>": 50267,
75
+ "<|ro|>": 50284,
76
+ "<|ru|>": 50263,
77
+ "<|sa|>": 50344,
78
+ "<|sd|>": 50332,
79
+ "<|si|>": 50322,
80
+ "<|sk|>": 50298,
81
+ "<|sl|>": 50305,
82
+ "<|sn|>": 50324,
83
+ "<|so|>": 50326,
84
+ "<|sq|>": 50317,
85
+ "<|sr|>": 50303,
86
+ "<|startoflm|>": 50360,
87
+ "<|startofprev|>": 50361,
88
+ "<|startoftranscript|>": 50258,
89
+ "<|su|>": 50357,
90
+ "<|sv|>": 50273,
91
+ "<|sw|>": 50318,
92
+ "<|ta|>": 50287,
93
+ "<|te|>": 50299,
94
+ "<|tg|>": 50331,
95
+ "<|th|>": 50289,
96
+ "<|tk|>": 50341,
97
+ "<|tl|>": 50348,
98
+ "<|transcribe|>": 50359,
99
+ "<|translate|>": 50358,
100
+ "<|tr|>": 50268,
101
+ "<|tt|>": 50351,
102
+ "<|uk|>": 50280,
103
+ "<|ur|>": 50290,
104
+ "<|uz|>": 50337,
105
+ "<|vi|>": 50278,
106
+ "<|yi|>": 50335,
107
+ "<|yo|>": 50325,
108
+ "<|zh|>": 50260
109
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.71,
3
+ "eval_loss": 0.22371040284633636,
4
+ "eval_runtime": 1250.9538,
5
+ "eval_samples": 5591,
6
+ "eval_samples_per_second": 4.469,
7
+ "eval_steps_per_second": 0.28,
8
+ "eval_wer": 0.45734639358860196,
9
+ "train_loss": 0.10388498471789062,
10
+ "train_runtime": 22145.5379,
11
+ "train_samples": 14014,
12
+ "train_samples_per_second": 3.612,
13
+ "train_steps_per_second": 0.226
14
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-medium",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 24,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 24,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": null,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "max_length": 448,
30
+ "max_source_positions": 1500,
31
+ "max_target_positions": 448,
32
+ "model_type": "whisper",
33
+ "num_hidden_layers": 24,
34
+ "num_mel_bins": 80,
35
+ "pad_token_id": 50257,
36
+ "scale_embedding": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.26.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 51865
41
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.71,
3
+ "eval_loss": 0.22371040284633636,
4
+ "eval_runtime": 1250.9538,
5
+ "eval_samples": 5591,
6
+ "eval_samples_per_second": 4.469,
7
+ "eval_steps_per_second": 0.28,
8
+ "eval_wer": 0.45734639358860196
9
+ }
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
The diff for this file is too large to render. See raw diff
 
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
+ "<|iw|>",
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": "",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ }
133
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "openai/whisper-medium",
23
+ "pad_token": null,
24
+ "processor_class": "WhisperProcessor",
25
+ "return_attention_mask": false,
26
+ "special_tokens_map_file": null,
27
+ "tokenizer_class": "WhisperTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.71,
3
+ "train_loss": 0.10388498471789062,
4
+ "train_runtime": 22145.5379,
5
+ "train_samples": 14014,
6
+ "train_samples_per_second": 3.612,
7
+ "train_steps_per_second": 0.226
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.707762557077626,
5
+ "global_step": 5000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 4.2000000000000006e-07,
13
+ "loss": 0.8716,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.06,
18
+ "learning_rate": 9.200000000000001e-07,
19
+ "loss": 0.7032,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.09,
24
+ "learning_rate": 1.42e-06,
25
+ "loss": 0.4696,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.11,
30
+ "learning_rate": 1.9200000000000003e-06,
31
+ "loss": 0.372,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.14,
36
+ "learning_rate": 2.42e-06,
37
+ "loss": 0.3581,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.17,
42
+ "learning_rate": 2.92e-06,
43
+ "loss": 0.3364,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.2,
48
+ "learning_rate": 3.4200000000000007e-06,
49
+ "loss": 0.3204,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.23,
54
+ "learning_rate": 3.920000000000001e-06,
55
+ "loss": 0.317,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.26,
60
+ "learning_rate": 4.42e-06,
61
+ "loss": 0.3132,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.29,
66
+ "learning_rate": 4.92e-06,
67
+ "loss": 0.3021,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.31,
72
+ "learning_rate": 5.420000000000001e-06,
73
+ "loss": 0.3206,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.34,
78
+ "learning_rate": 5.92e-06,
79
+ "loss": 0.319,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.37,
84
+ "learning_rate": 6.42e-06,
85
+ "loss": 0.3265,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.4,
90
+ "learning_rate": 6.92e-06,
91
+ "loss": 0.3211,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.43,
96
+ "learning_rate": 7.420000000000001e-06,
97
+ "loss": 0.3143,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.46,
102
+ "learning_rate": 7.92e-06,
103
+ "loss": 0.3265,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.49,
108
+ "learning_rate": 8.42e-06,
109
+ "loss": 0.2936,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.51,
114
+ "learning_rate": 8.920000000000001e-06,
115
+ "loss": 0.312,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.54,
120
+ "learning_rate": 9.42e-06,
121
+ "loss": 0.3164,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.57,
126
+ "learning_rate": 9.920000000000002e-06,
127
+ "loss": 0.317,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.6,
132
+ "learning_rate": 9.953333333333333e-06,
133
+ "loss": 0.315,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.63,
138
+ "learning_rate": 9.89777777777778e-06,
139
+ "loss": 0.3249,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.66,
144
+ "learning_rate": 9.842222222222223e-06,
145
+ "loss": 0.3308,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.68,
150
+ "learning_rate": 9.786666666666667e-06,
151
+ "loss": 0.3492,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.71,
156
+ "learning_rate": 9.731111111111113e-06,
157
+ "loss": 0.3101,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.74,
162
+ "learning_rate": 9.675555555555555e-06,
163
+ "loss": 0.3229,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 0.77,
168
+ "learning_rate": 9.620000000000001e-06,
169
+ "loss": 0.294,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 0.8,
174
+ "learning_rate": 9.564444444444445e-06,
175
+ "loss": 0.2862,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 0.83,
180
+ "learning_rate": 9.508888888888889e-06,
181
+ "loss": 0.3107,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 0.86,
186
+ "learning_rate": 9.453333333333335e-06,
187
+ "loss": 0.2819,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 0.88,
192
+ "learning_rate": 9.397777777777779e-06,
193
+ "loss": 0.3166,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 0.91,
198
+ "learning_rate": 9.342222222222223e-06,
199
+ "loss": 0.298,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 0.94,
204
+ "learning_rate": 9.286666666666667e-06,
205
+ "loss": 0.3088,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 0.97,
210
+ "learning_rate": 9.231111111111111e-06,
211
+ "loss": 0.2821,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 1.0,
216
+ "learning_rate": 9.175555555555557e-06,
217
+ "loss": 0.2961,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 1.03,
222
+ "learning_rate": 9.12e-06,
223
+ "loss": 0.169,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 1.06,
228
+ "learning_rate": 9.064444444444447e-06,
229
+ "loss": 0.1584,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 1.08,
234
+ "learning_rate": 9.008888888888889e-06,
235
+ "loss": 0.1422,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 1.11,
240
+ "learning_rate": 8.953333333333335e-06,
241
+ "loss": 0.1615,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 1.14,
246
+ "learning_rate": 8.897777777777779e-06,
247
+ "loss": 0.1544,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 1.14,
252
+ "eval_loss": 0.22604741156101227,
253
+ "eval_runtime": 1239.0181,
254
+ "eval_samples_per_second": 4.512,
255
+ "eval_steps_per_second": 0.282,
256
+ "eval_wer": 0.5485307212822796,
257
+ "step": 1000
258
+ },
259
+ {
260
+ "epoch": 1.17,
261
+ "learning_rate": 8.842222222222223e-06,
262
+ "loss": 0.1593,
263
+ "step": 1025
264
+ },
265
+ {
266
+ "epoch": 1.2,
267
+ "learning_rate": 8.786666666666668e-06,
268
+ "loss": 0.1527,
269
+ "step": 1050
270
+ },
271
+ {
272
+ "epoch": 1.23,
273
+ "learning_rate": 8.73111111111111e-06,
274
+ "loss": 0.1534,
275
+ "step": 1075
276
+ },
277
+ {
278
+ "epoch": 1.26,
279
+ "learning_rate": 8.675555555555556e-06,
280
+ "loss": 0.1723,
281
+ "step": 1100
282
+ },
283
+ {
284
+ "epoch": 1.28,
285
+ "learning_rate": 8.62e-06,
286
+ "loss": 0.1503,
287
+ "step": 1125
288
+ },
289
+ {
290
+ "epoch": 1.31,
291
+ "learning_rate": 8.564444444444445e-06,
292
+ "loss": 0.1418,
293
+ "step": 1150
294
+ },
295
+ {
296
+ "epoch": 1.34,
297
+ "learning_rate": 8.50888888888889e-06,
298
+ "loss": 0.1455,
299
+ "step": 1175
300
+ },
301
+ {
302
+ "epoch": 1.37,
303
+ "learning_rate": 8.453333333333334e-06,
304
+ "loss": 0.1622,
305
+ "step": 1200
306
+ },
307
+ {
308
+ "epoch": 1.4,
309
+ "learning_rate": 8.397777777777778e-06,
310
+ "loss": 0.1567,
311
+ "step": 1225
312
+ },
313
+ {
314
+ "epoch": 1.43,
315
+ "learning_rate": 8.342222222222222e-06,
316
+ "loss": 0.1787,
317
+ "step": 1250
318
+ },
319
+ {
320
+ "epoch": 1.46,
321
+ "learning_rate": 8.286666666666668e-06,
322
+ "loss": 0.1745,
323
+ "step": 1275
324
+ },
325
+ {
326
+ "epoch": 1.48,
327
+ "learning_rate": 8.231111111111112e-06,
328
+ "loss": 0.1718,
329
+ "step": 1300
330
+ },
331
+ {
332
+ "epoch": 1.51,
333
+ "learning_rate": 8.175555555555556e-06,
334
+ "loss": 0.1287,
335
+ "step": 1325
336
+ },
337
+ {
338
+ "epoch": 1.54,
339
+ "learning_rate": 8.120000000000002e-06,
340
+ "loss": 0.1293,
341
+ "step": 1350
342
+ },
343
+ {
344
+ "epoch": 1.57,
345
+ "learning_rate": 8.064444444444444e-06,
346
+ "loss": 0.1471,
347
+ "step": 1375
348
+ },
349
+ {
350
+ "epoch": 1.6,
351
+ "learning_rate": 8.00888888888889e-06,
352
+ "loss": 0.1538,
353
+ "step": 1400
354
+ },
355
+ {
356
+ "epoch": 1.63,
357
+ "learning_rate": 7.953333333333334e-06,
358
+ "loss": 0.1441,
359
+ "step": 1425
360
+ },
361
+ {
362
+ "epoch": 1.66,
363
+ "learning_rate": 7.897777777777778e-06,
364
+ "loss": 0.1452,
365
+ "step": 1450
366
+ },
367
+ {
368
+ "epoch": 1.68,
369
+ "learning_rate": 7.842222222222224e-06,
370
+ "loss": 0.1548,
371
+ "step": 1475
372
+ },
373
+ {
374
+ "epoch": 1.71,
375
+ "learning_rate": 7.786666666666666e-06,
376
+ "loss": 0.1548,
377
+ "step": 1500
378
+ },
379
+ {
380
+ "epoch": 1.74,
381
+ "learning_rate": 7.731111111111112e-06,
382
+ "loss": 0.137,
383
+ "step": 1525
384
+ },
385
+ {
386
+ "epoch": 1.77,
387
+ "learning_rate": 7.675555555555556e-06,
388
+ "loss": 0.1451,
389
+ "step": 1550
390
+ },
391
+ {
392
+ "epoch": 1.8,
393
+ "learning_rate": 7.620000000000001e-06,
394
+ "loss": 0.1367,
395
+ "step": 1575
396
+ },
397
+ {
398
+ "epoch": 1.83,
399
+ "learning_rate": 7.564444444444446e-06,
400
+ "loss": 0.1576,
401
+ "step": 1600
402
+ },
403
+ {
404
+ "epoch": 1.86,
405
+ "learning_rate": 7.50888888888889e-06,
406
+ "loss": 0.1764,
407
+ "step": 1625
408
+ },
409
+ {
410
+ "epoch": 1.88,
411
+ "learning_rate": 7.453333333333334e-06,
412
+ "loss": 0.1625,
413
+ "step": 1650
414
+ },
415
+ {
416
+ "epoch": 1.91,
417
+ "learning_rate": 7.3977777777777786e-06,
418
+ "loss": 0.1481,
419
+ "step": 1675
420
+ },
421
+ {
422
+ "epoch": 1.94,
423
+ "learning_rate": 7.342222222222223e-06,
424
+ "loss": 0.1523,
425
+ "step": 1700
426
+ },
427
+ {
428
+ "epoch": 1.97,
429
+ "learning_rate": 7.2866666666666675e-06,
430
+ "loss": 0.1404,
431
+ "step": 1725
432
+ },
433
+ {
434
+ "epoch": 2.0,
435
+ "learning_rate": 7.231111111111112e-06,
436
+ "loss": 0.1352,
437
+ "step": 1750
438
+ },
439
+ {
440
+ "epoch": 2.03,
441
+ "learning_rate": 7.1755555555555556e-06,
442
+ "loss": 0.0618,
443
+ "step": 1775
444
+ },
445
+ {
446
+ "epoch": 2.05,
447
+ "learning_rate": 7.1200000000000004e-06,
448
+ "loss": 0.0536,
449
+ "step": 1800
450
+ },
451
+ {
452
+ "epoch": 2.08,
453
+ "learning_rate": 7.0644444444444445e-06,
454
+ "loss": 0.0685,
455
+ "step": 1825
456
+ },
457
+ {
458
+ "epoch": 2.11,
459
+ "learning_rate": 7.008888888888889e-06,
460
+ "loss": 0.0755,
461
+ "step": 1850
462
+ },
463
+ {
464
+ "epoch": 2.14,
465
+ "learning_rate": 6.953333333333334e-06,
466
+ "loss": 0.053,
467
+ "step": 1875
468
+ },
469
+ {
470
+ "epoch": 2.17,
471
+ "learning_rate": 6.897777777777779e-06,
472
+ "loss": 0.0603,
473
+ "step": 1900
474
+ },
475
+ {
476
+ "epoch": 2.2,
477
+ "learning_rate": 6.842222222222222e-06,
478
+ "loss": 0.0709,
479
+ "step": 1925
480
+ },
481
+ {
482
+ "epoch": 2.23,
483
+ "learning_rate": 6.786666666666667e-06,
484
+ "loss": 0.0678,
485
+ "step": 1950
486
+ },
487
+ {
488
+ "epoch": 2.25,
489
+ "learning_rate": 6.731111111111111e-06,
490
+ "loss": 0.0696,
491
+ "step": 1975
492
+ },
493
+ {
494
+ "epoch": 2.28,
495
+ "learning_rate": 6.675555555555556e-06,
496
+ "loss": 0.0745,
497
+ "step": 2000
498
+ },
499
+ {
500
+ "epoch": 2.28,
501
+ "eval_loss": 0.2132357656955719,
502
+ "eval_runtime": 1250.3673,
503
+ "eval_samples_per_second": 4.471,
504
+ "eval_steps_per_second": 0.28,
505
+ "eval_wer": 0.4967052537845058,
506
+ "step": 2000
507
+ },
508
+ {
509
+ "epoch": 2.31,
510
+ "learning_rate": 6.620000000000001e-06,
511
+ "loss": 0.0547,
512
+ "step": 2025
513
+ },
514
+ {
515
+ "epoch": 2.34,
516
+ "learning_rate": 6.564444444444446e-06,
517
+ "loss": 0.06,
518
+ "step": 2050
519
+ },
520
+ {
521
+ "epoch": 2.37,
522
+ "learning_rate": 6.508888888888889e-06,
523
+ "loss": 0.0576,
524
+ "step": 2075
525
+ },
526
+ {
527
+ "epoch": 2.4,
528
+ "learning_rate": 6.453333333333334e-06,
529
+ "loss": 0.0797,
530
+ "step": 2100
531
+ },
532
+ {
533
+ "epoch": 2.43,
534
+ "learning_rate": 6.397777777777778e-06,
535
+ "loss": 0.0564,
536
+ "step": 2125
537
+ },
538
+ {
539
+ "epoch": 2.45,
540
+ "learning_rate": 6.342222222222223e-06,
541
+ "loss": 0.067,
542
+ "step": 2150
543
+ },
544
+ {
545
+ "epoch": 2.48,
546
+ "learning_rate": 6.286666666666668e-06,
547
+ "loss": 0.058,
548
+ "step": 2175
549
+ },
550
+ {
551
+ "epoch": 2.51,
552
+ "learning_rate": 6.231111111111111e-06,
553
+ "loss": 0.0614,
554
+ "step": 2200
555
+ },
556
+ {
557
+ "epoch": 2.54,
558
+ "learning_rate": 6.175555555555556e-06,
559
+ "loss": 0.0585,
560
+ "step": 2225
561
+ },
562
+ {
563
+ "epoch": 2.57,
564
+ "learning_rate": 6.120000000000001e-06,
565
+ "loss": 0.0621,
566
+ "step": 2250
567
+ },
568
+ {
569
+ "epoch": 2.6,
570
+ "learning_rate": 6.064444444444445e-06,
571
+ "loss": 0.0583,
572
+ "step": 2275
573
+ },
574
+ {
575
+ "epoch": 2.63,
576
+ "learning_rate": 6.00888888888889e-06,
577
+ "loss": 0.0609,
578
+ "step": 2300
579
+ },
580
+ {
581
+ "epoch": 2.65,
582
+ "learning_rate": 5.9533333333333345e-06,
583
+ "loss": 0.0641,
584
+ "step": 2325
585
+ },
586
+ {
587
+ "epoch": 2.68,
588
+ "learning_rate": 5.897777777777778e-06,
589
+ "loss": 0.0563,
590
+ "step": 2350
591
+ },
592
+ {
593
+ "epoch": 2.71,
594
+ "learning_rate": 5.8422222222222226e-06,
595
+ "loss": 0.0572,
596
+ "step": 2375
597
+ },
598
+ {
599
+ "epoch": 2.74,
600
+ "learning_rate": 5.7866666666666674e-06,
601
+ "loss": 0.0587,
602
+ "step": 2400
603
+ },
604
+ {
605
+ "epoch": 2.77,
606
+ "learning_rate": 5.7311111111111115e-06,
607
+ "loss": 0.0596,
608
+ "step": 2425
609
+ },
610
+ {
611
+ "epoch": 2.8,
612
+ "learning_rate": 5.675555555555556e-06,
613
+ "loss": 0.0605,
614
+ "step": 2450
615
+ },
616
+ {
617
+ "epoch": 2.83,
618
+ "learning_rate": 5.620000000000001e-06,
619
+ "loss": 0.0646,
620
+ "step": 2475
621
+ },
622
+ {
623
+ "epoch": 2.85,
624
+ "learning_rate": 5.5644444444444444e-06,
625
+ "loss": 0.0544,
626
+ "step": 2500
627
+ },
628
+ {
629
+ "epoch": 2.88,
630
+ "learning_rate": 5.508888888888889e-06,
631
+ "loss": 0.0593,
632
+ "step": 2525
633
+ },
634
+ {
635
+ "epoch": 2.91,
636
+ "learning_rate": 5.453333333333334e-06,
637
+ "loss": 0.0577,
638
+ "step": 2550
639
+ },
640
+ {
641
+ "epoch": 2.94,
642
+ "learning_rate": 5.397777777777778e-06,
643
+ "loss": 0.0706,
644
+ "step": 2575
645
+ },
646
+ {
647
+ "epoch": 2.97,
648
+ "learning_rate": 5.342222222222223e-06,
649
+ "loss": 0.056,
650
+ "step": 2600
651
+ },
652
+ {
653
+ "epoch": 3.0,
654
+ "learning_rate": 5.286666666666666e-06,
655
+ "loss": 0.0621,
656
+ "step": 2625
657
+ },
658
+ {
659
+ "epoch": 3.03,
660
+ "learning_rate": 5.231111111111111e-06,
661
+ "loss": 0.0297,
662
+ "step": 2650
663
+ },
664
+ {
665
+ "epoch": 3.05,
666
+ "learning_rate": 5.175555555555556e-06,
667
+ "loss": 0.0244,
668
+ "step": 2675
669
+ },
670
+ {
671
+ "epoch": 3.08,
672
+ "learning_rate": 5.12e-06,
673
+ "loss": 0.0276,
674
+ "step": 2700
675
+ },
676
+ {
677
+ "epoch": 3.11,
678
+ "learning_rate": 5.064444444444445e-06,
679
+ "loss": 0.0207,
680
+ "step": 2725
681
+ },
682
+ {
683
+ "epoch": 3.14,
684
+ "learning_rate": 5.00888888888889e-06,
685
+ "loss": 0.0264,
686
+ "step": 2750
687
+ },
688
+ {
689
+ "epoch": 3.17,
690
+ "learning_rate": 4.953333333333334e-06,
691
+ "loss": 0.0263,
692
+ "step": 2775
693
+ },
694
+ {
695
+ "epoch": 3.2,
696
+ "learning_rate": 4.897777777777778e-06,
697
+ "loss": 0.0263,
698
+ "step": 2800
699
+ },
700
+ {
701
+ "epoch": 3.22,
702
+ "learning_rate": 4.842222222222223e-06,
703
+ "loss": 0.0252,
704
+ "step": 2825
705
+ },
706
+ {
707
+ "epoch": 3.25,
708
+ "learning_rate": 4.786666666666667e-06,
709
+ "loss": 0.0254,
710
+ "step": 2850
711
+ },
712
+ {
713
+ "epoch": 3.28,
714
+ "learning_rate": 4.731111111111112e-06,
715
+ "loss": 0.0224,
716
+ "step": 2875
717
+ },
718
+ {
719
+ "epoch": 3.31,
720
+ "learning_rate": 4.675555555555556e-06,
721
+ "loss": 0.0257,
722
+ "step": 2900
723
+ },
724
+ {
725
+ "epoch": 3.34,
726
+ "learning_rate": 4.620000000000001e-06,
727
+ "loss": 0.0229,
728
+ "step": 2925
729
+ },
730
+ {
731
+ "epoch": 3.37,
732
+ "learning_rate": 4.564444444444445e-06,
733
+ "loss": 0.0214,
734
+ "step": 2950
735
+ },
736
+ {
737
+ "epoch": 3.4,
738
+ "learning_rate": 4.50888888888889e-06,
739
+ "loss": 0.022,
740
+ "step": 2975
741
+ },
742
+ {
743
+ "epoch": 3.42,
744
+ "learning_rate": 4.453333333333334e-06,
745
+ "loss": 0.0213,
746
+ "step": 3000
747
+ },
748
+ {
749
+ "epoch": 3.42,
750
+ "eval_loss": 0.21137936413288116,
751
+ "eval_runtime": 1246.2776,
752
+ "eval_samples_per_second": 4.486,
753
+ "eval_steps_per_second": 0.281,
754
+ "eval_wer": 0.4717720391807658,
755
+ "step": 3000
756
+ },
757
+ {
758
+ "epoch": 3.45,
759
+ "learning_rate": 4.397777777777778e-06,
760
+ "loss": 0.0261,
761
+ "step": 3025
762
+ },
763
+ {
764
+ "epoch": 3.48,
765
+ "learning_rate": 4.3422222222222225e-06,
766
+ "loss": 0.0287,
767
+ "step": 3050
768
+ },
769
+ {
770
+ "epoch": 3.51,
771
+ "learning_rate": 4.2866666666666666e-06,
772
+ "loss": 0.022,
773
+ "step": 3075
774
+ },
775
+ {
776
+ "epoch": 3.54,
777
+ "learning_rate": 4.2311111111111114e-06,
778
+ "loss": 0.0273,
779
+ "step": 3100
780
+ },
781
+ {
782
+ "epoch": 3.57,
783
+ "learning_rate": 4.175555555555556e-06,
784
+ "loss": 0.0224,
785
+ "step": 3125
786
+ },
787
+ {
788
+ "epoch": 3.6,
789
+ "learning_rate": 4.12e-06,
790
+ "loss": 0.0243,
791
+ "step": 3150
792
+ },
793
+ {
794
+ "epoch": 3.62,
795
+ "learning_rate": 4.064444444444444e-06,
796
+ "loss": 0.0168,
797
+ "step": 3175
798
+ },
799
+ {
800
+ "epoch": 3.65,
801
+ "learning_rate": 4.008888888888889e-06,
802
+ "loss": 0.0212,
803
+ "step": 3200
804
+ },
805
+ {
806
+ "epoch": 3.68,
807
+ "learning_rate": 3.953333333333333e-06,
808
+ "loss": 0.0205,
809
+ "step": 3225
810
+ },
811
+ {
812
+ "epoch": 3.71,
813
+ "learning_rate": 3.897777777777778e-06,
814
+ "loss": 0.0231,
815
+ "step": 3250
816
+ },
817
+ {
818
+ "epoch": 3.74,
819
+ "learning_rate": 3.842222222222223e-06,
820
+ "loss": 0.02,
821
+ "step": 3275
822
+ },
823
+ {
824
+ "epoch": 3.77,
825
+ "learning_rate": 3.7866666666666667e-06,
826
+ "loss": 0.0244,
827
+ "step": 3300
828
+ },
829
+ {
830
+ "epoch": 3.8,
831
+ "learning_rate": 3.7311111111111116e-06,
832
+ "loss": 0.0195,
833
+ "step": 3325
834
+ },
835
+ {
836
+ "epoch": 3.82,
837
+ "learning_rate": 3.675555555555556e-06,
838
+ "loss": 0.0211,
839
+ "step": 3350
840
+ },
841
+ {
842
+ "epoch": 3.85,
843
+ "learning_rate": 3.62e-06,
844
+ "loss": 0.0225,
845
+ "step": 3375
846
+ },
847
+ {
848
+ "epoch": 3.88,
849
+ "learning_rate": 3.564444444444445e-06,
850
+ "loss": 0.0162,
851
+ "step": 3400
852
+ },
853
+ {
854
+ "epoch": 3.91,
855
+ "learning_rate": 3.508888888888889e-06,
856
+ "loss": 0.0253,
857
+ "step": 3425
858
+ },
859
+ {
860
+ "epoch": 3.94,
861
+ "learning_rate": 3.4533333333333334e-06,
862
+ "loss": 0.0156,
863
+ "step": 3450
864
+ },
865
+ {
866
+ "epoch": 3.97,
867
+ "learning_rate": 3.3977777777777783e-06,
868
+ "loss": 0.0219,
869
+ "step": 3475
870
+ },
871
+ {
872
+ "epoch": 4.0,
873
+ "learning_rate": 3.3422222222222224e-06,
874
+ "loss": 0.0175,
875
+ "step": 3500
876
+ },
877
+ {
878
+ "epoch": 4.02,
879
+ "learning_rate": 3.286666666666667e-06,
880
+ "loss": 0.0133,
881
+ "step": 3525
882
+ },
883
+ {
884
+ "epoch": 4.05,
885
+ "learning_rate": 3.2311111111111117e-06,
886
+ "loss": 0.0065,
887
+ "step": 3550
888
+ },
889
+ {
890
+ "epoch": 4.08,
891
+ "learning_rate": 3.1755555555555557e-06,
892
+ "loss": 0.0087,
893
+ "step": 3575
894
+ },
895
+ {
896
+ "epoch": 4.11,
897
+ "learning_rate": 3.12e-06,
898
+ "loss": 0.0068,
899
+ "step": 3600
900
+ },
901
+ {
902
+ "epoch": 4.14,
903
+ "learning_rate": 3.064444444444445e-06,
904
+ "loss": 0.009,
905
+ "step": 3625
906
+ },
907
+ {
908
+ "epoch": 4.17,
909
+ "learning_rate": 3.008888888888889e-06,
910
+ "loss": 0.0071,
911
+ "step": 3650
912
+ },
913
+ {
914
+ "epoch": 4.2,
915
+ "learning_rate": 2.9533333333333336e-06,
916
+ "loss": 0.0063,
917
+ "step": 3675
918
+ },
919
+ {
920
+ "epoch": 4.22,
921
+ "learning_rate": 2.8977777777777785e-06,
922
+ "loss": 0.0082,
923
+ "step": 3700
924
+ },
925
+ {
926
+ "epoch": 4.25,
927
+ "learning_rate": 2.8422222222222225e-06,
928
+ "loss": 0.0054,
929
+ "step": 3725
930
+ },
931
+ {
932
+ "epoch": 4.28,
933
+ "learning_rate": 2.786666666666667e-06,
934
+ "loss": 0.0098,
935
+ "step": 3750
936
+ },
937
+ {
938
+ "epoch": 4.31,
939
+ "learning_rate": 2.7311111111111114e-06,
940
+ "loss": 0.0077,
941
+ "step": 3775
942
+ },
943
+ {
944
+ "epoch": 4.34,
945
+ "learning_rate": 2.675555555555556e-06,
946
+ "loss": 0.0043,
947
+ "step": 3800
948
+ },
949
+ {
950
+ "epoch": 4.37,
951
+ "learning_rate": 2.6200000000000003e-06,
952
+ "loss": 0.0064,
953
+ "step": 3825
954
+ },
955
+ {
956
+ "epoch": 4.39,
957
+ "learning_rate": 2.5644444444444444e-06,
958
+ "loss": 0.0062,
959
+ "step": 3850
960
+ },
961
+ {
962
+ "epoch": 4.42,
963
+ "learning_rate": 2.5088888888888892e-06,
964
+ "loss": 0.0038,
965
+ "step": 3875
966
+ },
967
+ {
968
+ "epoch": 4.45,
969
+ "learning_rate": 2.4533333333333333e-06,
970
+ "loss": 0.0121,
971
+ "step": 3900
972
+ },
973
+ {
974
+ "epoch": 4.48,
975
+ "learning_rate": 2.397777777777778e-06,
976
+ "loss": 0.006,
977
+ "step": 3925
978
+ },
979
+ {
980
+ "epoch": 4.51,
981
+ "learning_rate": 2.342222222222222e-06,
982
+ "loss": 0.0061,
983
+ "step": 3950
984
+ },
985
+ {
986
+ "epoch": 4.54,
987
+ "learning_rate": 2.2866666666666667e-06,
988
+ "loss": 0.0081,
989
+ "step": 3975
990
+ },
991
+ {
992
+ "epoch": 4.57,
993
+ "learning_rate": 2.2311111111111115e-06,
994
+ "loss": 0.0117,
995
+ "step": 4000
996
+ },
997
+ {
998
+ "epoch": 4.57,
999
+ "eval_loss": 0.2196018099784851,
1000
+ "eval_runtime": 1243.8383,
1001
+ "eval_samples_per_second": 4.495,
1002
+ "eval_steps_per_second": 0.281,
1003
+ "eval_wer": 0.4642920747996438,
1004
+ "step": 4000
1005
+ },
1006
+ {
1007
+ "epoch": 4.59,
1008
+ "learning_rate": 2.1755555555555556e-06,
1009
+ "loss": 0.0071,
1010
+ "step": 4025
1011
+ },
1012
+ {
1013
+ "epoch": 4.62,
1014
+ "learning_rate": 2.12e-06,
1015
+ "loss": 0.006,
1016
+ "step": 4050
1017
+ },
1018
+ {
1019
+ "epoch": 4.65,
1020
+ "learning_rate": 2.064444444444445e-06,
1021
+ "loss": 0.0051,
1022
+ "step": 4075
1023
+ },
1024
+ {
1025
+ "epoch": 4.68,
1026
+ "learning_rate": 2.008888888888889e-06,
1027
+ "loss": 0.0035,
1028
+ "step": 4100
1029
+ },
1030
+ {
1031
+ "epoch": 4.71,
1032
+ "learning_rate": 1.9533333333333334e-06,
1033
+ "loss": 0.0052,
1034
+ "step": 4125
1035
+ },
1036
+ {
1037
+ "epoch": 4.74,
1038
+ "learning_rate": 1.8977777777777779e-06,
1039
+ "loss": 0.0058,
1040
+ "step": 4150
1041
+ },
1042
+ {
1043
+ "epoch": 4.77,
1044
+ "learning_rate": 1.8422222222222225e-06,
1045
+ "loss": 0.0074,
1046
+ "step": 4175
1047
+ },
1048
+ {
1049
+ "epoch": 4.79,
1050
+ "learning_rate": 1.7866666666666668e-06,
1051
+ "loss": 0.0075,
1052
+ "step": 4200
1053
+ },
1054
+ {
1055
+ "epoch": 4.82,
1056
+ "learning_rate": 1.7311111111111112e-06,
1057
+ "loss": 0.0053,
1058
+ "step": 4225
1059
+ },
1060
+ {
1061
+ "epoch": 4.85,
1062
+ "learning_rate": 1.675555555555556e-06,
1063
+ "loss": 0.0064,
1064
+ "step": 4250
1065
+ },
1066
+ {
1067
+ "epoch": 4.88,
1068
+ "learning_rate": 1.6200000000000002e-06,
1069
+ "loss": 0.0067,
1070
+ "step": 4275
1071
+ },
1072
+ {
1073
+ "epoch": 4.91,
1074
+ "learning_rate": 1.5644444444444446e-06,
1075
+ "loss": 0.0044,
1076
+ "step": 4300
1077
+ },
1078
+ {
1079
+ "epoch": 4.94,
1080
+ "learning_rate": 1.5088888888888889e-06,
1081
+ "loss": 0.0049,
1082
+ "step": 4325
1083
+ },
1084
+ {
1085
+ "epoch": 4.97,
1086
+ "learning_rate": 1.4533333333333335e-06,
1087
+ "loss": 0.0028,
1088
+ "step": 4350
1089
+ },
1090
+ {
1091
+ "epoch": 4.99,
1092
+ "learning_rate": 1.397777777777778e-06,
1093
+ "loss": 0.0052,
1094
+ "step": 4375
1095
+ },
1096
+ {
1097
+ "epoch": 5.02,
1098
+ "learning_rate": 1.3422222222222222e-06,
1099
+ "loss": 0.0027,
1100
+ "step": 4400
1101
+ },
1102
+ {
1103
+ "epoch": 5.05,
1104
+ "learning_rate": 1.286666666666667e-06,
1105
+ "loss": 0.0021,
1106
+ "step": 4425
1107
+ },
1108
+ {
1109
+ "epoch": 5.08,
1110
+ "learning_rate": 1.2311111111111112e-06,
1111
+ "loss": 0.002,
1112
+ "step": 4450
1113
+ },
1114
+ {
1115
+ "epoch": 5.11,
1116
+ "learning_rate": 1.1755555555555556e-06,
1117
+ "loss": 0.0037,
1118
+ "step": 4475
1119
+ },
1120
+ {
1121
+ "epoch": 5.14,
1122
+ "learning_rate": 1.12e-06,
1123
+ "loss": 0.0014,
1124
+ "step": 4500
1125
+ },
1126
+ {
1127
+ "epoch": 5.17,
1128
+ "learning_rate": 1.0644444444444445e-06,
1129
+ "loss": 0.002,
1130
+ "step": 4525
1131
+ },
1132
+ {
1133
+ "epoch": 5.19,
1134
+ "learning_rate": 1.008888888888889e-06,
1135
+ "loss": 0.0012,
1136
+ "step": 4550
1137
+ },
1138
+ {
1139
+ "epoch": 5.22,
1140
+ "learning_rate": 9.533333333333335e-07,
1141
+ "loss": 0.002,
1142
+ "step": 4575
1143
+ },
1144
+ {
1145
+ "epoch": 5.25,
1146
+ "learning_rate": 8.977777777777778e-07,
1147
+ "loss": 0.0039,
1148
+ "step": 4600
1149
+ },
1150
+ {
1151
+ "epoch": 5.28,
1152
+ "learning_rate": 8.422222222222224e-07,
1153
+ "loss": 0.0025,
1154
+ "step": 4625
1155
+ },
1156
+ {
1157
+ "epoch": 5.31,
1158
+ "learning_rate": 7.866666666666667e-07,
1159
+ "loss": 0.0014,
1160
+ "step": 4650
1161
+ },
1162
+ {
1163
+ "epoch": 5.34,
1164
+ "learning_rate": 7.311111111111112e-07,
1165
+ "loss": 0.002,
1166
+ "step": 4675
1167
+ },
1168
+ {
1169
+ "epoch": 5.37,
1170
+ "learning_rate": 6.755555555555555e-07,
1171
+ "loss": 0.0013,
1172
+ "step": 4700
1173
+ },
1174
+ {
1175
+ "epoch": 5.39,
1176
+ "learning_rate": 6.200000000000001e-07,
1177
+ "loss": 0.0025,
1178
+ "step": 4725
1179
+ },
1180
+ {
1181
+ "epoch": 5.42,
1182
+ "learning_rate": 5.644444444444445e-07,
1183
+ "loss": 0.0023,
1184
+ "step": 4750
1185
+ },
1186
+ {
1187
+ "epoch": 5.45,
1188
+ "learning_rate": 5.088888888888889e-07,
1189
+ "loss": 0.0024,
1190
+ "step": 4775
1191
+ },
1192
+ {
1193
+ "epoch": 5.48,
1194
+ "learning_rate": 4.533333333333334e-07,
1195
+ "loss": 0.0012,
1196
+ "step": 4800
1197
+ },
1198
+ {
1199
+ "epoch": 5.51,
1200
+ "learning_rate": 3.9777777777777783e-07,
1201
+ "loss": 0.0016,
1202
+ "step": 4825
1203
+ },
1204
+ {
1205
+ "epoch": 5.54,
1206
+ "learning_rate": 3.422222222222223e-07,
1207
+ "loss": 0.0022,
1208
+ "step": 4850
1209
+ },
1210
+ {
1211
+ "epoch": 5.57,
1212
+ "learning_rate": 2.866666666666667e-07,
1213
+ "loss": 0.0012,
1214
+ "step": 4875
1215
+ },
1216
+ {
1217
+ "epoch": 5.59,
1218
+ "learning_rate": 2.3111111111111112e-07,
1219
+ "loss": 0.0011,
1220
+ "step": 4900
1221
+ },
1222
+ {
1223
+ "epoch": 5.62,
1224
+ "learning_rate": 1.7555555555555558e-07,
1225
+ "loss": 0.0013,
1226
+ "step": 4925
1227
+ },
1228
+ {
1229
+ "epoch": 5.65,
1230
+ "learning_rate": 1.2000000000000002e-07,
1231
+ "loss": 0.0021,
1232
+ "step": 4950
1233
+ },
1234
+ {
1235
+ "epoch": 5.68,
1236
+ "learning_rate": 6.444444444444445e-08,
1237
+ "loss": 0.0055,
1238
+ "step": 4975
1239
+ },
1240
+ {
1241
+ "epoch": 5.71,
1242
+ "learning_rate": 8.88888888888889e-09,
1243
+ "loss": 0.0014,
1244
+ "step": 5000
1245
+ },
1246
+ {
1247
+ "epoch": 5.71,
1248
+ "eval_loss": 0.22371040284633636,
1249
+ "eval_runtime": 1249.8343,
1250
+ "eval_samples_per_second": 4.473,
1251
+ "eval_steps_per_second": 0.28,
1252
+ "eval_wer": 0.45734639358860196,
1253
+ "step": 5000
1254
+ },
1255
+ {
1256
+ "epoch": 5.71,
1257
+ "step": 5000,
1258
+ "total_flos": 8.163818740396327e+19,
1259
+ "train_loss": 0.10388498471789062,
1260
+ "train_runtime": 22145.5379,
1261
+ "train_samples_per_second": 3.612,
1262
+ "train_steps_per_second": 0.226
1263
+ }
1264
+ ],
1265
+ "max_steps": 5000,
1266
+ "num_train_epochs": 6,
1267
+ "total_flos": 8.163818740396327e+19,
1268
+ "trial_name": null,
1269
+ "trial_params": null
1270
+ }
training_args.bin ADDED
Binary file (3.64 kB). View file
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff