Hugging Face's logo

geninhu
/
whisper-large-v2-multiset-vi

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Vietnamese
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
6
geninhu commited on
Commit
1926947
•
1 Parent(s): 7650c47

Training in progress, step 1000

Browse files
Files changed (16) hide show
  1. .gitignore +1 -0
  2. .ipynb_checkpoints/run-checkpoint.sh +38 -0
  3. added_tokens.json +109 -0
  4. config.json +41 -0
  5. merges.txt +0 -0
  6. normalizer.json +1742 -0
  7. preprocessor_config.json +0 -0
  8. pytorch_model.bin +3 -0
  9. run.sh +38 -0
  10. run_speech_recognition_seq2seq_streaming.py +703 -0
  11. runs/Dec09_13-54-47_132-145-179-103/1670594111.7554288/events.out.tfevents.1670594111.132-145-179-103.2897147.1 +3 -0
  12. runs/Dec09_13-54-47_132-145-179-103/events.out.tfevents.1670594111.132-145-179-103.2897147.0 +3 -0
  13. special_tokens_map.json +133 -0
  14. tokenizer_config.json +36 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
.ipynb_checkpoints/run-checkpoint.sh ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python run_speech_recognition_seq2seq_streaming.py \
2
+ --model_name_or_path="openai/whisper-large-v2" \
3
+ --dataset_name="mozilla-foundation/common_voice_11_0" \
4
+ --dataset_config_name="vi" \
5
+ --language="vietnamese" \
6
+ --train_split_name="train+validation" \
7
+ --eval_split_name="test" \
8
+ --model_index_name="Whisper Large V2 Vietnamese" \
9
+ --max_steps="5000" \
10
+ --output_dir="./" \
11
+ --per_device_train_batch_size="8" \
12
+ --per_device_eval_batch_size="4" \
13
+ --logging_steps="25" \
14
+ --learning_rate="1e-7" \
15
+ --warmup_steps="500" \
16
+ --evaluation_strategy="steps" \
17
+ --eval_steps="500" \
18
+ --save_strategy="steps" \
19
+ --save_steps="1000" \
20
+ --generation_max_length="225" \
21
+ --length_column_name="input_length" \
22
+ --max_duration_in_seconds="30" \
23
+ --text_column_name="sentence" \
24
+ --freeze_feature_encoder="False" \
25
+ --report_to="tensorboard" \
26
+ --metric_for_best_model="wer" \
27
+ --greater_is_better="False" \
28
+ --gradient_accumulation_steps="3" \
29
+ --load_best_model_at_end \
30
+ --gradient_checkpointing \
31
+ --fp16 \
32
+ --overwrite_output_dir \
33
+ --do_train \
34
+ --do_eval \
35
+ --predict_with_generate \
36
+ --do_normalize_eval \
37
+ --use_auth_token \
38
+ --push_to_hub
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
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-large-v2",
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": 1280,
15
+ "decoder_attention_heads": 20,
16
+ "decoder_ffn_dim": 5120,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 32,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 20,
22
+ "encoder_ffn_dim": 5120,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 32,
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": 32,
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": false,
40
+ "vocab_size": 51865
41
+ }
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
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c66f55e0e3d07c472441cb1ea13a59a3a307572c401bd1849acd7bd3e42a3c
3
+ size 6173655480
run.sh ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python run_speech_recognition_seq2seq_streaming.py \
2
+ --model_name_or_path="openai/whisper-large-v2" \
3
+ --dataset_name="mozilla-foundation/common_voice_11_0" \
4
+ --dataset_config_name="vi" \
5
+ --language="vietnamese" \
6
+ --train_split_name="train+validation" \
7
+ --eval_split_name="test" \
8
+ --model_index_name="Whisper Large V2 Vietnamese" \
9
+ --max_steps="5000" \
10
+ --output_dir="./" \
11
+ --per_device_train_batch_size="8" \
12
+ --per_device_eval_batch_size="4" \
13
+ --logging_steps="25" \
14
+ --learning_rate="1e-7" \
15
+ --warmup_steps="500" \
16
+ --evaluation_strategy="steps" \
17
+ --eval_steps="500" \
18
+ --save_strategy="steps" \
19
+ --save_steps="1000" \
20
+ --generation_max_length="225" \
21
+ --length_column_name="input_length" \
22
+ --max_duration_in_seconds="30" \
23
+ --text_column_name="sentence" \
24
+ --freeze_feature_encoder="False" \
25
+ --report_to="tensorboard" \
26
+ --metric_for_best_model="wer" \
27
+ --greater_is_better="False" \
28
+ --gradient_accumulation_steps="3" \
29
+ --load_best_model_at_end \
30
+ --gradient_checkpointing \
31
+ --fp16 \
32
+ --overwrite_output_dir \
33
+ --do_train \
34
+ --do_eval \
35
+ --predict_with_generate \
36
+ --do_normalize_eval \
37
+ --use_auth_token \
38
+ --push_to_hub
run_speech_recognition_seq2seq_streaming.py ADDED
@@ -0,0 +1,703 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+ # coding=utf-8
3
+ # Copyright 2022 The HuggingFace Team. All rights reserved.
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+ """
17
+ Fine-tuning the library models for sequence to sequence speech recognition
18
+ with 🤗 Datasets' streaming mode.
19
+ """
20
+ # You can also adapt this script for your own sequence to sequence speech
21
+ # recognition task. Pointers for this are left as comments.
22
+
23
+ import logging
24
+ import os
25
+ import sys
26
+ from dataclasses import dataclass, field
27
+ from typing import Any, Dict, List, Optional, Union
28
+
29
+ import datasets
30
+ import torch
31
+ from datasets import DatasetDict, IterableDatasetDict, interleave_datasets, load_dataset, Audio
32
+ from torch.utils.data import IterableDataset
33
+
34
+ import evaluate
35
+ import transformers
36
+ from transformers import (
37
+ AutoConfig,
38
+ AutoFeatureExtractor,
39
+ AutoModelForSpeechSeq2Seq,
40
+ AutoProcessor,
41
+ AutoTokenizer,
42
+ HfArgumentParser,
43
+ Seq2SeqTrainer,
44
+ Seq2SeqTrainingArguments,
45
+ TrainerCallback,
46
+ set_seed,
47
+ )
48
+ from transformers.trainer_pt_utils import IterableDatasetShard
49
+ from transformers.models.whisper.english_normalizer import BasicTextNormalizer
50
+ from transformers.trainer_pt_utils import IterableDatasetShard
51
+ from transformers.trainer_utils import get_last_checkpoint, is_main_process
52
+ from transformers.utils import check_min_version, send_example_telemetry
53
+ from transformers.utils.versions import require_version
54
+
55
+
56
+ # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
57
+ check_min_version("4.25.0.dev0")
58
+
59
+ require_version("datasets>=1.18.2", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
60
+
61
+ logger = logging.getLogger(__name__)
62
+
63
+
64
+ @dataclass
65
+ class ModelArguments:
66
+ """
67
+ Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
68
+ """
69
+
70
+ model_name_or_path: str = field(
71
+ metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
72
+ )
73
+ config_name: Optional[str] = field(
74
+ default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
75
+ )
76
+ tokenizer_name: Optional[str] = field(
77
+ default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
78
+ )
79
+ feature_extractor_name: Optional[str] = field(
80
+ default=None, metadata={"help": "feature extractor name or path if not the same as model_name"}
81
+ )
82
+ cache_dir: Optional[str] = field(
83
+ default=None,
84
+ metadata={"help": "Where to store the pretrained models downloaded from huggingface.co"},
85
+ )
86
+ use_fast_tokenizer: bool = field(
87
+ default=True,
88
+ metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
89
+ )
90
+ model_revision: str = field(
91
+ default="main",
92
+ metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
93
+ )
94
+ use_auth_token: bool = field(
95
+ default=False,
96
+ metadata={
97
+ "help": (
98
+ "Will use the token generated when running `huggingface-cli login` (necessary to use this script "
99
+ "with private models)."
100
+ )
101
+ },
102
+ )
103
+ freeze_feature_encoder: bool = field(
104
+ default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
105
+ )
106
+ freeze_encoder: bool = field(
107
+ default=False, metadata={"help": "Whether to freeze the entire encoder of the seq2seq model."}
108
+ )
109
+ forced_decoder_ids: List[List[int]] = field(
110
+ default=None,
111
+ metadata={
112
+ "help": (
113
+ "A list of pairs of integers which indicates a mapping from generation indices to token indices "
114
+ "that will be forced before sampling. For example, [[0, 123]] means the first generated token "
115
+ "will always be a token of index 123."
116
+ )
117
+ },
118
+ )
119
+ suppress_tokens: List[int] = field(
120
+ default=None, metadata={"help": "A list of tokens that will be suppressed at generation."}
121
+ )
122
+ model_index_name: str = field(default=None, metadata={"help": "Pretty name for the model card."})
123
+
124
+
125
+ @dataclass
126
+ class DataTrainingArguments:
127
+ """
128
+ Arguments pertaining to what data we are going to input our model for training and eval.
129
+ """
130
+
131
+ dataset_name: str = field(
132
+ default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
133
+ )
134
+ dataset_config_name: Optional[str] = field(
135
+ default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
136
+ )
137
+ text_column: Optional[str] = field(
138
+ default=None,
139
+ metadata={"help": "The name of the column in the datasets containing the full texts (for summarization)."},
140
+ )
141
+ max_train_samples: Optional[int] = field(
142
+ default=None,
143
+ metadata={
144
+ "help": (
145
+ "For debugging purposes or quicker training, truncate the number of training examples to this "
146
+ "value if set."
147
+ )
148
+ },
149
+ )
150
+ max_eval_samples: Optional[int] = field(
151
+ default=None,
152
+ metadata={
153
+ "help": (
154
+ "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
155
+ "value if set."
156
+ )
157
+ },
158
+ )
159
+ audio_column_name: str = field(
160
+ default="audio",
161
+ metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
162
+ )
163
+ text_column_name: str = field(
164
+ default="text",
165
+ metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
166
+ )
167
+ max_duration_in_seconds: float = field(
168
+ default=20.0,
169
+ metadata={
170
+ "help": (
171
+ "Truncate audio files that are longer than `max_duration_in_seconds` seconds to"
172
+ " 'max_duration_in_seconds`"
173
+ )
174
+ },
175
+ )
176
+ min_duration_in_seconds: float = field(
177
+ default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
178
+ )
179
+ train_split_name: str = field(
180
+ default="train",
181
+ metadata={
182
+ "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
183
+ },
184
+ )
185
+ eval_split_name: str = field(
186
+ default="test",
187
+ metadata={
188
+ "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
189
+ },
190
+ )
191
+ do_lower_case: bool = field(
192
+ default=False,
193
+ metadata={"help": "Whether the target text should be lower cased."},
194
+ )
195
+ do_remove_punctuation: bool = field(
196
+ default=False,
197
+ metadata={"help": "Whether the target text should be striped of punctuation."},
198
+ )
199
+ do_normalize_eval: bool = field(
200
+ default=True,
201
+ metadata={"help": "Whether to normalise the references and predictions in the eval WER calculation."},
202
+ )
203
+ language: str = field(
204
+ default=None,
205
+ metadata={
206
+ "help": (
207
+ "Language for multilingual fine-tuning. This argument should be set for multilingual fine-tuning "
208
+ "only. For English speech recognition, it should be set to `None`."
209
+ )
210
+ },
211
+ )
212
+ task: str = field(
213
+ default="transcribe",
214
+ metadata={"help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."},
215
+ )
216
+ shuffle_buffer_size: Optional[int] = field(
217
+ default=500,
218
+ metadata={
219
+ "help": (
220
+ "The number of streamed examples to download before shuffling them. The large the buffer, "
221
+ "the closer it is to real offline shuffling."
222
+ )
223
+ },
224
+ )
225
+ streaming: bool = field(
226
+ default=True,
227
+ metadata={"help": "Whether to use streaming mode to load and pre-process the data."},
228
+ )
229
+
230
+
231
+ @dataclass
232
+ class DataCollatorSpeechSeq2SeqWithPadding:
233
+ """
234
+ Data collator that will dynamically pad the inputs received.
235
+ Args:
236
+ processor ([`WhisperProcessor`])
237
+ The processor used for processing the data.
238
+ decoder_start_token_id (`int`)
239
+ The begin-of-sentence of the decoder.
240
+ """
241
+
242
+ processor: Any
243
+ decoder_start_token_id: int
244
+
245
+ def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
246
+ # split inputs and labels since they have to be of different lengths and need
247
+ # different padding methods
248
+ model_input_name = self.processor.model_input_names[0]
249
+ input_features = [{model_input_name: feature[model_input_name]} for feature in features]
250
+ label_features = [{"input_ids": feature["labels"]} for feature in features]
251
+
252
+ batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
253
+
254
+ labels_batch = self.processor.tokenizer.pad(label_features, return_tensors="pt")
255
+
256
+ # replace padding with -100 to ignore loss correctly
257
+ labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
258
+
259
+ # if bos token is appended in previous tokenization step,
260
+ # cut bos token here as it's append later anyways
261
+ if (labels[:, 0] == self.decoder_start_token_id).all().cpu().item():
262
+ labels = labels[:, 1:]
263
+
264
+ batch["labels"] = labels
265
+
266
+ return batch
267
+
268
+
269
+ def load_maybe_streaming_dataset(dataset_name, dataset_config_name, split="train", streaming=True, **kwargs):
270
+ """
271
+ Utility function to load a dataset in streaming mode. For datasets with multiple splits,
272
+ each split is loaded individually and then splits combined by taking alternating examples from
273
+ each (interleaving).
274
+ """
275
+ if "+" in split:
276
+ # load multiple splits separated by the `+` symbol with streaming mode
277
+ dataset_splits = [
278
+ load_dataset(dataset_name, dataset_config_name, split=split_name, streaming=streaming, **kwargs)
279
+ for split_name in split.split("+")
280
+ ]
281
+ # dataset_splits = [dataset.cast_column("audio", Audio(sampling_rate))
282
+ # for dataset in dataset_splits]
283
+
284
+ # interleave multiple splits to form one dataset
285
+ interleaved_dataset = interleave_datasets(dataset_splits)
286
+ return interleaved_dataset
287
+ else:
288
+ # load a single split *with* streaming mode
289
+ dataset = load_dataset(dataset_name, dataset_config_name, split=split, streaming=streaming, **kwargs)
290
+ # dataset = dataset.cast_column("audio", Audio(sampling_rate))
291
+ return dataset
292
+
293
+ def load_multiple_streaming_datasets(
294
+ dataset_names: List,
295
+ dataset_config_names: List,
296
+ splits: Optional[List] = None,
297
+ text_column_names: Optional[List] = None,
298
+ sampling_rate: Optional[int] = 16000,
299
+ stopping_strategy: Optional[str] = "all_exhausted",
300
+ **kwargs
301
+ ) -> IterableDataset:
302
+
303
+ if len(dataset_names) != len(dataset_config_names):
304
+ raise ValueError(
305
+ f"Ensure one config is passed for each dataset, got {len(dataset_names)} datasets and"
306
+ f" {len(dataset_config_names)} configs."
307
+ )
308
+
309
+ if splits is not None and len(splits) != len(dataset_names):
310
+ raise ValueError(
311
+ f"Ensure one split is passed for each dataset, got {len(dataset_names)} datasets and {len(splits)} splits."
312
+ )
313
+
314
+ if text_column_names is not None and len(text_column_names) != len(dataset_names):
315
+ raise ValueError(
316
+ f"Ensure one text column name is passed for each dataset, got {len(dataset_names)} datasets and"
317
+ f" {len(text_column_names)} text column names."
318
+ )
319
+
320
+ splits = splits if splits is not None else ["train" for i in range(len(dataset_names))]
321
+ text_column_names = (
322
+ text_column_names if text_column_names is not None else ["text" for i in range(len(dataset_names))]
323
+ )
324
+
325
+ all_datasets = []
326
+ # iterate over the datasets we want to interleave
327
+ for i, dataset_name in enumerate(dataset_names):
328
+ dataset = load_dataset(dataset_name, dataset_config_names[i], split=splits[i], streaming=True, **kwargs)
329
+ # resample to specified sampling rate
330
+ dataset = dataset.cast_column("audio", Audio(sampling_rate))
331
+ # normalise columns to ["audio", "sentence"]
332
+ if text_column_names[i] != "sentence":
333
+ dataset = dataset.rename_column(text_column_names[i], "sentence")
334
+ dataset = dataset.remove_columns(set(dataset.features.keys()) - set(["audio", "sentence"]))
335
+ all_datasets.append(dataset)
336
+
337
+ interleaved_dataset = interleave_datasets(all_datasets, stopping_strategy=stopping_strategy)
338
+ return interleaved_dataset
339
+
340
+ def main():
341
+ # 1. Parse input arguments
342
+ # See all possible arguments in src/transformers/training_args.py
343
+ # or by passing the --help flag to this script.
344
+ # We now keep distinct sets of args, for a cleaner separation of concerns.
345
+ parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
346
+
347
+ if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
348
+ # If we pass only one argument to the script and it's the path to a json file,
349
+ # let's parse it to get our arguments.
350
+ model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
351
+ else:
352
+ model_args, data_args, training_args = parser.parse_args_into_dataclasses()
353
+
354
+ # Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
355
+ # information sent is the one passed as arguments along with your Python/PyTorch versions.
356
+ send_example_telemetry("run_speech_recognition_seq2seq_streaming", model_args, data_args)
357
+
358
+ # 2. Setup logging
359
+ logging.basicConfig(
360
+ format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
361
+ datefmt="%m/%d/%Y %H:%M:%S",
362
+ handlers=[logging.StreamHandler(sys.stdout)],
363
+ )
364
+ log_level = training_args.get_process_log_level()
365
+ logger.setLevel(log_level)
366
+ datasets.utils.logging.set_verbosity(log_level)
367
+ transformers.utils.logging.set_verbosity(log_level)
368
+ transformers.utils.logging.enable_default_handler()
369
+ transformers.utils.logging.enable_explicit_format()
370
+
371
+ logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
372
+
373
+ # Log on each process the small summary:
374
+ logger.warning(
375
+ f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
376
+ f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
377
+ )
378
+ logger.info(f"Training/evaluation parameters {training_args}")
379
+
380
+ # Set the verbosity to info of the Transformers logger (on main process only):
381
+ if is_main_process(training_args.local_rank):
382
+ transformers.utils.logging.set_verbosity_info()
383
+ logger.info("Training/evaluation parameters %s", training_args)
384
+
385
+ # 3. Detecting last checkpoint and eventually continue from last checkpoint
386
+ last_checkpoint = None
387
+ if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
388
+ last_checkpoint = get_last_checkpoint(training_args.output_dir)
389
+ if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
390
+ raise ValueError(
391
+ f"Output directory ({training_args.output_dir}) already exists and is not empty. "
392
+ "Use --overwrite_output_dir to overcome."
393
+ )
394
+ elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
395
+ logger.info(
396
+ f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
397
+ "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
398
+ )
399
+
400
+ # Set seed before initializing model.
401
+ set_seed(training_args.seed)
402
+
403
+ # # 4. Load dataset
404
+ # raw_datasets = IterableDatasetDict() if data_args.streaming else DatasetDict()
405
+
406
+ # if training_args.do_train:
407
+ # raw_datasets["train"] = load_maybe_streaming_dataset(
408
+ # data_args.dataset_name,
409
+ # data_args.dataset_config_name,
410
+ # split=data_args.train_split_name,
411
+ # use_auth_token=True if model_args.use_auth_token else None,
412
+ # streaming=data_args.streaming,
413
+ # )
414
+
415
+ # 4. Load dataset
416
+ dataset_names = ["mozilla-foundation/common_voice_11_0", "mozilla-foundation/common_voice_11_0", "google/fleurs", "google/fleurs", "google/fleurs"]
417
+ dataset_config_names = ["vi", "vi", "vi_vn", "vi_vn", "vi_vn"]
418
+ text_column_names = ["sentence", "sentence", "raw_transcription", "raw_transcription", "raw_transcription"]
419
+ splits = ['train', 'validation', 'train', 'validation', 'test']
420
+
421
+ raw_datasets = IterableDatasetDict()
422
+
423
+ if training_args.do_train:
424
+ raw_datasets["train"] = load_multiple_streaming_datasets(
425
+ dataset_names,
426
+ splits=splits,
427
+ dataset_config_names=dataset_config_names,
428
+ text_column_names=text_column_names,
429
+ sampling_rate=16000,
430
+ use_auth_token=True)
431
+
432
+ if training_args.do_eval:
433
+ # raw_datasets["eval"] = load_maybe_streaming_dataset(
434
+ # data_args.dataset_name,
435
+ # data_args.dataset_config_name,
436
+ # split=data_args.eval_split_name,
437
+ # use_auth_token=True if model_args.use_auth_token else None,
438
+ # streaming=data_args.streaming,
439
+ # )
440
+
441
+ raw_datasets["eval"] = load_multiple_streaming_datasets(
442
+ ["mozilla-foundation/common_voice_11_0"],
443
+ splits=['test'],
444
+ dataset_config_names=["vi"],
445
+ text_column_names=["sentence"],
446
+ sampling_rate=16000,
447
+ use_auth_token=True if model_args.use_auth_token else None)
448
+
449
+ raw_datasets_features = list(next(iter(raw_datasets.values())).features.keys())
450
+
451
+ if data_args.audio_column_name not in raw_datasets_features:
452
+ raise ValueError(
453
+ f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
454
+ "Make sure to set `--audio_column_name` to the correct audio column - one of "
455
+ f"{', '.join(raw_datasets_features)}."
456
+ )
457
+
458
+ if data_args.text_column_name not in raw_datasets_features:
459
+ raise ValueError(
460
+ f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
461
+ "Make sure to set `--text_column_name` to the correct text column - one of "
462
+ f"{', '.join(raw_datasets_features)}."
463
+ )
464
+
465
+ # 5. Load pretrained model, tokenizer, and feature extractor
466
+ #
467
+ # Distributed training:
468
+ # The .from_pretrained methods guarantee that only one local process can concurrently
469
+ config = AutoConfig.from_pretrained(
470
+ model_args.config_name if model_args.config_name else model_args.model_name_or_path,
471
+ cache_dir=model_args.cache_dir,
472
+ revision=model_args.model_revision,
473
+ use_auth_token=True if model_args.use_auth_token else None,
474
+ )
475
+
476
+ config.update({"forced_decoder_ids": model_args.forced_decoder_ids, "suppress_tokens": model_args.suppress_tokens})
477
+
478
+ if training_args.gradient_checkpointing:
479
+ config.update({"use_cache": False})
480
+
481
+ feature_extractor = AutoFeatureExtractor.from_pretrained(
482
+ model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
483
+ cache_dir=model_args.cache_dir,
484
+ revision=model_args.model_revision,
485
+ use_auth_token=True if model_args.use_auth_token else None,
486
+ )
487
+ tokenizer = AutoTokenizer.from_pretrained(
488
+ model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
489
+ cache_dir=model_args.cache_dir,
490
+ use_fast=model_args.use_fast_tokenizer,
491
+ revision=model_args.model_revision,
492
+ use_auth_token=True if model_args.use_auth_token else None,
493
+ )
494
+ model = AutoModelForSpeechSeq2Seq.from_pretrained(
495
+ model_args.model_name_or_path,
496
+ config=config,
497
+ cache_dir=model_args.cache_dir,
498
+ revision=model_args.model_revision,
499
+ use_auth_token=True if model_args.use_auth_token else None,
500
+ )
501
+
502
+ if model.config.decoder_start_token_id is None:
503
+ raise ValueError("Make sure that `config.decoder_start_token_id` is correctly defined")
504
+
505
+ if model_args.freeze_feature_encoder:
506
+ model.freeze_feature_encoder()
507
+
508
+ if model_args.freeze_encoder:
509
+ model.freeze_encoder()
510
+
511
+ if data_args.language is not None:
512
+ # We only need to set the task id when the language is specified (i.e. in a multilingual setting)
513
+ tokenizer.set_prefix_tokens(language=data_args.language, task=data_args.task)
514
+
515
+ # 6. Resample speech dataset if necessary
516
+ dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
517
+ if dataset_sampling_rate != feature_extractor.sampling_rate:
518
+ raw_datasets = raw_datasets.cast_column(
519
+ data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
520
+ )
521
+
522
+ # 7. Preprocessing the datasets.
523
+ # We need to read the audio files as arrays and tokenize the targets.
524
+ max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
525
+ min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
526
+ audio_column_name = data_args.audio_column_name
527
+ text_column_name = data_args.text_column_name
528
+ model_input_name = feature_extractor.model_input_names[0]
529
+ do_lower_case = data_args.do_lower_case
530
+ do_remove_punctuation = data_args.do_remove_punctuation
531
+ normalizer = BasicTextNormalizer() # 'official' text normalizer from OpenAI
532
+
533
+ if data_args.max_train_samples is not None:
534
+ raw_datasets["train"] = (
535
+ raw_datasets["train"].take(data_args.max_train_samples)
536
+ if data_args.streaming
537
+ else raw_datasets["train"].select(range(data_args.max_train_samples))
538
+ )
539
+
540
+ if data_args.max_eval_samples is not None:
541
+ raw_datasets["eval"] = (
542
+ raw_datasets["eval"].take(data_args.max_eval_samples)
543
+ if data_args.streaming
544
+ else raw_datasets["eval"].select(range(data_args.max_eval_samples))
545
+ )
546
+
547
+ def prepare_dataset(batch):
548
+ # process audio
549
+ sample = batch[audio_column_name]
550
+ inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
551
+ # process audio length
552
+ batch[model_input_name] = inputs.get(model_input_name)[0]
553
+ batch["input_length"] = len(sample["array"])
554
+
555
+ # process targets
556
+ input_str = batch[text_column_name].lower() if do_lower_case else batch[text_column_name]
557
+ if do_remove_punctuation:
558
+ input_str = normalizer(input_str).strip()
559
+ batch["labels"] = tokenizer(input_str).input_ids
560
+ return batch
561
+
562
+ with training_args.main_process_first(desc="dataset map pre-processing"):
563
+ vectorized_datasets = raw_datasets.map(
564
+ prepare_dataset,
565
+ remove_columns=raw_datasets_features,
566
+ ).with_format("torch")
567
+
568
+ if training_args.do_train and data_args.streaming:
569
+ # manually shuffle if streaming (done by the trainer for non-streaming)
570
+ vectorized_datasets["train"] = vectorized_datasets["train"].shuffle(
571
+ buffer_size=data_args.shuffle_buffer_size,
572
+ seed=training_args.seed,
573
+ )
574
+
575
+ # filter training data that is shorter than min_input_length or longer than
576
+ # max_input_length
577
+ def is_audio_in_length_range(length):
578
+ return min_input_length < length < max_input_length
579
+
580
+ vectorized_datasets["train"] = vectorized_datasets["train"].filter(
581
+ is_audio_in_length_range,
582
+ input_columns=["input_length"],
583
+ )
584
+
585
+ # 8. Load Metric
586
+ wer_metric = evaluate.load("wer")
587
+ cer_metric = evaluate.load("cer")
588
+ do_normalize_eval = data_args.do_normalize_eval
589
+
590
+ def compute_metrics(pred):
591
+ pred_ids = pred.predictions
592
+
593
+ pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
594
+
595
+ pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
596
+ # we do not want to group tokens when computing the metrics
597
+ label_str = tokenizer.batch_decode(pred.label_ids, skip_special_tokens=True)
598
+
599
+ if do_normalize_eval:
600
+ pred_str = [normalizer(pred) for pred in pred_str]
601
+ label_str = [normalizer(label) for label in label_str]
602
+
603
+ wer = 100 * wer_metric.compute(predictions=pred_str, references=label_str)
604
+ cer = 100 * cer_metric.compute(predictions=pred_str, references=label_str)
605
+
606
+ return {"wer": wer, "cer": cer}
607
+
608
+ # 9. Create a single speech processor
609
+ if is_main_process(training_args.local_rank):
610
+ # save feature extractor, tokenizer and config
611
+ feature_extractor.save_pretrained(training_args.output_dir)
612
+ tokenizer.save_pretrained(training_args.output_dir)
613
+ config.save_pretrained(training_args.output_dir)
614
+
615
+ processor = AutoProcessor.from_pretrained(training_args.output_dir)
616
+
617
+ # 10. Define data collator
618
+ data_collator = DataCollatorSpeechSeq2SeqWithPadding(
619
+ processor=processor,
620
+ decoder_start_token_id=model.config.decoder_start_token_id,
621
+ )
622
+
623
+ # 11. Configure Trainer
624
+ # Trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch
625
+ # Only required for streaming: Trainer automatically shuffles non-streaming datasets
626
+ class ShuffleCallback(TrainerCallback):
627
+ def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):
628
+ if isinstance(train_dataloader.dataset, IterableDatasetShard):
629
+ pass # set_epoch() is handled by the Trainer
630
+ elif isinstance(train_dataloader.dataset, IterableDataset):
631
+ train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
632
+
633
+ # Initialize Trainer
634
+ trainer = Seq2SeqTrainer(
635
+ model=model,
636
+ args=training_args,
637
+ train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
638
+ eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
639
+ tokenizer=feature_extractor,
640
+ data_collator=data_collator,
641
+ compute_metrics=compute_metrics if training_args.predict_with_generate else None,
642
+ callbacks=[ShuffleCallback()] if data_args.streaming else None,
643
+ )
644
+
645
+ # 12. Training
646
+ if training_args.do_train:
647
+ checkpoint = None
648
+ if training_args.resume_from_checkpoint is not None:
649
+ checkpoint = training_args.resume_from_checkpoint
650
+ elif last_checkpoint is not None:
651
+ checkpoint = last_checkpoint
652
+ train_result = trainer.train(resume_from_checkpoint=checkpoint)
653
+ trainer.save_model() # Saves the feature extractor too for easy upload
654
+
655
+ metrics = train_result.metrics
656
+ if data_args.max_train_samples:
657
+ metrics["train_samples"] = data_args.max_train_samples
658
+ trainer.log_metrics("train", metrics)
659
+ trainer.save_metrics("train", metrics)
660
+ trainer.save_state()
661
+
662
+ # 13. Evaluation
663
+ results = {}
664
+ if training_args.do_eval:
665
+ logger.info("*** Evaluate ***")
666
+ metrics = trainer.evaluate(
667
+ metric_key_prefix="eval",
668
+ max_length=training_args.generation_max_length,
669
+ num_beams=training_args.generation_num_beams,
670
+ )
671
+ if data_args.max_eval_samples:
672
+ metrics["eval_samples"] = data_args.max_eval_samples
673
+
674
+ trainer.log_metrics("eval", metrics)
675
+ trainer.save_metrics("eval", metrics)
676
+
677
+ # 14. Write Training Stats
678
+ kwargs = {
679
+ "finetuned_from": model_args.model_name_or_path,
680
+ "tasks": "automatic-speech-recognition",
681
+ "tags": "whisper-event",
682
+ }
683
+ if data_args.dataset_name is not None:
684
+ kwargs["dataset_tags"] = data_args.dataset_name
685
+ if data_args.dataset_config_name is not None:
686
+ kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
687
+ else:
688
+ kwargs["dataset"] = data_args.dataset_name
689
+ if "common_voice" in data_args.dataset_name:
690
+ kwargs["language"] = data_args.dataset_config_name[:2]
691
+ if model_args.model_index_name is not None:
692
+ kwargs["model_name"] = model_args.model_index_name
693
+
694
+ if training_args.push_to_hub:
695
+ trainer.push_to_hub(**kwargs)
696
+ else:
697
+ trainer.create_model_card(**kwargs)
698
+
699
+ return results
700
+
701
+
702
+ if __name__ == "__main__":
703
+ main()
runs/Dec09_13-54-47_132-145-179-103/1670594111.7554288/events.out.tfevents.1670594111.132-145-179-103.2897147.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce573f6288dec6b193e07e2730376623504b98f3c0071bcaf8f872219ce572c1
3
+ size 5710
runs/Dec09_13-54-47_132-145-179-103/events.out.tfevents.1670594111.132-145-179-103.2897147.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3179ba0daeaef22e185c136803cf1b69c00ed116c04a335b535d0242717c66b8
3
+ size 11175
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-large-v2",
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51561127f24b24f4ea04dcd7a111a2a729565bbc9b194b59b16d916af0c17a5
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff