Training in progress, step 1000

README.md

@@ -1,60 +0,0 @@
----
-license: apache-2.0
-tags:
-- generated_from_trainer
-metrics:
-- wer
-model-index:
-- name: openai/whisper-small
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# openai/whisper-small
-
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.9569
-- Cer: 304.7818
-- Wer: 369.68
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 32
-- seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 64
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1000
-- training_steps: 50
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.28.0.dev0
-- Pytorch 2.0.0+cu117
-- Datasets 2.10.2.dev0
-- Tokenizers 0.13.2

added_tokens.json

@@ -1,108 +0,0 @@
-{
-  "<|af|>": 50327,
-  "<|am|>": 50334,
-  "<|ar|>": 50272,
-  "<|as|>": 50350,
-  "<|az|>": 50304,
-  "<|ba|>": 50355,
-  "<|be|>": 50330,
-  "<|bg|>": 50292,
-  "<|bn|>": 50302,
-  "<|bo|>": 50347,
-  "<|br|>": 50309,
-  "<|bs|>": 50315,
-  "<|ca|>": 50270,
-  "<|cs|>": 50283,
-  "<|cy|>": 50297,
-  "<|da|>": 50285,
-  "<|de|>": 50261,
-  "<|el|>": 50281,
-  "<|en|>": 50259,
-  "<|es|>": 50262,
-  "<|et|>": 50307,
-  "<|eu|>": 50310,
-  "<|fa|>": 50300,
-  "<|fi|>": 50277,
-  "<|fo|>": 50338,
-  "<|fr|>": 50265,
-  "<|gl|>": 50319,
-  "<|gu|>": 50333,
-  "<|haw|>": 50352,
-  "<|ha|>": 50354,
-  "<|he|>": 50279,
-  "<|hi|>": 50276,
-  "<|hr|>": 50291,
-  "<|ht|>": 50339,
-  "<|hu|>": 50286,
-  "<|hy|>": 50312,
-  "<|id|>": 50275,
-  "<|is|>": 50311,
-  "<|it|>": 50274,
-  "<|ja|>": 50266,
-  "<|jw|>": 50356,
-  "<|ka|>": 50329,
-  "<|kk|>": 50316,
-  "<|km|>": 50323,
-  "<|kn|>": 50306,
-  "<|ko|>": 50264,
-  "<|la|>": 50294,
-  "<|lb|>": 50345,
-  "<|ln|>": 50353,
-  "<|lo|>": 50336,
-  "<|lt|>": 50293,
-  "<|lv|>": 50301,
-  "<|mg|>": 50349,
-  "<|mi|>": 50295,
-  "<|mk|>": 50308,
-  "<|ml|>": 50296,
-  "<|mn|>": 50314,
-  "<|mr|>": 50320,
-  "<|ms|>": 50282,
-  "<|mt|>": 50343,
-  "<|my|>": 50346,
-  "<|ne|>": 50313,
-  "<|nl|>": 50271,
-  "<|nn|>": 50342,
-  "<|nocaptions|>": 50362,
-  "<|notimestamps|>": 50363,
-  "<|no|>": 50288,
-  "<|oc|>": 50328,
-  "<|pa|>": 50321,
-  "<|pl|>": 50269,
-  "<|ps|>": 50340,
-  "<|pt|>": 50267,
-  "<|ro|>": 50284,
-  "<|ru|>": 50263,
-  "<|sa|>": 50344,
-  "<|sd|>": 50332,
-  "<|si|>": 50322,
-  "<|sk|>": 50298,
-  "<|sl|>": 50305,
-  "<|sn|>": 50324,
-  "<|so|>": 50326,
-  "<|sq|>": 50317,
-  "<|sr|>": 50303,
-  "<|startoflm|>": 50360,
-  "<|startofprev|>": 50361,
-  "<|startoftranscript|>": 50258,
-  "<|su|>": 50357,
-  "<|sv|>": 50273,
-  "<|sw|>": 50318,
-  "<|ta|>": 50287,
-  "<|te|>": 50299,
-  "<|tg|>": 50331,
-  "<|th|>": 50289,
-  "<|tk|>": 50341,
-  "<|tl|>": 50348,
-  "<|transcribe|>": 50359,
-  "<|translate|>": 50358,
-  "<|tr|>": 50268,
-  "<|tt|>": 50351,
-  "<|uk|>": 50280,
-  "<|ur|>": 50290,
-  "<|uz|>": 50337,
-  "<|vi|>": 50278,
-  "<|yi|>": 50335,
-  "<|yo|>": 50325,
-  "<|zh|>": 50260
-}

all_results.json

@@ -1,13 +0,0 @@
-{
-    "epoch": 1.31,
-    "eval_cer": 304.78184991274,
-    "eval_loss": 1.9569354057312012,
-    "eval_runtime": 28.0459,
-    "eval_samples_per_second": 1.783,
-    "eval_steps_per_second": 0.071,
-    "eval_wer": 369.68,
-    "train_loss": 2.721541290283203,
-    "train_runtime": 665.7853,
-    "train_samples_per_second": 4.806,
-    "train_steps_per_second": 0.075
-}

best_model/tokenizer_config.json

@@ -9,6 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "eos_token": {
     "__type": "AddedToken",
     "content": "<|endoftext|>",
@@ -22,7 +23,6 @@
   "pad_token": null,
   "processor_class": "WhisperProcessor",
   "return_attention_mask": false,
-  "special_tokens_map_file": null,
   "tokenizer_class": "WhisperTokenizer",
   "unk_token": {
     "__type": "AddedToken",

config.json

@@ -44,7 +44,7 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.28.0.dev0",
+  "transformers_version": "4.30.0.dev0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 1.31,
-    "eval_cer": 304.78184991274,
-    "eval_loss": 1.9569354057312012,
-    "eval_runtime": 28.0459,
-    "eval_samples_per_second": 1.783,
-    "eval_steps_per_second": 0.071,
-    "eval_wer": 369.68
-}

generation_config.json

@@ -1,222 +0,0 @@
-{
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
-  "bos_token_id": 50257,
-  "decoder_start_token_id": 50258,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      null
-    ],
-    [
-      2,
-      50359
-    ]
-  ],
-  "is_multilingual": true,
-  "lang_to_id": {
-    "<|af|>": 50327,
-    "<|am|>": 50334,
-    "<|ar|>": 50272,
-    "<|as|>": 50350,
-    "<|az|>": 50304,
-    "<|ba|>": 50355,
-    "<|be|>": 50330,
-    "<|bg|>": 50292,
-    "<|bn|>": 50302,
-    "<|bo|>": 50347,
-    "<|br|>": 50309,
-    "<|bs|>": 50315,
-    "<|ca|>": 50270,
-    "<|cs|>": 50283,
-    "<|cy|>": 50297,
-    "<|da|>": 50285,
-    "<|de|>": 50261,
-    "<|el|>": 50281,
-    "<|en|>": 50259,
-    "<|es|>": 50262,
-    "<|et|>": 50307,
-    "<|eu|>": 50310,
-    "<|fa|>": 50300,
-    "<|fi|>": 50277,
-    "<|fo|>": 50338,
-    "<|fr|>": 50265,
-    "<|gl|>": 50319,
-    "<|gu|>": 50333,
-    "<|haw|>": 50352,
-    "<|ha|>": 50354,
-    "<|he|>": 50279,
-    "<|hi|>": 50276,
-    "<|hr|>": 50291,
-    "<|ht|>": 50339,
-    "<|hu|>": 50286,
-    "<|hy|>": 50312,
-    "<|id|>": 50275,
-    "<|is|>": 50311,
-    "<|it|>": 50274,
-    "<|ja|>": 50266,
-    "<|jw|>": 50356,
-    "<|ka|>": 50329,
-    "<|kk|>": 50316,
-    "<|km|>": 50323,
-    "<|kn|>": 50306,
-    "<|ko|>": 50264,
-    "<|la|>": 50294,
-    "<|lb|>": 50345,
-    "<|ln|>": 50353,
-    "<|lo|>": 50336,
-    "<|lt|>": 50293,
-    "<|lv|>": 50301,
-    "<|mg|>": 50349,
-    "<|mi|>": 50295,
-    "<|mk|>": 50308,
-    "<|ml|>": 50296,
-    "<|mn|>": 50314,
-    "<|mr|>": 50320,
-    "<|ms|>": 50282,
-    "<|mt|>": 50343,
-    "<|my|>": 50346,
-    "<|ne|>": 50313,
-    "<|nl|>": 50271,
-    "<|nn|>": 50342,
-    "<|no|>": 50288,
-    "<|oc|>": 50328,
-    "<|pa|>": 50321,
-    "<|pl|>": 50269,
-    "<|ps|>": 50340,
-    "<|pt|>": 50267,
-    "<|ro|>": 50284,
-    "<|ru|>": 50263,
-    "<|sa|>": 50344,
-    "<|sd|>": 50332,
-    "<|si|>": 50322,
-    "<|sk|>": 50298,
-    "<|sl|>": 50305,
-    "<|sn|>": 50324,
-    "<|so|>": 50326,
-    "<|sq|>": 50317,
-    "<|sr|>": 50303,
-    "<|su|>": 50357,
-    "<|sv|>": 50273,
-    "<|sw|>": 50318,
-    "<|ta|>": 50287,
-    "<|te|>": 50299,
-    "<|tg|>": 50331,
-    "<|th|>": 50289,
-    "<|tk|>": 50341,
-    "<|tl|>": 50348,
-    "<|tr|>": 50268,
-    "<|tt|>": 50351,
-    "<|uk|>": 50280,
-    "<|ur|>": 50290,
-    "<|uz|>": 50337,
-    "<|vi|>": 50278,
-    "<|yi|>": 50335,
-    "<|yo|>": 50325,
-    "<|zh|>": 50260
-  },
-  "max_initial_timestamp_index": 1,
-  "max_length": 448,
-  "max_new_tokens": 448,
-  "no_timestamps_token_id": 50363,
-  "pad_token_id": 50257,
-  "return_timestamps": false,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
-  "task_to_id": {
-    "transcribe": 50359,
-    "translate": 50358
-  },
-  "transformers_version": "4.28.0.dev0"
-}

my-training.py

@@ -57,9 +57,9 @@ print(f"\n\n Loading {model_name} for {language} to {task}...this might take a w
 ## 3. Setting Up Training Args
 output_dir = "./" 
 overwrite_output_dir = True
-max_steps = 50
+max_steps = 40000
 # max_steps = 5
-per_device_train_batch_size = 4 
+per_device_train_batch_size = 4
 # per_device_train_batch_size = 1 
 per_device_eval_batch_size = 32 
 # per_device_eval_batch_size = 1 
@@ -69,14 +69,14 @@ dataloader_num_workers = 0 #Default: 0 and 0 for Windows
 gradient_checkpointing = False 
 evaluation_strategy ="steps" 
 # eval_steps = 5
-eval_steps = 100 
+eval_steps = 1000 
 save_strategy = "steps" 
-save_steps = 100 
+save_steps = 1000
 # save_steps = 5
 save_total_limit = 5 
 learning_rate = 1e-5 
 lr_scheduler_type = "cosine" # "constant", "constant_with_warmup", "cosine", "cosine_with_restarts", "linear"(default), "polynomial", "inverse_sqrt"
-warmup_steps = 1000 # (1 epoch)
+warmup_steps = 8000 # (1 epoch)
 # warmup_steps = 1 
 logging_steps = 25
 # logging_steps = 1
@@ -90,7 +90,7 @@ bf16 = True
 # bf16 = False
 tf32 = True 
 # tf32 = False
-generation_max_length = 448 # ensure that the generation_max_length is equal to model_max_length. model_max_length = 1024 for whisper-small (see tokenizer config.json) also make model.config.max_length = 1024
+generation_max_length = 448 # ensure that the generation_max_length is equal to model max_length. model max_length = 448 for whisper-small (see config.json).
 report_to = ["tensorboard"] 
 predict_with_generate = True
 push_to_hub = True
@@ -320,8 +320,9 @@ my_dataset["train"] = concatenate_datasets([my_dataset["train"], augmented_raw_t
 my_dataset["train"] = my_dataset["train"].shuffle(seed=42)
 
 
-my_dataset["train"] = my_dataset["train"].select(range(2500))
-my_dataset["test"] = my_dataset["test"].select(range(50))
+# For debugging
+# my_dataset["train"] = my_dataset["train"].select(range(2500, 5000))
+# my_dataset["test"] = my_dataset["test"].select(range(50))
 
 print("\n\n AFTER AUGMENTATION, FINAL train and validation sets are: ")
 print("\n FINAL DATASET: \n")
@@ -337,6 +338,7 @@ from transformers import WhisperFeatureExtractor, WhisperTokenizer, WhisperToken
 
 feature_extractor = WhisperFeatureExtractor.from_pretrained(model_name)
 
+## No need as tokenizer gets already loaded while loading the processor
 # tokenizer = WhisperTokenizer.from_pretrained(model_name, language=language, task=task)
 # tokenizer = WhisperTokenizerFast.from_pretrained(model_name, language=language, task=task)
 
@@ -388,7 +390,6 @@ def prepare_dataset(batch):
 
     # compute input length
     batch["input_length"] = len(batch["audio"])
-    # batch["input_length"] = len(batch["input_features"])
     
     # if spec augmentation applied, get attention_mask to guide the mask along time axis
     if apply_spec_augment:
@@ -426,8 +427,8 @@ my_dataset = my_dataset.map(prepare_dataset,
                             num_proc=1, # if num_proc>1, then mapping might get stuck. use num_proc=1 in that case.
                             load_from_cache_file=True, 
                             cache_file_names={
-                                "train" : os.path.join(base_dir, 'datasets_cache', 'lol_preprocessed_train_cache.arrow'),
-                                "test" : os.path.join(base_dir, 'datasets_cache', 'lol_preprocessed_test_cache.arrow'),
+                                "train" : os.path.join(base_dir, 'datasets_cache', 'preprocessed_train_cache.arrow'),
+                                "test" : os.path.join(base_dir, 'datasets_cache', 'preprocessed_test_cache.arrow'),
                                 }
                             )
 ## OR this,
@@ -473,7 +474,7 @@ print("\n\n AFTER FILTERING INPUTS, final train and validation sets are: ")
 print(my_dataset)
 print("\n")
 
-max_label_length = generation_max_length #(max_label_length should be equal to generation_max_length)
+max_label_length = generation_max_length #(max_label_length should be equal to max_length of model which is equal to generation_max_length)
 
 def filter_labels(labels_length):
     """Filter label sequences longer than max length (448)"""
@@ -643,7 +644,6 @@ if freeze_feature_encoder:
     model.freeze_feature_encoder()
 
 model.generation_config.max_length = generation_max_length
-model.generation_config.max_new_tokens = generation_max_length
 
 ## 16. Define the Training Configuration
 from transformers import Seq2SeqTrainingArguments

normalizer.json

@@ -1,1742 +0,0 @@
-{
-  "accessorise": "accessorize",
-  "accessorised": "accessorized",
-  "accessorises": "accessorizes",
-  "accessorising": "accessorizing",
-  "acclimatisation": "acclimatization",
-  "acclimatise": "acclimatize",
-  "acclimatised": "acclimatized",
-  "acclimatises": "acclimatizes",
-  "acclimatising": "acclimatizing",
-  "accoutrements": "accouterments",
-  "aeon": "eon",
-  "aeons": "eons",
-  "aerogramme": "aerogram",
-  "aerogrammes": "aerograms",
-  "aeroplane": "airplane",
-  "aeroplanes": "airplanes",
-  "aesthete": "esthete",
-  "aesthetes": "esthetes",
-  "aesthetic": "esthetic",
-  "aesthetically": "esthetically",
-  "aesthetics": "esthetics",
-  "aetiology": "etiology",
-  "ageing": "aging",
-  "aggrandisement": "aggrandizement",
-  "agonise": "agonize",
-  "agonised": "agonized",
-  "agonises": "agonizes",
-  "agonising": "agonizing",
-  "agonisingly": "agonizingly",
-  "almanack": "almanac",
-  "almanacks": "almanacs",
-  "aluminium": "aluminum",
-  "amortisable": "amortizable",
-  "amortisation": "amortization",
-  "amortisations": "amortizations",
-  "amortise": "amortize",
-  "amortised": "amortized",
-  "amortises": "amortizes",
-  "amortising": "amortizing",
-  "amphitheatre": "amphitheater",
-  "amphitheatres": "amphitheaters",
-  "anaemia": "anemia",
-  "anaemic": "anemic",
-  "anaesthesia": "anesthesia",
-  "anaesthetic": "anesthetic",
-  "anaesthetics": "anesthetics",
-  "anaesthetise": "anesthetize",
-  "anaesthetised": "anesthetized",
-  "anaesthetises": "anesthetizes",
-  "anaesthetising": "anesthetizing",
-  "anaesthetist": "anesthetist",
-  "anaesthetists": "anesthetists",
-  "anaesthetize": "anesthetize",
-  "anaesthetized": "anesthetized",
-  "anaesthetizes": "anesthetizes",
-  "anaesthetizing": "anesthetizing",
-  "analogue": "analog",
-  "analogues": "analogs",
-  "analyse": "analyze",
-  "analysed": "analyzed",
-  "analyses": "analyzes",
-  "analysing": "analyzing",
-  "anglicise": "anglicize",
-  "anglicised": "anglicized",
-  "anglicises": "anglicizes",
-  "anglicising": "anglicizing",
-  "annualised": "annualized",
-  "antagonise": "antagonize",
-  "antagonised": "antagonized",
-  "antagonises": "antagonizes",
-  "antagonising": "antagonizing",
-  "apologise": "apologize",
-  "apologised": "apologized",
-  "apologises": "apologizes",
-  "apologising": "apologizing",
-  "appal": "appall",
-  "appals": "appalls",
-  "appetiser": "appetizer",
-  "appetisers": "appetizers",
-  "appetising": "appetizing",
-  "appetisingly": "appetizingly",
-  "arbour": "arbor",
-  "arbours": "arbors",
-  "archaeologically": "archeologically",
-  "archaeologist": "archeologist",
-  "archaeologists": "archeologists",
-  "archaeology": "archeology</span>",
-  "archeological": "archaeological",
-  "ardour": "ardor",
-  "armour": "armor",
-  "armoured": "armored",
-  "armourer": "armorer",
-  "armourers": "armorers",
-  "armouries": "armories",
-  "armoury": "armory",
-  "artefact": "artifact",
-  "artefacts": "artifacts",
-  "authorise": "authorize",
-  "authorised": "authorized",
-  "authorises": "authorizes",
-  "authorising": "authorizing",
-  "axe": "ax",
-  "backpedalled": "backpedaled",
-  "backpedalling": "backpedaling",
-  "bannister": "banister",
-  "bannisters": "banisters",
-  "baptise": "baptize",
-  "baptised": "baptized",
-  "baptises": "baptizes",
-  "baptising": "baptizing",
-  "bastardise": "bastardize",
-  "bastardised": "bastardized",
-  "bastardises": "bastardizes",
-  "bastardising": "bastardizing",
-  "battleax": "battleaxe",
-  "baulk": "balk",
-  "baulked": "balked",
-  "baulking": "balking",
-  "baulks": "balks",
-  "bedevilled": "bedeviled",
-  "bedevilling": "bedeviling",
-  "behaviour": "behavior",
-  "behavioural": "behavioral",
-  "behaviourism": "behaviorism",
-  "behaviourist": "behaviorist",
-  "behaviourists": "behaviorists",
-  "behaviours": "behaviors",
-  "behove": "behoove",
-  "behoved": "behooved",
-  "behoves": "behooves",
-  "bejewelled": "bejeweled",
-  "belabour": "belabor",
-  "belaboured": "belabored",
-  "belabouring": "belaboring",
-  "belabours": "belabors",
-  "bevelled": "beveled",
-  "bevvies": "bevies",
-  "bevvy": "bevy",
-  "biassed": "biased",
-  "biassing": "biasing",
-  "bingeing": "binging",
-  "bougainvillaea": "bougainvillea",
-  "bougainvillaeas": "bougainvilleas",
-  "bowdlerise": "bowdlerize",
-  "bowdlerised": "bowdlerized",
-  "bowdlerises": "bowdlerizes",
-  "bowdlerising": "bowdlerizing",
-  "breathalyse": "breathalyze",
-  "breathalysed": "breathalyzed",
-  "breathalyser": "breathalyzer",
-  "breathalysers": "breathalyzers",
-  "breathalyses": "breathalyzes",
-  "breathalysing": "breathalyzing",
-  "brutalise": "brutalize",
-  "brutalised": "brutalized",
-  "brutalises": "brutalizes",
-  "brutalising": "brutalizing",
-  "busses": "buses",
-  "bussing": "busing",
-  "caesarean": "cesarean",
-  "caesareans": "cesareans",
-  "calibre": "caliber",
-  "calibres": "calibers",
-  "calliper": "caliper",
-  "callipers": "calipers",
-  "callisthenics": "calisthenics",
-  "canalise": "canalize",
-  "canalised": "canalized",
-  "canalises": "canalizes",
-  "canalising": "canalizing",
-  "cancelation": "cancellation",
-  "cancelations": "cancellations",
-  "cancelled": "canceled",
-  "cancelling": "canceling",
-  "candour": "candor",
-  "cannibalise": "cannibalize",
-  "cannibalised": "cannibalized",
-  "cannibalises": "cannibalizes",
-  "cannibalising": "cannibalizing",
-  "canonise": "canonize",
-  "canonised": "canonized",
-  "canonises": "canonizes",
-  "canonising": "canonizing",
-  "capitalise": "capitalize",
-  "capitalised": "capitalized",
-  "capitalises": "capitalizes",
-  "capitalising": "capitalizing",
-  "caramelise": "caramelize",
-  "caramelised": "caramelized",
-  "caramelises": "caramelizes",
-  "caramelising": "caramelizing",
-  "carbonise": "carbonize",
-  "carbonised": "carbonized",
-  "carbonises": "carbonizes",
-  "carbonising": "carbonizing",
-  "carolled": "caroled",
-  "carolling": "caroling",
-  "catalogue": "catalog",
-  "catalogued": "cataloged",
-  "catalogues": "catalogs",
-  "cataloguing": "cataloging",
-  "catalyse": "catalyze",
-  "catalysed": "catalyzed",
-  "catalyses": "catalyzes",
-  "catalysing": "catalyzing",
-  "categorise": "categorize",
-  "categorised": "categorized",
-  "categorises": "categorizes",
-  "categorising": "categorizing",
-  "cauterise": "cauterize",
-  "cauterised": "cauterized",
-  "cauterises": "cauterizes",
-  "cauterising": "cauterizing",
-  "cavilled": "caviled",
-  "cavilling": "caviling",
-  "centigramme": "centigram",
-  "centigrammes": "centigrams",
-  "centilitre": "centiliter",
-  "centilitres": "centiliters",
-  "centimetre": "centimeter",
-  "centimetres": "centimeters",
-  "centralise": "centralize",
-  "centralised": "centralized",
-  "centralises": "centralizes",
-  "centralising": "centralizing",
-  "centre": "center",
-  "centred": "centered",
-  "centrefold": "centerfold",
-  "centrefolds": "centerfolds",
-  "centrepiece": "centerpiece",
-  "centrepieces": "centerpieces",
-  "centres": "centers",
-  "channelled": "channeled",
-  "channelling": "channeling",
-  "characterise": "characterize",
-  "characterised": "characterized",
-  "characterises": "characterizes",
-  "characterising": "characterizing",
-  "cheque": "check",
-  "chequebook": "checkbook",
-  "chequebooks": "checkbooks",
-  "chequered": "checkered",
-  "cheques": "checks",
-  "chilli": "chili",
-  "chimaera": "chimera",
-  "chimaeras": "chimeras",
-  "chiselled": "chiseled",
-  "chiselling": "chiseling",
-  "circularise": "circularize",
-  "circularised": "circularized",
-  "circularises": "circularizes",
-  "circularising": "circularizing",
-  "civilise": "civilize",
-  "civilised": "civilized",
-  "civilises": "civilizes",
-  "civilising": "civilizing",
-  "clamour": "clamor",
-  "clamoured": "clamored",
-  "clamouring": "clamoring",
-  "clamours": "clamors",
-  "clangour": "clangor",
-  "clarinettist": "clarinetist",
-  "clarinettists": "clarinetists",
-  "collectivise": "collectivize",
-  "collectivised": "collectivized",
-  "collectivises": "collectivizes",
-  "collectivising": "collectivizing",
-  "colonisation": "colonization",
-  "colonise": "colonize",
-  "colonised": "colonized",
-  "coloniser": "colonizer",
-  "colonisers": "colonizers",
-  "colonises": "colonizes",
-  "colonising": "colonizing",
-  "colour": "color",
-  "colourant": "colorant",
-  "colourants": "colorants",
-  "coloured": "colored",
-  "coloureds": "coloreds",
-  "colourful": "colorful",
-  "colourfully": "colorfully",
-  "colouring": "coloring",
-  "colourize": "colorize",
-  "colourized": "colorized",
-  "colourizes": "colorizes",
-  "colourizing": "colorizing",
-  "colourless": "colorless",
-  "colours": "colors",
-  "commercialise": "commercialize",
-  "commercialised": "commercialized",
-  "commercialises": "commercializes",
-  "commercialising": "commercializing",
-  "compartmentalise": "compartmentalize",
-  "compartmentalised": "compartmentalized",
-  "compartmentalises": "compartmentalizes",
-  "compartmentalising": "compartmentalizing",
-  "computerise": "computerize",
-  "computerised": "computerized",
-  "computerises": "computerizes",
-  "computerising": "computerizing",
-  "conceptualise": "conceptualize",
-  "conceptualised": "conceptualized",
-  "conceptualises": "conceptualizes",
-  "conceptualising": "conceptualizing",
-  "connexion": "connection",
-  "connexions": "connections",
-  "contextualise": "contextualize",
-  "contextualised": "contextualized",
-  "contextualises": "contextualizes",
-  "contextualising": "contextualizing",
-  "cosier": "cozier",
-  "cosies": "cozies",
-  "cosiest": "coziest",
-  "cosily": "cozily",
-  "cosiness": "coziness",
-  "cosy": "cozy",
-  "councillor": "councilor",
-  "councillors": "councilors",
-  "counselled": "counseled",
-  "counselling": "counseling",
-  "counsellor": "counselor",
-  "counsellors": "counselors",
-  "crenelated": "crenellated",
-  "criminalise": "criminalize",
-  "criminalised": "criminalized",
-  "criminalises": "criminalizes",
-  "criminalising": "criminalizing",
-  "criticise": "criticize",
-  "criticised": "criticized",
-  "criticises": "criticizes",
-  "criticising": "criticizing",
-  "crueller": "crueler",
-  "cruellest": "cruelest",
-  "crystallisation": "crystallization",
-  "crystallise": "crystallize",
-  "crystallised": "crystallized",
-  "crystallises": "crystallizes",
-  "crystallising": "crystallizing",
-  "cudgelled": "cudgeled",
-  "cudgelling": "cudgeling",
-  "customise": "customize",
-  "customised": "customized",
-  "customises": "customizes",
-  "customising": "customizing",
-  "cypher": "cipher",
-  "cyphers": "ciphers",
-  "decentralisation": "decentralization",
-  "decentralise": "decentralize",
-  "decentralised": "decentralized",
-  "decentralises": "decentralizes",
-  "decentralising": "decentralizing",
-  "decriminalisation": "decriminalization",
-  "decriminalise": "decriminalize",
-  "decriminalised": "decriminalized",
-  "decriminalises": "decriminalizes",
-  "decriminalising": "decriminalizing",
-  "defence": "defense",
-  "defenceless": "defenseless",
-  "defences": "defenses",
-  "dehumanisation": "dehumanization",
-  "dehumanise": "dehumanize",
-  "dehumanised": "dehumanized",
-  "dehumanises": "dehumanizes",
-  "dehumanising": "dehumanizing",
-  "demeanour": "demeanor",
-  "demilitarisation": "demilitarization",
-  "demilitarise": "demilitarize",
-  "demilitarised": "demilitarized",
-  "demilitarises": "demilitarizes",
-  "demilitarising": "demilitarizing",
-  "demobilisation": "demobilization",
-  "demobilise": "demobilize",
-  "demobilised": "demobilized",
-  "demobilises": "demobilizes",
-  "demobilising": "demobilizing",
-  "democratisation": "democratization",
-  "democratise": "democratize",
-  "democratised": "democratized",
-  "democratises": "democratizes",
-  "democratising": "democratizing",
-  "demonise": "demonize",
-  "demonised": "demonized",
-  "demonises": "demonizes",
-  "demonising": "demonizing",
-  "demoralisation": "demoralization",
-  "demoralise": "demoralize",
-  "demoralised": "demoralized",
-  "demoralises": "demoralizes",
-  "demoralising": "demoralizing",
-  "denationalisation": "denationalization",
-  "denationalise": "denationalize",
-  "denationalised": "denationalized",
-  "denationalises": "denationalizes",
-  "denationalising": "denationalizing",
-  "deodorise": "deodorize",
-  "deodorised": "deodorized",
-  "deodorises": "deodorizes",
-  "deodorising": "deodorizing",
-  "depersonalise": "depersonalize",
-  "depersonalised": "depersonalized",
-  "depersonalises": "depersonalizes",
-  "depersonalising": "depersonalizing",
-  "deputise": "deputize",
-  "deputised": "deputized",
-  "deputises": "deputizes",
-  "deputising": "deputizing",
-  "desensitisation": "desensitization",
-  "desensitise": "desensitize",
-  "desensitised": "desensitized",
-  "desensitises": "desensitizes",
-  "desensitising": "desensitizing",
-  "destabilisation": "destabilization",
-  "destabilise": "destabilize",
-  "destabilised": "destabilized",
-  "destabilises": "destabilizes",
-  "destabilising": "destabilizing",
-  "dialled": "dialed",
-  "dialling": "dialing",
-  "dialogue": "dialog",
-  "dialogues": "dialogs",
-  "diarrhoea": "diarrhea",
-  "digitise": "digitize",
-  "digitised": "digitized",
-  "digitises": "digitizes",
-  "digitising": "digitizing",
-  "disc": "disk",
-  "discolour": "discolor",
-  "discoloured": "discolored",
-  "discolouring": "discoloring",
-  "discolours": "discolors",
-  "discs": "disks",
-  "disembowelled": "disemboweled",
-  "disembowelling": "disemboweling",
-  "disfavour": "disfavor",
-  "dishevelled": "disheveled",
-  "dishonour": "dishonor",
-  "dishonourable": "dishonorable",
-  "dishonourably": "dishonorably",
-  "dishonoured": "dishonored",
-  "dishonouring": "dishonoring",
-  "dishonours": "dishonors",
-  "disorganisation": "disorganization",
-  "disorganised": "disorganized",
-  "distil": "distill",
-  "distils": "distills",
-  "dramatisation": "dramatization",
-  "dramatisations": "dramatizations",
-  "dramatise": "dramatize",
-  "dramatised": "dramatized",
-  "dramatises": "dramatizes",
-  "dramatising": "dramatizing",
-  "draught": "draft",
-  "draughtboard": "draftboard",
-  "draughtboards": "draftboards",
-  "draughtier": "draftier",
-  "draughtiest": "draftiest",
-  "draughts": "drafts",
-  "draughtsman": "draftsman",
-  "draughtsmanship": "draftsmanship",
-  "draughtsmen": "draftsmen",
-  "draughtswoman": "draftswoman",
-  "draughtswomen": "draftswomen",
-  "draughty": "drafty",
-  "drivelled": "driveled",
-  "drivelling": "driveling",
-  "duelled": "dueled",
-  "duelling": "dueling",
-  "economise": "economize",
-  "economised": "economized",
-  "economises": "economizes",
-  "economising": "economizing",
-  "editorialise": "editorialize",
-  "editorialised": "editorialized",
-  "editorialises": "editorializes",
-  "editorialising": "editorializing",
-  "edoema": "edema",
-  "empathise": "empathize",
-  "empathised": "empathized",
-  "empathises": "empathizes",
-  "empathising": "empathizing",
-  "emphasise": "emphasize",
-  "emphasised": "emphasized",
-  "emphasises": "emphasizes",
-  "emphasising": "emphasizing",
-  "enamelled": "enameled",
-  "enamelling": "enameling",
-  "enamoured": "enamored",
-  "encyclopaedia": "encyclopedia",
-  "encyclopaedias": "encyclopedias",
-  "encyclopaedic": "encyclopedic",
-  "endeavour": "endeavor",
-  "endeavoured": "endeavored",
-  "endeavouring": "endeavoring",
-  "endeavours": "endeavors",
-  "energise": "energize",
-  "energised": "energized",
-  "energises": "energizes",
-  "energising": "energizing",
-  "enrol": "enroll",
-  "enrols": "enrolls",
-  "enthral": "enthrall",
-  "enthrals": "enthralls",
-  "epaulette": "epaulet",
-  "epaulettes": "epaulets",
-  "epicentre": "epicenter",
-  "epicentres": "epicenters",
-  "epilogue": "epilog",
-  "epilogues": "epilogs",
-  "epitomise": "epitomize",
-  "epitomised": "epitomized",
-  "epitomises": "epitomizes",
-  "epitomising": "epitomizing",
-  "equalisation": "equalization",
-  "equalise": "equalize",
-  "equalised": "equalized",
-  "equaliser": "equalizer",
-  "equalisers": "equalizers",
-  "equalises": "equalizes",
-  "equalising": "equalizing",
-  "eulogise": "eulogize",
-  "eulogised": "eulogized",
-  "eulogises": "eulogizes",
-  "eulogising": "eulogizing",
-  "evangelise": "evangelize",
-  "evangelised": "evangelized",
-  "evangelises": "evangelizes",
-  "evangelising": "evangelizing",
-  "exorcise": "exorcize",
-  "exorcised": "exorcized",
-  "exorcises": "exorcizes",
-  "exorcising": "exorcizing",
-  "extemporisation": "extemporization",
-  "extemporise": "extemporize",
-  "extemporised": "extemporized",
-  "extemporises": "extemporizes",
-  "extemporising": "extemporizing",
-  "externalisation": "externalization",
-  "externalisations": "externalizations",
-  "externalise": "externalize",
-  "externalised": "externalized",
-  "externalises": "externalizes",
-  "externalising": "externalizing",
-  "factorise": "factorize",
-  "factorised": "factorized",
-  "factorises": "factorizes",
-  "factorising": "factorizing",
-  "faecal": "fecal",
-  "faeces": "feces",
-  "familiarisation": "familiarization",
-  "familiarise": "familiarize",
-  "familiarised": "familiarized",
-  "familiarises": "familiarizes",
-  "familiarising": "familiarizing",
-  "fantasise": "fantasize",
-  "fantasised": "fantasized",
-  "fantasises": "fantasizes",
-  "fantasising": "fantasizing",
-  "favour": "favor",
-  "favourable": "favorable",
-  "favourably": "favorably",
-  "favoured": "favored",
-  "favouring": "favoring",
-  "favourite": "favorite",
-  "favourites": "favorites",
-  "favouritism": "favoritism",
-  "favours": "favors",
-  "feminise": "feminize",
-  "feminised": "feminized",
-  "feminises": "feminizes",
-  "feminising": "feminizing",
-  "fertilisation": "fertilization",
-  "fertilise": "fertilize",
-  "fertilised": "fertilized",
-  "fertiliser": "fertilizer",
-  "fertilisers": "fertilizers",
-  "fertilises": "fertilizes",
-  "fertilising": "fertilizing",
-  "fervour": "fervor",
-  "fibre": "fiber",
-  "fibreglass": "fiberglass",
-  "fibres": "fibers",
-  "fictionalisation": "fictionalization",
-  "fictionalisations": "fictionalizations",
-  "fictionalise": "fictionalize",
-  "fictionalised": "fictionalized",
-  "fictionalises": "fictionalizes",
-  "fictionalising": "fictionalizing",
-  "fillet": "filet",
-  "filleted": "fileted",
-  "filleting": "fileting",
-  "fillets": "filets",
-  "finalisation": "finalization",
-  "finalise": "finalize",
-  "finalised": "finalized",
-  "finalises": "finalizes",
-  "finalising": "finalizing",
-  "flautist": "flutist",
-  "flautists": "flutists",
-  "flavour": "flavor",
-  "flavoured": "flavored",
-  "flavouring": "flavoring",
-  "flavourings": "flavorings",
-  "flavourless": "flavorless",
-  "flavours": "flavors",
-  "flavoursome": "flavorsome",
-  "flyer / flier": "flier / flyer",
-  "foetal": "fetal",
-  "foetid": "fetid",
-  "foetus": "fetus",
-  "foetuses": "fetuses",
-  "formalisation": "formalization",
-  "formalise": "formalize",
-  "formalised": "formalized",
-  "formalises": "formalizes",
-  "formalising": "formalizing",
-  "fossilisation": "fossilization",
-  "fossilise": "fossilize",
-  "fossilised": "fossilized",
-  "fossilises": "fossilizes",
-  "fossilising": "fossilizing",
-  "fraternisation": "fraternization",
-  "fraternise": "fraternize",
-  "fraternised": "fraternized",
-  "fraternises": "fraternizes",
-  "fraternising": "fraternizing",
-  "fulfil": "fulfill",
-  "fulfilment": "fulfillment",
-  "fulfils": "fulfills",
-  "funnelled": "funneled",
-  "funnelling": "funneling",
-  "gage": "gauge",
-  "gaged": "gauged",
-  "gages": "gauges",
-  "gaging": "gauging",
-  "galvanise": "galvanize",
-  "galvanised": "galvanized",
-  "galvanises": "galvanizes",
-  "galvanising": "galvanizing",
-  "gambolled": "gamboled",
-  "gambolling": "gamboling",
-  "gaol": "jail",
-  "gaolbird": "jailbird",
-  "gaolbirds": "jailbirds",
-  "gaolbreak": "jailbreak",
-  "gaolbreaks": "jailbreaks",
-  "gaoled": "jailed",
-  "gaoler": "jailer",
-  "gaolers": "jailers",
-  "gaoling": "jailing",
-  "gaols": "jails",
-  "gasses": "gases",
-  "generalisation": "generalization",
-  "generalisations": "generalizations",
-  "generalise": "generalize",
-  "generalised": "generalized",
-  "generalises": "generalizes",
-  "generalising": "generalizing",
-  "ghettoise": "ghettoize",
-  "ghettoised": "ghettoized",
-  "ghettoises": "ghettoizes",
-  "ghettoising": "ghettoizing",
-  "gipsies": "gypsies",
-  "glamor": "glamour",
-  "glamorise": "glamorize",
-  "glamorised": "glamorized",
-  "glamorises": "glamorizes",
-  "glamorising": "glamorizing",
-  "globalisation": "globalization",
-  "globalise": "globalize",
-  "globalised": "globalized",
-  "globalises": "globalizes",
-  "globalising": "globalizing",
-  "glueing": "gluing",
-  "goitre": "goiter",
-  "goitres": "goiters",
-  "gonorrhoea": "gonorrhea",
-  "gramme": "gram",
-  "grammes": "grams",
-  "gravelled": "graveled",
-  "grey": "gray",
-  "greyed": "grayed",
-  "greying": "graying",
-  "greyish": "grayish",
-  "greyness": "grayness",
-  "greys": "grays",
-  "grovelled": "groveled",
-  "grovelling": "groveling",
-  "groyne": "groin",
-  "groynes": "groins",
-  "gruelling": "grueling",
-  "gruellingly": "gruelingly",
-  "gryphon": "griffin",
-  "gryphons": "griffins",
-  "gynaecological": "gynecological",
-  "gynaecologist": "gynecologist",
-  "gynaecologists": "gynecologists",
-  "gynaecology": "gynecology",
-  "haematological": "hematological",
-  "haematologist": "hematologist",
-  "haematologists": "hematologists",
-  "haematology": "hematology",
-  "haemoglobin": "hemoglobin",
-  "haemophilia": "hemophilia",
-  "haemophiliac": "hemophiliac",
-  "haemophiliacs": "hemophiliacs",
-  "haemorrhage": "hemorrhage",
-  "haemorrhaged": "hemorrhaged",
-  "haemorrhages": "hemorrhages",
-  "haemorrhaging": "hemorrhaging",
-  "haemorrhoids": "hemorrhoids",
-  "harbour": "harbor",
-  "harboured": "harbored",
-  "harbouring": "harboring",
-  "harbours": "harbors",
-  "harmonisation": "harmonization",
-  "harmonise": "harmonize",
-  "harmonised": "harmonized",
-  "harmonises": "harmonizes",
-  "harmonising": "harmonizing",
-  "homoeopath": "homeopath",
-  "homoeopathic": "homeopathic",
-  "homoeopaths": "homeopaths",
-  "homoeopathy": "homeopathy",
-  "homogenise": "homogenize",
-  "homogenised": "homogenized",
-  "homogenises": "homogenizes",
-  "homogenising": "homogenizing",
-  "honour": "honor",
-  "honourable": "honorable",
-  "honourably": "honorably",
-  "honoured": "honored",
-  "honouring": "honoring",
-  "honours": "honors",
-  "hospitalisation": "hospitalization",
-  "hospitalise": "hospitalize",
-  "hospitalised": "hospitalized",
-  "hospitalises": "hospitalizes",
-  "hospitalising": "hospitalizing",
-  "humanise": "humanize",
-  "humanised": "humanized",
-  "humanises": "humanizes",
-  "humanising": "humanizing",
-  "humour": "humor",
-  "humoured": "humored",
-  "humouring": "humoring",
-  "humourless": "humorless",
-  "humours": "humors",
-  "hybridise": "hybridize",
-  "hybridised": "hybridized",
-  "hybridises": "hybridizes",
-  "hybridising": "hybridizing",
-  "hypnotise": "hypnotize",
-  "hypnotised": "hypnotized",
-  "hypnotises": "hypnotizes",
-  "hypnotising": "hypnotizing",
-  "hypothesise": "hypothesize",
-  "hypothesised": "hypothesized",
-  "hypothesises": "hypothesizes",
-  "hypothesising": "hypothesizing",
-  "idealisation": "idealization",
-  "idealise": "idealize",
-  "idealised": "idealized",
-  "idealises": "idealizes",
-  "idealising": "idealizing",
-  "idolise": "idolize",
-  "idolised": "idolized",
-  "idolises": "idolizes",
-  "idolising": "idolizing",
-  "immobilisation": "immobilization",
-  "immobilise": "immobilize",
-  "immobilised": "immobilized",
-  "immobiliser": "immobilizer",
-  "immobilisers": "immobilizers",
-  "immobilises": "immobilizes",
-  "immobilising": "immobilizing",
-  "immortalise": "immortalize",
-  "immortalised": "immortalized",
-  "immortalises": "immortalizes",
-  "immortalising": "immortalizing",
-  "immunisation": "immunization",
-  "immunise": "immunize",
-  "immunised": "immunized",
-  "immunises": "immunizes",
-  "immunising": "immunizing",
-  "impanelled": "impaneled",
-  "impanelling": "impaneling",
-  "imperilled": "imperiled",
-  "imperilling": "imperiling",
-  "individualise": "individualize",
-  "individualised": "individualized",
-  "individualises": "individualizes",
-  "individualising": "individualizing",
-  "industrialise": "industrialize",
-  "industrialised": "industrialized",
-  "industrialises": "industrializes",
-  "industrialising": "industrializing",
-  "inflexion": "inflection",
-  "inflexions": "inflections",
-  "initialise": "initialize",
-  "initialised": "initialized",
-  "initialises": "initializes",
-  "initialising": "initializing",
-  "initialled": "initialed",
-  "initialling": "initialing",
-  "instal": "install",
-  "instalment": "installment",
-  "instalments": "installments",
-  "instals": "installs",
-  "instil": "instill",
-  "instils": "instills",
-  "institutionalisation": "institutionalization",
-  "institutionalise": "institutionalize",
-  "institutionalised": "institutionalized",
-  "institutionalises": "institutionalizes",
-  "institutionalising": "institutionalizing",
-  "intellectualise": "intellectualize",
-  "intellectualised": "intellectualized",
-  "intellectualises": "intellectualizes",
-  "intellectualising": "intellectualizing",
-  "internalisation": "internalization",
-  "internalise": "internalize",
-  "internalised": "internalized",
-  "internalises": "internalizes",
-  "internalising": "internalizing",
-  "internationalisation": "internationalization",
-  "internationalise": "internationalize",
-  "internationalised": "internationalized",
-  "internationalises": "internationalizes",
-  "internationalising": "internationalizing",
-  "ionisation": "ionization",
-  "ionise": "ionize",
-  "ionised": "ionized",
-  "ioniser": "ionizer",
-  "ionisers": "ionizers",
-  "ionises": "ionizes",
-  "ionising": "ionizing",
-  "italicise": "italicize",
-  "italicised": "italicized",
-  "italicises": "italicizes",
-  "italicising": "italicizing",
-  "itemise": "itemize",
-  "itemised": "itemized",
-  "itemises": "itemizes",
-  "itemising": "itemizing",
-  "jeopardise": "jeopardize",
-  "jeopardised": "jeopardized",
-  "jeopardises": "jeopardizes",
-  "jeopardising": "jeopardizing",
-  "jewelled": "jeweled",
-  "jeweller": "jeweler",
-  "jewellers": "jewelers",
-  "jewellery": "jewelry",
-  "judgement": "judgment",
-  "kilogramme": "kilogram",
-  "kilogrammes": "kilograms",
-  "kilometre": "kilometer",
-  "kilometres": "kilometers",
-  "labelled": "labeled",
-  "labelling": "labeling",
-  "labour": "labor",
-  "laboured": "labored",
-  "labourer": "laborer",
-  "labourers": "laborers",
-  "labouring": "laboring",
-  "labours": "labors",
-  "lacklustre": "lackluster",
-  "legalisation": "legalization",
-  "legalise": "legalize",
-  "legalised": "legalized",
-  "legalises": "legalizes",
-  "legalising": "legalizing",
-  "legitimise": "legitimize",
-  "legitimised": "legitimized",
-  "legitimises": "legitimizes",
-  "legitimising": "legitimizing",
-  "leukaemia": "leukemia",
-  "levelled": "leveled",
-  "leveller": "leveler",
-  "levellers": "levelers",
-  "levelling": "leveling",
-  "libelled": "libeled",
-  "libelling": "libeling",
-  "libellous": "libelous",
-  "liberalisation": "liberalization",
-  "liberalise": "liberalize",
-  "liberalised": "liberalized",
-  "liberalises": "liberalizes",
-  "liberalising": "liberalizing",
-  "licence": "license",
-  "licenced": "licensed",
-  "licences": "licenses",
-  "licencing": "licensing",
-  "likeable": "likable",
-  "lionisation": "lionization",
-  "lionise": "lionize",
-  "lionised": "lionized",
-  "lionises": "lionizes",
-  "lionising": "lionizing",
-  "liquidise": "liquidize",
-  "liquidised": "liquidized",
-  "liquidiser": "liquidizer",
-  "liquidisers": "liquidizers",
-  "liquidises": "liquidizes",
-  "liquidising": "liquidizing",
-  "litre": "liter",
-  "litres": "liters",
-  "localise": "localize",
-  "localised": "localized",
-  "localises": "localizes",
-  "localising": "localizing",
-  "louvre": "louver",
-  "louvred": "louvered",
-  "louvres": "louvers",
-  "lustre": "luster",
-  "magnetise": "magnetize",
-  "magnetised": "magnetized",
-  "magnetises": "magnetizes",
-  "magnetising": "magnetizing",
-  "manoeuvrability": "maneuverability",
-  "manoeuvrable": "maneuverable",
-  "manoeuvre": "maneuver",
-  "manoeuvred": "maneuvered",
-  "manoeuvres": "maneuvers",
-  "manoeuvring": "maneuvering",
-  "manoeuvrings": "maneuverings",
-  "marginalisation": "marginalization",
-  "marginalise": "marginalize",
-  "marginalised": "marginalized",
-  "marginalises": "marginalizes",
-  "marginalising": "marginalizing",
-  "marshalled": "marshaled",
-  "marshalling": "marshaling",
-  "marvelled": "marveled",
-  "marvelling": "marveling",
-  "marvellous": "marvelous",
-  "marvellously": "marvelously",
-  "materialisation": "materialization",
-  "materialise": "materialize",
-  "materialised": "materialized",
-  "materialises": "materializes",
-  "materialising": "materializing",
-  "maximisation": "maximization",
-  "maximise": "maximize",
-  "maximised": "maximized",
-  "maximises": "maximizes",
-  "maximising": "maximizing",
-  "meagre": "meager",
-  "mechanisation": "mechanization",
-  "mechanise": "mechanize",
-  "mechanised": "mechanized",
-  "mechanises": "mechanizes",
-  "mechanising": "mechanizing",
-  "mediaeval": "medieval",
-  "memorialise": "memorialize",
-  "memorialised": "memorialized",
-  "memorialises": "memorializes",
-  "memorialising": "memorializing",
-  "memorise": "memorize",
-  "memorised": "memorized",
-  "memorises": "memorizes",
-  "memorising": "memorizing",
-  "mesmerise": "mesmerize",
-  "mesmerised": "mesmerized",
-  "mesmerises": "mesmerizes",
-  "mesmerising": "mesmerizing",
-  "metabolise": "metabolize",
-  "metabolised": "metabolized",
-  "metabolises": "metabolizes",
-  "metabolising": "metabolizing",
-  "metre": "meter",
-  "metres": "meters",
-  "mhm": "hmm",
-  "micrometre": "micrometer",
-  "micrometres": "micrometers",
-  "militarise": "militarize",
-  "militarised": "militarized",
-  "militarises": "militarizes",
-  "militarising": "militarizing",
-  "milligramme": "milligram",
-  "milligrammes": "milligrams",
-  "millilitre": "milliliter",
-  "millilitres": "milliliters",
-  "millimetre": "millimeter",
-  "millimetres": "millimeters",
-  "miniaturisation": "miniaturization",
-  "miniaturise": "miniaturize",
-  "miniaturised": "miniaturized",
-  "miniaturises": "miniaturizes",
-  "miniaturising": "miniaturizing",
-  "minibusses": "minibuses",
-  "minimise": "minimize",
-  "minimised": "minimized",
-  "minimises": "minimizes",
-  "minimising": "minimizing",
-  "misbehaviour": "misbehavior",
-  "misdemeanour": "misdemeanor",
-  "misdemeanours": "misdemeanors",
-  "misspelt": "misspelled",
-  "mitre": "miter",
-  "mitres": "miters",
-  "mm": "hmm",
-  "mmm": "hmm",
-  "mobilisation": "mobilization",
-  "mobilise": "mobilize",
-  "mobilised": "mobilized",
-  "mobilises": "mobilizes",
-  "mobilising": "mobilizing",
-  "modelled": "modeled",
-  "modeller": "modeler",
-  "modellers": "modelers",
-  "modelling": "modeling",
-  "modernise": "modernize",
-  "modernised": "modernized",
-  "modernises": "modernizes",
-  "modernising": "modernizing",
-  "moisturise": "moisturize",
-  "moisturised": "moisturized",
-  "moisturiser": "moisturizer",
-  "moisturisers": "moisturizers",
-  "moisturises": "moisturizes",
-  "moisturising": "moisturizing",
-  "monologue": "monolog",
-  "monologues": "monologs",
-  "monopolisation": "monopolization",
-  "monopolise": "monopolize",
-  "monopolised": "monopolized",
-  "monopolises": "monopolizes",
-  "monopolising": "monopolizing",
-  "moralise": "moralize",
-  "moralised": "moralized",
-  "moralises": "moralizes",
-  "moralising": "moralizing",
-  "motorised": "motorized",
-  "mould": "mold",
-  "moulded": "molded",
-  "moulder": "molder",
-  "mouldered": "moldered",
-  "mouldering": "moldering",
-  "moulders": "molders",
-  "mouldier": "moldier",
-  "mouldiest": "moldiest",
-  "moulding": "molding",
-  "mouldings": "moldings",
-  "moulds": "molds",
-  "mouldy": "moldy",
-  "moult": "molt",
-  "moulted": "molted",
-  "moulting": "molting",
-  "moults": "molts",
-  "moustache": "mustache",
-  "moustached": "mustached",
-  "moustaches": "mustaches",
-  "moustachioed": "mustachioed",
-  "multicoloured": "multicolored",
-  "nationalisation": "nationalization",
-  "nationalisations": "nationalizations",
-  "nationalise": "nationalize",
-  "nationalised": "nationalized",
-  "nationalises": "nationalizes",
-  "nationalising": "nationalizing",
-  "naturalisation": "naturalization",
-  "naturalise": "naturalize",
-  "naturalised": "naturalized",
-  "naturalises": "naturalizes",
-  "naturalising": "naturalizing",
-  "neighbour": "neighbor",
-  "neighbourhood": "neighborhood",
-  "neighbourhoods": "neighborhoods",
-  "neighbouring": "neighboring",
-  "neighbourliness": "neighborliness",
-  "neighbourly": "neighborly",
-  "neighbours": "neighbors",
-  "neutralisation": "neutralization",
-  "neutralise": "neutralize",
-  "neutralised": "neutralized",
-  "neutralises": "neutralizes",
-  "neutralising": "neutralizing",
-  "normalisation": "normalization",
-  "normalise": "normalize",
-  "normalised": "normalized",
-  "normalises": "normalizes",
-  "normalising": "normalizing",
-  "odour": "odor",
-  "odourless": "odorless",
-  "odours": "odors",
-  "oesophagus": "esophagus",
-  "oesophaguses": "esophaguses",
-  "oestrogen": "estrogen",
-  "offence": "offense",
-  "offences": "offenses",
-  "omelette": "omelet",
-  "omelettes": "omelets",
-  "optimise": "optimize",
-  "optimised": "optimized",
-  "optimises": "optimizes",
-  "optimising": "optimizing",
-  "organisation": "organization",
-  "organisational": "organizational",
-  "organisations": "organizations",
-  "organise": "organize",
-  "organised": "organized",
-  "organiser": "organizer",
-  "organisers": "organizers",
-  "organises": "organizes",
-  "organising": "organizing",
-  "orthopaedic": "orthopedic",
-  "orthopaedics": "orthopedics",
-  "ostracise": "ostracize",
-  "ostracised": "ostracized",
-  "ostracises": "ostracizes",
-  "ostracising": "ostracizing",
-  "outmanoeuvre": "outmaneuver",
-  "outmanoeuvred": "outmaneuvered",
-  "outmanoeuvres": "outmaneuvers",
-  "outmanoeuvring": "outmaneuvering",
-  "overemphasise": "overemphasize",
-  "overemphasised": "overemphasized",
-  "overemphasises": "overemphasizes",
-  "overemphasising": "overemphasizing",
-  "oxidisation": "oxidization",
-  "oxidise": "oxidize",
-  "oxidised": "oxidized",
-  "oxidises": "oxidizes",
-  "oxidising": "oxidizing",
-  "paederast": "pederast",
-  "paederasts": "pederasts",
-  "paediatric": "pediatric",
-  "paediatrician": "pediatrician",
-  "paediatricians": "pediatricians",
-  "paediatrics": "pediatrics",
-  "paedophile": "pedophile",
-  "paedophiles": "pedophiles",
-  "paedophilia": "pedophilia",
-  "palaeolithic": "paleolithic",
-  "palaeontologist": "paleontologist",
-  "palaeontologists": "paleontologists",
-  "palaeontology": "paleontology",
-  "panelled": "paneled",
-  "panelling": "paneling",
-  "panellist": "panelist",
-  "panellists": "panelists",
-  "paralyse": "paralyze",
-  "paralysed": "paralyzed",
-  "paralyses": "paralyzes",
-  "paralysing": "paralyzing",
-  "parcelled": "parceled",
-  "parcelling": "parceling",
-  "parlour": "parlor",
-  "parlours": "parlors",
-  "particularise": "particularize",
-  "particularised": "particularized",
-  "particularises": "particularizes",
-  "particularising": "particularizing",
-  "passivisation": "passivization",
-  "passivise": "passivize",
-  "passivised": "passivized",
-  "passivises": "passivizes",
-  "passivising": "passivizing",
-  "pasteurisation": "pasteurization",
-  "pasteurise": "pasteurize",
-  "pasteurised": "pasteurized",
-  "pasteurises": "pasteurizes",
-  "pasteurising": "pasteurizing",
-  "patronise": "patronize",
-  "patronised": "patronized",
-  "patronises": "patronizes",
-  "patronising": "patronizing",
-  "patronisingly": "patronizingly",
-  "pedalled": "pedaled",
-  "pedalling": "pedaling",
-  "pedestrianisation": "pedestrianization",
-  "pedestrianise": "pedestrianize",
-  "pedestrianised": "pedestrianized",
-  "pedestrianises": "pedestrianizes",
-  "pedestrianising": "pedestrianizing",
-  "penalise": "penalize",
-  "penalised": "penalized",
-  "penalises": "penalizes",
-  "penalising": "penalizing",
-  "pencilled": "penciled",
-  "pencilling": "penciling",
-  "personalise": "personalize",
-  "personalised": "personalized",
-  "personalises": "personalizes",
-  "personalising": "personalizing",
-  "pharmacopoeia": "pharmacopeia",
-  "pharmacopoeias": "pharmacopeias",
-  "philosophise": "philosophize",
-  "philosophised": "philosophized",
-  "philosophises": "philosophizes",
-  "philosophising": "philosophizing",
-  "philtre": "filter",
-  "philtres": "filters",
-  "phoney": "phony",
-  "plagiarise": "plagiarize",
-  "plagiarised": "plagiarized",
-  "plagiarises": "plagiarizes",
-  "plagiarising": "plagiarizing",
-  "plough": "plow",
-  "ploughed": "plowed",
-  "ploughing": "plowing",
-  "ploughman": "plowman",
-  "ploughmen": "plowmen",
-  "ploughs": "plows",
-  "ploughshare": "plowshare",
-  "ploughshares": "plowshares",
-  "polarisation": "polarization",
-  "polarise": "polarize",
-  "polarised": "polarized",
-  "polarises": "polarizes",
-  "polarising": "polarizing",
-  "politicisation": "politicization",
-  "politicise": "politicize",
-  "politicised": "politicized",
-  "politicises": "politicizes",
-  "politicising": "politicizing",
-  "popularisation": "popularization",
-  "popularise": "popularize",
-  "popularised": "popularized",
-  "popularises": "popularizes",
-  "popularising": "popularizing",
-  "pouffe": "pouf",
-  "pouffes": "poufs",
-  "practise": "practice",
-  "practised": "practiced",
-  "practises": "practices",
-  "practising": "practicing",
-  "praesidium": "presidium",
-  "praesidiums": "presidiums",
-  "pressurisation": "pressurization",
-  "pressurise": "pressurize",
-  "pressurised": "pressurized",
-  "pressurises": "pressurizes",
-  "pressurising": "pressurizing",
-  "pretence": "pretense",
-  "pretences": "pretenses",
-  "primaeval": "primeval",
-  "prioritisation": "prioritization",
-  "prioritise": "prioritize",
-  "prioritised": "prioritized",
-  "prioritises": "prioritizes",
-  "prioritising": "prioritizing",
-  "privatisation": "privatization",
-  "privatisations": "privatizations",
-  "privatise": "privatize",
-  "privatised": "privatized",
-  "privatises": "privatizes",
-  "privatising": "privatizing",
-  "professionalisation": "professionalization",
-  "professionalise": "professionalize",
-  "professionalised": "professionalized",
-  "professionalises": "professionalizes",
-  "professionalising": "professionalizing",
-  "programme": "program",
-  "programmes": "programs",
-  "prologue": "prolog",
-  "prologues": "prologs",
-  "propagandise": "propagandize",
-  "propagandised": "propagandized",
-  "propagandises": "propagandizes",
-  "propagandising": "propagandizing",
-  "proselytise": "proselytize",
-  "proselytised": "proselytized",
-  "proselytiser": "proselytizer",
-  "proselytisers": "proselytizers",
-  "proselytises": "proselytizes",
-  "proselytising": "proselytizing",
-  "psychoanalyse": "psychoanalyze",
-  "psychoanalysed": "psychoanalyzed",
-  "psychoanalyses": "psychoanalyzes",
-  "psychoanalysing": "psychoanalyzing",
-  "publicise": "publicize",
-  "publicised": "publicized",
-  "publicises": "publicizes",
-  "publicising": "publicizing",
-  "pulverisation": "pulverization",
-  "pulverise": "pulverize",
-  "pulverised": "pulverized",
-  "pulverises": "pulverizes",
-  "pulverising": "pulverizing",
-  "pummelled": "pummel",
-  "pummelling": "pummeled",
-  "pyjama": "pajama",
-  "pyjamas": "pajamas",
-  "pzazz": "pizzazz",
-  "quarrelled": "quarreled",
-  "quarrelling": "quarreling",
-  "radicalise": "radicalize",
-  "radicalised": "radicalized",
-  "radicalises": "radicalizes",
-  "radicalising": "radicalizing",
-  "rancour": "rancor",
-  "randomise": "randomize",
-  "randomised": "randomized",
-  "randomises": "randomizes",
-  "randomising": "randomizing",
-  "rationalisation": "rationalization",
-  "rationalisations": "rationalizations",
-  "rationalise": "rationalize",
-  "rationalised": "rationalized",
-  "rationalises": "rationalizes",
-  "rationalising": "rationalizing",
-  "ravelled": "raveled",
-  "ravelling": "raveling",
-  "realisable": "realizable",
-  "realisation": "realization",
-  "realisations": "realizations",
-  "realise": "realize",
-  "realised": "realized",
-  "realises": "realizes",
-  "realising": "realizing",
-  "recognisable": "recognizable",
-  "recognisably": "recognizably",
-  "recognisance": "recognizance",
-  "recognise": "recognize",
-  "recognised": "recognized",
-  "recognises": "recognizes",
-  "recognising": "recognizing",
-  "reconnoitre": "reconnoiter",
-  "reconnoitred": "reconnoitered",
-  "reconnoitres": "reconnoiters",
-  "reconnoitring": "reconnoitering",
-  "refuelled": "refueled",
-  "refuelling": "refueling",
-  "regularisation": "regularization",
-  "regularise": "regularize",
-  "regularised": "regularized",
-  "regularises": "regularizes",
-  "regularising": "regularizing",
-  "remodelled": "remodeled",
-  "remodelling": "remodeling",
-  "remould": "remold",
-  "remoulded": "remolded",
-  "remoulding": "remolding",
-  "remoulds": "remolds",
-  "reorganisation": "reorganization",
-  "reorganisations": "reorganizations",
-  "reorganise": "reorganize",
-  "reorganised": "reorganized",
-  "reorganises": "reorganizes",
-  "reorganising": "reorganizing",
-  "revelled": "reveled",
-  "reveller": "reveler",
-  "revellers": "revelers",
-  "revelling": "reveling",
-  "revitalise": "revitalize",
-  "revitalised": "revitalized",
-  "revitalises": "revitalizes",
-  "revitalising": "revitalizing",
-  "revolutionise": "revolutionize",
-  "revolutionised": "revolutionized",
-  "revolutionises": "revolutionizes",
-  "revolutionising": "revolutionizing",
-  "rhapsodise": "rhapsodize",
-  "rhapsodised": "rhapsodized",
-  "rhapsodises": "rhapsodizes",
-  "rhapsodising": "rhapsodizing",
-  "rigour": "rigor",
-  "rigours": "rigors",
-  "ritualised": "ritualized",
-  "rivalled": "rivaled",
-  "rivalling": "rivaling",
-  "romanticise": "romanticize",
-  "romanticised": "romanticized",
-  "romanticises": "romanticizes",
-  "romanticising": "romanticizing",
-  "rumour": "rumor",
-  "rumoured": "rumored",
-  "rumours": "rumors",
-  "sabre": "saber",
-  "sabres": "sabers",
-  "saltpetre": "saltpeter",
-  "sanitise": "sanitize",
-  "sanitised": "sanitized",
-  "sanitises": "sanitizes",
-  "sanitising": "sanitizing",
-  "satirise": "satirize",
-  "satirised": "satirized",
-  "satirises": "satirizes",
-  "satirising": "satirizing",
-  "saviour": "savior",
-  "saviours": "saviors",
-  "savour": "savor",
-  "savoured": "savored",
-  "savouries": "savories",
-  "savouring": "savoring",
-  "savours": "savors",
-  "savoury": "savory",
-  "scandalise": "scandalize",
-  "scandalised": "scandalized",
-  "scandalises": "scandalizes",
-  "scandalising": "scandalizing",
-  "sceptic": "skeptic",
-  "sceptical": "skeptical",
-  "sceptically": "skeptically",
-  "scepticism": "skepticism",
-  "sceptics": "skeptics",
-  "sceptre": "scepter",
-  "sceptres": "scepters",
-  "scrutinise": "scrutinize",
-  "scrutinised": "scrutinized",
-  "scrutinises": "scrutinizes",
-  "scrutinising": "scrutinizing",
-  "secularisation": "secularization",
-  "secularise": "secularize",
-  "secularised": "secularized",
-  "secularises": "secularizes",
-  "secularising": "secularizing",
-  "sensationalise": "sensationalize",
-  "sensationalised": "sensationalized",
-  "sensationalises": "sensationalizes",
-  "sensationalising": "sensationalizing",
-  "sensitise": "sensitize",
-  "sensitised": "sensitized",
-  "sensitises": "sensitizes",
-  "sensitising": "sensitizing",
-  "sentimentalise": "sentimentalize",
-  "sentimentalised": "sentimentalized",
-  "sentimentalises": "sentimentalizes",
-  "sentimentalising": "sentimentalizing",
-  "sepulchre": "sepulcher",
-  "sepulchres": "sepulchers",
-  "serialisation": "serialization",
-  "serialisations": "serializations",
-  "serialise": "serialize",
-  "serialised": "serialized",
-  "serialises": "serializes",
-  "serialising": "serializing",
-  "sermonise": "sermonize",
-  "sermonised": "sermonized",
-  "sermonises": "sermonizes",
-  "sermonising": "sermonizing",
-  "sheikh": "sheik",
-  "shovelled": "shoveled",
-  "shovelling": "shoveling",
-  "shrivelled": "shriveled",
-  "shrivelling": "shriveling",
-  "signalise": "signalize",
-  "signalised": "signalized",
-  "signalises": "signalizes",
-  "signalising": "signalizing",
-  "signalled": "signaled",
-  "signalling": "signaling",
-  "smoulder": "smolder",
-  "smouldered": "smoldered",
-  "smouldering": "smoldering",
-  "smoulders": "smolders",
-  "snivelled": "sniveled",
-  "snivelling": "sniveling",
-  "snorkelled": "snorkeled",
-  "snorkelling": "snorkeling",
-  "snowplough": "snowplow",
-  "snowploughs": "snowplow",
-  "socialisation": "socialization",
-  "socialise": "socialize",
-  "socialised": "socialized",
-  "socialises": "socializes",
-  "socialising": "socializing",
-  "sodomise": "sodomize",
-  "sodomised": "sodomized",
-  "sodomises": "sodomizes",
-  "sodomising": "sodomizing",
-  "solemnise": "solemnize",
-  "solemnised": "solemnized",
-  "solemnises": "solemnizes",
-  "solemnising": "solemnizing",
-  "sombre": "somber",
-  "specialisation": "specialization",
-  "specialisations": "specializations",
-  "specialise": "specialize",
-  "specialised": "specialized",
-  "specialises": "specializes",
-  "specialising": "specializing",
-  "spectre": "specter",
-  "spectres": "specters",
-  "spiralled": "spiraled",
-  "spiralling": "spiraling",
-  "splendour": "splendor",
-  "splendours": "splendors",
-  "squirrelled": "squirreled",
-  "squirrelling": "squirreling",
-  "stabilisation": "stabilization",
-  "stabilise": "stabilize",
-  "stabilised": "stabilized",
-  "stabiliser": "stabilizer",
-  "stabilisers": "stabilizers",
-  "stabilises": "stabilizes",
-  "stabilising": "stabilizing",
-  "standardisation": "standardization",
-  "standardise": "standardize",
-  "standardised": "standardized",
-  "standardises": "standardizes",
-  "standardising": "standardizing",
-  "stencilled": "stenciled",
-  "stencilling": "stenciling",
-  "sterilisation": "sterilization",
-  "sterilisations": "sterilizations",
-  "sterilise": "sterilize",
-  "sterilised": "sterilized",
-  "steriliser": "sterilizer",
-  "sterilisers": "sterilizers",
-  "sterilises": "sterilizes",
-  "sterilising": "sterilizing",
-  "stigmatisation": "stigmatization",
-  "stigmatise": "stigmatize",
-  "stigmatised": "stigmatized",
-  "stigmatises": "stigmatizes",
-  "stigmatising": "stigmatizing",
-  "storey": "story",
-  "storeys": "stories",
-  "subsidisation": "subsidization",
-  "subsidise": "subsidize",
-  "subsidised": "subsidized",
-  "subsidiser": "subsidizer",
-  "subsidisers": "subsidizers",
-  "subsidises": "subsidizes",
-  "subsidising": "subsidizing",
-  "succour": "succor",
-  "succoured": "succored",
-  "succouring": "succoring",
-  "succours": "succors",
-  "sulphate": "sulfate",
-  "sulphates": "sulfates",
-  "sulphide": "sulfide",
-  "sulphides": "sulfides",
-  "sulphur": "sulfur",
-  "sulphurous": "sulfurous",
-  "summarise": "summarize",
-  "summarised": "summarized",
-  "summarises": "summarizes",
-  "summarising": "summarizing",
-  "swivelled": "swiveled",
-  "swivelling": "swiveling",
-  "symbolise": "symbolize",
-  "symbolised": "symbolized",
-  "symbolises": "symbolizes",
-  "symbolising": "symbolizing",
-  "sympathise": "sympathize",
-  "sympathised": "sympathized",
-  "sympathiser": "sympathizer",
-  "sympathisers": "sympathizers",
-  "sympathises": "sympathizes",
-  "sympathising": "sympathizing",
-  "synchronisation": "synchronization",
-  "synchronise": "synchronize",
-  "synchronised": "synchronized",
-  "synchronises": "synchronizes",
-  "synchronising": "synchronizing",
-  "synthesise": "synthesize",
-  "synthesised": "synthesized",
-  "synthesiser": "synthesizer",
-  "synthesisers": "synthesizers",
-  "synthesises": "synthesizes",
-  "synthesising": "synthesizing",
-  "syphon": "siphon",
-  "syphoned": "siphoned",
-  "syphoning": "siphoning",
-  "syphons": "siphons",
-  "systematisation": "systematization",
-  "systematise": "systematize",
-  "systematised": "systematized",
-  "systematises": "systematizes",
-  "systematising": "systematizing",
-  "tantalise": "tantalize",
-  "tantalised": "tantalized",
-  "tantalises": "tantalizes",
-  "tantalising": "tantalizing",
-  "tantalisingly": "tantalizingly",
-  "tasselled": "tasseled",
-  "technicolour": "technicolor",
-  "temporise": "temporize",
-  "temporised": "temporized",
-  "temporises": "temporizes",
-  "temporising": "temporizing",
-  "tenderise": "tenderize",
-  "tenderised": "tenderized",
-  "tenderises": "tenderizes",
-  "tenderising": "tenderizing",
-  "terrorise": "terrorize",
-  "terrorised": "terrorized",
-  "terrorises": "terrorizes",
-  "terrorising": "terrorizing",
-  "theatre": "theater",
-  "theatregoer": "theatergoer",
-  "theatregoers": "theatergoers",
-  "theatres": "theaters",
-  "theorise": "theorize",
-  "theorised": "theorized",
-  "theorises": "theorizes",
-  "theorising": "theorizing",
-  "tonne": "ton",
-  "tonnes": "tons",
-  "towelled": "toweled",
-  "towelling": "toweling",
-  "toxaemia": "toxemia",
-  "tranquillise": "tranquilize",
-  "tranquillised": "tranquilized",
-  "tranquilliser": "tranquilizer",
-  "tranquillisers": "tranquilizers",
-  "tranquillises": "tranquilizes",
-  "tranquillising": "tranquilizing",
-  "tranquillity": "tranquility",
-  "tranquillize": "tranquilize",
-  "tranquillized": "tranquilized",
-  "tranquillizer": "tranquilizer",
-  "tranquillizers": "tranquilizers",
-  "tranquillizes": "tranquilizes",
-  "tranquillizing": "tranquilizing",
-  "tranquilly": "tranquility",
-  "transistorised": "transistorized",
-  "traumatise": "traumatize",
-  "traumatised": "traumatized",
-  "traumatises": "traumatizes",
-  "traumatising": "traumatizing",
-  "travelled": "traveled",
-  "traveller": "traveler",
-  "travellers": "travelers",
-  "travelling": "traveling",
-  "travelog": "travelogue",
-  "travelogs": "travelogues",
-  "trialled": "trialed",
-  "trialling": "trialing",
-  "tricolour": "tricolor",
-  "tricolours": "tricolors",
-  "trivialise": "trivialize",
-  "trivialised": "trivialized",
-  "trivialises": "trivializes",
-  "trivialising": "trivializing",
-  "tumour": "tumor",
-  "tumours": "tumors",
-  "tunnelled": "tunneled",
-  "tunnelling": "tunneling",
-  "tyrannise": "tyrannize",
-  "tyrannised": "tyrannized",
-  "tyrannises": "tyrannizes",
-  "tyrannising": "tyrannizing",
-  "tyre": "tire",
-  "tyres": "tires",
-  "unauthorised": "unauthorized",
-  "uncivilised": "uncivilized",
-  "underutilised": "underutilized",
-  "unequalled": "unequaled",
-  "unfavourable": "unfavorable",
-  "unfavourably": "unfavorably",
-  "unionisation": "unionization",
-  "unionise": "unionize",
-  "unionised": "unionized",
-  "unionises": "unionizes",
-  "unionising": "unionizing",
-  "unorganised": "unorganized",
-  "unravelled": "unraveled",
-  "unravelling": "unraveling",
-  "unrecognisable": "unrecognizable",
-  "unrecognised": "unrecognized",
-  "unrivalled": "unrivaled",
-  "unsavoury": "unsavory",
-  "untrammelled": "untrammeled",
-  "urbanisation": "urbanization",
-  "urbanise": "urbanize",
-  "urbanised": "urbanized",
-  "urbanises": "urbanizes",
-  "urbanising": "urbanizing",
-  "utilisable": "utilizable",
-  "utilisation": "utilization",
-  "utilise": "utilize",
-  "utilised": "utilized",
-  "utilises": "utilizes",
-  "utilising": "utilizing",
-  "valour": "valor",
-  "vandalise": "vandalize",
-  "vandalised": "vandalized",
-  "vandalises": "vandalizes",
-  "vandalising": "vandalizing",
-  "vaporisation": "vaporization",
-  "vaporise": "vaporize",
-  "vaporised": "vaporized",
-  "vaporises": "vaporizes",
-  "vaporising": "vaporizing",
-  "vapour": "vapor",
-  "vapours": "vapors",
-  "verbalise": "verbalize",
-  "verbalised": "verbalized",
-  "verbalises": "verbalizes",
-  "verbalising": "verbalizing",
-  "victimisation": "victimization",
-  "victimise": "victimize",
-  "victimised": "victimized",
-  "victimises": "victimizes",
-  "victimising": "victimizing",
-  "videodisc": "videodisk",
-  "videodiscs": "videodisks",
-  "vigour": "vigor",
-  "visualisation": "visualization",
-  "visualisations": "visualizations",
-  "visualise": "visualize",
-  "visualised": "visualized",
-  "visualises": "visualizes",
-  "visualising": "visualizing",
-  "vocalisation": "vocalization",
-  "vocalisations": "vocalizations",
-  "vocalise": "vocalize",
-  "vocalised": "vocalized",
-  "vocalises": "vocalizes",
-  "vocalising": "vocalizing",
-  "vulcanised": "vulcanized",
-  "vulgarisation": "vulgarization",
-  "vulgarise": "vulgarize",
-  "vulgarised": "vulgarized",
-  "vulgarises": "vulgarizes",
-  "vulgarising": "vulgarizing",
-  "waggon": "wagon",
-  "waggons": "wagons",
-  "watercolour": "watercolor",
-  "watercolours": "watercolors",
-  "weaselled": "weaseled",
-  "weaselling": "weaseling",
-  "westernisation": "westernization",
-  "westernise": "westernize",
-  "westernised": "westernized",
-  "westernises": "westernizes",
-  "westernising": "westernizing",
-  "womanise": "womanize",
-  "womanised": "womanized",
-  "womaniser": "womanizer",
-  "womanisers": "womanizers",
-  "womanises": "womanizes",
-  "womanising": "womanizing",
-  "woollen": "woolen",
-  "woollens": "woolens",
-  "woollies": "woolies",
-  "woolly": "wooly",
-  "worshipped": "worshiped",
-  "worshipper": "worshiper",
-  "worshipping": "worshiping",
-  "yodelled": "yodeled",
-  "yodelling": "yodeling",
-  "yoghourt": "yogurt",
-  "yoghourts": "yogurts",
-  "yoghurt": "yogurt",
-  "yoghurts": "yogurts"
-}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b7db43722c09d7b27c717393cd01d6cbbb0a0bfed84454c6a435e84f2c91e3
+oid sha256:70a0558d32f090315b932d793e742d46101a6286e87e680c5fecb4a2c0ed862e
 size 967102601

runs/May15_12-08-38_DESKTOP-OD7C1Q6/1684130924.7925029/events.out.tfevents.1684130924.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe9bb07ee7147ed13370775248e8175483467d394f172e9df238681872eb6fdb
-size 5703

runs/May15_12-08-38_DESKTOP-OD7C1Q6/events.out.tfevents.1684130924.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:71fd799105968dd35d677c29854f23281e86af2c6d3f7bbed8c24da422c9f048
-size 4653

runs/May15_12-15-25_DESKTOP-OD7C1Q6/1684131331.9202273/events.out.tfevents.1684131331.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:995a70cbd10c9b915a4f03748e27c73a22c77ffd02c4f73e76d933de2d638600
-size 5703

runs/May15_12-15-25_DESKTOP-OD7C1Q6/events.out.tfevents.1684131331.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9591d48d0b369e45899d52da758713c70d27066f1fe17d2dc1734ab6622567a4
-size 4653

runs/May15_13-19-50_DESKTOP-OD7C1Q6/1684135196.836124/events.out.tfevents.1684135196.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d6332a943560b994b9e1c5e6fea83e2dbdfbfc566ec1f3c3487dbad891fc685
-size 5703

runs/May15_13-19-50_DESKTOP-OD7C1Q6/events.out.tfevents.1684135196.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe27f44c89226fe5ca8a0f988fc02e971cca6d52aab2909f258876b025018a19
-size 4653

runs/May15_13-32-25_DESKTOP-OD7C1Q6/1684135953.274833/events.out.tfevents.1684135953.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c9922d8fc99c889753ff3f067c78ba4d3a11a47b9f3daecdce75d8ed0a78066e
-size 5703

runs/May15_13-32-25_DESKTOP-OD7C1Q6/events.out.tfevents.1684135953.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95377feb15e59e0a2f1d3ab8f81cbc31e0a49d1f3012e6d07681da11dc886a0b
-size 4653

runs/May15_14-04-02_DESKTOP-OD7C1Q6/1684137848.1832855/events.out.tfevents.1684137848.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:213d087e3fb61f154c8694c09d30bad5bc3109226fa1d9e566507382d0ae45ac
-size 5703

runs/May15_14-04-02_DESKTOP-OD7C1Q6/events.out.tfevents.1684137848.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7758c998ec59f03b698b9a3b2ff1658d99c5ad33b25f4b80a6812c8704330234
-size 4653

runs/May15_14-48-43_DESKTOP-OD7C1Q6/1684140528.8114798/events.out.tfevents.1684140528.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:90a6ecc9f4a4c81927451d61f7496b6ec064be68188e9a7cb73f32db8a39d440
-size 5703

runs/May15_14-48-43_DESKTOP-OD7C1Q6/events.out.tfevents.1684140528.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b4846721872455fd2d2ff248594f373c2fcbb7033960a086c99d64ca397b51e
-size 4651

runs/May15_14-59-56_DESKTOP-OD7C1Q6/1684141202.0174327/events.out.tfevents.1684141202.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:af86acda2ac7b5492bc1b3dfc2156f198c0bedf8169be3a02e4c522d93967cc0
-size 5703

runs/May15_14-59-56_DESKTOP-OD7C1Q6/events.out.tfevents.1684141202.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11bcb7ce9661734f1b0632c3bced8caceffa4bc12d7e2bcda30ba9676a9e1579
-size 4651

runs/May15_15-12-20_DESKTOP-OD7C1Q6/1684141947.2878134/events.out.tfevents.1684141947.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fbc6a7bb119f6716a0f6973d4581c27d654a865cbb15222f5e8c7aec7dbc3219
-size 5703

runs/May15_15-12-20_DESKTOP-OD7C1Q6/events.out.tfevents.1684141947.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:895a151daf82bdf531cbe4831fcf8d893b9d259cd6e658799427af55a66543a0
-size 4651

runs/May15_15-29-19_DESKTOP-OD7C1Q6/1684142964.8228638/events.out.tfevents.1684142964.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b32d2bb64351a9127b77d7aa942ea6ebad69ebfedf460670004aad6b50f5c4f
-size 5703

runs/May15_15-29-19_DESKTOP-OD7C1Q6/events.out.tfevents.1684142964.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:878bc7a54e38676db288d52bc9e371752ce156e84aeb59c75ba2d4849aac0d51
-size 4652

runs/May15_15-47-11_DESKTOP-OD7C1Q6/1684144037.0687504/events.out.tfevents.1684144037.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:047eac77f0811a1700aa302de08a6039dbef0aebe4ce56344ead0062a466104e
-size 5703

runs/May15_15-47-11_DESKTOP-OD7C1Q6/events.out.tfevents.1684144037.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d450b8be43c3c9af390685b9f4c2c389f884b6d76e24b074f75f69fb6aafd00
-size 5305

runs/May15_15-47-11_DESKTOP-OD7C1Q6/events.out.tfevents.1684144731.DESKTOP-OD7C1Q6

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2aef58d48fc6abdae3c1509a074d50455a62a6510ae62a0eb8365f93862817d7
-size 40

runs/{May13_23-09-22_DESKTOP-OD7C1Q6/1683997770.2403045/events.out.tfevents.1683997770.DESKTOP-OD7C1Q6 → May15_16-55-04_DESKTOP-OD7C1Q6/1684148109.9478214/events.out.tfevents.1684148109.DESKTOP-OD7C1Q6}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b1ab019a8e871e28c10a48cdb1416e162572c30d2af32033600a2fc2991bfa
-size 5703
+oid sha256:fbd2d3c6d2a78470ee2e09b7e00686e640c9a5c821bf5ef7d2efd7a1053cad75
+size 5841

runs/{May13_23-09-22_DESKTOP-OD7C1Q6/events.out.tfevents.1683997770.DESKTOP-OD7C1Q6 → May15_16-55-04_DESKTOP-OD7C1Q6/events.out.tfevents.1684148109.DESKTOP-OD7C1Q6}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:606040c60ee7708fa1dbad905eca79a7cc664c90dbdcffcd12bad8348a09e774
-size 4652
+oid sha256:b36951b2c94b6cd36f420649b1cadfd923728f2888493bb08e5496b19de6884a
+size 8016

runs/{May15_11-17-07_DESKTOP-OD7C1Q6/1684127833.5408869/events.out.tfevents.1684127833.DESKTOP-OD7C1Q6 → May15_22-40-19_DESKTOP-OD7C1Q6/1684168824.9625106/events.out.tfevents.1684168824.DESKTOP-OD7C1Q6}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189723d8061b53912805ea4ef9844b48e639b30b44e3f8c96cd157052005777b
-size 5703
+oid sha256:7175c9a71b9fc363128a8e188589c9821513a6e490763e38556788f9be25b0e8
+size 5841

runs/{May15_11-17-07_DESKTOP-OD7C1Q6/events.out.tfevents.1684127833.DESKTOP-OD7C1Q6 → May15_22-40-19_DESKTOP-OD7C1Q6/events.out.tfevents.1684168824.DESKTOP-OD7C1Q6}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d8ce96f93a61adef1f60c1ab18d0b1e82e4a5f31ceec9900c5d914b68de370
-size 4653
+oid sha256:bfa01668cd97f52fc93b6bfed9c83a78013bc282e264501ef890a1d36706eb00
+size 11364

special_tokens_map.json

@@ -1,133 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<|startoftranscript|>",
-    "<|en|>",
-    "<|zh|>",
-    "<|de|>",
-    "<|es|>",
-    "<|ru|>",
-    "<|ko|>",
-    "<|fr|>",
-    "<|ja|>",
-    "<|pt|>",
-    "<|tr|>",
-    "<|pl|>",
-    "<|ca|>",
-    "<|nl|>",
-    "<|ar|>",
-    "<|sv|>",
-    "<|it|>",
-    "<|id|>",
-    "<|hi|>",
-    "<|fi|>",
-    "<|vi|>",
-    "<|he|>",
-    "<|uk|>",
-    "<|el|>",
-    "<|ms|>",
-    "<|cs|>",
-    "<|ro|>",
-    "<|da|>",
-    "<|hu|>",
-    "<|ta|>",
-    "<|no|>",
-    "<|th|>",
-    "<|ur|>",
-    "<|hr|>",
-    "<|bg|>",
-    "<|lt|>",
-    "<|la|>",
-    "<|mi|>",
-    "<|ml|>",
-    "<|cy|>",
-    "<|sk|>",
-    "<|te|>",
-    "<|fa|>",
-    "<|lv|>",
-    "<|bn|>",
-    "<|sr|>",
-    "<|az|>",
-    "<|sl|>",
-    "<|kn|>",
-    "<|et|>",
-    "<|mk|>",
-    "<|br|>",
-    "<|eu|>",
-    "<|is|>",
-    "<|hy|>",
-    "<|ne|>",
-    "<|mn|>",
-    "<|bs|>",
-    "<|kk|>",
-    "<|sq|>",
-    "<|sw|>",
-    "<|gl|>",
-    "<|mr|>",
-    "<|pa|>",
-    "<|si|>",
-    "<|km|>",
-    "<|sn|>",
-    "<|yo|>",
-    "<|so|>",
-    "<|af|>",
-    "<|oc|>",
-    "<|ka|>",
-    "<|be|>",
-    "<|tg|>",
-    "<|sd|>",
-    "<|gu|>",
-    "<|am|>",
-    "<|yi|>",
-    "<|lo|>",
-    "<|uz|>",
-    "<|fo|>",
-    "<|ht|>",
-    "<|ps|>",
-    "<|tk|>",
-    "<|nn|>",
-    "<|mt|>",
-    "<|sa|>",
-    "<|lb|>",
-    "<|my|>",
-    "<|bo|>",
-    "<|tl|>",
-    "<|mg|>",
-    "<|as|>",
-    "<|tt|>",
-    "<|haw|>",
-    "<|ln|>",
-    "<|ha|>",
-    "<|ba|>",
-    "<|jw|>",
-    "<|su|>",
-    "<|translate|>",
-    "<|transcribe|>",
-    "<|startoflm|>",
-    "<|startofprev|>",
-    "<|nocaptions|>",
-    "<|notimestamps|>"
-  ],
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer_config.json

@@ -1,35 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 1024,
-  "pad_token": null,
-  "processor_class": "WhisperProcessor",
-  "return_attention_mask": false,
-  "special_tokens_map_file": null,
-  "tokenizer_class": "WhisperTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

train_results.json

@@ -1,7 +0,0 @@
-{
-    "epoch": 1.31,
-    "train_loss": 2.721541290283203,
-    "train_runtime": 665.7853,
-    "train_samples_per_second": 4.806,
-    "train_steps_per_second": 0.075
-}

trainer_state.json

@@ -1,37 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.3114754098360657,
-  "global_step": 50,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.66,
-      "learning_rate": 2.5000000000000004e-07,
-      "loss": 2.792,
-      "step": 25
-    },
-    {
-      "epoch": 1.31,
-      "learning_rate": 5.000000000000001e-07,
-      "loss": 2.651,
-      "step": 50
-    },
-    {
-      "epoch": 1.31,
-      "step": 50,
-      "total_flos": 9.2289611022336e+17,
-      "train_loss": 2.721541290283203,
-      "train_runtime": 665.7853,
-      "train_samples_per_second": 4.806,
-      "train_steps_per_second": 0.075
-    }
-  ],
-  "max_steps": 50,
-  "num_train_epochs": 2,
-  "total_flos": 9.2289611022336e+17,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f2b349d8fb07d165078798d56f36a2b9658e4125b02c036200330e9feede40
-size 3643
+oid sha256:c6927498f6d9e476fef21df4100ff020985091bef32f4658d85097f9b619e9cf
+size 4027