End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,60 @@
+---
+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

@@ -0,0 +1,108 @@
+{
+  "<|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

@@ -0,0 +1,13 @@
+{
+    "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/added_tokens.json

@@ -0,0 +1,108 @@
+{
+  "<|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
+}

best_model/normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "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"
+}

best_model/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

best_model/special_tokens_map.json

@@ -0,0 +1,133 @@
+{
+  "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
+  }
+}

best_model/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "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
+  }
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": true,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

corrupt_files.txt

@@ -0,0 +1,3718 @@
+# These files were identified has having issues due to failing text-audio alignment
+# between reference transcript and audio.
+
+common_voice_bn_30665285
+common_voice_bn_30665286
+common_voice_bn_30665287
+common_voice_bn_30665288
+common_voice_bn_30665290
+common_voice_bn_30665291
+common_voice_bn_30665294
+common_voice_bn_30665295
+common_voice_bn_30665296
+common_voice_bn_30665297
+common_voice_bn_30665298
+common_voice_bn_30677291
+common_voice_bn_30677292
+common_voice_bn_30677293
+common_voice_bn_30677294
+common_voice_bn_30677295
+common_voice_bn_30995469
+common_voice_bn_30995470
+common_voice_bn_30998934
+common_voice_bn_31000747
+common_voice_bn_31000750
+common_voice_bn_31000753
+common_voice_bn_31005676
+common_voice_bn_31005686
+common_voice_bn_31009001
+common_voice_bn_31011206
+common_voice_bn_31013329
+common_voice_bn_31013418
+common_voice_bn_31016821
+common_voice_bn_31016823
+common_voice_bn_31016825
+common_voice_bn_31016831
+common_voice_bn_31019660
+common_voice_bn_31019914
+common_voice_bn_31021589
+common_voice_bn_31021790
+common_voice_bn_31021831
+common_voice_bn_31021833
+common_voice_bn_31021834
+common_voice_bn_31021835
+common_voice_bn_31021847
+common_voice_bn_31021861
+common_voice_bn_31025585
+common_voice_bn_31026100
+common_voice_bn_31037299
+common_voice_bn_31043545
+common_voice_bn_31052304
+common_voice_bn_31174226
+common_voice_bn_31174227
+common_voice_bn_31217111
+common_voice_bn_31277603
+common_voice_bn_31362334
+common_voice_bn_31445621
+common_voice_bn_31497795
+common_voice_bn_31498452
+common_voice_bn_31498453
+common_voice_bn_31498455
+common_voice_bn_31498456
+common_voice_bn_31498467
+common_voice_bn_31498469
+common_voice_bn_31498470
+common_voice_bn_31498471
+common_voice_bn_31500246
+common_voice_bn_31500248
+common_voice_bn_31500250
+common_voice_bn_31500370
+common_voice_bn_31500372
+common_voice_bn_31500374
+common_voice_bn_31500444
+common_voice_bn_31500446
+common_voice_bn_31500447
+common_voice_bn_31500509
+common_voice_bn_31500511
+common_voice_bn_31500805
+common_voice_bn_31508353
+common_voice_bn_31508469
+common_voice_bn_31508593
+common_voice_bn_31508596
+common_voice_bn_31508652
+common_voice_bn_31508719
+common_voice_bn_31508987
+common_voice_bn_31508990
+common_voice_bn_31509003
+common_voice_bn_31509014
+common_voice_bn_31509079
+common_voice_bn_31509152
+common_voice_bn_31509201
+common_voice_bn_31509256
+common_voice_bn_31509356
+common_voice_bn_31509610
+common_voice_bn_31509722
+common_voice_bn_31509753
+common_voice_bn_31509771
+common_voice_bn_31509803
+common_voice_bn_31509808
+common_voice_bn_31509879
+common_voice_bn_31509983
+common_voice_bn_31510143
+common_voice_bn_31510163
+common_voice_bn_31510205
+common_voice_bn_31510212
+common_voice_bn_31510219
+common_voice_bn_31510223
+common_voice_bn_31510388
+common_voice_bn_31510468
+common_voice_bn_31510520
+common_voice_bn_31510909
+common_voice_bn_31511001
+common_voice_bn_31511003
+common_voice_bn_31511028
+common_voice_bn_31511211
+common_voice_bn_31511213
+common_voice_bn_31511298
+common_voice_bn_31511365
+common_voice_bn_31511378
+common_voice_bn_31511414
+common_voice_bn_31511666
+common_voice_bn_31511748
+common_voice_bn_31511759
+common_voice_bn_31511859
+common_voice_bn_31512000
+common_voice_bn_31512004
+common_voice_bn_31512204
+common_voice_bn_31512403
+common_voice_bn_31512543
+common_voice_bn_31512550
+common_voice_bn_31512816
+common_voice_bn_31512818
+common_voice_bn_31512832
+common_voice_bn_31513134
+common_voice_bn_31513221
+common_voice_bn_31513229
+common_voice_bn_31513256
+common_voice_bn_31513270
+common_voice_bn_31513308
+common_voice_bn_31513356
+common_voice_bn_31513517
+common_voice_bn_31513590
+common_voice_bn_31513841
+common_voice_bn_31513896
+common_voice_bn_31513922
+common_voice_bn_31513951
+common_voice_bn_31513994
+common_voice_bn_31514003
+common_voice_bn_31514010
+common_voice_bn_31514021
+common_voice_bn_31514143
+common_voice_bn_31514223
+common_voice_bn_31514369
+common_voice_bn_31514407
+common_voice_bn_31514428
+common_voice_bn_31514595
+common_voice_bn_31514624
+common_voice_bn_31514630
+common_voice_bn_31514639
+common_voice_bn_31514796
+common_voice_bn_31514857
+common_voice_bn_31514863
+common_voice_bn_31514873
+common_voice_bn_31515005
+common_voice_bn_31515025
+common_voice_bn_31515082
+common_voice_bn_31515083
+common_voice_bn_31515086
+common_voice_bn_31515089
+common_voice_bn_31515269
+common_voice_bn_31515482
+common_voice_bn_31515505
+common_voice_bn_31515527
+common_voice_bn_31515539
+common_voice_bn_31515579
+common_voice_bn_31515673
+common_voice_bn_31515694
+common_voice_bn_31515714
+common_voice_bn_31515758
+common_voice_bn_31515766
+common_voice_bn_31515788
+common_voice_bn_31515797
+common_voice_bn_31515815
+common_voice_bn_31515816
+common_voice_bn_31515823
+common_voice_bn_31515873
+common_voice_bn_31515898
+common_voice_bn_31515987
+common_voice_bn_31515998
+common_voice_bn_31516005
+common_voice_bn_31516007
+common_voice_bn_31516082
+common_voice_bn_31516234
+common_voice_bn_31516277
+common_voice_bn_31516280
+common_voice_bn_31516283
+common_voice_bn_31516300
+common_voice_bn_31516322
+common_voice_bn_31516338
+common_voice_bn_31516377
+common_voice_bn_31516433
+common_voice_bn_31516460
+common_voice_bn_31516550
+common_voice_bn_31516569
+common_voice_bn_31516609
+common_voice_bn_31516909
+common_voice_bn_31516925
+common_voice_bn_31517054
+common_voice_bn_31517120
+common_voice_bn_31517376
+common_voice_bn_31517392
+common_voice_bn_31517403
+common_voice_bn_31517532
+common_voice_bn_31517643
+common_voice_bn_31517650
+common_voice_bn_31517652
+common_voice_bn_31517655
+common_voice_bn_31517664
+common_voice_bn_31517847
+common_voice_bn_31517855
+common_voice_bn_31517862
+common_voice_bn_31518009
+common_voice_bn_31518022
+common_voice_bn_31518061
+common_voice_bn_31518191
+common_voice_bn_31518357
+common_voice_bn_31518373
+common_voice_bn_31518626
+common_voice_bn_31518852
+common_voice_bn_31518878
+common_voice_bn_31518894
+common_voice_bn_31519067
+common_voice_bn_31519093
+common_voice_bn_31519196
+common_voice_bn_31519242
+common_voice_bn_31519289
+common_voice_bn_31519295
+common_voice_bn_31519319
+common_voice_bn_31519327
+common_voice_bn_31519341
+common_voice_bn_31519517
+common_voice_bn_31519523
+common_voice_bn_31519692
+common_voice_bn_31519747
+common_voice_bn_31519775
+common_voice_bn_31519868
+common_voice_bn_31519879
+common_voice_bn_31519915
+common_voice_bn_31519924
+common_voice_bn_31519976
+common_voice_bn_31520024
+common_voice_bn_31520029
+common_voice_bn_31520036
+common_voice_bn_31520045
+common_voice_bn_31520157
+common_voice_bn_31520174
+common_voice_bn_31520317
+common_voice_bn_31520417
+common_voice_bn_31520521
+common_voice_bn_31520741
+common_voice_bn_31520804
+common_voice_bn_31520812
+common_voice_bn_31520826
+common_voice_bn_31521025
+common_voice_bn_31521122
+common_voice_bn_31521124
+common_voice_bn_31521259
+common_voice_bn_31521397
+common_voice_bn_31521405
+common_voice_bn_31521407
+common_voice_bn_31521515
+common_voice_bn_31521580
+common_voice_bn_31521643
+common_voice_bn_31521687
+common_voice_bn_31521753
+common_voice_bn_31521846
+common_voice_bn_31521866
+common_voice_bn_31522003
+common_voice_bn_31522008
+common_voice_bn_31522014
+common_voice_bn_31522023
+common_voice_bn_31522030
+common_voice_bn_31522098
+common_voice_bn_31522217
+common_voice_bn_31522336
+common_voice_bn_31522340
+common_voice_bn_31522430
+common_voice_bn_31522515
+common_voice_bn_31522534
+common_voice_bn_31522556
+common_voice_bn_31522565
+common_voice_bn_31522569
+common_voice_bn_31522615
+common_voice_bn_31522712
+common_voice_bn_31522718
+common_voice_bn_31522853
+common_voice_bn_31522859
+common_voice_bn_31522995
+common_voice_bn_31523000
+common_voice_bn_31523005
+common_voice_bn_31523006
+common_voice_bn_31523053
+common_voice_bn_31523196
+common_voice_bn_31523205
+common_voice_bn_31523212
+common_voice_bn_31523220
+common_voice_bn_31523222
+common_voice_bn_31523305
+common_voice_bn_31523342
+common_voice_bn_31523429
+common_voice_bn_31523441
+common_voice_bn_31523450
+common_voice_bn_31523469
+common_voice_bn_31523595
+common_voice_bn_31523597
+common_voice_bn_31523600
+common_voice_bn_31523689
+common_voice_bn_31523696
+common_voice_bn_31523701
+common_voice_bn_31523704
+common_voice_bn_31523889
+common_voice_bn_31523916
+common_voice_bn_31523925
+common_voice_bn_31523930
+common_voice_bn_31523934
+common_voice_bn_31524003
+common_voice_bn_31524010
+common_voice_bn_31524026
+common_voice_bn_31524123
+common_voice_bn_31524126
+common_voice_bn_31524216
+common_voice_bn_31524222
+common_voice_bn_31524249
+common_voice_bn_31524479
+common_voice_bn_31524844
+common_voice_bn_31524852
+common_voice_bn_31524858
+common_voice_bn_31524861
+common_voice_bn_31524870
+common_voice_bn_31524967
+common_voice_bn_31524982
+common_voice_bn_31525122
+common_voice_bn_31525127
+common_voice_bn_31525140
+common_voice_bn_31525297
+common_voice_bn_31525301
+common_voice_bn_31525310
+common_voice_bn_31525689
+common_voice_bn_31525699
+common_voice_bn_31525704
+common_voice_bn_31525711
+common_voice_bn_31525724
+common_voice_bn_31525730
+common_voice_bn_31525731
+common_voice_bn_31525747
+common_voice_bn_31525757
+common_voice_bn_31525764
+common_voice_bn_31525773
+common_voice_bn_31525794
+common_voice_bn_31525817
+common_voice_bn_31525832
+common_voice_bn_31525839
+common_voice_bn_31525846
+common_voice_bn_31525858
+common_voice_bn_31526072
+common_voice_bn_31526082
+common_voice_bn_31526197
+common_voice_bn_31526200
+common_voice_bn_31526203
+common_voice_bn_31526372
+common_voice_bn_31526401
+common_voice_bn_31526402
+common_voice_bn_31526497
+common_voice_bn_31526500
+common_voice_bn_31526514
+common_voice_bn_31526543
+common_voice_bn_31526545
+common_voice_bn_31526549
+common_voice_bn_31526613
+common_voice_bn_31526627
+common_voice_bn_31526673
+common_voice_bn_31526676
+common_voice_bn_31526681
+common_voice_bn_31526689
+common_voice_bn_31526760
+common_voice_bn_31526819
+common_voice_bn_31526821
+common_voice_bn_31526833
+common_voice_bn_31526844
+common_voice_bn_31526852
+common_voice_bn_31526875
+common_voice_bn_31526877
+common_voice_bn_31527198
+common_voice_bn_31527223
+common_voice_bn_31527224
+common_voice_bn_31527331
+common_voice_bn_31527336
+common_voice_bn_31527341
+common_voice_bn_31527466
+common_voice_bn_31527563
+common_voice_bn_31527588
+common_voice_bn_31527593
+common_voice_bn_31527696
+common_voice_bn_31527766
+common_voice_bn_31528179
+common_voice_bn_31528290
+common_voice_bn_31528291
+common_voice_bn_31528297
+common_voice_bn_31528300
+common_voice_bn_31528306
+common_voice_bn_31528309
+common_voice_bn_31528489
+common_voice_bn_31528497
+common_voice_bn_31528499
+common_voice_bn_31528633
+common_voice_bn_31528635
+common_voice_bn_31528637
+common_voice_bn_31528652
+common_voice_bn_31528657
+common_voice_bn_31528667
+common_voice_bn_31528670
+common_voice_bn_31528953
+common_voice_bn_31529063
+common_voice_bn_31529083
+common_voice_bn_31529086
+common_voice_bn_31529127
+common_voice_bn_31529171
+common_voice_bn_31529186
+common_voice_bn_31529212
+common_voice_bn_31529301
+common_voice_bn_31529473
+common_voice_bn_31529871
+common_voice_bn_31529924
+common_voice_bn_31529929
+common_voice_bn_31529934
+common_voice_bn_31529938
+common_voice_bn_31530055
+common_voice_bn_31530060
+common_voice_bn_31530065
+common_voice_bn_31530100
+common_voice_bn_31530147
+common_voice_bn_31530261
+common_voice_bn_31530267
+common_voice_bn_31530331
+common_voice_bn_31530419
+common_voice_bn_31530482
+common_voice_bn_31530832
+common_voice_bn_31530951
+common_voice_bn_31530953
+common_voice_bn_31531040
+common_voice_bn_31531189
+common_voice_bn_31531192
+common_voice_bn_31531302
+common_voice_bn_31531672
+common_voice_bn_31531681
+common_voice_bn_31531682
+common_voice_bn_31531831
+common_voice_bn_31531855
+common_voice_bn_31531879
+common_voice_bn_31531924
+common_voice_bn_31531948
+common_voice_bn_31531954
+common_voice_bn_31531957
+common_voice_bn_31531966
+common_voice_bn_31531975
+common_voice_bn_31531996
+common_voice_bn_31531999
+common_voice_bn_31532003
+common_voice_bn_31532019
+common_voice_bn_31532035
+common_voice_bn_31532114
+common_voice_bn_31532115
+common_voice_bn_31532152
+common_voice_bn_31532188
+common_voice_bn_31532222
+common_voice_bn_31532330
+common_voice_bn_31532336
+common_voice_bn_31532343
+common_voice_bn_31532419
+common_voice_bn_31532422
+common_voice_bn_31532428
+common_voice_bn_31532596
+common_voice_bn_31532633
+common_voice_bn_31532639
+common_voice_bn_31532644
+common_voice_bn_31532647
+common_voice_bn_31532820
+common_voice_bn_31532829
+common_voice_bn_31532834
+common_voice_bn_31532837
+common_voice_bn_31532843
+common_voice_bn_31533113
+common_voice_bn_31533120
+common_voice_bn_31533134
+common_voice_bn_31533273
+common_voice_bn_31533429
+common_voice_bn_31533496
+common_voice_bn_31533568
+common_voice_bn_31533620
+common_voice_bn_31533858
+common_voice_bn_31533999
+common_voice_bn_31534171
+common_voice_bn_31534241
+common_voice_bn_31534567
+common_voice_bn_31534730
+common_voice_bn_31534774
+common_voice_bn_31534777
+common_voice_bn_31534853
+common_voice_bn_31535156
+common_voice_bn_31535190
+common_voice_bn_31535194
+common_voice_bn_31535198
+common_voice_bn_31535199
+common_voice_bn_31535485
+common_voice_bn_31535579
+common_voice_bn_31535586
+common_voice_bn_31535590
+common_voice_bn_31535594
+common_voice_bn_31535764
+common_voice_bn_31535768
+common_voice_bn_31535770
+common_voice_bn_31535978
+common_voice_bn_31535983
+common_voice_bn_31536120
+common_voice_bn_31536417
+common_voice_bn_31536515
+common_voice_bn_31536726
+common_voice_bn_31536728
+common_voice_bn_31536730
+common_voice_bn_31536888
+common_voice_bn_31536970
+common_voice_bn_31536972
+common_voice_bn_31537068
+common_voice_bn_31537152
+common_voice_bn_31537253
+common_voice_bn_31537257
+common_voice_bn_31537260
+common_voice_bn_31537282
+common_voice_bn_31537333
+common_voice_bn_31537416
+common_voice_bn_31537822
+common_voice_bn_31538019
+common_voice_bn_31538050
+common_voice_bn_31538142
+common_voice_bn_31538269
+common_voice_bn_31538294
+common_voice_bn_31538443
+common_voice_bn_31538723
+common_voice_bn_31538917
+common_voice_bn_31539292
+common_voice_bn_31539380
+common_voice_bn_31539408
+common_voice_bn_31539495
+common_voice_bn_31539499
+common_voice_bn_31539513
+common_voice_bn_31539582
+common_voice_bn_31539640
+common_voice_bn_31539643
+common_voice_bn_31539863
+common_voice_bn_31539877
+common_voice_bn_31539941
+common_voice_bn_31540166
+common_voice_bn_31540168
+common_voice_bn_31540184
+common_voice_bn_31540192
+common_voice_bn_31540229
+common_voice_bn_31540242
+common_voice_bn_31540303
+common_voice_bn_31540306
+common_voice_bn_31540311
+common_voice_bn_31540372
+common_voice_bn_31540397
+common_voice_bn_31540400
+common_voice_bn_31540408
+common_voice_bn_31540411
+common_voice_bn_31540554
+common_voice_bn_31540557
+common_voice_bn_31540562
+common_voice_bn_31540679
+common_voice_bn_31540690
+common_voice_bn_31540721
+common_voice_bn_31540787
+common_voice_bn_31540791
+common_voice_bn_31540792
+common_voice_bn_31540801
+common_voice_bn_31540808
+common_voice_bn_31540812
+common_voice_bn_31540871
+common_voice_bn_31540958
+common_voice_bn_31540960
+common_voice_bn_31541201
+common_voice_bn_31541440
+common_voice_bn_31541521
+common_voice_bn_31541660
+common_voice_bn_31541664
+common_voice_bn_31541669
+common_voice_bn_31541820
+common_voice_bn_31541830
+common_voice_bn_31541832
+common_voice_bn_31541835
+common_voice_bn_31541912
+common_voice_bn_31542009
+common_voice_bn_31542190
+common_voice_bn_31542381
+common_voice_bn_31542474
+common_voice_bn_31542476
+common_voice_bn_31542482
+common_voice_bn_31542559
+common_voice_bn_31542760
+common_voice_bn_31542763
+common_voice_bn_31542814
+common_voice_bn_31542849
+common_voice_bn_31542863
+common_voice_bn_31542899
+common_voice_bn_31542976
+common_voice_bn_31543398
+common_voice_bn_31543523
+common_voice_bn_31543601
+common_voice_bn_31543635
+common_voice_bn_31543674
+common_voice_bn_31543677
+common_voice_bn_31543687
+common_voice_bn_31543691
+common_voice_bn_31543699
+common_voice_bn_31543828
+common_voice_bn_31543833
+common_voice_bn_31543931
+common_voice_bn_31543933
+common_voice_bn_31543934
+common_voice_bn_31543991
+common_voice_bn_31544066
+common_voice_bn_31544213
+common_voice_bn_31544273
+common_voice_bn_31544360
+common_voice_bn_31544364
+common_voice_bn_31544366
+common_voice_bn_31544367
+common_voice_bn_31544369
+common_voice_bn_31544406
+common_voice_bn_31544460
+common_voice_bn_31544461
+common_voice_bn_31544462
+common_voice_bn_31544463
+common_voice_bn_31544465
+common_voice_bn_31544510
+common_voice_bn_31544520
+common_voice_bn_31544523
+common_voice_bn_31544529
+common_voice_bn_31544531
+common_voice_bn_31544532
+common_voice_bn_31544569
+common_voice_bn_31544651
+common_voice_bn_31544678
+common_voice_bn_31544683
+common_voice_bn_31544693
+common_voice_bn_31544786
+common_voice_bn_31544788
+common_voice_bn_31545029
+common_voice_bn_31545032
+common_voice_bn_31545825
+common_voice_bn_31545828
+common_voice_bn_31546134
+common_voice_bn_31546171
+common_voice_bn_31546172
+common_voice_bn_31546175
+common_voice_bn_31546431
+common_voice_bn_31546440
+common_voice_bn_31546477
+common_voice_bn_31546480
+common_voice_bn_31546481
+common_voice_bn_31546532
+common_voice_bn_31546557
+common_voice_bn_31546744
+common_voice_bn_31547044
+common_voice_bn_31547045
+common_voice_bn_31547046
+common_voice_bn_31547048
+common_voice_bn_31547556
+common_voice_bn_31547559
+common_voice_bn_31547679
+common_voice_bn_31547681
+common_voice_bn_31547683
+common_voice_bn_31547707
+common_voice_bn_31547820
+common_voice_bn_31547895
+common_voice_bn_31547900
+common_voice_bn_31547937
+common_voice_bn_31547965
+common_voice_bn_31548235
+common_voice_bn_31548343
+common_voice_bn_31548409
+common_voice_bn_31548463
+common_voice_bn_31548573
+common_voice_bn_31548593
+common_voice_bn_31548638
+common_voice_bn_31548641
+common_voice_bn_31548644
+common_voice_bn_31548714
+common_voice_bn_31548744
+common_voice_bn_31548745
+common_voice_bn_31548862
+common_voice_bn_31548878
+common_voice_bn_31549074
+common_voice_bn_31549075
+common_voice_bn_31549164
+common_voice_bn_31549167
+common_voice_bn_31549169
+common_voice_bn_31549249
+common_voice_bn_31549526
+common_voice_bn_31549716
+common_voice_bn_31550180
+common_voice_bn_31550182
+common_voice_bn_31550183
+common_voice_bn_31550187
+common_voice_bn_31550338
+common_voice_bn_31550340
+common_voice_bn_31550341
+common_voice_bn_31550342
+common_voice_bn_31550452
+common_voice_bn_31550453
+common_voice_bn_31550454
+common_voice_bn_31550456
+common_voice_bn_31550459
+common_voice_bn_31550475
+common_voice_bn_31550477
+common_voice_bn_31550617
+common_voice_bn_31550619
+common_voice_bn_31551087
+common_voice_bn_31551090
+common_voice_bn_31551094
+common_voice_bn_31551144
+common_voice_bn_31551208
+common_voice_bn_31551212
+common_voice_bn_31551215
+common_voice_bn_31551226
+common_voice_bn_31551584
+common_voice_bn_31551634
+common_voice_bn_31551793
+common_voice_bn_31551796
+common_voice_bn_31551798
+common_voice_bn_31552162
+common_voice_bn_31552193
+common_voice_bn_31552326
+common_voice_bn_31552443
+common_voice_bn_31552561
+common_voice_bn_31552568
+common_voice_bn_31552638
+common_voice_bn_31552665
+common_voice_bn_31552666
+common_voice_bn_31552668
+common_voice_bn_31552669
+common_voice_bn_31552676
+common_voice_bn_31552823
+common_voice_bn_31552824
+common_voice_bn_31552864
+common_voice_bn_31552868
+common_voice_bn_31552897
+common_voice_bn_31552944
+common_voice_bn_31552947
+common_voice_bn_31552984
+common_voice_bn_31552985
+common_voice_bn_31553034
+common_voice_bn_31553249
+common_voice_bn_31553251
+common_voice_bn_31553337
+common_voice_bn_31553339
+common_voice_bn_31553341
+common_voice_bn_31553733
+common_voice_bn_31553743
+common_voice_bn_31553744
+common_voice_bn_31553870
+common_voice_bn_31553871
+common_voice_bn_31553872
+common_voice_bn_31553873
+common_voice_bn_31553936
+common_voice_bn_31553938
+common_voice_bn_31553939
+common_voice_bn_31554444
+common_voice_bn_31554445
+common_voice_bn_31554500
+common_voice_bn_31554501
+common_voice_bn_31554502
+common_voice_bn_31554642
+common_voice_bn_31554712
+common_voice_bn_31555261
+common_voice_bn_31555333
+common_voice_bn_31555529
+common_voice_bn_31555621
+common_voice_bn_31555623
+common_voice_bn_31555639
+common_voice_bn_31555653
+common_voice_bn_31555655
+common_voice_bn_31555657
+common_voice_bn_31555673
+common_voice_bn_31555674
+common_voice_bn_31555890
+common_voice_bn_31555894
+common_voice_bn_31555899
+common_voice_bn_31555938
+common_voice_bn_31555943
+common_voice_bn_31555958
+common_voice_bn_31555959
+common_voice_bn_31555968
+common_voice_bn_31556001
+common_voice_bn_31556094
+common_voice_bn_31556095
+common_voice_bn_31556132
+common_voice_bn_31556149
+common_voice_bn_31556384
+common_voice_bn_31556539
+common_voice_bn_31556570
+common_voice_bn_31556601
+common_voice_bn_31556642
+common_voice_bn_31556685
+common_voice_bn_31556713
+common_voice_bn_31556782
+common_voice_bn_31556834
+common_voice_bn_31556959
+common_voice_bn_31556962
+common_voice_bn_31556966
+common_voice_bn_31556967
+common_voice_bn_31557002
+common_voice_bn_31557003
+common_voice_bn_31557004
+common_voice_bn_31557005
+common_voice_bn_31557122
+common_voice_bn_31557125
+common_voice_bn_31557215
+common_voice_bn_31557217
+common_voice_bn_31557261
+common_voice_bn_31557392
+common_voice_bn_31557393
+common_voice_bn_31557492
+common_voice_bn_31557494
+common_voice_bn_31557496
+common_voice_bn_31557498
+common_voice_bn_31557550
+common_voice_bn_31557552
+common_voice_bn_31557572
+common_voice_bn_31557637
+common_voice_bn_31557638
+common_voice_bn_31557642
+common_voice_bn_31557676
+common_voice_bn_31557864
+common_voice_bn_31557866
+common_voice_bn_31557971
+common_voice_bn_31557972
+common_voice_bn_31557973
+common_voice_bn_31558022
+common_voice_bn_31558045
+common_voice_bn_31558047
+common_voice_bn_31558154
+common_voice_bn_31558200
+common_voice_bn_31558345
+common_voice_bn_31558346
+common_voice_bn_31558678
+common_voice_bn_31558707
+common_voice_bn_31558708
+common_voice_bn_31558709
+common_voice_bn_31558773
+common_voice_bn_31558872
+common_voice_bn_31559180
+common_voice_bn_31559540
+common_voice_bn_31559542
+common_voice_bn_31559544
+common_voice_bn_31559549
+common_voice_bn_31559559
+common_voice_bn_31559813
+common_voice_bn_31559826
+common_voice_bn_31560022
+common_voice_bn_31560138
+common_voice_bn_31560397
+common_voice_bn_31560400
+common_voice_bn_31560401
+common_voice_bn_31560695
+common_voice_bn_31560699
+common_voice_bn_31560703
+common_voice_bn_31560766
+common_voice_bn_31560801
+common_voice_bn_31560879
+common_voice_bn_31560882
+common_voice_bn_31560903
+common_voice_bn_31561039
+common_voice_bn_31561042
+common_voice_bn_31561386
+common_voice_bn_31561568
+common_voice_bn_31561955
+common_voice_bn_31562016
+common_voice_bn_31562021
+common_voice_bn_31562067
+common_voice_bn_31562068
+common_voice_bn_31562186
+common_voice_bn_31562189
+common_voice_bn_31562476
+common_voice_bn_31562480
+common_voice_bn_31562485
+common_voice_bn_31562486
+common_voice_bn_31562594
+common_voice_bn_31562595
+common_voice_bn_31562597
+common_voice_bn_31562622
+common_voice_bn_31562625
+common_voice_bn_31562636
+common_voice_bn_31562786
+common_voice_bn_31562876
+common_voice_bn_31562915
+common_voice_bn_31563025
+common_voice_bn_31563027
+common_voice_bn_31563029
+common_voice_bn_31563058
+common_voice_bn_31563107
+common_voice_bn_31563108
+common_voice_bn_31563443
+common_voice_bn_31563476
+common_voice_bn_31563557
+common_voice_bn_31563767
+common_voice_bn_31563901
+common_voice_bn_31564072
+common_voice_bn_31564073
+common_voice_bn_31564074
+common_voice_bn_31564076
+common_voice_bn_31564146
+common_voice_bn_31564148
+common_voice_bn_31564151
+common_voice_bn_31564155
+common_voice_bn_31564156
+common_voice_bn_31564226
+common_voice_bn_31564228
+common_voice_bn_31564250
+common_voice_bn_31564283
+common_voice_bn_31564284
+common_voice_bn_31564285
+common_voice_bn_31564287
+common_voice_bn_31564292
+common_voice_bn_31564297
+common_voice_bn_31564318
+common_voice_bn_31564355
+common_voice_bn_31564357
+common_voice_bn_31564358
+common_voice_bn_31564407
+common_voice_bn_31564410
+common_voice_bn_31564412
+common_voice_bn_31564491
+common_voice_bn_31564507
+common_voice_bn_31564529
+common_voice_bn_31564546
+common_voice_bn_31564547
+common_voice_bn_31564549
+common_voice_bn_31564550
+common_voice_bn_31564579
+common_voice_bn_31564581
+common_voice_bn_31564584
+common_voice_bn_31564586
+common_voice_bn_31564588
+common_voice_bn_31564686
+common_voice_bn_31564700
+common_voice_bn_31564811
+common_voice_bn_31564893
+common_voice_bn_31565257
+common_voice_bn_31565288
+common_voice_bn_31565304
+common_voice_bn_31565421
+common_voice_bn_31565423
+common_voice_bn_31565428
+common_voice_bn_31565481
+common_voice_bn_31565490
+common_voice_bn_31565519
+common_voice_bn_31565547
+common_voice_bn_31565548
+common_voice_bn_31565746
+common_voice_bn_31565752
+common_voice_bn_31565759
+common_voice_bn_31565792
+common_voice_bn_31566026
+common_voice_bn_31566083
+common_voice_bn_31566197
+common_voice_bn_31566555
+common_voice_bn_31566571
+common_voice_bn_31566779
+common_voice_bn_31566890
+common_voice_bn_31567078
+common_voice_bn_31567141
+common_voice_bn_31567144
+common_voice_bn_31567272
+common_voice_bn_31567441
+common_voice_bn_31567652
+common_voice_bn_31567655
+common_voice_bn_31567701
+common_voice_bn_31568104
+common_voice_bn_31568266
+common_voice_bn_31568410
+common_voice_bn_31568734
+common_voice_bn_31568735
+common_voice_bn_31568736
+common_voice_bn_31568738
+common_voice_bn_31568774
+common_voice_bn_31568781
+common_voice_bn_31568897
+common_voice_bn_31568903
+common_voice_bn_31568949
+common_voice_bn_31569188
+common_voice_bn_31569200
+common_voice_bn_31569203
+common_voice_bn_31569205
+common_voice_bn_31569378
+common_voice_bn_31569426
+common_voice_bn_31569501
+common_voice_bn_31569506
+common_voice_bn_31569520
+common_voice_bn_31569659
+common_voice_bn_31569686
+common_voice_bn_31569691
+common_voice_bn_31569822
+common_voice_bn_31569824
+common_voice_bn_31570041
+common_voice_bn_31570044
+common_voice_bn_31570047
+common_voice_bn_31570050
+common_voice_bn_31570071
+common_voice_bn_31570076
+common_voice_bn_31570293
+common_voice_bn_31570366
+common_voice_bn_31570384
+common_voice_bn_31570438
+common_voice_bn_31570445
+common_voice_bn_31570457
+common_voice_bn_31570525
+common_voice_bn_31570527
+common_voice_bn_31570639
+common_voice_bn_31570648
+common_voice_bn_31570650
+common_voice_bn_31570794
+common_voice_bn_31570932
+common_voice_bn_31570985
+common_voice_bn_31571111
+common_voice_bn_31571149
+common_voice_bn_31571169
+common_voice_bn_31571171
+common_voice_bn_31571191
+common_voice_bn_31571308
+common_voice_bn_31571310
+common_voice_bn_31571311
+common_voice_bn_31571313
+common_voice_bn_31571746
+common_voice_bn_31571749
+common_voice_bn_31571752
+common_voice_bn_31571822
+common_voice_bn_31572029
+common_voice_bn_31572237
+common_voice_bn_31572255
+common_voice_bn_31572262
+common_voice_bn_31572391
+common_voice_bn_31572396
+common_voice_bn_31572397
+common_voice_bn_31572491
+common_voice_bn_31572548
+common_voice_bn_31572603
+common_voice_bn_31572610
+common_voice_bn_31572615
+common_voice_bn_31572616
+common_voice_bn_31572617
+common_voice_bn_31572696
+common_voice_bn_31572797
+common_voice_bn_31572928
+common_voice_bn_31572940
+common_voice_bn_31573081
+common_voice_bn_31573141
+common_voice_bn_31573198
+common_voice_bn_31573199
+common_voice_bn_31573200
+common_voice_bn_31573201
+common_voice_bn_31573202
+common_voice_bn_31573616
+common_voice_bn_31573619
+common_voice_bn_31573620
+common_voice_bn_31573662
+common_voice_bn_31573762
+common_voice_bn_31574308
+common_voice_bn_31574367
+common_voice_bn_31574435
+common_voice_bn_31574499
+common_voice_bn_31574500
+common_voice_bn_31574503
+common_voice_bn_31574523
+common_voice_bn_31574527
+common_voice_bn_31574529
+common_voice_bn_31574545
+common_voice_bn_31574557
+common_voice_bn_31574574
+common_voice_bn_31574641
+common_voice_bn_31574667
+common_voice_bn_31574670
+common_voice_bn_31574673
+common_voice_bn_31574932
+common_voice_bn_31575032
+common_voice_bn_31575062
+common_voice_bn_31575069
+common_voice_bn_31575083
+common_voice_bn_31575090
+common_voice_bn_31575180
+common_voice_bn_31575363
+common_voice_bn_31575365
+common_voice_bn_31575367
+common_voice_bn_31575369
+common_voice_bn_31575373
+common_voice_bn_31575619
+common_voice_bn_31575621
+common_voice_bn_31575624
+common_voice_bn_31575626
+common_voice_bn_31575634
+common_voice_bn_31575800
+common_voice_bn_31575932
+common_voice_bn_31575938
+common_voice_bn_31575976
+common_voice_bn_31576043
+common_voice_bn_31576052
+common_voice_bn_31576057
+common_voice_bn_31576127
+common_voice_bn_31576233
+common_voice_bn_31576288
+common_voice_bn_31576371
+common_voice_bn_31576562
+common_voice_bn_31576637
+common_voice_bn_31576644
+common_voice_bn_31576806
+common_voice_bn_31576855
+common_voice_bn_31576909
+common_voice_bn_31576917
+common_voice_bn_31576921
+common_voice_bn_31576924
+common_voice_bn_31576927
+common_voice_bn_31577137
+common_voice_bn_31577144
+common_voice_bn_31577145
+common_voice_bn_31577211
+common_voice_bn_31577229
+common_voice_bn_31577233
+common_voice_bn_31577236
+common_voice_bn_31577259
+common_voice_bn_31577288
+common_voice_bn_31577289
+common_voice_bn_31577290
+common_voice_bn_31577292
+common_voice_bn_31577293
+common_voice_bn_31577365
+common_voice_bn_31577369
+common_voice_bn_31577382
+common_voice_bn_31577420
+common_voice_bn_31577728
+common_voice_bn_31578109
+common_voice_bn_31578113
+common_voice_bn_31578178
+common_voice_bn_31578187
+common_voice_bn_31578333
+common_voice_bn_31578376
+common_voice_bn_31578380
+common_voice_bn_31578385
+common_voice_bn_31578454
+common_voice_bn_31578651
+common_voice_bn_31578652
+common_voice_bn_31578653
+common_voice_bn_31578654
+common_voice_bn_31578655
+common_voice_bn_31578692
+common_voice_bn_31578742
+common_voice_bn_31578743
+common_voice_bn_31578744
+common_voice_bn_31578745
+common_voice_bn_31578869
+common_voice_bn_31578935
+common_voice_bn_31579063
+common_voice_bn_31579108
+common_voice_bn_31579110
+common_voice_bn_31579113
+common_voice_bn_31579116
+common_voice_bn_31579239
+common_voice_bn_31579252
+common_voice_bn_31579421
+common_voice_bn_31579509
+common_voice_bn_31579512
+common_voice_bn_31579515
+common_voice_bn_31579592
+common_voice_bn_31579695
+common_voice_bn_31579721
+common_voice_bn_31579816
+common_voice_bn_31579974
+common_voice_bn_31579976
+common_voice_bn_31579977
+common_voice_bn_31580292
+common_voice_bn_31580414
+common_voice_bn_31580508
+common_voice_bn_31580511
+common_voice_bn_31580731
+common_voice_bn_31580733
+common_voice_bn_31580736
+common_voice_bn_31580738
+common_voice_bn_31581273
+common_voice_bn_31581606
+common_voice_bn_31581653
+common_voice_bn_31581654
+common_voice_bn_31581655
+common_voice_bn_31581657
+common_voice_bn_31581659
+common_voice_bn_31581837
+common_voice_bn_31581838
+common_voice_bn_31581923
+common_voice_bn_31581929
+common_voice_bn_31582092
+common_voice_bn_31582099
+common_voice_bn_31582363
+common_voice_bn_31582370
+common_voice_bn_31582505
+common_voice_bn_31582646
+common_voice_bn_31582678
+common_voice_bn_31582897
+common_voice_bn_31582900
+common_voice_bn_31582952
+common_voice_bn_31583009
+common_voice_bn_31583196
+common_voice_bn_31583215
+common_voice_bn_31583218
+common_voice_bn_31583220
+common_voice_bn_31583264
+common_voice_bn_31583349
+common_voice_bn_31583422
+common_voice_bn_31583757
+common_voice_bn_31583758
+common_voice_bn_31583759
+common_voice_bn_31583760
+common_voice_bn_31583774
+common_voice_bn_31583883
+common_voice_bn_31583895
+common_voice_bn_31583940
+common_voice_bn_31584432
+common_voice_bn_31584469
+common_voice_bn_31584607
+common_voice_bn_31584712
+common_voice_bn_31584734
+common_voice_bn_31584916
+common_voice_bn_31585417
+common_voice_bn_31585507
+common_voice_bn_31585575
+common_voice_bn_31585689
+common_voice_bn_31585745
+common_voice_bn_31585865
+common_voice_bn_31585866
+common_voice_bn_31585872
+common_voice_bn_31586109
+common_voice_bn_31586116
+common_voice_bn_31586268
+common_voice_bn_31586471
+common_voice_bn_31586791
+common_voice_bn_31587127
+common_voice_bn_31587128
+common_voice_bn_31587130
+common_voice_bn_31587318
+common_voice_bn_31587320
+common_voice_bn_31587399
+common_voice_bn_31587453
+common_voice_bn_31587457
+common_voice_bn_31587744
+common_voice_bn_31587808
+common_voice_bn_31587875
+common_voice_bn_31588068
+common_voice_bn_31588363
+common_voice_bn_31588416
+common_voice_bn_31588631
+common_voice_bn_31588635
+common_voice_bn_31588637
+common_voice_bn_31588727
+common_voice_bn_31588731
+common_voice_bn_31588733
+common_voice_bn_31588735
+common_voice_bn_31588738
+common_voice_bn_31588792
+common_voice_bn_31589044
+common_voice_bn_31589049
+common_voice_bn_31589050
+common_voice_bn_31589056
+common_voice_bn_31589203
+common_voice_bn_31589251
+common_voice_bn_31589354
+common_voice_bn_31589415
+common_voice_bn_31589451
+common_voice_bn_31589461
+common_voice_bn_31589467
+common_voice_bn_31589472
+common_voice_bn_31589560
+common_voice_bn_31589561
+common_voice_bn_31589564
+common_voice_bn_31589568
+common_voice_bn_31589572
+common_voice_bn_31589692
+common_voice_bn_31589697
+common_voice_bn_31589699
+common_voice_bn_31589867
+common_voice_bn_31589951
+common_voice_bn_31590022
+common_voice_bn_31590081
+common_voice_bn_31590092
+common_voice_bn_31590470
+common_voice_bn_31590511
+common_voice_bn_31590584
+common_voice_bn_31590597
+common_voice_bn_31590911
+common_voice_bn_31591028
+common_voice_bn_31591032
+common_voice_bn_31591033
+common_voice_bn_31591078
+common_voice_bn_31591136
+common_voice_bn_31591139
+common_voice_bn_31591368
+common_voice_bn_31591382
+common_voice_bn_31591384
+common_voice_bn_31591386
+common_voice_bn_31591388
+common_voice_bn_31591473
+common_voice_bn_31591489
+common_voice_bn_31591505
+common_voice_bn_31591558
+common_voice_bn_31591563
+common_voice_bn_31591608
+common_voice_bn_31591853
+common_voice_bn_31591915
+common_voice_bn_31591920
+common_voice_bn_31591922
+common_voice_bn_31591923
+common_voice_bn_31592349
+common_voice_bn_31592370
+common_voice_bn_31592513
+common_voice_bn_31592541
+common_voice_bn_31592796
+common_voice_bn_31592798
+common_voice_bn_31592802
+common_voice_bn_31592804
+common_voice_bn_31592805
+common_voice_bn_31593035
+common_voice_bn_31593089
+common_voice_bn_31593113
+common_voice_bn_31593251
+common_voice_bn_31593282
+common_voice_bn_31593284
+common_voice_bn_31593288
+common_voice_bn_31593296
+common_voice_bn_31593308
+common_voice_bn_31593363
+common_voice_bn_31593445
+common_voice_bn_31593688
+common_voice_bn_31593693
+common_voice_bn_31593695
+common_voice_bn_31593696
+common_voice_bn_31594035
+common_voice_bn_31594164
+common_voice_bn_31594167
+common_voice_bn_31594170
+common_voice_bn_31594227
+common_voice_bn_31594231
+common_voice_bn_31594361
+common_voice_bn_31594441
+common_voice_bn_31594470
+common_voice_bn_31594478
+common_voice_bn_31594484
+common_voice_bn_31594588
+common_voice_bn_31594607
+common_voice_bn_31594635
+common_voice_bn_31594637
+common_voice_bn_31594717
+common_voice_bn_31594749
+common_voice_bn_31594750
+common_voice_bn_31594784
+common_voice_bn_31594785
+common_voice_bn_31594848
+common_voice_bn_31594855
+common_voice_bn_31594957
+common_voice_bn_31594991
+common_voice_bn_31594995
+common_voice_bn_31595000
+common_voice_bn_31595021
+common_voice_bn_31595022
+common_voice_bn_31595023
+common_voice_bn_31595024
+common_voice_bn_31595148
+common_voice_bn_31595197
+common_voice_bn_31595433
+common_voice_bn_31595526
+common_voice_bn_31595557
+common_voice_bn_31595634
+common_voice_bn_31595649
+common_voice_bn_31596007
+common_voice_bn_31596052
+common_voice_bn_31596057
+common_voice_bn_31596063
+common_voice_bn_31596066
+common_voice_bn_31596259
+common_voice_bn_31596269
+common_voice_bn_31596271
+common_voice_bn_31596272
+common_voice_bn_31596738
+common_voice_bn_31596748
+common_voice_bn_31596752
+common_voice_bn_31596757
+common_voice_bn_31596783
+common_voice_bn_31597103
+common_voice_bn_31597106
+common_voice_bn_31597218
+common_voice_bn_31597589
+common_voice_bn_31597590
+common_voice_bn_31597591
+common_voice_bn_31597602
+common_voice_bn_31597837
+common_voice_bn_31597842
+common_voice_bn_31597887
+common_voice_bn_31597905
+common_voice_bn_31597909
+common_voice_bn_31597914
+common_voice_bn_31597917
+common_voice_bn_31598209
+common_voice_bn_31598210
+common_voice_bn_31598220
+common_voice_bn_31598223
+common_voice_bn_31598224
+common_voice_bn_31598248
+common_voice_bn_31598249
+common_voice_bn_31598255
+common_voice_bn_31598440
+common_voice_bn_31598494
+common_voice_bn_31598507
+common_voice_bn_31598526
+common_voice_bn_31598527
+common_voice_bn_31598658
+common_voice_bn_31598679
+common_voice_bn_31598692
+common_voice_bn_31598759
+common_voice_bn_31598808
+common_voice_bn_31599037
+common_voice_bn_31599052
+common_voice_bn_31599073
+common_voice_bn_31599090
+common_voice_bn_31599092
+common_voice_bn_31599116
+common_voice_bn_31599202
+common_voice_bn_31599203
+common_voice_bn_31599236
+common_voice_bn_31599243
+common_voice_bn_31599368
+common_voice_bn_31599589
+common_voice_bn_31599607
+common_voice_bn_31599825
+common_voice_bn_31599831
+common_voice_bn_31599834
+common_voice_bn_31599852
+common_voice_bn_31599873
+common_voice_bn_31600022
+common_voice_bn_31600063
+common_voice_bn_31600064
+common_voice_bn_31600065
+common_voice_bn_31600066
+common_voice_bn_31600169
+common_voice_bn_31600176
+common_voice_bn_31600254
+common_voice_bn_31600258
+common_voice_bn_31600260
+common_voice_bn_31600261
+common_voice_bn_31600273
+common_voice_bn_31600304
+common_voice_bn_31600308
+common_voice_bn_31600319
+common_voice_bn_31600396
+common_voice_bn_31600509
+common_voice_bn_31600577
+common_voice_bn_31600703
+common_voice_bn_31600707
+common_voice_bn_31600747
+common_voice_bn_31600780
+common_voice_bn_31600855
+common_voice_bn_31600856
+common_voice_bn_31600857
+common_voice_bn_31600858
+common_voice_bn_31601057
+common_voice_bn_31601199
+common_voice_bn_31601203
+common_voice_bn_31601311
+common_voice_bn_31601320
+common_voice_bn_31601329
+common_voice_bn_31601337
+common_voice_bn_31601340
+common_voice_bn_31601606
+common_voice_bn_31601773
+common_voice_bn_31601774
+common_voice_bn_31601775
+common_voice_bn_31601776
+common_voice_bn_31601904
+common_voice_bn_31601929
+common_voice_bn_31602378
+common_voice_bn_31602548
+common_voice_bn_31602729
+common_voice_bn_31602825
+common_voice_bn_31602920
+common_voice_bn_31603073
+common_voice_bn_31603132
+common_voice_bn_31603135
+common_voice_bn_31603202
+common_voice_bn_31603205
+common_voice_bn_31603408
+common_voice_bn_31603575
+common_voice_bn_31603798
+common_voice_bn_31603801
+common_voice_bn_31603802
+common_voice_bn_31603803
+common_voice_bn_31603901
+common_voice_bn_31603902
+common_voice_bn_31603947
+common_voice_bn_31604206
+common_voice_bn_31604343
+common_voice_bn_31604388
+common_voice_bn_31604737
+common_voice_bn_31604797
+common_voice_bn_31604948
+common_voice_bn_31605020
+common_voice_bn_31605206
+common_voice_bn_31605289
+common_voice_bn_31605299
+common_voice_bn_31605332
+common_voice_bn_31605391
+common_voice_bn_31605432
+common_voice_bn_31605537
+common_voice_bn_31605574
+common_voice_bn_31605650
+common_voice_bn_31605656
+common_voice_bn_31605658
+common_voice_bn_31605664
+common_voice_bn_31605691
+common_voice_bn_31605693
+common_voice_bn_31605705
+common_voice_bn_31605706
+common_voice_bn_31605967
+common_voice_bn_31606081
+common_voice_bn_31606375
+common_voice_bn_31606470
+common_voice_bn_31606501
+common_voice_bn_31606509
+common_voice_bn_31606746
+common_voice_bn_31606747
+common_voice_bn_31606748
+common_voice_bn_31606749
+common_voice_bn_31606933
+common_voice_bn_31606937
+common_voice_bn_31606939
+common_voice_bn_31606947
+common_voice_bn_31606948
+common_voice_bn_31606949
+common_voice_bn_31606950
+common_voice_bn_31606988
+common_voice_bn_31606990
+common_voice_bn_31606994
+common_voice_bn_31606999
+common_voice_bn_31607026
+common_voice_bn_31607321
+common_voice_bn_31607324
+common_voice_bn_31607325
+common_voice_bn_31607379
+common_voice_bn_31607401
+common_voice_bn_31607402
+common_voice_bn_31607403
+common_voice_bn_31607404
+common_voice_bn_31607416
+common_voice_bn_31607490
+common_voice_bn_31607517
+common_voice_bn_31607593
+common_voice_bn_31607763
+common_voice_bn_31607841
+common_voice_bn_31607936
+common_voice_bn_31607937
+common_voice_bn_31607938
+common_voice_bn_31607940
+common_voice_bn_31607943
+common_voice_bn_31607944
+common_voice_bn_31608148
+common_voice_bn_31608180
+common_voice_bn_31608185
+common_voice_bn_31608186
+common_voice_bn_31608188
+common_voice_bn_31608212
+common_voice_bn_31608251
+common_voice_bn_31608301
+common_voice_bn_31608406
+common_voice_bn_31608407
+common_voice_bn_31608409
+common_voice_bn_31608410
+common_voice_bn_31608447
+common_voice_bn_31608453
+common_voice_bn_31608590
+common_voice_bn_31608595
+common_voice_bn_31608649
+common_voice_bn_31608653
+common_voice_bn_31608665
+common_voice_bn_31608674
+common_voice_bn_31608708
+common_voice_bn_31608712
+common_voice_bn_31608715
+common_voice_bn_31608864
+common_voice_bn_31608865
+common_voice_bn_31608867
+common_voice_bn_31608944
+common_voice_bn_31608959
+common_voice_bn_31609564
+common_voice_bn_31609565
+common_voice_bn_31609583
+common_voice_bn_31609624
+common_voice_bn_31609686
+common_voice_bn_31610000
+common_voice_bn_31610158
+common_voice_bn_31610163
+common_voice_bn_31610292
+common_voice_bn_31610293
+common_voice_bn_31610685
+common_voice_bn_31610690
+common_voice_bn_31610730
+common_voice_bn_31610735
+common_voice_bn_31610753
+common_voice_bn_31610803
+common_voice_bn_31610804
+common_voice_bn_31610939
+common_voice_bn_31610941
+common_voice_bn_31610960
+common_voice_bn_31610964
+common_voice_bn_31611124
+common_voice_bn_31611147
+common_voice_bn_31611154
+common_voice_bn_31611156
+common_voice_bn_31611212
+common_voice_bn_31611222
+common_voice_bn_31611235
+common_voice_bn_31611237
+common_voice_bn_31611238
+common_voice_bn_31611267
+common_voice_bn_31611269
+common_voice_bn_31611296
+common_voice_bn_31611297
+common_voice_bn_31611298
+common_voice_bn_31611332
+common_voice_bn_31611346
+common_voice_bn_31611350
+common_voice_bn_31611351
+common_voice_bn_31611422
+common_voice_bn_31611423
+common_voice_bn_31611617
+common_voice_bn_31611619
+common_voice_bn_31611620
+common_voice_bn_31611623
+common_voice_bn_31611659
+common_voice_bn_31611661
+common_voice_bn_31611662
+common_voice_bn_31611664
+common_voice_bn_31611793
+common_voice_bn_31611794
+common_voice_bn_31611797
+common_voice_bn_31611888
+common_voice_bn_31611962
+common_voice_bn_31611977
+common_voice_bn_31611980
+common_voice_bn_31611981
+common_voice_bn_31611983
+common_voice_bn_31612000
+common_voice_bn_31612055
+common_voice_bn_31612058
+common_voice_bn_31612059
+common_voice_bn_31612061
+common_voice_bn_31612080
+common_voice_bn_31612224
+common_voice_bn_31612225
+common_voice_bn_31612227
+common_voice_bn_31612228
+common_voice_bn_31612280
+common_voice_bn_31612281
+common_voice_bn_31612302
+common_voice_bn_31612303
+common_voice_bn_31612304
+common_voice_bn_31612374
+common_voice_bn_31612431
+common_voice_bn_31612592
+common_voice_bn_31612619
+common_voice_bn_31612662
+common_voice_bn_31612868
+common_voice_bn_31612869
+common_voice_bn_31612870
+common_voice_bn_31612887
+common_voice_bn_31612889
+common_voice_bn_31612894
+common_voice_bn_31612901
+common_voice_bn_31613079
+common_voice_bn_31613278
+common_voice_bn_31613316
+common_voice_bn_31613317
+common_voice_bn_31613320
+common_voice_bn_31613324
+common_voice_bn_31613585
+common_voice_bn_31613586
+common_voice_bn_31613587
+common_voice_bn_31613588
+common_voice_bn_31613589
+common_voice_bn_31613590
+common_voice_bn_31613621
+common_voice_bn_31613780
+common_voice_bn_31613788
+common_voice_bn_31613855
+common_voice_bn_31613856
+common_voice_bn_31613897
+common_voice_bn_31613898
+common_voice_bn_31613900
+common_voice_bn_31613985
+common_voice_bn_31613987
+common_voice_bn_31613988
+common_voice_bn_31613989
+common_voice_bn_31614029
+common_voice_bn_31614242
+common_voice_bn_31614244
+common_voice_bn_31614306
+common_voice_bn_31614480
+common_voice_bn_31614485
+common_voice_bn_31614489
+common_voice_bn_31614492
+common_voice_bn_31614553
+common_voice_bn_31614961
+common_voice_bn_31615007
+common_voice_bn_31615129
+common_voice_bn_31615206
+common_voice_bn_31615359
+common_voice_bn_31615420
+common_voice_bn_31615433
+common_voice_bn_31615447
+common_voice_bn_31615451
+common_voice_bn_31615518
+common_voice_bn_31615523
+common_voice_bn_31615525
+common_voice_bn_31615658
+common_voice_bn_31615686
+common_voice_bn_31615812
+common_voice_bn_31615964
+common_voice_bn_31615966
+common_voice_bn_31615968
+common_voice_bn_31615970
+common_voice_bn_31615972
+common_voice_bn_31616171
+common_voice_bn_31616172
+common_voice_bn_31616178
+common_voice_bn_31616199
+common_voice_bn_31616312
+common_voice_bn_31616331
+common_voice_bn_31616335
+common_voice_bn_31616339
+common_voice_bn_31616387
+common_voice_bn_31616598
+common_voice_bn_31616711
+common_voice_bn_31616723
+common_voice_bn_31616857
+common_voice_bn_31616905
+common_voice_bn_31616969
+common_voice_bn_31617185
+common_voice_bn_31617187
+common_voice_bn_31617233
+common_voice_bn_31617279
+common_voice_bn_31617323
+common_voice_bn_31617329
+common_voice_bn_31617330
+common_voice_bn_31617331
+common_voice_bn_31617333
+common_voice_bn_31617417
+common_voice_bn_31617423
+common_voice_bn_31617428
+common_voice_bn_31617430
+common_voice_bn_31617516
+common_voice_bn_31617609
+common_voice_bn_31617612
+common_voice_bn_31617618
+common_voice_bn_31617620
+common_voice_bn_31617823
+common_voice_bn_31617824
+common_voice_bn_31617995
+common_voice_bn_31618133
+common_voice_bn_31618134
+common_voice_bn_31618276
+common_voice_bn_31618277
+common_voice_bn_31618279
+common_voice_bn_31618280
+common_voice_bn_31618282
+common_voice_bn_31618321
+common_voice_bn_31618323
+common_voice_bn_31618327
+common_voice_bn_31618474
+common_voice_bn_31618529
+common_voice_bn_31618531
+common_voice_bn_31618533
+common_voice_bn_31618784
+common_voice_bn_31618853
+common_voice_bn_31618856
+common_voice_bn_31618914
+common_voice_bn_31618919
+common_voice_bn_31619046
+common_voice_bn_31619084
+common_voice_bn_31619087
+common_voice_bn_31619090
+common_voice_bn_31619093
+common_voice_bn_31619202
+common_voice_bn_31619207
+common_voice_bn_31619212
+common_voice_bn_31619213
+common_voice_bn_31619234
+common_voice_bn_31619315
+common_voice_bn_31619320
+common_voice_bn_31619519
+common_voice_bn_31619540
+common_voice_bn_31619582
+common_voice_bn_31619674
+common_voice_bn_31619697
+common_voice_bn_31619772
+common_voice_bn_31619783
+common_voice_bn_31619785
+common_voice_bn_31619786
+common_voice_bn_31619846
+common_voice_bn_31619913
+common_voice_bn_31620064
+common_voice_bn_31620079
+common_voice_bn_31620084
+common_voice_bn_31620261
+common_voice_bn_31620262
+common_voice_bn_31620315
+common_voice_bn_31620374
+common_voice_bn_31620378
+common_voice_bn_31620381
+common_voice_bn_31620387
+common_voice_bn_31620398
+common_voice_bn_31620428
+common_voice_bn_31620436
+common_voice_bn_31620619
+common_voice_bn_31620650
+common_voice_bn_31620991
+common_voice_bn_31620993
+common_voice_bn_31620996
+common_voice_bn_31621006
+common_voice_bn_31621013
+common_voice_bn_31621147
+common_voice_bn_31621353
+common_voice_bn_31621454
+common_voice_bn_31621459
+common_voice_bn_31621460
+common_voice_bn_31621461
+common_voice_bn_31621468
+common_voice_bn_31621474
+common_voice_bn_31621477
+common_voice_bn_31621548
+common_voice_bn_31621549
+common_voice_bn_31621550
+common_voice_bn_31621551
+common_voice_bn_31621552
+common_voice_bn_31621689
+common_voice_bn_31621788
+common_voice_bn_31621804
+common_voice_bn_31621932
+common_voice_bn_31622153
+common_voice_bn_31622197
+common_voice_bn_31622221
+common_voice_bn_31622367
+common_voice_bn_31622488
+common_voice_bn_31622866
+common_voice_bn_31622920
+common_voice_bn_31622950
+common_voice_bn_31623122
+common_voice_bn_31623128
+common_voice_bn_31623129
+common_voice_bn_31623249
+common_voice_bn_31623266
+common_voice_bn_31623333
+common_voice_bn_31623335
+common_voice_bn_31623337
+common_voice_bn_31623338
+common_voice_bn_31623476
+common_voice_bn_31623478
+common_voice_bn_31623479
+common_voice_bn_31623481
+common_voice_bn_31623596
+common_voice_bn_31623904
+common_voice_bn_31624189
+common_voice_bn_31624195
+common_voice_bn_31624200
+common_voice_bn_31624284
+common_voice_bn_31624285
+common_voice_bn_31624759
+common_voice_bn_31624765
+common_voice_bn_31624766
+common_voice_bn_31624767
+common_voice_bn_31624768
+common_voice_bn_31624897
+common_voice_bn_31625042
+common_voice_bn_31625166
+common_voice_bn_31625204
+common_voice_bn_31625314
+common_voice_bn_31625316
+common_voice_bn_31625319
+common_voice_bn_31625320
+common_voice_bn_31625350
+common_voice_bn_31625376
+common_voice_bn_31625395
+common_voice_bn_31625473
+common_voice_bn_31625552
+common_voice_bn_31625573
+common_voice_bn_31625576
+common_voice_bn_31625776
+common_voice_bn_31625857
+common_voice_bn_31625869
+common_voice_bn_31625874
+common_voice_bn_31625882
+common_voice_bn_31625907
+common_voice_bn_31625908
+common_voice_bn_31625909
+common_voice_bn_31625910
+common_voice_bn_31625911
+common_voice_bn_31625952
+common_voice_bn_31626003
+common_voice_bn_31626046
+common_voice_bn_31626125
+common_voice_bn_31626400
+common_voice_bn_31626417
+common_voice_bn_31626539
+common_voice_bn_31626551
+common_voice_bn_31626553
+common_voice_bn_31626556
+common_voice_bn_31626559
+common_voice_bn_31626562
+common_voice_bn_31626601
+common_voice_bn_31626674
+common_voice_bn_31626677
+common_voice_bn_31626762
+common_voice_bn_31626806
+common_voice_bn_31626969
+common_voice_bn_31627076
+common_voice_bn_31627079
+common_voice_bn_31627145
+common_voice_bn_31627158
+common_voice_bn_31627162
+common_voice_bn_31627164
+common_voice_bn_31627167
+common_voice_bn_31627173
+common_voice_bn_31627176
+common_voice_bn_31627358
+common_voice_bn_31627361
+common_voice_bn_31627385
+common_voice_bn_31627396
+common_voice_bn_31627629
+common_voice_bn_31627754
+common_voice_bn_31627755
+common_voice_bn_31627756
+common_voice_bn_31627778
+common_voice_bn_31627814
+common_voice_bn_31627876
+common_voice_bn_31627877
+common_voice_bn_31627927
+common_voice_bn_31628097
+common_voice_bn_31628112
+common_voice_bn_31628132
+common_voice_bn_31628197
+common_voice_bn_31628349
+common_voice_bn_31628413
+common_voice_bn_31628485
+common_voice_bn_31628628
+common_voice_bn_31628629
+common_voice_bn_31628707
+common_voice_bn_31628709
+common_voice_bn_31628806
+common_voice_bn_31629130
+common_voice_bn_31629420
+common_voice_bn_31629421
+common_voice_bn_31629422
+common_voice_bn_31629763
+common_voice_bn_31630030
+common_voice_bn_31630035
+common_voice_bn_31630036
+common_voice_bn_31630049
+common_voice_bn_31630109
+common_voice_bn_31630130
+common_voice_bn_31630131
+common_voice_bn_31630133
+common_voice_bn_31630137
+common_voice_bn_31630285
+common_voice_bn_31630536
+common_voice_bn_31630547
+common_voice_bn_31630788
+common_voice_bn_31630800
+common_voice_bn_31631175
+common_voice_bn_31631418
+common_voice_bn_31631453
+common_voice_bn_31631459
+common_voice_bn_31631460
+common_voice_bn_31631547
+common_voice_bn_31631619
+common_voice_bn_31631742
+common_voice_bn_31631942
+common_voice_bn_31631966
+common_voice_bn_31632154
+common_voice_bn_31632156
+common_voice_bn_31632200
+common_voice_bn_31632202
+common_voice_bn_31632207
+common_voice_bn_31632464
+common_voice_bn_31632540
+common_voice_bn_31632702
+common_voice_bn_31632703
+common_voice_bn_31632705
+common_voice_bn_31632706
+common_voice_bn_31632915
+common_voice_bn_31632917
+common_voice_bn_31632919
+common_voice_bn_31632999
+common_voice_bn_31633043
+common_voice_bn_31633044
+common_voice_bn_31633045
+common_voice_bn_31633046
+common_voice_bn_31633101
+common_voice_bn_31633171
+common_voice_bn_31633232
+common_voice_bn_31633340
+common_voice_bn_31633641
+common_voice_bn_31633649
+common_voice_bn_31633651
+common_voice_bn_31633756
+common_voice_bn_31634487
+common_voice_bn_31634777
+common_voice_bn_31634778
+common_voice_bn_31634784
+common_voice_bn_31634876
+common_voice_bn_31634879
+common_voice_bn_31634881
+common_voice_bn_31635125
+common_voice_bn_31635127
+common_voice_bn_31635331
+common_voice_bn_31635341
+common_voice_bn_31635342
+common_voice_bn_31635343
+common_voice_bn_31635344
+common_voice_bn_31635687
+common_voice_bn_31635689
+common_voice_bn_31635691
+common_voice_bn_31635779
+common_voice_bn_31635781
+common_voice_bn_31635862
+common_voice_bn_31635969
+common_voice_bn_31636138
+common_voice_bn_31636211
+common_voice_bn_31636230
+common_voice_bn_31636285
+common_voice_bn_31636377
+common_voice_bn_31636379
+common_voice_bn_31636380
+common_voice_bn_31637036
+common_voice_bn_31637220
+common_voice_bn_31637534
+common_voice_bn_31637538
+common_voice_bn_31637543
+common_voice_bn_31637764
+common_voice_bn_31637924
+common_voice_bn_31637953
+common_voice_bn_31637960
+common_voice_bn_31637962
+common_voice_bn_31638243
+common_voice_bn_31638244
+common_voice_bn_31638378
+common_voice_bn_31638379
+common_voice_bn_31638380
+common_voice_bn_31638531
+common_voice_bn_31638548
+common_voice_bn_31638601
+common_voice_bn_31638784
+common_voice_bn_31638785
+common_voice_bn_31638959
+common_voice_bn_31638960
+common_voice_bn_31638967
+common_voice_bn_31638968
+common_voice_bn_31638969
+common_voice_bn_31638970
+common_voice_bn_31638971
+common_voice_bn_31638978
+common_voice_bn_31638979
+common_voice_bn_31638980
+common_voice_bn_31638981
+common_voice_bn_31638984
+common_voice_bn_31639028
+common_voice_bn_31639030
+common_voice_bn_31639032
+common_voice_bn_31639061
+common_voice_bn_31639063
+common_voice_bn_31639065
+common_voice_bn_31639078
+common_voice_bn_31639082
+common_voice_bn_31639085
+common_voice_bn_31639086
+common_voice_bn_31639087
+common_voice_bn_31639108
+common_voice_bn_31639109
+common_voice_bn_31639112
+common_voice_bn_31639113
+common_voice_bn_31639114
+common_voice_bn_31639219
+common_voice_bn_31639584
+common_voice_bn_31639733
+common_voice_bn_31639735
+common_voice_bn_31639755
+common_voice_bn_31639928
+common_voice_bn_31639932
+common_voice_bn_31640172
+common_voice_bn_31640668
+common_voice_bn_31641247
+common_voice_bn_31641248
+common_voice_bn_31641274
+common_voice_bn_31641375
+common_voice_bn_31641376
+common_voice_bn_31641378
+common_voice_bn_31641434
+common_voice_bn_31641436
+common_voice_bn_31641464
+common_voice_bn_31641624
+common_voice_bn_31641640
+common_voice_bn_31641700
+common_voice_bn_31641882
+common_voice_bn_31641902
+common_voice_bn_31641909
+common_voice_bn_31642016
+common_voice_bn_31642018
+common_voice_bn_31642019
+common_voice_bn_31642066
+common_voice_bn_31642357
+common_voice_bn_31642358
+common_voice_bn_31642359
+common_voice_bn_31642360
+common_voice_bn_31642513
+common_voice_bn_31642518
+common_voice_bn_31642607
+common_voice_bn_31642608
+common_voice_bn_31642638
+common_voice_bn_31642649
+common_voice_bn_31642694
+common_voice_bn_31642747
+common_voice_bn_31642771
+common_voice_bn_31642954
+common_voice_bn_31643260
+common_voice_bn_31643263
+common_voice_bn_31643382
+common_voice_bn_31643530
+common_voice_bn_31643668
+common_voice_bn_31643669
+common_voice_bn_31643879
+common_voice_bn_31643880
+common_voice_bn_31643936
+common_voice_bn_31644058
+common_voice_bn_31644148
+common_voice_bn_31644181
+common_voice_bn_31644307
+common_voice_bn_31644313
+common_voice_bn_31644321
+common_voice_bn_31644322
+common_voice_bn_31644323
+common_voice_bn_31644325
+common_voice_bn_31644722
+common_voice_bn_31644954
+common_voice_bn_31645005
+common_voice_bn_31645064
+common_voice_bn_31645065
+common_voice_bn_31645351
+common_voice_bn_31645709
+common_voice_bn_31645780
+common_voice_bn_31645782
+common_voice_bn_31645838
+common_voice_bn_31645839
+common_voice_bn_31645840
+common_voice_bn_31645842
+common_voice_bn_31645913
+common_voice_bn_31645979
+common_voice_bn_31646017
+common_voice_bn_31646033
+common_voice_bn_31646161
+common_voice_bn_31646367
+common_voice_bn_31646626
+common_voice_bn_31646727
+common_voice_bn_31646979
+common_voice_bn_31647017
+common_voice_bn_31647088
+common_voice_bn_31647360
+common_voice_bn_31647423
+common_voice_bn_31647426
+common_voice_bn_31647427
+common_voice_bn_31647626
+common_voice_bn_31647911
+common_voice_bn_31647999
+common_voice_bn_31648269
+common_voice_bn_31648518
+common_voice_bn_31648595
+common_voice_bn_31648910
+common_voice_bn_31648911
+common_voice_bn_31648915
+common_voice_bn_31649018
+common_voice_bn_31649055
+common_voice_bn_31649056
+common_voice_bn_31649060
+common_voice_bn_31649153
+common_voice_bn_31649214
+common_voice_bn_31649216
+common_voice_bn_31649378
+common_voice_bn_31649486
+common_voice_bn_31649621
+common_voice_bn_31649658
+common_voice_bn_31649933
+common_voice_bn_31650269
+common_voice_bn_31650316
+common_voice_bn_31650318
+common_voice_bn_31651000
+common_voice_bn_31651114
+common_voice_bn_31651155
+common_voice_bn_31651158
+common_voice_bn_31651331
+common_voice_bn_31651622
+common_voice_bn_31651624
+common_voice_bn_31651627
+common_voice_bn_31651651
+common_voice_bn_31651686
+common_voice_bn_31652035
+common_voice_bn_31652070
+common_voice_bn_31652217
+common_voice_bn_31652218
+common_voice_bn_31652221
+common_voice_bn_31652303
+common_voice_bn_31652464
+common_voice_bn_31652540
+common_voice_bn_31652681
+common_voice_bn_31652682
+common_voice_bn_31652684
+common_voice_bn_31652685
+common_voice_bn_31652711
+common_voice_bn_31652900
+common_voice_bn_31653282
+common_voice_bn_31653287
+common_voice_bn_31653399
+common_voice_bn_31653400
+common_voice_bn_31653465
+common_voice_bn_31653473
+common_voice_bn_31653653
+common_voice_bn_31653840
+common_voice_bn_31653842
+common_voice_bn_31653844
+common_voice_bn_31653845
+common_voice_bn_31653939
+common_voice_bn_31653966
+common_voice_bn_31653967
+common_voice_bn_31654128
+common_voice_bn_31654150
+common_voice_bn_31654260
+common_voice_bn_31654281
+common_voice_bn_31654316
+common_voice_bn_31654317
+common_voice_bn_31654318
+common_voice_bn_31654319
+common_voice_bn_31654320
+common_voice_bn_31654409
+common_voice_bn_31654439
+common_voice_bn_31654440
+common_voice_bn_31654442
+common_voice_bn_31654458
+common_voice_bn_31654459
+common_voice_bn_31654460
+common_voice_bn_31654461
+common_voice_bn_31654462
+common_voice_bn_31654523
+common_voice_bn_31654678
+common_voice_bn_31654696
+common_voice_bn_31654862
+common_voice_bn_31654972
+common_voice_bn_31655367
+common_voice_bn_31655444
+common_voice_bn_31655735
+common_voice_bn_31655737
+common_voice_bn_31655738
+common_voice_bn_31656119
+common_voice_bn_31656132
+common_voice_bn_31656135
+common_voice_bn_31656140
+common_voice_bn_31656146
+common_voice_bn_31656157
+common_voice_bn_31656158
+common_voice_bn_31656159
+common_voice_bn_31656161
+common_voice_bn_31656292
+common_voice_bn_31656305
+common_voice_bn_31656327
+common_voice_bn_31656435
+common_voice_bn_31656438
+common_voice_bn_31656439
+common_voice_bn_31656546
+common_voice_bn_31656583
+common_voice_bn_31656622
+common_voice_bn_31656632
+common_voice_bn_31656661
+common_voice_bn_31656724
+common_voice_bn_31656872
+common_voice_bn_31657205
+common_voice_bn_31657588
+common_voice_bn_31657592
+common_voice_bn_31657596
+common_voice_bn_31657728
+common_voice_bn_31657782
+common_voice_bn_31657783
+common_voice_bn_31657858
+common_voice_bn_31657860
+common_voice_bn_31657861
+common_voice_bn_31657862
+common_voice_bn_31657863
+common_voice_bn_31658209
+common_voice_bn_31658304
+common_voice_bn_31658638
+common_voice_bn_31658639
+common_voice_bn_31658640
+common_voice_bn_31658643
+common_voice_bn_31658827
+common_voice_bn_31658829
+common_voice_bn_31658831
+common_voice_bn_31658892
+common_voice_bn_31658898
+common_voice_bn_31658903
+common_voice_bn_31659036
+common_voice_bn_31659060
+common_voice_bn_31659240
+common_voice_bn_31659284
+common_voice_bn_31659372
+common_voice_bn_31659380
+common_voice_bn_31659383
+common_voice_bn_31659384
+common_voice_bn_31659385
+common_voice_bn_31659386
+common_voice_bn_31659418
+common_voice_bn_31659419
+common_voice_bn_31659783
+common_voice_bn_31660287
+common_voice_bn_31660380
+common_voice_bn_31660384
+common_voice_bn_31660445
+common_voice_bn_31660448
+common_voice_bn_31660455
+common_voice_bn_31660611
+common_voice_bn_31660650
+common_voice_bn_31660652
+common_voice_bn_31660706
+common_voice_bn_31660714
+common_voice_bn_31660749
+common_voice_bn_31660768
+common_voice_bn_31660880
+common_voice_bn_31661079
+common_voice_bn_31661081
+common_voice_bn_31661083
+common_voice_bn_31661085
+common_voice_bn_31661089
+common_voice_bn_31661175
+common_voice_bn_31661177
+common_voice_bn_31661178
+common_voice_bn_31661656
+common_voice_bn_31661661
+common_voice_bn_31661664
+common_voice_bn_31661694
+common_voice_bn_31661897
+common_voice_bn_31661951
+common_voice_bn_31662161
+common_voice_bn_31662193
+common_voice_bn_31662354
+common_voice_bn_31662356
+common_voice_bn_31662359
+common_voice_bn_31662361
+common_voice_bn_31662364
+common_voice_bn_31662671
+common_voice_bn_31662674
+common_voice_bn_31662693
+common_voice_bn_31662742
+common_voice_bn_31662917
+common_voice_bn_31662934
+common_voice_bn_31662942
+common_voice_bn_31662946
+common_voice_bn_31663150
+common_voice_bn_31663165
+common_voice_bn_31663334
+common_voice_bn_31663359
+common_voice_bn_31663374
+common_voice_bn_31663440
+common_voice_bn_31663443
+common_voice_bn_31663489
+common_voice_bn_31663524
+common_voice_bn_31663528
+common_voice_bn_31663530
+common_voice_bn_31663532
+common_voice_bn_31663539
+common_voice_bn_31663559
+common_voice_bn_31663561
+common_voice_bn_31663574
+common_voice_bn_31663576
+common_voice_bn_31663598
+common_voice_bn_31663601
+common_voice_bn_31663606
+common_voice_bn_31663611
+common_voice_bn_31663615
+common_voice_bn_31663679
+common_voice_bn_31664130
+common_voice_bn_31664200
+common_voice_bn_31664308
+common_voice_bn_31664842
+common_voice_bn_31664848
+common_voice_bn_31664852
+common_voice_bn_31664854
+common_voice_bn_31664857
+common_voice_bn_31664891
+common_voice_bn_31665026
+common_voice_bn_31665053
+common_voice_bn_31665108
+common_voice_bn_31665186
+common_voice_bn_31665318
+common_voice_bn_31665339
+common_voice_bn_31665522
+common_voice_bn_31665543
+common_voice_bn_31665657
+common_voice_bn_31665659
+common_voice_bn_31665662
+common_voice_bn_31665665
+common_voice_bn_31665669
+common_voice_bn_31665670
+common_voice_bn_31665707
+common_voice_bn_31665708
+common_voice_bn_31665709
+common_voice_bn_31665710
+common_voice_bn_31665711
+common_voice_bn_31665751
+common_voice_bn_31665867
+common_voice_bn_31665995
+common_voice_bn_31666307
+common_voice_bn_31666309
+common_voice_bn_31666310
+common_voice_bn_31666311
+common_voice_bn_31666560
+common_voice_bn_31666578
+common_voice_bn_31666583
+common_voice_bn_31666592
+common_voice_bn_31666599
+common_voice_bn_31666631
+common_voice_bn_31666655
+common_voice_bn_31666690
+common_voice_bn_31666732
+common_voice_bn_31666734
+common_voice_bn_31666735
+common_voice_bn_31666737
+common_voice_bn_31666739
+common_voice_bn_31666761
+common_voice_bn_31666925
+common_voice_bn_31667220
+common_voice_bn_31667240
+common_voice_bn_31667245
+common_voice_bn_31667248
+common_voice_bn_31667430
+common_voice_bn_31667435
+common_voice_bn_31667438
+common_voice_bn_31667441
+common_voice_bn_31667443
+common_voice_bn_31667786
+common_voice_bn_31667830
+common_voice_bn_31667833
+common_voice_bn_31668207
+common_voice_bn_31668402
+common_voice_bn_31668613
+common_voice_bn_31668615
+common_voice_bn_31668757
+common_voice_bn_31668774
+common_voice_bn_31668797
+common_voice_bn_31668800
+common_voice_bn_31668801
+common_voice_bn_31668822
+common_voice_bn_31669005
+common_voice_bn_31669346
+common_voice_bn_31669533
+common_voice_bn_31669534
+common_voice_bn_31669536
+common_voice_bn_31669538
+common_voice_bn_31669555
+common_voice_bn_31669643
+common_voice_bn_31669646
+common_voice_bn_31669775
+common_voice_bn_31669915
+common_voice_bn_31669959
+common_voice_bn_31669962
+common_voice_bn_31669963
+common_voice_bn_31669965
+common_voice_bn_31670133
+common_voice_bn_31670137
+common_voice_bn_31670219
+common_voice_bn_31670640
+common_voice_bn_31670641
+common_voice_bn_31670643
+common_voice_bn_31670644
+common_voice_bn_31670731
+common_voice_bn_31670799
+common_voice_bn_31671151
+common_voice_bn_31671159
+common_voice_bn_31671161
+common_voice_bn_31671164
+common_voice_bn_31671549
+common_voice_bn_31671579
+common_voice_bn_31671663
+common_voice_bn_31671665
+common_voice_bn_31671667
+common_voice_bn_31671675
+common_voice_bn_31671681
+common_voice_bn_31671776
+common_voice_bn_31671785
+common_voice_bn_31671814
+common_voice_bn_31671912
+common_voice_bn_31672112
+common_voice_bn_31672151
+common_voice_bn_31672174
+common_voice_bn_31672176
+common_voice_bn_31672181
+common_voice_bn_31672382
+common_voice_bn_31672393
+common_voice_bn_31672395
+common_voice_bn_31672397
+common_voice_bn_31672766
+common_voice_bn_31672865
+common_voice_bn_31673065
+common_voice_bn_31673068
+common_voice_bn_31673076
+common_voice_bn_31673078
+common_voice_bn_31673225
+common_voice_bn_31673286
+common_voice_bn_31673296
+common_voice_bn_31673331
+common_voice_bn_31673341
+common_voice_bn_31673619
+common_voice_bn_31673620
+common_voice_bn_31673623
+common_voice_bn_31673635
+common_voice_bn_31673802
+common_voice_bn_31673839
+common_voice_bn_31673862
+common_voice_bn_31673878
+common_voice_bn_31673879
+common_voice_bn_31673939
+common_voice_bn_31674079
+common_voice_bn_31674238
+common_voice_bn_31674266
+common_voice_bn_31674413
+common_voice_bn_31674431
+common_voice_bn_31674782
+common_voice_bn_31674876
+common_voice_bn_31674900
+common_voice_bn_31674904
+common_voice_bn_31674911
+common_voice_bn_31674914
+common_voice_bn_31674974
+common_voice_bn_31675014
+common_voice_bn_31675038
+common_voice_bn_31675052
+common_voice_bn_31675153
+common_voice_bn_31675619
+common_voice_bn_31675625
+common_voice_bn_31675630
+common_voice_bn_31675733
+common_voice_bn_31675740
+common_voice_bn_31675773
+common_voice_bn_31675776
+common_voice_bn_31675793
+common_voice_bn_31675819
+common_voice_bn_31675829
+common_voice_bn_31675830
+common_voice_bn_31675833
+common_voice_bn_31675835
+common_voice_bn_31675836
+common_voice_bn_31675838
+common_voice_bn_31675841
+common_voice_bn_31675843
+common_voice_bn_31675844
+common_voice_bn_31675863
+common_voice_bn_31675864
+common_voice_bn_31675865
+common_voice_bn_31675866
+common_voice_bn_31675899
+common_voice_bn_31675900
+common_voice_bn_31675904
+common_voice_bn_31675927
+common_voice_bn_31675928
+common_voice_bn_31675932
+common_voice_bn_31675934
+common_voice_bn_31675943
+common_voice_bn_31676041
+common_voice_bn_31676043
+common_voice_bn_31676044
+common_voice_bn_31676046
+common_voice_bn_31676082
+common_voice_bn_31676083
+common_voice_bn_31676085
+common_voice_bn_31676087
+common_voice_bn_31676089
+common_voice_bn_31676133
+common_voice_bn_31676135
+common_voice_bn_31676386
+common_voice_bn_31676388
+common_voice_bn_31676450
+common_voice_bn_31676549
+common_voice_bn_31676552
+common_voice_bn_31676613
+common_voice_bn_31676616
+common_voice_bn_31676617
+common_voice_bn_31676669
+common_voice_bn_31676719
+common_voice_bn_31676761
+common_voice_bn_31676767
+common_voice_bn_31677033
+common_voice_bn_31677271
+common_voice_bn_31677276
+common_voice_bn_31677294
+common_voice_bn_31677297
+common_voice_bn_31677454
+common_voice_bn_31677467
+common_voice_bn_31677468
+common_voice_bn_31677469
+common_voice_bn_31677470
+common_voice_bn_31677471
+common_voice_bn_31677593
+common_voice_bn_31677596
+common_voice_bn_31677599
+common_voice_bn_31677602
+common_voice_bn_31677605
+common_voice_bn_31677735
+common_voice_bn_31677741
+common_voice_bn_31678086
+common_voice_bn_31678090
+common_voice_bn_31678092
+common_voice_bn_31678097
+common_voice_bn_31678415
+common_voice_bn_31678492
+common_voice_bn_31678560
+common_voice_bn_31678564
+common_voice_bn_31678842
+common_voice_bn_31678862
+common_voice_bn_31678895
+common_voice_bn_31678995
+common_voice_bn_31678996
+common_voice_bn_31679119
+common_voice_bn_31679164
+common_voice_bn_31679185
+common_voice_bn_31679269
+common_voice_bn_31680174
+common_voice_bn_31680234
+common_voice_bn_31680291
+common_voice_bn_31680326
+common_voice_bn_31680387
+common_voice_bn_31680414
+common_voice_bn_31680417
+common_voice_bn_31680426
+common_voice_bn_31680444
+common_voice_bn_31680449
+common_voice_bn_31680453
+common_voice_bn_31680474
+common_voice_bn_31680535
+common_voice_bn_31680547
+common_voice_bn_31680556
+common_voice_bn_31680564
+common_voice_bn_31680566
+common_voice_bn_31680697
+common_voice_bn_31680717
+common_voice_bn_31680788
+common_voice_bn_31680858
+common_voice_bn_31680878
+common_voice_bn_31680961
+common_voice_bn_31681011
+common_voice_bn_31681221
+common_voice_bn_31681397
+common_voice_bn_31681398
+common_voice_bn_31681449
+common_voice_bn_31681552
+common_voice_bn_31681689
+common_voice_bn_31681786
+common_voice_bn_31681833
+common_voice_bn_31681919
+common_voice_bn_31681957
+common_voice_bn_31681986
+common_voice_bn_31681990
+common_voice_bn_31681996
+common_voice_bn_31682004
+common_voice_bn_31682285
+common_voice_bn_31682329
+common_voice_bn_31682344
+common_voice_bn_31682353
+common_voice_bn_31682379
+common_voice_bn_31682410
+common_voice_bn_31682485
+common_voice_bn_31682505
+common_voice_bn_31682699
+common_voice_bn_31682741
+common_voice_bn_31682825
+common_voice_bn_31682922
+common_voice_bn_31683180
+common_voice_bn_31683253
+common_voice_bn_31683375
+common_voice_bn_31683407
+common_voice_bn_31683484
+common_voice_bn_31683619
+common_voice_bn_31683653
+common_voice_bn_31683734
+common_voice_bn_31683849
+common_voice_bn_31683957
+common_voice_bn_31684170
+common_voice_bn_31684235
+common_voice_bn_31684258
+common_voice_bn_31684521
+common_voice_bn_31684697
+common_voice_bn_31684891
+common_voice_bn_31684919
+common_voice_bn_31684927
+common_voice_bn_31685059
+common_voice_bn_31685343
+common_voice_bn_31685497
+common_voice_bn_31685571
+common_voice_bn_31685574
+common_voice_bn_31685577
+common_voice_bn_31685741
+common_voice_bn_31685914
+common_voice_bn_31686218
+common_voice_bn_31686295
+common_voice_bn_31686334
+common_voice_bn_31686365
+common_voice_bn_31686455
+common_voice_bn_31686462
+common_voice_bn_31686479
+common_voice_bn_31686481
+common_voice_bn_31686806
+common_voice_bn_31686947
+common_voice_bn_31686953
+common_voice_bn_31686959
+common_voice_bn_31686963
+common_voice_bn_31686971
+common_voice_bn_31687002
+common_voice_bn_31687235
+common_voice_bn_31687281
+common_voice_bn_31687396
+common_voice_bn_31687423
+common_voice_bn_31687643
+common_voice_bn_31687798
+common_voice_bn_31688457
+common_voice_bn_31688492
+common_voice_bn_31688538
+common_voice_bn_31688822
+common_voice_bn_31688849
+common_voice_bn_31689791
+common_voice_bn_31689802
+common_voice_bn_31689849
+common_voice_bn_31690285
+common_voice_bn_31690509
+common_voice_bn_31690541
+common_voice_bn_31690653
+common_voice_bn_31690737
+common_voice_bn_31690851
+common_voice_bn_31691118
+common_voice_bn_31691287
+common_voice_bn_31691392
+common_voice_bn_31691432
+common_voice_bn_31691458
+common_voice_bn_31691459
+common_voice_bn_31691460
+common_voice_bn_31691582
+common_voice_bn_31691585
+common_voice_bn_31691588
+common_voice_bn_31691661
+common_voice_bn_31691690
+common_voice_bn_31691737
+common_voice_bn_31691755
+common_voice_bn_31691792
+common_voice_bn_31692010
+common_voice_bn_31692132
+common_voice_bn_31692182
+common_voice_bn_31692425
+common_voice_bn_31692824
+common_voice_bn_31692871
+common_voice_bn_31692924
+common_voice_bn_31692988
+common_voice_bn_31693077
+common_voice_bn_31693286
+common_voice_bn_31693298
+common_voice_bn_31693304
+common_voice_bn_31693428
+common_voice_bn_31693702
+common_voice_bn_31693848
+common_voice_bn_31694041
+common_voice_bn_31694049
+common_voice_bn_31694057
+common_voice_bn_31694114
+common_voice_bn_31694264
+common_voice_bn_31694456
+common_voice_bn_31694872
+common_voice_bn_31694877
+common_voice_bn_31695082
+common_voice_bn_31695228
+common_voice_bn_31695243
+common_voice_bn_31695409
+common_voice_bn_31695784
+common_voice_bn_31695894
+common_voice_bn_31695905
+common_voice_bn_31695937
+common_voice_bn_31696022
+common_voice_bn_31696150
+common_voice_bn_31696250
+common_voice_bn_31696376
+common_voice_bn_31696454
+common_voice_bn_31696604
+common_voice_bn_31697177
+common_voice_bn_31697461
+common_voice_bn_31697494
+common_voice_bn_31697581
+common_voice_bn_31697700
+common_voice_bn_31697748
+common_voice_bn_31697936
+common_voice_bn_31698026
+common_voice_bn_31698607
+common_voice_bn_31698708
+common_voice_bn_31698780
+common_voice_bn_31698833
+common_voice_bn_31698978
+common_voice_bn_31698987
+common_voice_bn_31699184
+common_voice_bn_31699255
+common_voice_bn_31699474
+common_voice_bn_31699592
+common_voice_bn_31699937
+common_voice_bn_31700463
+common_voice_bn_31700900
+common_voice_bn_31701049
+common_voice_bn_31701063
+common_voice_bn_31701200
+common_voice_bn_31701288
+common_voice_bn_31701395
+common_voice_bn_31701433
+common_voice_bn_31701438
+common_voice_bn_31701445
+common_voice_bn_31701499
+common_voice_bn_31701551
+common_voice_bn_31701584
+common_voice_bn_31701687
+common_voice_bn_31701717
+common_voice_bn_31701727
+common_voice_bn_31702093
+common_voice_bn_31702140
+common_voice_bn_31702154
+common_voice_bn_31702181
+common_voice_bn_31702342
+common_voice_bn_31702356
+common_voice_bn_31702372
+common_voice_bn_31702373
+common_voice_bn_31702383
+common_voice_bn_31702387
+common_voice_bn_31702402
+common_voice_bn_31702503
+common_voice_bn_31702575
+common_voice_bn_31702652
+common_voice_bn_31702654
+common_voice_bn_31702853
+common_voice_bn_31702870
+common_voice_bn_31703102
+common_voice_bn_31703733
+common_voice_bn_31703757
+common_voice_bn_31703885
+common_voice_bn_31703972
+common_voice_bn_31704358
+common_voice_bn_31704397
+common_voice_bn_31704635
+common_voice_bn_31704805
+common_voice_bn_31704811
+common_voice_bn_31704856
+common_voice_bn_31704948
+common_voice_bn_31704965
+common_voice_bn_31704977
+common_voice_bn_31705071
+common_voice_bn_31705098
+common_voice_bn_31705175
+common_voice_bn_31705176
+common_voice_bn_31705198
+common_voice_bn_31705207
+common_voice_bn_31705344
+common_voice_bn_31705424
+common_voice_bn_31705426
+common_voice_bn_31705434
+common_voice_bn_31705472
+common_voice_bn_31705520
+common_voice_bn_31705596
+common_voice_bn_31705632
+common_voice_bn_31705643
+common_voice_bn_31705651
+common_voice_bn_31705996
+common_voice_bn_31706550
+common_voice_bn_31706552
+common_voice_bn_31706553
+common_voice_bn_31706634
+common_voice_bn_31706644
+common_voice_bn_31706753
+common_voice_bn_31706983
+common_voice_bn_31707054
+common_voice_bn_31707841
+common_voice_bn_31707901
+common_voice_bn_31708103
+common_voice_bn_31708106
+common_voice_bn_31708112
+common_voice_bn_31708907
+common_voice_bn_31709116
+common_voice_bn_31709117
+common_voice_bn_31709141
+common_voice_bn_31709148
+common_voice_bn_31709290
+common_voice_bn_31709328
+common_voice_bn_31709680
+common_voice_bn_31709711
+common_voice_bn_31709728
+common_voice_bn_31710046
+common_voice_bn_31710182
+common_voice_bn_31710324
+common_voice_bn_31711171
+common_voice_bn_31711335
+common_voice_bn_31711344
+common_voice_bn_31711346
+common_voice_bn_31711350
+common_voice_bn_31711352
+common_voice_bn_31711357
+common_voice_bn_31711359
+common_voice_bn_31711629
+common_voice_bn_31711707
+common_voice_bn_31711714
+common_voice_bn_31711779
+common_voice_bn_31711791
+common_voice_bn_31711809
+common_voice_bn_31712081
+common_voice_bn_31712119
+common_voice_bn_31712125
+common_voice_bn_31712233
+common_voice_bn_31712299
+common_voice_bn_31712402
+common_voice_bn_31712612
+common_voice_bn_31712621
+common_voice_bn_31712752
+common_voice_bn_31712768
+common_voice_bn_31712947
+common_voice_bn_31712952
+common_voice_bn_31713162
+common_voice_bn_31713194
+common_voice_bn_31713357
+common_voice_bn_31713358
+common_voice_bn_31713372
+common_voice_bn_31713498
+common_voice_bn_31713550
+common_voice_bn_31714158
+common_voice_bn_31714250
+common_voice_bn_31714478
+common_voice_bn_31714486
+common_voice_bn_31714507
+common_voice_bn_31715041
+common_voice_bn_31715052
+common_voice_bn_31715182
+common_voice_bn_31715448
+common_voice_bn_31715489
+common_voice_bn_31715500
+common_voice_bn_31715775
+common_voice_bn_31715830
+common_voice_bn_31715877
+common_voice_bn_31715903
+common_voice_bn_31715966
+common_voice_bn_31715983
+common_voice_bn_31716186
+common_voice_bn_31716968
+common_voice_bn_31717377
+common_voice_bn_31717918
+common_voice_bn_31717929
+common_voice_bn_31717951
+common_voice_bn_31717952
+common_voice_bn_31717961
+common_voice_bn_31717978
+common_voice_bn_31718001
+common_voice_bn_31718022
+common_voice_bn_31718452
+common_voice_bn_31719216
+common_voice_bn_31719218
+common_voice_bn_31719219
+common_voice_bn_31720064
+common_voice_bn_31720143
+common_voice_bn_31720251
+common_voice_bn_31720379
+common_voice_bn_31720553
+common_voice_bn_31720656
+common_voice_bn_31721298
+common_voice_bn_31721458
+common_voice_bn_31721677
+common_voice_bn_31721690
+common_voice_bn_31721856
+common_voice_bn_31722306
+common_voice_bn_31722618
+common_voice_bn_31722664
+common_voice_bn_31722719
+common_voice_bn_31722983
+common_voice_bn_31723117
+common_voice_bn_31723176
+common_voice_bn_31723226
+common_voice_bn_31723276
+common_voice_bn_31723344
+common_voice_bn_31723349
+common_voice_bn_31723351
+common_voice_bn_31723353
+common_voice_bn_31723357
+common_voice_bn_31723499
+common_voice_bn_31723500
+common_voice_bn_31723502
+common_voice_bn_31723605
+common_voice_bn_31723612
+common_voice_bn_31723615
+common_voice_bn_31723616
+common_voice_bn_31723626
+common_voice_bn_31723633
+common_voice_bn_31723634
+common_voice_bn_31723635
+common_voice_bn_31723636
+common_voice_bn_31723791
+common_voice_bn_31723872
+common_voice_bn_31724080
+common_voice_bn_31724098
+common_voice_bn_31724884
+common_voice_bn_31725045
+common_voice_bn_31725103
+common_voice_bn_31725106
+common_voice_bn_31725109
+common_voice_bn_31725606
+common_voice_bn_31725796
+common_voice_bn_31725798
+common_voice_bn_31725799
+common_voice_bn_31725800
+common_voice_bn_31725812
+common_voice_bn_31726155
+common_voice_bn_31726419
+common_voice_bn_31726421
+common_voice_bn_31726618
+common_voice_bn_31726916
+common_voice_bn_31727347
+common_voice_bn_31727426
+common_voice_bn_31727427
+common_voice_bn_31727428
+common_voice_bn_31727497
+common_voice_bn_31727498
+common_voice_bn_31727499
+common_voice_bn_31727561
+common_voice_bn_31727562
+common_voice_bn_31727593
+common_voice_bn_31727693
+common_voice_bn_31727695
+common_voice_bn_31727697
+common_voice_bn_31727828
+common_voice_bn_31727831
+common_voice_bn_31727833
+common_voice_bn_31727834
+common_voice_bn_31727835
+common_voice_bn_31727988
+common_voice_bn_31727993
+common_voice_bn_31727995
+common_voice_bn_31727996
+common_voice_bn_31727997
+common_voice_bn_31727998
+common_voice_bn_31728311
+common_voice_bn_31728467
+common_voice_bn_31728468
+common_voice_bn_31728469
+common_voice_bn_31728470
+common_voice_bn_31728471
+common_voice_bn_31728779
+common_voice_bn_31729188
+common_voice_bn_31729191
+common_voice_bn_31729193
+common_voice_bn_31729357
+common_voice_bn_31730298
+common_voice_bn_31730515
+common_voice_bn_31730547
+common_voice_bn_31730716
+common_voice_bn_31730749
+common_voice_bn_31730751
+common_voice_bn_31730885
+common_voice_bn_31731089
+common_voice_bn_31731107
+common_voice_bn_31731127
+common_voice_bn_31731130
+common_voice_bn_31731154
+common_voice_bn_31731213
+common_voice_bn_31731230
+common_voice_bn_31731260
+common_voice_bn_31731291
+common_voice_bn_31731321
+common_voice_bn_31731322
+common_voice_bn_31731324
+common_voice_bn_31731555
+common_voice_bn_31731556
+common_voice_bn_31731557
+common_voice_bn_31731558
+common_voice_bn_31731559
+common_voice_bn_31732032
+common_voice_bn_31732263
+common_voice_bn_31732265
+common_voice_bn_31732268
+common_voice_bn_31732279
+common_voice_bn_31732281
+common_voice_bn_31732652
+common_voice_bn_31732980
+common_voice_bn_31732981
+common_voice_bn_31732982
+common_voice_bn_31733319
+common_voice_bn_31733320
+common_voice_bn_31733321
+common_voice_bn_31733322
+common_voice_bn_31733485
+common_voice_bn_31733486
+common_voice_bn_31733487
+common_voice_bn_31733488
+common_voice_bn_31733677
+common_voice_bn_31733686
+common_voice_bn_31733687
+common_voice_bn_31733689
+common_voice_bn_31733690
+common_voice_bn_31733709
+common_voice_bn_31733710
+common_voice_bn_31733753
+common_voice_bn_31733755
+common_voice_bn_31733942
+common_voice_bn_31734229
+common_voice_bn_31734431
+common_voice_bn_31734642
+common_voice_bn_31734967
+common_voice_bn_31735284
+common_voice_bn_31735287
+common_voice_bn_31735288
+common_voice_bn_31735290
+common_voice_bn_31735412
+common_voice_bn_31735415
+common_voice_bn_31735417
+common_voice_bn_31735763
+common_voice_bn_31735765
+common_voice_bn_31735767
+common_voice_bn_31735835
+common_voice_bn_31736035
+common_voice_bn_31736106
+common_voice_bn_31736217
+common_voice_bn_31736324
+common_voice_bn_31736524
+common_voice_bn_31736525
+common_voice_bn_31736526
+common_voice_bn_31736528
+common_voice_bn_31736529
+common_voice_bn_31736721
+common_voice_bn_31736722
+common_voice_bn_31736724
+common_voice_bn_31736725
+common_voice_bn_31737197
+common_voice_bn_31737199
+common_voice_bn_31737735
+common_voice_bn_31739536
+common_voice_bn_31739701
+common_voice_bn_31739704
+common_voice_bn_31739705
+common_voice_bn_31739706
+common_voice_bn_31740100
+common_voice_bn_31740101
+common_voice_bn_31740102
+common_voice_bn_31740104
+common_voice_bn_31740125
+common_voice_bn_31740126
+common_voice_bn_31740158
+common_voice_bn_31740311
+common_voice_bn_31740313
+common_voice_bn_31740662
+common_voice_bn_31740666
+common_voice_bn_31740667
+common_voice_bn_31740668
+common_voice_bn_31741197
+common_voice_bn_31741349
+common_voice_bn_31741578
+common_voice_bn_31741746
+common_voice_bn_31741833
+common_voice_bn_31741837
+common_voice_bn_31741847
+common_voice_bn_31741848
+common_voice_bn_31741849
+common_voice_bn_31741851
+common_voice_bn_31741853
+common_voice_bn_31741867
+common_voice_bn_31741868
+common_voice_bn_31741871
+common_voice_bn_31741872
+common_voice_bn_31742441
+common_voice_bn_31742442
+common_voice_bn_31742443
+common_voice_bn_31742445
+common_voice_bn_31742699
+common_voice_bn_31742700
+common_voice_bn_31742701
+common_voice_bn_31742702
+common_voice_bn_31742703
+common_voice_bn_31743018
+common_voice_bn_31743074
+common_voice_bn_31743259
+common_voice_bn_31743260
+common_voice_bn_31743261
+common_voice_bn_31743262
+common_voice_bn_31743642
+common_voice_bn_31743767
+common_voice_bn_31743845
+common_voice_bn_31743847
+common_voice_bn_31743849
+common_voice_bn_31744241
+common_voice_bn_31744294
+common_voice_bn_31744302
+common_voice_bn_31744523
+common_voice_bn_31744524
+common_voice_bn_31744543
+common_voice_bn_31744610
+common_voice_bn_31744613
+common_voice_bn_31744793
+common_voice_bn_31744836
+common_voice_bn_31744868
+common_voice_bn_31744870
+common_voice_bn_31744875
+common_voice_bn_31744876
+common_voice_bn_31744877
+common_voice_bn_31744910
+common_voice_bn_31744995
+common_voice_bn_31744996
+common_voice_bn_31744997
+common_voice_bn_31744998
+common_voice_bn_31744999
+common_voice_bn_31745020
+common_voice_bn_31745021
+common_voice_bn_31745022
+common_voice_bn_31745023
+common_voice_bn_31745024
+common_voice_bn_31745045
+common_voice_bn_31745046
+common_voice_bn_31745048
+common_voice_bn_31745049
+common_voice_bn_31745311
+common_voice_bn_31745319
+common_voice_bn_31745426
+common_voice_bn_31745427
+common_voice_bn_31745428
+common_voice_bn_31745573
+common_voice_bn_31745630
+common_voice_bn_31745633
+common_voice_bn_31745959
+common_voice_bn_31746089
+common_voice_bn_31746096
+common_voice_bn_31746541
+common_voice_bn_31746606
+common_voice_bn_31746607
+common_voice_bn_31746608
+common_voice_bn_31746609
+common_voice_bn_31746610
+common_voice_bn_31746796
+common_voice_bn_31746854
+common_voice_bn_31747204
+common_voice_bn_31747272
+common_voice_bn_31747396
+common_voice_bn_31747433
+common_voice_bn_31747471
+common_voice_bn_31747509
+common_voice_bn_31747513
+common_voice_bn_31747606
+common_voice_bn_31747692
+common_voice_bn_31747826
+common_voice_bn_31747842
+common_voice_bn_31747874
+common_voice_bn_31747950
+common_voice_bn_31748101
+common_voice_bn_31748165
+common_voice_bn_31748327
+common_voice_bn_31748328
+common_voice_bn_31748329
+common_voice_bn_31748365
+common_voice_bn_31748369
+common_voice_bn_31749407
+common_voice_bn_31749408
+common_voice_bn_31749410
+common_voice_bn_31750052
+common_voice_bn_31750712
+common_voice_bn_31750945
+common_voice_bn_31751376
+common_voice_bn_31751399
+common_voice_bn_31751560
+common_voice_bn_31751561
+common_voice_bn_31751563
+common_voice_bn_31751683
+common_voice_bn_31751748
+common_voice_bn_31751757
+common_voice_bn_31752083
+common_voice_bn_31752308
+common_voice_bn_31752309
+common_voice_bn_31752311
+common_voice_bn_31752684
+common_voice_bn_31752722
+common_voice_bn_31752723
+common_voice_bn_31752724
+common_voice_bn_31752725
+common_voice_bn_31752726
+common_voice_bn_31753218
+common_voice_bn_31753300
+common_voice_bn_31753315
+common_voice_bn_31753323
+common_voice_bn_31753326
+common_voice_bn_31753386
+common_voice_bn_31753461
+common_voice_bn_31753463
+common_voice_bn_31753464
+common_voice_bn_31753465
+common_voice_bn_31753494
+common_voice_bn_31753519
+common_voice_bn_31753693
+common_voice_bn_31753719
+common_voice_bn_31753949
+common_voice_bn_31753964
+common_voice_bn_31754006
+common_voice_bn_31754780
+common_voice_bn_31754841
+common_voice_bn_31755336
+common_voice_bn_31755367
+common_voice_bn_31755478
+common_voice_bn_31755479
+common_voice_bn_31755481
+common_voice_bn_31755482
+common_voice_bn_31755719
+common_voice_bn_31756018
+common_voice_bn_31756323
+common_voice_bn_31756392
+common_voice_bn_31756729
+common_voice_bn_31756941
+common_voice_bn_31757262
+common_voice_bn_31757301
+common_voice_bn_31757962
+common_voice_bn_31758172
+common_voice_bn_31758173
+common_voice_bn_31758174
+common_voice_bn_31758175
+common_voice_bn_31758176
+common_voice_bn_31758495
+common_voice_bn_31758614
+common_voice_bn_31758881
+common_voice_bn_31758991
+common_voice_bn_31758993
+common_voice_bn_31759033
+common_voice_bn_31759078
+common_voice_bn_31759080
+common_voice_bn_31759104
+common_voice_bn_31759229
+common_voice_bn_31759230
+common_voice_bn_31759691
+common_voice_bn_31760073
+common_voice_bn_31760112
+common_voice_bn_31760113
+common_voice_bn_31760114
+common_voice_bn_31760115
+common_voice_bn_31760116
+common_voice_bn_31760213
+common_voice_bn_31760218
+common_voice_bn_31760515
+common_voice_bn_31760581
+common_voice_bn_31761102
+common_voice_bn_31761351
+common_voice_bn_31761924
+common_voice_bn_31762220
+common_voice_bn_31762225
+common_voice_bn_31762245
+common_voice_bn_31762657
+common_voice_bn_31762694
+common_voice_bn_31762748
+common_voice_bn_31762751
+common_voice_bn_31762752
+common_voice_bn_31762999
+common_voice_bn_31763178
+common_voice_bn_31763260
+common_voice_bn_31763261
+common_voice_bn_31763263
+common_voice_bn_31763264
+common_voice_bn_31763310
+common_voice_bn_31763313
+common_voice_bn_31763812
+common_voice_bn_31763960
+common_voice_bn_31763961
+common_voice_bn_31763962
+common_voice_bn_31763963
+common_voice_bn_31763964
+common_voice_bn_31764098
+common_voice_bn_31764099
+common_voice_bn_31764100
+common_voice_bn_31764101
+common_voice_bn_31764102
+common_voice_bn_31764515
+common_voice_bn_31764659
+common_voice_bn_31765194
+common_voice_bn_31765196
+common_voice_bn_31765197
+common_voice_bn_31765198
+common_voice_bn_31765260
+common_voice_bn_31765262
+common_voice_bn_31765265
+common_voice_bn_31765349
+common_voice_bn_31765507
+common_voice_bn_31765546
+common_voice_bn_31765548
+common_voice_bn_31765554
+common_voice_bn_31765813
+common_voice_bn_31765852
+common_voice_bn_31765907
+common_voice_bn_31766244
+common_voice_bn_31766248
+common_voice_bn_31766642
+common_voice_bn_31767017
+common_voice_bn_31767632
+common_voice_bn_31767891
+common_voice_bn_31767894
+common_voice_bn_31768268
+common_voice_bn_31768545
+common_voice_bn_31768722
+common_voice_bn_31769081
+common_voice_bn_31769082
+common_voice_bn_31769090
+common_voice_bn_31769095
+common_voice_bn_31769097
+common_voice_bn_31769098
+common_voice_bn_31769099
+common_voice_bn_31769100
+common_voice_bn_31769101
+common_voice_bn_31769103
+common_voice_bn_31769104
+common_voice_bn_31769105
+common_voice_bn_31769107
+common_voice_bn_31769108
+common_voice_bn_31769170
+common_voice_bn_31769172
+common_voice_bn_31769173
+common_voice_bn_31769174
+common_voice_bn_31769538
+common_voice_bn_31769614
+common_voice_bn_31769777
+common_voice_bn_31769778
+common_voice_bn_31769779
+common_voice_bn_31769780
+common_voice_bn_31769856
+common_voice_bn_31769859
+common_voice_bn_31769862
+common_voice_bn_31769864
+common_voice_bn_31769867
+common_voice_bn_31769872
+common_voice_bn_31769878
+common_voice_bn_31769880
+common_voice_bn_31769886
+common_voice_bn_31769887
+common_voice_bn_31769888
+common_voice_bn_31769890
+common_voice_bn_31769977
+common_voice_bn_31770031
+common_voice_bn_31770083
+common_voice_bn_31770084
+common_voice_bn_31770085
+common_voice_bn_31770087
+common_voice_bn_31770212
+common_voice_bn_31770399
+common_voice_bn_31770686
+common_voice_bn_31770688
+common_voice_bn_31770708
+common_voice_bn_31770861
+common_voice_bn_31770863
+common_voice_bn_31770864
+common_voice_bn_31770865
+common_voice_bn_31771361
+common_voice_bn_31771409
+common_voice_bn_31771410
+common_voice_bn_31771625
+common_voice_bn_31771627
+common_voice_bn_31771630
+common_voice_bn_31771703
+common_voice_bn_31771721
+common_voice_bn_31771973
+common_voice_bn_31772113
+common_voice_bn_31772124
+common_voice_bn_31772222
+common_voice_bn_31772223
+common_voice_bn_31772265
+common_voice_bn_31772266
+common_voice_bn_31772346
+common_voice_bn_31772398
+common_voice_bn_31772399
+common_voice_bn_31772400
+common_voice_bn_31772404
+common_voice_bn_31772652
+common_voice_bn_31772653
+common_voice_bn_31772654
+common_voice_bn_31772655
+common_voice_bn_31772656
+common_voice_bn_31772672
+common_voice_bn_31772892
+common_voice_bn_31772972
+common_voice_bn_31773505
+common_voice_bn_31773535
+common_voice_bn_31773539
+common_voice_bn_31773651
+common_voice_bn_31773653
+common_voice_bn_31773655
+common_voice_bn_31773657
+common_voice_bn_31773659
+common_voice_bn_31773758
+common_voice_bn_31773760
+common_voice_bn_31773761
+common_voice_bn_31773812
+common_voice_bn_31773855
+common_voice_bn_31773913
+common_voice_bn_31773946
+common_voice_bn_31774320
+common_voice_bn_31774502
+common_voice_bn_31774544
+common_voice_bn_31774547
+common_voice_bn_31775860
+common_voice_bn_31775861
+common_voice_bn_31775862
+common_voice_bn_31775864
+common_voice_bn_31775886
+common_voice_bn_31775888
+common_voice_bn_31775889
+common_voice_bn_31775891
+common_voice_bn_31775893
+common_voice_bn_31775960
+common_voice_bn_31776246
+common_voice_bn_31776372
+common_voice_bn_31776435
+common_voice_bn_31776457
+common_voice_bn_31776459
+common_voice_bn_31776460
+common_voice_bn_31776461
+common_voice_bn_31776568
+common_voice_bn_31776700
+common_voice_bn_31777342
+common_voice_bn_31777802
+common_voice_bn_31777848
+common_voice_bn_31777864
+common_voice_bn_31777865
+common_voice_bn_31777868
+common_voice_bn_31777920
+common_voice_bn_31778016
+common_voice_bn_31778368
+common_voice_bn_31778691
+common_voice_bn_31778693
+common_voice_bn_31778886
+common_voice_bn_31779197
+common_voice_bn_31779659
+common_voice_bn_31779765
+common_voice_bn_31779767
+common_voice_bn_31780047
+common_voice_bn_31780049
+common_voice_bn_31780501
+common_voice_bn_31780589
+common_voice_bn_31780792
+common_voice_bn_31780840
+common_voice_bn_31780976
+common_voice_bn_31781084
+common_voice_bn_31781605
+common_voice_bn_31782044
+common_voice_bn_31782079
+common_voice_bn_31783553
+common_voice_bn_31784057
+common_voice_bn_31784318
+common_voice_bn_31784333
+common_voice_bn_31784384
+common_voice_bn_31784538
+common_voice_bn_31784564
+common_voice_bn_31784566
+common_voice_bn_31785133
+common_voice_bn_31785212
+common_voice_bn_31785249
+common_voice_bn_31785528
+common_voice_bn_31785667
+common_voice_bn_31785668
+common_voice_bn_31785944
+common_voice_bn_31785979
+common_voice_bn_31785980
+common_voice_bn_31785981
+common_voice_bn_31786203
+common_voice_bn_31786217
+common_voice_bn_31786281
+common_voice_bn_31786282
+common_voice_bn_31786283
+common_voice_bn_31786285
+common_voice_bn_31786367
+common_voice_bn_31786516
+common_voice_bn_31786519
+common_voice_bn_31786520
+common_voice_bn_31786521
+common_voice_bn_31786522
+common_voice_bn_31786845
+common_voice_bn_31787124
+common_voice_bn_31787691
+common_voice_bn_31788045
+common_voice_bn_31788130
+common_voice_bn_31788418
+common_voice_bn_31788513
+common_voice_bn_31788515
+common_voice_bn_31788516
+common_voice_bn_31788673
+common_voice_bn_31789054
+common_voice_bn_31789055
+common_voice_bn_31789056
+common_voice_bn_31789392
+common_voice_bn_31789393
+common_voice_bn_31789394
+common_voice_bn_31789395
+common_voice_bn_31789397
+common_voice_bn_31789475
+common_voice_bn_31789476
+common_voice_bn_31789477
+common_voice_bn_31789478
+common_voice_bn_31789479
+common_voice_bn_31789669
+common_voice_bn_31789694
+common_voice_bn_31790059
+common_voice_bn_31791040
+common_voice_bn_31791041
+common_voice_bn_31791043
+common_voice_bn_31791044
+common_voice_bn_31791090
+common_voice_bn_31791092
+common_voice_bn_31791138
+common_voice_bn_31791139
+common_voice_bn_31791140
+common_voice_bn_31791141
+common_voice_bn_31791142
+common_voice_bn_31791910
+common_voice_bn_31791987
+common_voice_bn_31792072
+common_voice_bn_31793357
+common_voice_bn_31793766
+common_voice_bn_31794478
+common_voice_bn_31794575
+common_voice_bn_31796218
+common_voice_bn_31796716
+common_voice_bn_31797835
+common_voice_bn_31797836
+common_voice_bn_31798447
+common_voice_bn_31798570
+common_voice_bn_31799923
+common_voice_bn_31800225
+common_voice_bn_31802483
+common_voice_bn_31803201
+common_voice_bn_31803980
+common_voice_bn_31804361
+common_voice_bn_31805137
+common_voice_bn_31805387
+common_voice_bn_31805441
+common_voice_bn_31805468
+common_voice_bn_31806488
+common_voice_bn_31806490
+common_voice_bn_31807719
+common_voice_bn_31808188
+common_voice_bn_31809237
+common_voice_bn_31810075
+common_voice_bn_31810245
+common_voice_bn_31810246
+common_voice_bn_31810247
+common_voice_bn_31810248
+common_voice_bn_31810249
+common_voice_bn_31810418
+common_voice_bn_31810435
+common_voice_bn_31810437
+common_voice_bn_31810438
+common_voice_bn_31810693
+common_voice_bn_31810714
+common_voice_bn_31811341
+common_voice_bn_31811425
+common_voice_bn_31811494
+common_voice_bn_31811511
+common_voice_bn_31811533
+common_voice_bn_31811914
+common_voice_bn_31815179
+common_voice_bn_31815991
+common_voice_bn_31816315
+common_voice_bn_31816316
+common_voice_bn_31816710
+common_voice_bn_31817036
+common_voice_bn_31817037
+common_voice_bn_31817038
+common_voice_bn_31817090
+common_voice_bn_31817127
+common_voice_bn_31817130
+common_voice_bn_31817132
+common_voice_bn_31817134
+common_voice_bn_31817159
+common_voice_bn_31818272
+common_voice_bn_31818995
+common_voice_bn_31818996
+common_voice_bn_31818997
+common_voice_bn_31818998
+common_voice_bn_31818999
+common_voice_bn_31819000
+common_voice_bn_31819001
+common_voice_bn_31819002
+common_voice_bn_31819004
+common_voice_bn_31819251
+common_voice_bn_31819471
+common_voice_bn_31819565
+common_voice_bn_31820299
+common_voice_bn_31828135
+common_voice_bn_31828948
+common_voice_bn_31828950
+common_voice_bn_31828952
+common_voice_bn_31828954
+common_voice_bn_31828955
+common_voice_bn_31831117
+common_voice_bn_31831119
+common_voice_bn_31832651

eval-args.txt

@@ -0,0 +1,63 @@
+
+## Generates eval.sh for testing if script works
+echo 'python my-evaluation.py \
+	--model_id="openai/whisper-tiny" \
+	--dataset="google/fleurs" \
+	--config="bn_in" \
+	--language="bn" \
+	--split="test" \
+	--max_eval_samples="50" \
+	--batch_size="16" \
+	--do_bangla_unicode_normalize="True" \
+	--device="0" \
+	--streaming="False"' >> eval.sh
+
+##  Evaluates on google/fleurs test set
+echo 'python my-evaluation.py \
+	--model_id="openai/whisper-small-bn-all-400" \
+	--dataset="google/fleurs" \
+	--config="bn_in" \
+	--language="bn" \
+	--split="test" \
+	--batch_size="16" \
+	--do_bangla_unicode_normalize="True" \
+	--device="0" \
+	--streaming="False"' >> eval.sh
+	
+## Evaluates on common voice 11.0
+echo 'python my-evaluation.py \
+	--model_id="openai/whisper-small-bn-all-400" \
+	--dataset="mozilla-foundation/common_voice_11_0" \
+	--config="bn" \
+	--language="bn" \
+	--split="test" \
+	--batch_size="16" \
+	--do_bangla_unicode_normalize="True" \
+	--device="0" \
+	--streaming="False"' >> eval.sh
+	
+## Evaluates on openslr 53
+echo 'python my-evaluation.py \
+	--model_id="openai/whisper-small-bn-all-400" \
+	--dataset="openslr" \
+	--config="SLR53" \
+	--language="bn" \
+	--split="test" \
+	--batch_size="16" \
+	--do_bangla_unicode_normalize="True" \
+	--device="0" \
+	--streaming="False"' >> eval.sh
+
+
+
+
+#max_eval_samples MAX_EVAL_SAMPLES. Number of samples to be evaluated. Put a lower number e.g. 64 for testing this script.
+#(default: None)
+
+	--max_eval_samples="50"
+
+
+
+
+
+

eval.sh

@@ -0,0 +1,11 @@
+python my-evaluation.py \
+--model_id="openai/whisper-tiny" \
+--dataset="google/fleurs" \
+--config="bn_in" \
+--language="bn" \
+--split="test" \
+--max_eval_samples="50" \
+--batch_size="16" \
+--do_bangla_unicode_normalize="True" \
+--device="0" \
+--streaming="False"

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "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

@@ -0,0 +1,222 @@
+{
+  "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-evaluation.py

@@ -0,0 +1,237 @@
+import argparse
+import os
+from regex import R
+
+abs_path = os.path.abspath('.')
+# base_dir = os.path.dirname(os.path.dirname(abs_path))
+base_dir = os.path.dirname(abs_path)
+
+
+os.environ['TRANSFORMERS_CACHE'] = os.path.join(base_dir, 'models_cache')
+os.environ['TRANSFORMERS_OFFLINE'] = '0'
+os.environ['HF_DATASETS_CACHE'] = os.path.join(base_dir, 'datasets_cache')
+os.environ['HF_DATASETS_OFFLINE'] = '0'
+
+from transformers import pipeline
+from transformers.models.whisper.english_normalizer import BasicTextNormalizer
+from datasets import load_dataset, Audio
+from bnunicodenormalizer import Normalizer
+import evaluate
+import unicodedata
+
+wer_metric = evaluate.load("wer", cache_dir=os.path.join(base_dir, "metrics_cache"))
+cer_metric = evaluate.load("cer", cache_dir=os.path.join(base_dir, "metrics_cache"))
+
+
+def is_target_text_in_range(ref):
+    if ref.strip() == "ignore time segment in scoring":
+        return False
+    else:
+        return ref.strip() != ""
+
+
+def get_text(sample):
+    if "text" in sample:
+        return sample["text"]
+    elif "sentence" in sample:
+        return sample["sentence"]
+    elif "normalized_text" in sample:
+        return sample["normalized_text"]
+    elif "transcript" in sample:
+        return sample["transcript"]
+    elif "transcription" in sample:
+        return sample["transcription"]
+    else:
+        raise ValueError(
+            "Expected transcript column of either 'text', 'sentence', 'normalized_text' or 'transcript'. Got sample of "
+            ".join{sample.keys()}. Ensure a text column name is present in the dataset."
+        )
+
+
+whisper_norm = BasicTextNormalizer()
+bangla_normalizer = Normalizer(allow_english=True)
+
+
+def normalise(batch):
+    batch["norm_text"] = whisper_norm(get_text(batch))
+    return batch
+
+def removeOptionalZW(text):
+    """
+    Removes all optional occurrences of ZWNJ or ZWJ from Bangla text.
+    """
+    # Regex for matching zero witdh joiner variations.
+    STANDARDIZE_ZW = re.compile(r'(?<=\u09b0)[\u200c\u200d]+(?=\u09cd\u09af)')
+
+    # Regex for removing standardized zero width joiner, except in edge cases.
+    DELETE_ZW = re.compile(r'(?<!\u09b0)[\u200c\u200d](?!\u09cd\u09af)')
+    
+    text = STANDARDIZE_ZW.sub('\u200D', text)
+    text = DELETE_ZW.sub('', text)
+    return text
+
+def bn_unicode_normalise(batch):
+    _words = [bangla_normalizer(word)['normalized'] for word in get_text(batch).split()]
+    normalized_text = " ".join([word for word in _words if word is not None])
+    normalized_text = normalized_text.replace("\u2047", "-")
+    normalized_text = normalized_text.replace(u"\u098c", u"\u09ef")
+    normalized_text = unicodedata.normalize("NFC", normalized_text)
+    normalized_text = removeOptionalZW(normalized_text)
+    batch["norm_text"] = whisper_norm(normalized_text)
+    return batch
+
+
+def data(dataset):
+    for item in dataset:
+        yield {**item["audio"], "reference": item["norm_text"]}
+
+
+def main(args):
+    batch_size = args.batch_size
+    whisper_asr = pipeline(
+        "automatic-speech-recognition", model=args.model_id, device=args.device
+    )
+
+    whisper_asr.model.config.forced_decoder_ids = (
+        whisper_asr.tokenizer.get_decoder_prompt_ids(
+            language=args.language, task="transcribe"
+        )
+    )
+
+    dataset = load_dataset(
+        args.dataset,
+        args.config,
+        split=args.split,
+        streaming=args.streaming,
+        use_auth_token=True,
+        cache_dir=os.path.join(base_dir, 'datasets_cache'),
+    )
+
+    # Only uncomment for debugging
+    dataset = dataset.take(args.max_eval_samples)
+
+    dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
+    
+    if args.do_bangla_unicode_normalize:
+        print("\n\n Doing Unicode Normalization! Make sure you have chosen the Bengali split of your dataset! \n\n")
+        dataset = dataset.map(bn_unicode_normalise)
+    else:
+        dataset = dataset.map(normalise)
+            
+    dataset = dataset.filter(is_target_text_in_range, input_columns=["norm_text"])
+
+    predictions = []
+    references = []
+
+    # run streamed inference
+    for out in whisper_asr(data(dataset), batch_size=batch_size):
+        predictions.append(whisper_norm(out["text"]))
+        references.append(out["reference"][0])
+
+    wer = wer_metric.compute(references=references, predictions=predictions)
+    wer = round(100 * wer, 2)
+    
+    cer = cer_metric.compute(references=references, predictions=predictions)
+    cer = round(100 * cer, 2)
+
+    print(f"\n\n WER: {wer} \n\n")
+    print(f"\n\n CER: {cer} \n\n")
+    
+    evaluate.push_to_hub(
+        model_id=args.model_id,
+        metric_value=wer,
+        metric_type="wer",
+        metric_name="WER",
+        dataset_name=args.dataset,
+        dataset_type=args.dataset,
+        dataset_split=args.split,
+        dataset_config=args.config,
+        task_type="automatic-speech-recognition",
+        task_name="Automatic Speech Recognition",
+        overwrite=True
+    )
+    
+    evaluate.push_to_hub(
+        model_id=args.model_id,
+        metric_value=cer,
+        metric_type="cer",
+        metric_name="CER",
+        dataset_name=args.dataset,
+        dataset_type=args.dataset,
+        dataset_split=args.split,
+        dataset_config=args.config,
+        task_type="automatic-speech-recognition",
+        task_name="Automatic Speech Recognition",
+        overwrite=True
+    )
+        
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--model_id",
+        type=str,
+        required=True,
+        help="Model identifier. Should be loadable with 🤗 Transformers",
+    )
+    parser.add_argument(
+        "--dataset",
+        type=str,
+        default="mozilla-foundation/common_voice_11_0",
+        help="Dataset name to evaluate the `model_id`. Should be loadable with 🤗 Datasets",
+    )
+    parser.add_argument(
+        "--config",
+        type=str,
+        required=True,
+        help="Config of the dataset. *E.g.* `'en'` for the English split of Common Voice",
+    )
+    parser.add_argument(
+        "--split",
+        type=str,
+        default="test",
+        help="Split of the dataset. *E.g.* `'test'`",
+    )
+
+    parser.add_argument(
+        "--device",
+        type=int,
+        default=-1,
+        help="The device to run the pipeline on. -1 for CPU (default), 0 for the first GPU and so on.",
+    )
+    parser.add_argument(
+        "--batch_size",
+        type=int,
+        default=16,
+        help="Number of samples to go through each streamed batch.",
+    )
+    parser.add_argument(
+        "--max_eval_samples",
+        type=int,
+        default=None,
+        help="Number of samples to be evaluated. Put a lower number e.g. 64 for testing this script.",
+    )
+    parser.add_argument(
+        "--streaming",
+        type=bool,
+        default=True,
+        help="Choose whether you'd like to download the entire dataset or stream it during the evaluation.",
+    )
+    parser.add_argument(
+        "--do_bangla_unicode_normalize",
+        type=bool,
+        default=True,
+        help="Choose whether you'd like to perform unicode normalization on your Bengali",
+    )
+    parser.add_argument(
+        "--language",
+        type=str,
+        required=True,
+        help="Two letter language code for the transcription language, e.g. use 'en' for English.",
+    )
+    
+    args = parser.parse_args()
+
+    main(args)

my-training.py

@@ -0,0 +1,767 @@
+## Dependencies (run in the venv before running this script)
+# pip install git+https://github.com/huggingface/datasets git+https://github.com/huggingface/transformers 
+# pip install huggingface_hub ipywidgets librosa evaluate>=0.3.0 jiwer bnunicodenormalizer
+# pip install tensorboardX
+# sudo add-apt-repository -y ppa:jonathonf/ffmpeg-4
+# sudo apt update
+# sudo apt install -y ffmpeg
+#sudo apt-get install git-lfs
+
+
+## Run the following commands separately before running the py version of this notebook to connect to HuggningFace Hub!
+#   git config --global credential.helper store
+#   huggingface-cli login
+## Enter your token by visiting: https://huggingface.co/settings/tokens
+## Create a repo in the hub:
+#   huggingface-cli repo create whisper-small-es OR, huggingface-cli repo create <repo_name/model_name>
+## Install git lfs and clone the just created repo
+#   git lfs install
+#   git clone <repo_link>
+## cd to the cloned repo and copy (cp) this python script or everything in training dir to that repo
+#   cd <repo_name/model_name>
+#   cp /home/mamun/asr_training/Govt_Speech_Demo/training/my-training.py .
+
+
+#For more details: https://github.com/huggingface/community-events/tree/main/whisper-fine-tuning-event
+
+
+
+## 1. Setting Up Environment Variables & Devices
+import os
+import torch
+
+abs_path = os.path.abspath('.')
+# base_dir = os.path.dirname(os.path.dirname(abs_path))
+base_dir = os.path.dirname(abs_path)
+
+os.environ['TRANSFORMERS_CACHE'] = os.path.join(base_dir, 'models_cache')
+os.environ['TRANSFORMERS_OFFLINE'] = '0'
+os.environ['HF_DATASETS_CACHE'] = os.path.join(base_dir, 'datasets_cache')
+os.environ['HF_DATASETS_OFFLINE'] = '0'
+
+# device = "GPU" if torch.cuda.is_available() else "CPU"
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+print(f"\n\n Device to be used: {device} \n\n")
+
+
+## 2. Setting Up Variables
+# model_name = "openai/whisper-tiny"
+model_name = "openai/whisper-small"
+# model_name = "openai/whisper-large-v2"
+
+language = "Bengali"
+task = "transcribe" # transcribe or translate
+print(f"\n\n Loading {model_name} for {language} to {task}...this might take a while.. \n\n")
+
+
+## 3. Setting Up Training Args
+output_dir = "./" 
+overwrite_output_dir = True
+max_steps = 50
+# max_steps = 5
+per_device_train_batch_size = 4 
+# per_device_train_batch_size = 1 
+per_device_eval_batch_size = 32 
+# per_device_eval_batch_size = 1 
+gradient_accumulation_steps = 16 
+# gradient_accumulation_steps = 1 
+dataloader_num_workers = 0 #Default: 0 and 0 for Windows
+gradient_checkpointing = False 
+evaluation_strategy ="steps" 
+# eval_steps = 5
+eval_steps = 100 
+save_strategy = "steps" 
+save_steps = 100 
+# 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 = 1 
+logging_steps = 25
+# logging_steps = 1
+# weight_decay = 0.01
+weight_decay = 0 
+dropout = 0.1  # any value > 0.1 hurts performance. So, use values between 0.0 and 0.1
+load_best_model_at_end = True 
+metric_for_best_model = "wer" 
+greater_is_better = False 
+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
+report_to = ["tensorboard"] 
+predict_with_generate = True
+push_to_hub = True
+# push_to_hub = False
+freeze_feature_encoder = False 
+early_stopping_patience = 10
+apply_spec_augment = True
+torch_compile = False #Windows not yet supported
+optim="adamw_hf" # adamw_hf (default), adamw_torch, adamw_torch_fused (improved), adamw_apex_fused, adamw_anyprecision or adafactor
+
+
+## 4. Load Datasets
+print("\n\n Loading Datasets...this might take a while..\n\n")
+
+from datasets import load_dataset, DatasetDict, Features, Value, Audio
+
+common_voice = DatasetDict()
+google_fleurs = DatasetDict()
+openslr = DatasetDict()
+## commonvoice_11.0 + google_fleurs + openslr53
+my_dataset = DatasetDict()
+
+common_voice["train"] = load_dataset("mozilla-foundation/common_voice_11_0", "bn", split="train+validation", cache_dir=os.path.join(base_dir, 'datasets_cache'))
+google_fleurs["train"] = load_dataset("google/fleurs", "bn_in", split="train+validation", cache_dir=os.path.join(base_dir, 'datasets_cache'))
+openslr = load_dataset("openslr", "SLR53", cache_dir=os.path.join(base_dir, 'datasets_cache'))
+
+# loading crblp dataset
+features = Features(
+    {
+        "text": Value("string"), 
+        'path': Value('string'),
+        "audio": Audio(sampling_rate=16000)
+    }
+)
+
+crblp = load_dataset(
+    'csv', 
+    data_files='D:/Govt_Speech_Demo/crblp_speech_corpus/crblp_train.csv', 
+    split='train',
+    cache_dir=os.path.join(base_dir, 'datasets_cache'),
+    features=features
+    )
+
+
+common_voice["test"] = load_dataset("mozilla-foundation/common_voice_11_0", "bn", split="test", cache_dir=os.path.join(base_dir, 'datasets_cache'))
+google_fleurs["test"] = load_dataset("google/fleurs", "bn_in", split="test", cache_dir=os.path.join(base_dir, 'datasets_cache'))
+
+
+# see count of samples in each dataset
+print("\n\n Datasets Loaded \n\n")
+print(common_voice)
+print(google_fleurs)
+print(openslr)
+print(crblp)
+
+
+## 5. Small Subset for Testing
+# common_voice['train']  = common_voice['train'].select(range(50))
+# common_voice['test']  = common_voice['test'].select(range(50))
+# google_fleurs['train']  = google_fleurs['train'].select(range(50))
+# google_fleurs['test']  = google_fleurs['test'].select(range(50))
+# openslr['train'] = openslr['train'].select(range(50))
+# crblp = crblp.select(range(50))
+
+# print("\n\n For testing, the small subsets are:")
+# print(common_voice)
+# print(google_fleurs)
+# print(openslr)
+# print(crblp)
+# print("\n")
+
+# print("\n EXITING \n")
+# import sys
+# sys.exit()
+
+
+## Removing bad samples from common_voice based on upvotes and downvotes
+print("\n BEFORE Filtering by Upvotes (Common Voice): \n")
+print(common_voice["train"])
+# FILTERING!!! Will get 37k Data if >0 and will get 201k Data if >=0 out of 207k
+common_voice["train"] = common_voice["train"].filter(lambda x: (x["up_votes"] - x["down_votes"]) >= 0, num_proc=None)
+print("\n AFTER Filtering by Upvotes (Common Voice): \n")
+print(common_voice["train"])
+
+
+## REMOVE Corrupt Files (Only required if you use the "other" split of Common Voice)
+# skipFiles = open("corrupt_files.txt").read().splitlines()
+# skipFiles = skipFiles[3:]
+# length = len(skipFiles)
+# first = skipFiles[0]
+# last = skipFiles[-1]
+# print(f"\n No. of corrupt files: {length}, First: {first}, Last {last}\n")
+
+# print("\n Finding indexes of corrupt files... \n")
+# from tqdm import tqdm
+# count=0
+# error_index = []
+# for i in tqdm(range(len(common_voice["train"]))):
+#     path = common_voice["train"][i]["path"].split("/")[-1].split(".")[0]
+#     if path in skipFiles:
+#         # print(path)
+#         count+=1
+#         error_index.append(i)
+# print(f"\n Total Corrupt Files: {count} \n")
+
+# print("\n Removing corrupt files from the Common Voice dataset...\n")
+# common_voice["train"] = common_voice["train"].filter(lambda example, idx: idx not in error_index, with_indices=True)
+
+
+print("\n\n So, the datasets to be trained are: \n\n")
+print("\n Common Voice 11.0 - Bangla\n")
+print(common_voice)
+print("\n Google Fleurs - Bangla \n")
+print(google_fleurs)
+print("\n OpenSLR-53 - Bangla \n")
+print(openslr)
+print("\n CRBLP - Bangla \n")
+print(crblp)
+print("\n")
+
+
+
+## 6. Merge Datasets
+from datasets import concatenate_datasets, Audio
+
+sampling_rate = 16000
+
+## resample to specified sampling rate
+common_voice = common_voice.cast_column("audio", Audio(sampling_rate))
+google_fleurs = google_fleurs.cast_column("audio", Audio(sampling_rate))
+openslr = openslr.cast_column("audio", Audio(sampling_rate))
+crblp = crblp.cast_column("audio", Audio(sampling_rate))
+
+## normalise columns to ["audio", "sentence"]
+common_voice = common_voice.remove_columns(
+    set(common_voice['test'].features.keys()) - {"audio", "sentence"}
+)
+
+google_fleurs = google_fleurs.rename_column("raw_transcription", "sentence")
+google_fleurs = google_fleurs.remove_columns(
+    set(google_fleurs['test'].features.keys()) - {"audio", "sentence"}
+)
+
+openslr = openslr.remove_columns(
+    set(openslr['train'].features.keys()) - {"audio", "sentence"}
+)
+
+crblp = crblp.rename_column("text", "sentence")
+crblp = crblp.remove_columns(
+    set(crblp.features.keys()) - {"audio", "sentence"}
+)
+
+## check if all audio are in float32 dtype or not.
+## a fix is: https://github.com/huggingface/datasets/issues/5345
+print("\n Checking all audio dtype is float32 or not... \n")
+print(f'Common Voice Train: {common_voice["train"][0]["audio"]["array"].dtype}')
+print(f'Common Voice Test: {common_voice["test"][0]["audio"]["array"].dtype}')
+print(f'Google Fleurs Train: {google_fleurs["train"][0]["audio"]["array"].dtype}')
+print(f'Google Fleurs Test: {google_fleurs["test"][0]["audio"]["array"].dtype}')
+print(f'OpenSlR: {openslr["train"][0]["audio"]["array"].dtype}')
+print(f'CRBLP: {crblp[0]["audio"]["array"].dtype}')
+print("\n")
+
+
+## merge the three datasets
+# my_dataset['train'] = concatenate_datasets([common_voice['train'], google_fleurs['train'], openslr['train']]) #for linux
+my_dataset['train'] = concatenate_datasets([common_voice['train'], google_fleurs['train'], openslr['train'], crblp]) #for linux
+# my_dataset['train'] = concatenate_datasets([common_voice['train'], openslr['train']])
+# my_dataset['train'] = concatenate_datasets([google_fleurs['train'], openslr['train']]) #for windows no commonvoice as it requires ffmpeg-4
+# my_dataset['train'] = google_fleurs['train']
+my_dataset['test'] = concatenate_datasets([common_voice['test'], google_fleurs['test']]) #for linux
+# my_dataset['test'] = common_voice['test']
+# my_dataset['test'] = concatenate_datasets([google_fleurs['test']]) #for windows no commonvoice as it requires ffmpeg-4
+
+#shuffle train set with seed=42
+my_dataset['train'] = my_dataset['train'].shuffle(seed=10)
+
+print("\n\n AFTER MERGING, train and validation sets are: ")
+print(my_dataset)
+print("\n")
+
+
+## 6. Augmentation
+print("\n\n Augmenting Datasets...this might take a while..\n\n")
+from audiomentations import (
+    AddBackgroundNoise,
+    AddGaussianNoise,
+    Compose,
+    Gain,
+    OneOf,
+    PitchShift,
+    PolarityInversion,
+    TimeStretch,
+)
+
+# define augmentation
+augmentation = Compose(
+    [
+        TimeStretch(min_rate=0.9, max_rate=1.1, p=0.2, leave_length_unchanged=False),
+        Gain(min_gain_in_db=-6, max_gain_in_db=6, p=0.1),
+        PitchShift(min_semitones=-4, max_semitones=4, p=0.2),
+        AddGaussianNoise(min_amplitude=0.005, max_amplitude=0.015, p=1.0),
+    ]
+)
+
+def augment_dataset(batch):
+    # load and (possibly) resample audio data to 16kHz
+    sample = batch['audio']
+
+    # apply augmentation
+    augmented_waveform = augmentation(sample["array"], sample_rate=sample["sampling_rate"])
+    batch['audio']["array"] = augmented_waveform
+    return batch
+
+# augment training data
+augmented_raw_training_dataset = my_dataset["train"].map(
+    augment_dataset, 
+    num_proc=1, 
+    desc="augment train dataset",
+    load_from_cache_file=True, 
+    cache_file_name=os.path.join(base_dir, 'datasets_cache', 'augmented_train_cache.arrow')
+)
+
+print("\n COMBINING Augmented Dataset with Normal Dataset..... \n")
+# combine
+my_dataset["train"] = concatenate_datasets([my_dataset["train"], augmented_raw_training_dataset])
+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))
+
+print("\n\n AFTER AUGMENTATION, FINAL train and validation sets are: ")
+print("\n FINAL DATASET: \n")
+print(my_dataset)
+
+# #debugging
+# print("\n EXITING \n")
+# import sys
+# sys.exit()
+
+## 7. Prepare Feature Extractor, Tokenizer and Processor
+from transformers import WhisperFeatureExtractor, WhisperTokenizer, WhisperTokenizerFast, WhisperProcessor
+
+feature_extractor = WhisperFeatureExtractor.from_pretrained(model_name)
+
+# tokenizer = WhisperTokenizer.from_pretrained(model_name, language=language, task=task)
+# tokenizer = WhisperTokenizerFast.from_pretrained(model_name, language=language, task=task)
+
+processor = WhisperProcessor.from_pretrained(model_name, language=language, task=task)
+
+
+## 8. Preprocessing Data
+print("\n\n Preprocessing Datasets...this might take a while..\n\n")
+
+from transformers.models.whisper.english_normalizer import BasicTextNormalizer
+from bnunicodenormalizer import Normalizer
+import unicodedata
+import re
+
+do_lower_case = False
+do_remove_punctuation = False
+do_bangla_unicode_normalization = True
+
+normalizer = BasicTextNormalizer()
+bangla_normalizer = Normalizer(allow_english=True)
+
+
+def removeOptionalZW(text):
+    """
+    Removes all optional occurrences of ZWNJ or ZWJ from Bangla text.
+    """
+    # Regex for matching zero witdh joiner variations.
+    STANDARDIZE_ZW = re.compile(r'(?<=\u09b0)[\u200c\u200d]+(?=\u09cd\u09af)')
+
+    # Regex for removing standardized zero width joiner, except in edge cases.
+    DELETE_ZW = re.compile(r'(?<!\u09b0)[\u200c\u200d](?!\u09cd\u09af)')
+    
+    text = STANDARDIZE_ZW.sub('\u200D', text)
+    text = DELETE_ZW.sub('', text)
+    return text
+
+
+def prepare_dataset(batch):
+    # load and (possibly) resample audio data to 16kHz
+    audio = batch["audio"]
+
+    # compute log-Mel input features from input audio array 
+    inputs = processor.feature_extractor(
+        audio["array"], 
+        sampling_rate=audio["sampling_rate"], 
+        return_attention_mask=apply_spec_augment,
+        )
+    batch["input_features"] = inputs.input_features[0]
+
+    # 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:
+        batch["attention_mask"] = inputs.get("attention_mask")[0]
+    
+    
+    # optional pre-processing steps
+    transcription = batch["sentence"]
+    if do_lower_case:
+        transcription = transcription.lower()
+    if do_remove_punctuation:
+        transcription = normalizer(transcription).strip()
+    if do_bangla_unicode_normalization:
+        _words = [bangla_normalizer(word)['normalized'] for word in transcription.split()]
+        transcription = " ".join([word for word in _words if word is not None])
+        transcription = transcription.replace("\u2047", "-")
+        transcription = transcription.replace(u"\u098c", u"\u09ef")
+        transcription = unicodedata.normalize("NFC", transcription)
+        transcription = removeOptionalZW(transcription)
+    
+    # encode target text to label ids
+    batch["labels"] = processor.tokenizer(transcription).input_ids
+    
+     # compute labels length **with** special tokens! -> total label length
+    batch["labels_length"] = len(batch["labels"])
+    
+    return batch
+
+## my_dataset is DatasetDict dictionary whereas my_dataset["train"] is Dataset Object.
+## map function parameters for both are different!
+## see: https://github.com/huggingface/datasets/issues/2407
+
+## This,
+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'),
+                                }
+                            )
+## OR this,
+# my_dataset["train"] = my_dataset["train"].map(
+#                             prepare_dataset, 
+#                             num_proc=4, # if num_proc>1, then mapping might get stuck. use num_proc=1 in that case.
+#                             load_from_cache_file=True, 
+#                             cache_file_name=os.path.join(base_dir, 'datasets_cache', 'preprocessed_train_cache.arrow')
+#                             )
+
+# my_dataset["test"] = my_dataset["test"].map(
+#                             prepare_dataset, 
+#                             num_proc=4, # if num_proc>1, then mapping might get stuck. use num_proc=1 in that case.
+#                             load_from_cache_file=True, 
+#                             cache_file_name=os.path.join(base_dir, 'datasets_cache', 'preprocessed_test_cache.arrow')
+#                             )
+
+
+print("\n\n AFTER PREPROCESSING, final train and validation sets are: ")
+print(my_dataset)
+print("\n")
+
+## 9. Filter too Short or too Long Audio Files
+MAX_DURATION_IN_SECONDS = 30.0
+max_input_length = MAX_DURATION_IN_SECONDS * 16000
+
+def filter_inputs(input_length):
+    """Filter inputs with zero input length or longer than 30s"""
+    return 0 < input_length < max_input_length
+
+my_dataset = my_dataset.filter(filter_inputs, input_columns=["input_length"])
+
+# my_dataset["train"] = my_dataset["train"].filter(
+#     filter_inputs,
+#     input_columns=["input_length"],
+# )
+# my_dataset["test"] = my_dataset["test"].filter(
+#     filter_inputs,
+#     input_columns=["input_length"],
+# )
+
+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)
+
+def filter_labels(labels_length):
+    """Filter label sequences longer than max length (448)"""
+    return labels_length < max_label_length
+
+my_dataset = my_dataset.filter(filter_labels, input_columns=["labels_length"])
+
+# my_dataset["train"] = my_dataset["train"].filter(
+#     filter_labels,
+#     input_columns=["labels_length"],
+# )
+
+# my_dataset["test"] = my_dataset["test"].filter(
+#     filter_labels,
+#     input_columns=["labels_length"],
+# )
+
+print("\n\n AFTER FILTERING LABELS, final train and validation sets are: ")
+print(my_dataset)
+print("\n")
+
+
+import re
+def filter_transcripts(transcript):
+    """Filter transcripts with empty strings and samples containing English characters & numbers"""
+    pattern = r'^.*[a-zA-Z0-9]+.*$'
+    match = re.match(pattern, transcript)
+    return len(transcript.split(" ")) > 1 and not bool(match)
+
+my_dataset = my_dataset.filter(filter_transcripts, input_columns=["sentence"])
+
+# my_dataset["train"] = my_dataset["train"].filter(
+#     filter_transcripts,
+#     input_columns=["sentence"],
+# )
+# my_dataset["test"] = my_dataset["test"].filter(
+#     filter_transcripts,
+#     input_columns=["sentence"],
+# )
+
+print("\n\n AFTER FILTERING TRANSCRIPTS, final train and validation sets are: ")
+print("\n My FINAL DATASET \n")
+print(my_dataset)
+print("\n")
+
+
+## 10. Save & Cleanup Cache Files (DON'T save too large datasets..will take up all space!!)
+## Only save, if you want it to export it to another PC!! 
+## Else, map function stores the cache files via cache_file_name parameter!!
+
+# print("\n\n Saving Preprocessed Dataset to Disk..\n\n")
+
+# my_dataset.save_to_disk(os.path.join(base_dir, "datasets_cache"))
+
+## Removes unused cached files & returns the number of removed cache files
+print("\n Removing UNUSED Cache Files: \n")
+try:
+    print(f"{common_voice.cleanup_cache_files()} for common_voice")
+    print(f"{google_fleurs.cleanup_cache_files()} for google_fleurs")
+    print(f"{openslr.cleanup_cache_files()} for openslr")
+    print(f"{crblp.cleanup_cache_files()} for crblp")
+    print(f"{my_dataset.cleanup_cache_files()} for my_dataset")
+  
+except Exception as e:
+    print(f"\n\n UNABLE to REMOVE some Cache files. \n Error: {e} \n\n")
+
+
+## 11. Load Already Preprocessed Dataset from Disk
+## Only load if you have a saved dataset via save_to_disk method!!
+## Do Once 4 to 6 and 8 to 10. Then start from 7 and 11. EVERYTIME!!!
+
+# from datasets import load_from_disk
+# print("\n\n Loading Preprocessed Dataset from Disk..\n\n")
+
+# my_dataset = load_from_disk(os.path.join(base_dir, "datasets_cache"))
+
+
+## 12. Define Data Collator
+import torch
+from dataclasses import dataclass
+from typing import Any, Dict, List, Union
+
+@dataclass
+class DataCollatorSpeechSeq2SeqWithPadding:
+    processor: Any
+    forward_attention_mask: bool
+
+    def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
+        # split inputs and labels since they have to be of different lengths and need different padding methods
+        # first treat the audio inputs by simply returning torch tensors
+        input_features = [{"input_features": feature["input_features"]} for feature in features]
+        batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
+
+        if self.forward_attention_mask:
+            batch["attention_mask"] = torch.LongTensor([feature["attention_mask"] for feature in features])
+        
+        # get the tokenized label sequences
+        label_features = [{"input_ids": feature["labels"]} for feature in features]
+        # pad the labels to max length
+        labels_batch = self.processor.tokenizer.pad(label_features, return_tensors="pt")
+
+        # replace padding with -100 to ignore loss correctly
+        labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
+
+        # if bos token is appended in previous tokenization step,
+        # cut bos token here as it's append later anyways
+        if (labels[:, 0] == self.processor.tokenizer.bos_token_id).all().cpu().item():
+            labels = labels[:, 1:]
+
+        batch["labels"] = labels
+
+        return batch
+
+
+
+data_collator = DataCollatorSpeechSeq2SeqWithPadding(processor=processor, forward_attention_mask=apply_spec_augment)
+
+
+
+## 13. Define Evaluation Metrics
+import evaluate
+
+wer_metric = evaluate.load("wer", cache_dir=os.path.join(base_dir, "metrics_cache"))
+cer_metric = evaluate.load("cer", cache_dir=os.path.join(base_dir, "metrics_cache"))
+
+do_normalize_eval = True
+
+def compute_metrics(pred):
+    pred_ids = pred.predictions
+    label_ids = pred.label_ids
+
+    # replace -100 with the pad_token_id
+    label_ids[label_ids == -100] = processor.tokenizer.pad_token_id
+
+    # we do not want to group tokens when computing the metrics
+    pred_str = processor.tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
+    label_str = processor.tokenizer.batch_decode(label_ids, skip_special_tokens=True)
+
+    if do_normalize_eval:
+        pred_str = [normalizer(pred) for pred in pred_str]
+        label_str = [normalizer(label) for label in label_str]
+
+    wer = 100 * wer_metric.compute(predictions=pred_str, references=label_str)
+    cer = 100 * cer_metric.compute(predictions=pred_str, references=label_str)
+
+    return {"cer": cer, "wer": wer}
+
+
+## 14. Load a Pre-Trained Checkpoint
+print("\n\n Loading Model to Device..\n\n")
+
+from transformers import WhisperForConditionalGeneration
+
+model = WhisperForConditionalGeneration.from_pretrained(model_name)
+model = model.to(device)
+
+
+## 15. Override generation arguments
+model.config.apply_spec_augment = apply_spec_augment
+model.config.max_length = generation_max_length
+model.config.dropout = dropout
+model.config.forced_decoder_ids = None
+model.config.suppress_tokens = []
+if gradient_checkpointing:
+    model.config.use_cache = False
+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
+
+training_args = Seq2SeqTrainingArguments(
+    output_dir=output_dir,
+    overwrite_output_dir=overwrite_output_dir,
+    max_steps=max_steps,
+    per_device_train_batch_size=per_device_train_batch_size,
+    per_device_eval_batch_size=per_device_eval_batch_size,
+    gradient_accumulation_steps=gradient_accumulation_steps,
+    gradient_checkpointing=gradient_checkpointing,
+    dataloader_num_workers=dataloader_num_workers,
+    evaluation_strategy=evaluation_strategy,
+    eval_steps=eval_steps,
+    save_strategy=save_strategy,
+    save_steps=save_steps,
+    save_total_limit=save_total_limit,
+    learning_rate=learning_rate,
+    lr_scheduler_type=lr_scheduler_type,
+    warmup_steps=warmup_steps,
+    logging_steps=logging_steps,
+    weight_decay=weight_decay,
+    load_best_model_at_end=load_best_model_at_end,
+    metric_for_best_model=metric_for_best_model,
+    greater_is_better=greater_is_better,
+    bf16=bf16,
+    tf32=tf32,
+    torch_compile=torch_compile,
+    optim=optim,
+    generation_max_length=generation_max_length,
+    report_to=report_to,
+    predict_with_generate=predict_with_generate,
+    push_to_hub=push_to_hub,
+)
+
+from transformers import Seq2SeqTrainer
+import transformers as tf
+
+trainer = Seq2SeqTrainer(
+    args=training_args,
+    model=model,
+    train_dataset=my_dataset["train"],
+    eval_dataset=my_dataset["test"],
+    data_collator=data_collator,
+    compute_metrics=compute_metrics,
+    tokenizer=processor.feature_extractor,
+    callbacks=[tf.EarlyStoppingCallback(early_stopping_patience=early_stopping_patience)],
+)
+
+## We'll save the processor object once before starting training. Since the processor is not trainable, it won't change over the course of training.
+## The checkpoint dirs don't save the processor files: 
+## (added_tokens.json, merges.txt, normalizer.json, special_tokens_map.json, tokenizer_config.json, vocab.json)
+## So, we save beforehand the processor in the best_model directory. 
+## This is done so that if we stop training earlier than expected, 
+## then we can copy the above files from the best_model dir to the checkpoint folder 
+## to load the processor and run the model from the checkpoint dir.
+
+# No need to create best_model folder as trainer automatically creates it!
+# if not os.path.exists("best_model"):
+#     os.makedirs("best_model")
+processor.save_pretrained("best_model")
+
+
+## 17. Training
+print("\n\n Training STARTED..\n\n")
+
+train_result = trainer.train()
+
+## resume from the latest checkpoint
+# train_result = trainer.train(resume_from_checkpoint=True)
+
+## resume training from the specific checkpoint in the directory passed
+# train_result = trainer.train(resume_from_checkpoint="checkpoint-4000")
+
+print("\n\n Training COMPLETED...\n\n")
+
+
+## 18. Evaluating & Saving Metrics & Model
+print("\n\n Evaluating Model & Saving Metrics...\n\n")
+
+processor.save_pretrained(save_directory=output_dir)
+# trainer.save_model() 
+
+metrics = train_result.metrics
+trainer.save_metrics("train", metrics)
+trainer.save_state()
+
+metrics = trainer.evaluate(
+    metric_key_prefix="eval",
+    max_length=training_args.generation_max_length,
+    num_beams=training_args.generation_num_beams,
+)
+
+trainer.save_metrics("eval", metrics)
+
+
+## 19. Push to Hub
+if push_to_hub:
+    print("\n\n Pushing to Hub...\n\n")
+    
+    trainer.create_model_card()
+    # kwargs = {
+    #     # "dataset_tags": ["mozilla-foundation/common_voice_11_0", "google/fleurs", "openslr"],
+    #     "dataset_tags": ["mozilla-foundation/common_voice_11_0", "google/fleurs"],
+    #     # "dataset_tags": ["mozilla-foundation/common_voice_11_0", "openslr"],
+    #     # "dataset": ["common-voice-11", "google-fleurs", "openslr53"],  # a 'pretty' name for the training dataset
+    #     "dataset": ["common-voice-11", "google-fleurs"],  # a 'pretty' name for the training dataset
+    #     # "dataset": "common-voice-11+openslr53",  # a 'pretty' name for the training dataset
+    #     "language": "bn",
+    #     "model_name": "Whisper Small - Mohammed Rakib", # a 'pretty' name for your model
+    #     "finetuned_from": "Rakib/whisper-small-bn-all-600",
+    #     "tasks": "automatic-speech-recognition",
+    #     "tags": "whisper-event",
+    # }
+
+    # trainer.push_to_hub(**kwargs)
+    trainer.push_to_hub()
+
+
+print("\n\n DONEEEEEE \n\n")

normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "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"
+}

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b7db43722c09d7b27c717393cd01d6cbbb0a0bfed84454c6a435e84f2c91e3
+size 967102601

runs/May13_23-09-22_DESKTOP-OD7C1Q6/1683997770.2403045/events.out.tfevents.1683997770.DESKTOP-OD7C1Q6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b1ab019a8e871e28c10a48cdb1416e162572c30d2af32033600a2fc2991bfa
+size 5703

runs/May13_23-09-22_DESKTOP-OD7C1Q6/events.out.tfevents.1683997770.DESKTOP-OD7C1Q6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606040c60ee7708fa1dbad905eca79a7cc664c90dbdcffcd12bad8348a09e774
+size 4652

runs/May15_11-17-07_DESKTOP-OD7C1Q6/1684127833.5408869/events.out.tfevents.1684127833.DESKTOP-OD7C1Q6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189723d8061b53912805ea4ef9844b48e639b30b44e3f8c96cd157052005777b
+size 5703

runs/May15_11-17-07_DESKTOP-OD7C1Q6/events.out.tfevents.1684127833.DESKTOP-OD7C1Q6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d8ce96f93a61adef1f60c1ab18d0b1e82e4a5f31ceec9900c5d914b68de370
+size 4653

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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,3 @@
+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

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

special_tokens_map.json

@@ -0,0 +1,133 @@
+{
+  "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

@@ -0,0 +1,35 @@
+{
+  "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
+  }
+}