Training in progress, step 1000

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb filter=lfs diff=lfs merge=lfs -text

.gitignore

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

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
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "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": 0.0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

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 sha256:1be05096f1055ca0b3022a876a2827ad24ff96a673483fa8886e418ff25d1f07
+size 967102601

run.sh

@@ -0,0 +1,40 @@
+python run_speech_recognition_seq2seq_streaming.py \
+--model_name_or_path="openai/whisper-small" \
+--dataset_name="mozilla-foundation/common_voice_11_0" \
+--dataset_config_name="ar" \
+--language="arabic" \
+--train_split_name="train+validation" \
+--eval_split_name="test" \
+--model_index_name="Whisper Small Arabic" \
+--max_steps="5000" \
+--output_dir="./" \
+--per_device_train_batch_size="32" \
+--gradient_accumulation_steps="2" \
+--per_device_eval_batch_size="32" \
+--logging_steps="25" \
+--learning_rate="1e-5" \
+--warmup_steps="500" \
+--evaluation_strategy="steps" \
+--eval_steps="1000" \
+--save_strategy="steps" \
+--save_steps="1000" \
+--generation_max_length="225" \
+--length_column_name="input_length" \
+--max_duration_in_seconds="30" \
+--text_column_name="sentence" \
+--freeze_feature_encoder="False" \
+--report_to="tensorboard" \
+--report_to="wandb" \
+--metric_for_best_model="wer" \
+--greater_is_better="False" \
+--load_best_model_at_end \
+--gradient_checkpointing \
+--fp16 \
+--overwrite_output_dir \
+--do_train \
+--do_eval \
+--predict_with_generate \
+--do_normalize_eval \
+--streaming \
+--use_auth_token \
+--push_to_hub

run_speech_recognition_seq2seq_streaming.py

@@ -0,0 +1,629 @@
+#!/usr/bin/env python
+# coding=utf-8
+# Copyright 2022 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Fine-tuning the library models for sequence to sequence speech recognition
+with 🤗 Datasets' streaming mode.
+"""
+# You can also adapt this script for your own sequence to sequence speech
+# recognition task. Pointers for this are left as comments.
+
+import logging
+import os
+import sys
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Union
+
+import datasets
+import torch
+from datasets import DatasetDict, IterableDatasetDict, interleave_datasets, load_dataset
+from torch.utils.data import IterableDataset
+
+import evaluate
+import transformers
+from transformers import (
+    AutoConfig,
+    AutoFeatureExtractor,
+    AutoModelForSpeechSeq2Seq,
+    AutoProcessor,
+    AutoTokenizer,
+    HfArgumentParser,
+    Seq2SeqTrainer,
+    Seq2SeqTrainingArguments,
+    TrainerCallback,
+    set_seed,
+)
+from transformers.models.whisper.english_normalizer import BasicTextNormalizer
+from transformers.trainer_pt_utils import IterableDatasetShard
+from transformers.trainer_utils import get_last_checkpoint, is_main_process
+from transformers.utils import check_min_version, send_example_telemetry
+from transformers.utils.versions import require_version
+
+
+# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
+check_min_version("4.25.0.dev0")
+
+require_version("datasets>=1.18.2", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class ModelArguments:
+    """
+    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
+    """
+
+    model_name_or_path: str = field(
+        metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
+    )
+    config_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
+    )
+    tokenizer_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
+    )
+    feature_extractor_name: Optional[str] = field(
+        default=None, metadata={"help": "feature extractor name or path if not the same as model_name"}
+    )
+    cache_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Where to store the pretrained models downloaded from huggingface.co"},
+    )
+    use_fast_tokenizer: bool = field(
+        default=True,
+        metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
+    )
+    model_revision: str = field(
+        default="main",
+        metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
+    )
+    use_auth_token: bool = field(
+        default=False,
+        metadata={
+            "help": (
+                "Will use the token generated when running `huggingface-cli login` (necessary to use this script "
+                "with private models)."
+            )
+        },
+    )
+    freeze_feature_encoder: bool = field(
+        default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
+    )
+    freeze_encoder: bool = field(
+        default=False, metadata={"help": "Whether to freeze the entire encoder of the seq2seq model."}
+    )
+    forced_decoder_ids: List[List[int]] = field(
+        default=None,
+        metadata={
+            "help": (
+                "A list of pairs of integers which indicates a mapping from generation indices to token indices "
+                "that will be forced before sampling. For example, [[0, 123]] means the first generated token "
+                "will always be a token of index 123."
+            )
+        },
+    )
+    suppress_tokens: List[int] = field(
+        default=None, metadata={"help": "A list of tokens that will be suppressed at generation."}
+    )
+    model_index_name: str = field(default=None, metadata={"help": "Pretty name for the model card."})
+
+
+@dataclass
+class DataTrainingArguments:
+    """
+    Arguments pertaining to what data we are going to input our model for training and eval.
+    """
+
+    dataset_name: str = field(
+        default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
+    )
+    dataset_config_name: Optional[str] = field(
+        default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
+    )
+    text_column: Optional[str] = field(
+        default=None,
+        metadata={"help": "The name of the column in the datasets containing the full texts (for summarization)."},
+    )
+    max_train_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": (
+                "For debugging purposes or quicker training, truncate the number of training examples to this "
+                "value if set."
+            )
+        },
+    )
+    max_eval_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": (
+                "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
+                "value if set."
+            )
+        },
+    )
+    audio_column_name: str = field(
+        default="audio",
+        metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
+    )
+    text_column_name: str = field(
+        default="text",
+        metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
+    )
+    max_duration_in_seconds: float = field(
+        default=20.0,
+        metadata={
+            "help": (
+                "Truncate audio files that are longer than `max_duration_in_seconds` seconds to"
+                " 'max_duration_in_seconds`"
+            )
+        },
+    )
+    min_duration_in_seconds: float = field(
+        default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
+    )
+    train_split_name: str = field(
+        default="train",
+        metadata={
+            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
+        },
+    )
+    eval_split_name: str = field(
+        default="test",
+        metadata={
+            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
+        },
+    )
+    do_lower_case: bool = field(
+        default=False,
+        metadata={"help": "Whether the target text should be lower cased."},
+    )
+    do_remove_punctuation: bool = field(
+        default=False,
+        metadata={"help": "Whether the target text should be striped of punctuation."},
+    )
+    do_normalize_eval: bool = field(
+        default=True,
+        metadata={"help": "Whether to normalise the references and predictions in the eval WER calculation."},
+    )
+    language: str = field(
+        default=None,
+        metadata={
+            "help": (
+                "Language for multilingual fine-tuning. This argument should be set for multilingual fine-tuning "
+                "only. For English speech recognition, it should be set to `None`."
+            )
+        },
+    )
+    task: str = field(
+        default="transcribe",
+        metadata={"help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."},
+    )
+    shuffle_buffer_size: Optional[int] = field(
+        default=500,
+        metadata={
+            "help": (
+                "The number of streamed examples to download before shuffling them. The large the buffer, "
+                "the closer it is to real offline shuffling."
+            )
+        },
+    )
+    streaming: bool = field(
+        default=True,
+        metadata={"help": "Whether to use streaming mode to load and pre-process the data."},
+    )
+
+
+@dataclass
+class DataCollatorSpeechSeq2SeqWithPadding:
+    """
+    Data collator that will dynamically pad the inputs received.
+    Args:
+        processor ([`WhisperProcessor`])
+            The processor used for processing the data.
+        decoder_start_token_id (`int`)
+            The begin-of-sentence of the decoder.
+    """
+
+    processor: Any
+    decoder_start_token_id: int
+
+    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
+        model_input_name = self.processor.model_input_names[0]
+        input_features = [{model_input_name: feature[model_input_name]} for feature in features]
+        label_features = [{"input_ids": feature["labels"]} for feature in features]
+
+        batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
+
+        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.decoder_start_token_id).all().cpu().item():
+            labels = labels[:, 1:]
+
+        batch["labels"] = labels
+
+        return batch
+
+
+def load_maybe_streaming_dataset(dataset_name, dataset_config_name, split="train", streaming=True, **kwargs):
+    """
+    Utility function to load a dataset in streaming mode. For datasets with multiple splits,
+    each split is loaded individually and then splits combined by taking alternating examples from
+    each (interleaving).
+    """
+    if "+" in split:
+        # load multiple splits separated by the `+` symbol with streaming mode
+        dataset_splits = [
+            load_dataset(dataset_name, dataset_config_name, split=split_name, streaming=streaming, **kwargs)
+            for split_name in split.split("+")
+        ]
+        # interleave multiple splits to form one dataset
+        interleaved_dataset = interleave_datasets(dataset_splits)
+        return interleaved_dataset
+    else:
+        # load a single split *with* streaming mode
+        dataset = load_dataset(dataset_name, dataset_config_name, split=split, streaming=streaming, **kwargs)
+        return dataset
+
+
+def main():
+    # 1. Parse input arguments
+    # See all possible arguments in src/transformers/training_args.py
+    # or by passing the --help flag to this script.
+    # We now keep distinct sets of args, for a cleaner separation of concerns.
+    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
+
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        # If we pass only one argument to the script and it's the path to a json file,
+        # let's parse it to get our arguments.
+        model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
+    else:
+        model_args, data_args, training_args = parser.parse_args_into_dataclasses()
+
+    # Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
+    # information sent is the one passed as arguments along with your Python/PyTorch versions.
+    send_example_telemetry("run_speech_recognition_seq2seq_streaming", model_args, data_args)
+
+    # 2. Setup logging
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+    log_level = training_args.get_process_log_level()
+    logger.setLevel(log_level)
+    datasets.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.enable_default_handler()
+    transformers.utils.logging.enable_explicit_format()
+
+    logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
+
+    # Log on each process the small summary:
+    logger.warning(
+        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+        f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
+    )
+    logger.info(f"Training/evaluation parameters {training_args}")
+
+    # Set the verbosity to info of the Transformers logger (on main process only):
+    if is_main_process(training_args.local_rank):
+        transformers.utils.logging.set_verbosity_info()
+    logger.info("Training/evaluation parameters %s", training_args)
+
+    # 3. Detecting last checkpoint and eventually continue from last checkpoint
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
+    # Set seed before initializing model.
+    set_seed(training_args.seed)
+
+    # 4. Load dataset
+    raw_datasets = IterableDatasetDict() if data_args.streaming else DatasetDict()
+
+    if training_args.do_train:
+        raw_datasets["train"] = load_maybe_streaming_dataset(
+            data_args.dataset_name,
+            data_args.dataset_config_name,
+            split=data_args.train_split_name,
+            use_auth_token=True if model_args.use_auth_token else None,
+            streaming=data_args.streaming,
+        )
+
+    if training_args.do_eval:
+        raw_datasets["eval"] = load_maybe_streaming_dataset(
+            data_args.dataset_name,
+            data_args.dataset_config_name,
+            split=data_args.eval_split_name,
+            use_auth_token=True if model_args.use_auth_token else None,
+            streaming=data_args.streaming,
+        )
+
+    raw_datasets_features = list(next(iter(raw_datasets.values())).features.keys())
+
+    if data_args.audio_column_name not in raw_datasets_features:
+        raise ValueError(
+            f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
+            "Make sure to set `--audio_column_name` to the correct audio column - one of "
+            f"{', '.join(raw_datasets_features)}."
+        )
+
+    if data_args.text_column_name not in raw_datasets_features:
+        raise ValueError(
+            f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
+            "Make sure to set `--text_column_name` to the correct text column - one of "
+            f"{', '.join(raw_datasets_features)}."
+        )
+
+    # 5. Load pretrained model, tokenizer, and feature extractor
+    #
+    # Distributed training:
+    # The .from_pretrained methods guarantee that only one local process can concurrently
+    config = AutoConfig.from_pretrained(
+        model_args.config_name if model_args.config_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+
+    config.update({"forced_decoder_ids": model_args.forced_decoder_ids, "suppress_tokens": model_args.suppress_tokens})
+
+    if training_args.gradient_checkpointing:
+        config.update({"use_cache": False})
+
+    feature_extractor = AutoFeatureExtractor.from_pretrained(
+        model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        use_fast=model_args.use_fast_tokenizer,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+    model = AutoModelForSpeechSeq2Seq.from_pretrained(
+        model_args.model_name_or_path,
+        config=config,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+
+    if model.config.decoder_start_token_id is None:
+        raise ValueError("Make sure that `config.decoder_start_token_id` is correctly defined")
+
+    if model_args.freeze_feature_encoder:
+        model.freeze_feature_encoder()
+
+    if model_args.freeze_encoder:
+        model.freeze_encoder()
+
+    if data_args.language is not None:
+        # We only need to set the task id when the language is specified (i.e. in a multilingual setting)
+        tokenizer.set_prefix_tokens(language=data_args.language, task=data_args.task)
+
+    # 6. Resample speech dataset if necessary
+    dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
+    if dataset_sampling_rate != feature_extractor.sampling_rate:
+        raw_datasets = raw_datasets.cast_column(
+            data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
+        )
+
+    # 7. Preprocessing the datasets.
+    # We need to read the audio files as arrays and tokenize the targets.
+    max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
+    min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
+    audio_column_name = data_args.audio_column_name
+    text_column_name = data_args.text_column_name
+    model_input_name = feature_extractor.model_input_names[0]
+    do_lower_case = data_args.do_lower_case
+    do_remove_punctuation = data_args.do_remove_punctuation
+    normalizer = BasicTextNormalizer()  # 'official' text normalizer from OpenAI
+
+    if data_args.max_train_samples is not None:
+        raw_datasets["train"] = (
+            raw_datasets["train"].take(data_args.max_train_samples)
+            if data_args.streaming
+            else raw_datasets["train"].select(range(data_args.max_train_samples))
+        )
+
+    if data_args.max_eval_samples is not None:
+        raw_datasets["eval"] = (
+            raw_datasets["eval"].take(data_args.max_eval_samples)
+            if data_args.streaming
+            else raw_datasets["eval"].select(range(data_args.max_eval_samples))
+        )
+
+    def prepare_dataset(batch):
+        # process audio
+        sample = batch[audio_column_name]
+        inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
+        # process audio length
+        batch[model_input_name] = inputs.get(model_input_name)[0]
+        batch["input_length"] = len(sample["array"])
+
+        # process targets
+        input_str = batch[text_column_name].lower() if do_lower_case else batch[text_column_name]
+        if do_remove_punctuation:
+            input_str = normalizer(input_str).strip()
+        batch["labels"] = tokenizer(input_str).input_ids
+        return batch
+
+    with training_args.main_process_first(desc="dataset map pre-processing"):
+        vectorized_datasets = raw_datasets.map(
+            prepare_dataset,
+            remove_columns=raw_datasets_features,
+        ).with_format("torch")
+
+        if training_args.do_train and data_args.streaming:
+            # manually shuffle if streaming (done by the trainer for non-streaming)
+            vectorized_datasets["train"] = vectorized_datasets["train"].shuffle(
+                buffer_size=data_args.shuffle_buffer_size,
+                seed=training_args.seed,
+            )
+
+    # filter training data that is shorter than min_input_length or longer than
+    # max_input_length
+    def is_audio_in_length_range(length):
+        return min_input_length < length < max_input_length
+
+    if training_args.do_train:
+        vectorized_datasets["train"] = vectorized_datasets["train"].filter(
+            is_audio_in_length_range,
+            input_columns=["input_length"],
+        )
+
+    # 8. Load Metric
+    metric = evaluate.load("wer")
+    do_normalize_eval = data_args.do_normalize_eval
+
+    def compute_metrics(pred):
+        pred_ids = pred.predictions
+
+        pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
+
+        pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
+        # we do not want to group tokens when computing the metrics
+        label_str = tokenizer.batch_decode(pred.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]
+            # filtering step to only evaluate the samples that correspond to non-zero references:
+            pred_str = [pred_str[i] for i in range(len(pred_str)) if len(label_str[i]) > 0]
+            label_str = [label_str[i] for i in range(len(label_str)) if len(label_str[i]) > 0]
+
+        wer = 100 * metric.compute(predictions=pred_str, references=label_str)
+
+        return {"wer": wer}
+
+    # 9. Create a single speech processor
+    if is_main_process(training_args.local_rank):
+        # save feature extractor, tokenizer and config
+        feature_extractor.save_pretrained(training_args.output_dir)
+        tokenizer.save_pretrained(training_args.output_dir)
+        config.save_pretrained(training_args.output_dir)
+
+    processor = AutoProcessor.from_pretrained(training_args.output_dir)
+
+    # 10. Define data collator
+    data_collator = DataCollatorSpeechSeq2SeqWithPadding(
+        processor=processor,
+        decoder_start_token_id=model.config.decoder_start_token_id,
+    )
+
+    # 11. Configure Trainer
+    # Trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch
+    # Only required for streaming: Trainer automatically shuffles non-streaming datasets
+    class ShuffleCallback(TrainerCallback):
+        def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):
+            if isinstance(train_dataloader.dataset, IterableDatasetShard):
+                pass  # set_epoch() is handled by the Trainer
+            elif isinstance(train_dataloader.dataset, IterableDataset):
+                train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
+
+    # Initialize Trainer
+    trainer = Seq2SeqTrainer(
+        model=model,
+        args=training_args,
+        train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
+        eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
+        tokenizer=feature_extractor,
+        data_collator=data_collator,
+        compute_metrics=compute_metrics if training_args.predict_with_generate else None,
+        callbacks=[ShuffleCallback()] if data_args.streaming else None,
+    )
+
+    # 12. Training
+    if training_args.do_train:
+        checkpoint = None
+        if training_args.resume_from_checkpoint is not None:
+            checkpoint = training_args.resume_from_checkpoint
+        elif last_checkpoint is not None:
+            checkpoint = last_checkpoint
+        train_result = trainer.train(resume_from_checkpoint=checkpoint)
+        trainer.save_model()  # Saves the feature extractor too for easy upload
+
+        metrics = train_result.metrics
+        if data_args.max_train_samples:
+            metrics["train_samples"] = data_args.max_train_samples
+        trainer.log_metrics("train", metrics)
+        trainer.save_metrics("train", metrics)
+        trainer.save_state()
+
+    # 13. Evaluation
+    results = {}
+    if training_args.do_eval:
+        logger.info("*** Evaluate ***")
+        metrics = trainer.evaluate(
+            metric_key_prefix="eval",
+            max_length=training_args.generation_max_length,
+            num_beams=training_args.generation_num_beams,
+        )
+        if data_args.max_eval_samples:
+            metrics["eval_samples"] = data_args.max_eval_samples
+
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    # 14. Write Training Stats
+    kwargs = {
+        "finetuned_from": model_args.model_name_or_path,
+        "tasks": "automatic-speech-recognition",
+        "tags": "whisper-event",
+    }
+    if data_args.dataset_name is not None:
+        kwargs["dataset_tags"] = data_args.dataset_name
+        if data_args.dataset_config_name is not None:
+            kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
+        else:
+            kwargs["dataset"] = data_args.dataset_name
+        if "common_voice" in data_args.dataset_name:
+            kwargs["language"] = data_args.dataset_config_name.split('-')[0]
+        if model_args.model_index_name is not None:
+            kwargs["model_name"] = model_args.model_index_name
+
+    if training_args.push_to_hub:
+        trainer.push_to_hub(**kwargs)
+    else:
+        trainer.create_model_card(**kwargs)
+
+    return results
+
+
+if __name__ == "__main__":
+    main()

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
+  },
+  "clean_up_tokenization_spaces": true,
+  "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,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41ee1723077d9367104b059cfecdb53a548d49fcfc2a3cd253a6e7408db5fbf
+size 4027

wandb/debug-internal.log

@@ -0,0 +1 @@
+run-20230507_103405-9zf5xxpu/logs/debug-internal.log

wandb/debug.log

@@ -0,0 +1 @@
+run-20230507_103405-9zf5xxpu/logs/debug.log

wandb/latest-run

@@ -0,0 +1 @@
+run-20230507_103405-9zf5xxpu

wandb/run-20230506_113337-ysywp688/files/conda-environment.yaml

@@ -0,0 +1,133 @@
+name: whisper
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=h7f98852_4
+  - ca-certificates=2022.12.7=ha878542_0
+  - git-lfs=3.3.0=ha770c72_0
+  - ld_impl_linux-64=2.40=h41732ed_0
+  - libffi=3.4.2=h7f98852_5
+  - libgcc-ng=12.2.0=h65d4601_19
+  - libgomp=12.2.0=h65d4601_19
+  - libnsl=2.0.0=h7f98852_0
+  - libsqlite=3.40.0=h753d276_1
+  - libuuid=2.38.1=h0b41bf4_0
+  - libzlib=1.2.13=h166bdaf_4
+  - ncurses=6.3=h27087fc_1
+  - openssl=3.1.0=hd590300_3
+  - pip=23.1.2=pyhd8ed1ab_0
+  - python=3.9.16=h2782a2a_0_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=67.7.2=pyhd8ed1ab_0
+  - tk=8.6.12=h27826a3_0
+  - wheel=0.40.0=pyhd8ed1ab_0
+  - xz=5.2.6=h166bdaf_0
+  - pip:
+      - absl-py==1.4.0
+      - accelerate==0.18.0
+      - aiohttp==3.8.4
+      - aiosignal==1.3.1
+      - appdirs==1.4.4
+      - async-timeout==4.0.2
+      - attrs==23.1.0
+      - audioread==3.0.0
+      - cachetools==5.3.0
+      - certifi==2022.12.7
+      - cffi==1.15.1
+      - charset-normalizer==3.1.0
+      - click==8.1.3
+      - cmake==3.26.3
+      - datasets==2.12.1.dev0
+      - decorator==5.1.1
+      - dill==0.3.6
+      - docker-pycreds==0.4.0
+      - evaluate==0.4.0
+      - filelock==3.12.0
+      - frozenlist==1.3.3
+      - fsspec==2023.4.0
+      - gitdb==4.0.10
+      - gitpython==3.1.31
+      - google-auth==2.17.3
+      - google-auth-oauthlib==1.0.0
+      - grpcio==1.54.0
+      - huggingface-hub==0.14.1
+      - idna==3.4
+      - importlib-metadata==6.6.0
+      - jinja2==3.1.2
+      - jiwer==3.0.1
+      - joblib==1.2.0
+      - lazy-loader==0.2
+      - librosa==0.10.0.post2
+      - lit==16.0.2
+      - llvmlite==0.40.0
+      - markdown==3.4.3
+      - markupsafe==2.1.2
+      - more-itertools==9.1.0
+      - mpmath==1.3.0
+      - msgpack==1.0.5
+      - multidict==6.0.4
+      - multiprocess==0.70.14
+      - networkx==3.1
+      - numba==0.57.0
+      - numpy==1.24.3
+      - nvidia-cublas-cu11==11.10.3.66
+      - nvidia-cuda-cupti-cu11==11.7.101
+      - nvidia-cuda-nvrtc-cu11==11.7.99
+      - nvidia-cuda-runtime-cu11==11.7.99
+      - nvidia-cudnn-cu11==8.5.0.96
+      - nvidia-cufft-cu11==10.9.0.58
+      - nvidia-curand-cu11==10.2.10.91
+      - nvidia-cusolver-cu11==11.4.0.1
+      - nvidia-cusparse-cu11==11.7.4.91
+      - nvidia-nccl-cu11==2.14.3
+      - nvidia-nvtx-cu11==11.7.91
+      - oauthlib==3.2.2
+      - packaging==23.1
+      - pandas==2.0.1
+      - pathtools==0.1.2
+      - pooch==1.6.0
+      - protobuf==4.22.3
+      - psutil==5.9.5
+      - pyarrow==12.0.0
+      - pyasn1==0.5.0
+      - pyasn1-modules==0.3.0
+      - pycparser==2.21
+      - python-dateutil==2.8.2
+      - pytz==2023.3
+      - pyyaml==6.0
+      - rapidfuzz==2.13.7
+      - regex==2023.5.4
+      - requests==2.29.0
+      - requests-oauthlib==1.3.1
+      - responses==0.18.0
+      - rsa==4.9
+      - scikit-learn==1.2.2
+      - scipy==1.10.1
+      - sentry-sdk==1.22.1
+      - setproctitle==1.3.2
+      - six==1.16.0
+      - smmap==5.0.0
+      - soundfile==0.12.1
+      - soxr==0.3.5
+      - sympy==1.11.1
+      - tensorboard==2.12.3
+      - tensorboard-data-server==0.7.0
+      - threadpoolctl==3.1.0
+      - tokenizers==0.13.3
+      - torch==2.0.0
+      - torchaudio==2.0.1
+      - tqdm==4.65.0
+      - transformers==4.29.0.dev0
+      - triton==2.0.0
+      - typing-extensions==4.5.0
+      - tzdata==2023.3
+      - urllib3==1.26.15
+      - wandb==0.15.2
+      - werkzeug==2.3.3
+      - xxhash==3.2.0
+      - yarl==1.9.2
+      - zipp==3.15.0
+prefix: /home/local/QCRI/dizham/miniconda3/envs/whisper

wandb/run-20230506_113337-ysywp688/files/config.yaml

@@ -0,0 +1,688 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.9.16
+    cli_version: 0.15.2
+    framework: huggingface
+    huggingface_version: 4.29.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1683362017.131512
+    t:
+      1:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      2:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      3:
+      - 7
+      - 23
+      4: 3.9.16
+      5: 0.15.2
+      6: 4.29.0.dev0
+      8:
+      - 5
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/wer
+      5: 1
+      6:
+      - 1
+    - 1: eval/runtime
+      5: 1
+      6:
+      - 1
+    - 1: eval/samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: eval/steps_per_second
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 51865
+num_mel_bins:
+  desc: null
+  value: 80
+d_model:
+  desc: null
+  value: 768
+encoder_layers:
+  desc: null
+  value: 12
+encoder_attention_heads:
+  desc: null
+  value: 12
+decoder_layers:
+  desc: null
+  value: 12
+decoder_attention_heads:
+  desc: null
+  value: 12
+decoder_ffn_dim:
+  desc: null
+  value: 3072
+encoder_ffn_dim:
+  desc: null
+  value: 3072
+dropout:
+  desc: null
+  value: 0.0
+attention_dropout:
+  desc: null
+  value: 0.0
+activation_dropout:
+  desc: null
+  value: 0.0
+activation_function:
+  desc: null
+  value: gelu
+init_std:
+  desc: null
+  value: 0.02
+encoder_layerdrop:
+  desc: null
+  value: 0.0
+decoder_layerdrop:
+  desc: null
+  value: 0.0
+use_cache:
+  desc: null
+  value: false
+num_hidden_layers:
+  desc: null
+  value: 12
+scale_embedding:
+  desc: null
+  value: false
+max_source_positions:
+  desc: null
+  value: 1500
+max_target_positions:
+  desc: null
+  value: 448
+classifier_proj_size:
+  desc: null
+  value: 256
+use_weighted_layer_sum:
+  desc: null
+  value: false
+apply_spec_augment:
+  desc: null
+  value: false
+mask_time_prob:
+  desc: null
+  value: 0.05
+mask_time_length:
+  desc: null
+  value: 10
+mask_time_min_masks:
+  desc: null
+  value: 2
+mask_feature_prob:
+  desc: null
+  value: 0.0
+mask_feature_length:
+  desc: null
+  value: 10
+mask_feature_min_masks:
+  desc: null
+  value: 0
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: float32
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: true
+is_encoder_decoder:
+  desc: null
+  value: true
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 448
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value:
+  - 220
+  - 50257
+architectures:
+  desc: null
+  value:
+  - WhisperForConditionalGeneration
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 50257
+pad_token_id:
+  desc: null
+  value: 50257
+eos_token_id:
+  desc: null
+  value: 50257
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: 50258
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: openai/whisper-small
+transformers_version:
+  desc: null
+  value: 4.29.0.dev0
+forced_decoder_ids:
+  desc: null
+  value: null
+model_type:
+  desc: null
+  value: whisper
+output_dir:
+  desc: null
+  value: ./
+overwrite_output_dir:
+  desc: null
+  value: true
+do_train:
+  desc: null
+  value: true
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+evaluation_strategy:
+  desc: null
+  value: steps
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 32
+per_device_eval_batch_size:
+  desc: null
+  value: 32
+per_gpu_train_batch_size:
+  desc: null
+  value: None
+per_gpu_eval_batch_size:
+  desc: null
+  value: None
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: None
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 1.0e-05
+weight_decay:
+  desc: null
+  value: 0.0
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 3.0
+max_steps:
+  desc: null
+  value: 5000
+lr_scheduler_type:
+  desc: null
+  value: linear
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 500
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/May06_11-33-02_crimv3mgpu025
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 25
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 1000
+save_total_limit:
+  desc: null
+  value: None
+save_safetensors:
+  desc: null
+  value: false
+save_on_each_node:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: None
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: false
+fp16:
+  desc: null
+  value: true
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: cuda_amp
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: None
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: None
+tpu_num_cores:
+  desc: null
+  value: None
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: '[]'
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: 1000
+dataloader_num_workers:
+  desc: null
+  value: 0
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: ./
+disable_tqdm:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+label_names:
+  desc: null
+  value: None
+load_best_model_at_end:
+  desc: null
+  value: true
+metric_for_best_model:
+  desc: null
+  value: wer
+greater_is_better:
+  desc: null
+  value: false
+ignore_data_skip:
+  desc: null
+  value: false
+sharded_ddp:
+  desc: null
+  value: '[]'
+fsdp:
+  desc: null
+  value: '[]'
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value: '{''fsdp_min_num_params'': 0, ''xla'': False, ''xla_fsdp_grad_ckpt'': False}'
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: None
+deepspeed:
+  desc: null
+  value: None
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_hf
+optim_args:
+  desc: null
+  value: None
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: input_length
+report_to:
+  desc: null
+  value: '[''wandb'']'
+ddp_find_unused_parameters:
+  desc: null
+  value: None
+ddp_bucket_cap_mb:
+  desc: null
+  value: None
+dataloader_pin_memory:
+  desc: null
+  value: true
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: true
+resume_from_checkpoint:
+  desc: null
+  value: None
+hub_model_id:
+  desc: null
+  value: None
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: true
+include_inputs_for_metrics:
+  desc: null
+  value: false
+fp16_backend:
+  desc: null
+  value: auto
+push_to_hub_model_id:
+  desc: null
+  value: None
+push_to_hub_organization:
+  desc: null
+  value: None
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: None
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: None
+torch_compile_mode:
+  desc: null
+  value: None
+xpu_backend:
+  desc: null
+  value: None
+sortish_sampler:
+  desc: null
+  value: false
+predict_with_generate:
+  desc: null
+  value: true
+generation_max_length:
+  desc: null
+  value: 225
+generation_num_beams:
+  desc: null
+  value: None
+generation_config:
+  desc: null
+  value: None
+train_batch_size:
+  desc: null
+  value: 64
+eval_batch_size:
+  desc: null
+  value: 64

wandb/run-20230506_113337-ysywp688/files/output.log

@@ -0,0 +1,1101 @@
+  0%|          | 0/5000 [00:00<?, ?it/s]
+
+
+Reading metadata...: 23332it [00:04, 5566.60it/s]
+
+
+[INFO|trainer_utils.py:693] 2023-05-06 11:35:39,880 >> The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
+  warnings.warn('Was asked to gather along dimension 0, but all '
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  0%|          | 25/5000 [14:20<40:49:08, 29.54s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|          | 49/5000 [25:57<39:52:38, 29.00s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|▏         | 74/5000 [38:10<39:26:07, 28.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|▏         | 99/5000 [50:13<39:03:58, 28.70s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|▏         | 124/5000 [1:02:25<38:47:32, 28.64s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|▎         | 150/5000 [1:15:09<40:31:35, 30.08s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|▎         | 163/5000 [1:20:20<21:29:00, 15.99s/it]
+
+Reading metadata...: 22927it [00:03, 10857.89it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|▎         | 174/5000 [1:26:45<37:53:20, 28.26s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|▍         | 200/5000 [1:38:49<36:55:58, 27.70s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|▍         | 224/5000 [1:49:53<36:01:48, 27.16s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  5%|▍         | 249/5000 [2:01:25<35:37:24, 26.99s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  5%|▌         | 274/5000 [2:12:59<36:06:06, 27.50s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|▌         | 299/5000 [2:24:40<37:31:10, 28.73s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|▋         | 324/5000 [2:35:58<29:09:59, 22.45s/it]
+
+
+
+  7%|▋         | 327/5000 [2:36:27<18:05:01, 13.93s/it]
+
+
+Reading metadata...: 24506it [00:05, 5432.25it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|▋         | 349/5000 [2:48:13<35:54:20, 27.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|▋         | 374/5000 [3:00:12<40:33:48, 31.57s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|▊         | 400/5000 [3:12:45<36:54:59, 28.89s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|▊         | 425/5000 [3:24:31<35:49:54, 28.20s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  9%|▉         | 449/5000 [3:35:37<34:58:52, 27.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|▉         | 475/5000 [3:47:38<34:53:17, 27.76s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|▉         | 490/5000 [3:53:33<19:04:32, 15.23s/it]
+
+Reading metadata...: 10438it [00:00, 25934.78it/s]
+
+
+
+
+
+
+
+
+
+ 10%|▉         | 499/5000 [3:58:50<37:18:31, 29.84s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|█         | 525/5000 [4:10:52<34:41:42, 27.91s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 11%|█         | 550/5000 [4:22:29<34:29:35, 27.90s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█▏        | 575/5000 [4:34:05<34:32:46, 28.11s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█▏        | 600/5000 [4:45:35<34:09:51, 27.95s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█▎        | 625/5000 [4:57:10<33:31:38, 27.59s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 13%|█▎        | 650/5000 [5:08:39<31:35:25, 26.14s/it]
+
+
+
+ 13%|█▎        | 654/5000 [5:09:19<16:25:57, 13.61s/it]
+
+Reading metadata...: 10438it [00:00, 25770.40it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 13%|█▎        | 674/5000 [5:19:54<34:45:47, 28.93s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|█▍        | 700/5000 [5:31:55<32:45:38, 27.43s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|█▍        | 724/5000 [5:43:03<33:14:52, 27.99s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 15%|█▌        | 750/5000 [5:55:12<34:08:13, 28.92s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|█▌        | 775/5000 [6:06:46<32:23:45, 27.60s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|█▌        | 800/5000 [6:18:21<32:13:15, 27.62s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Reading metadata...: 28043it [00:01, 19987.99it/s]s/it]
+Reading metadata...: 10438it [00:00, 25735.72it/s]
+
+
+
+
+
+
+
+
+ 16%|█▋        | 825/5000 [6:29:57<33:54:47, 29.24s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 17%|█▋        | 850/5000 [6:41:29<31:44:09, 27.53s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█▊        | 875/5000 [6:53:08<31:50:31, 27.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█▊        | 900/5000 [7:04:43<31:41:55, 27.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█▊        | 925/5000 [7:16:16<31:19:18, 27.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 19%|█▉        | 949/5000 [7:27:24<31:16:42, 27.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|█▉        | 975/5000 [7:39:31<30:54:27, 27.64s/it]
+
+
+
+
+
+Reading metadata...: 28043it [00:00, 28643.05it/s]s/it]
+Reading metadata...: 10438it [00:00, 24507.54it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|██        | 1000/5000 [7:51:12<31:18:37, 28.18s/it][INFO|trainer.py:3138] 2023-05-06 19:25:00,699 >> ***** Running Evaluation *****
+[INFO|trainer.py:3142] 2023-05-06 19:25:00,699 >>   Num examples: Unknown
+[INFO|trainer.py:3143] 2023-05-06 19:25:00,699 >>   Batch size = 64
+{'loss': 0.0517, 'learning_rate': 8.893333333333333e-06, 'epoch': 6.0}
+
+
+[INFO|trainer_utils.py:693] 2023-05-06 19:25:16,854 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+{'eval_loss': 0.43406692147254944, 'eval_wer': 54.476, 'eval_runtime': 2259.524, 'eval_samples_per_second': 4.62, 'eval_steps_per_second': 0.073, 'epoch': 6.0}
+ 20%|██        | 1000/5000 [8:28:52<31:18:37, 28.18s/it][INFO|trainer.py:2877] 2023-05-06 20:02:40,234 >> Saving model checkpoint to ./checkpoint-1000
+[INFO|configuration_utils.py:458] 2023-05-06 20:02:40,239 >> Configuration saved in ./checkpoint-1000/config.json
+[INFO|configuration_utils.py:364] 2023-05-06 20:02:40,243 >> Configuration saved in ./checkpoint-1000/generation_config.json
+[INFO|modeling_utils.py:1855] 2023-05-06 20:02:43,051 >> Model weights saved in ./checkpoint-1000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:369] 2023-05-06 20:02:43,056 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:369] 2023-05-06 20:02:51,152 >> Feature extractor saved in ./preprocessor_config.json
+Traceback (most recent call last):
+  File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 629, in <module>
+    main()
+  File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 578, in main
+    train_result = trainer.train(resume_from_checkpoint=checkpoint)
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 1664, in train
+    return inner_training_loop(
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 2011, in _inner_training_loop
+    self._maybe_log_save_evaluate(tr_loss, model, trial, epoch, ignore_keys_for_eval)
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 2300, in _maybe_log_save_evaluate
+    self._save_checkpoint(model, trial, metrics=metrics)
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 2444, in _save_checkpoint
+    self._push_from_checkpoint(output_dir)
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 3622, in _push_from_checkpoint
+    _, self.push_in_progress = self.repo.push_to_hub(
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 1305, in push_to_hub
+    self.git_add(auto_lfs_track=True)
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 1009, in git_add
+    tracked_files.extend(self.auto_track_binary_files(pattern))
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 903, in auto_track_binary_files
+    is_binary = is_binary_file(path_to_file)
+  File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 230, in is_binary_file
+    with open(filename, "rb") as f:
+IsADirectoryError: [Errno 21] Is a directory: '/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/./wandb/latest-run'

wandb/run-20230506_113337-ysywp688/files/requirements.txt

@@ -0,0 +1,107 @@
+absl-py==1.4.0
+accelerate==0.18.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+appdirs==1.4.4
+async-timeout==4.0.2
+attrs==23.1.0
+audioread==3.0.0
+cachetools==5.3.0
+certifi==2022.12.7
+cffi==1.15.1
+charset-normalizer==3.1.0
+click==8.1.3
+cmake==3.26.3
+datasets==2.12.1.dev0
+decorator==5.1.1
+dill==0.3.6
+docker-pycreds==0.4.0
+evaluate==0.4.0
+filelock==3.12.0
+frozenlist==1.3.3
+fsspec==2023.4.0
+gitdb==4.0.10
+gitpython==3.1.31
+google-auth-oauthlib==1.0.0
+google-auth==2.17.3
+grpcio==1.54.0
+huggingface-hub==0.14.1
+idna==3.4
+importlib-metadata==6.6.0
+jinja2==3.1.2
+jiwer==3.0.1
+joblib==1.2.0
+lazy-loader==0.2
+librosa==0.10.0.post2
+lit==16.0.2
+llvmlite==0.40.0
+markdown==3.4.3
+markupsafe==2.1.2
+more-itertools==9.1.0
+mpmath==1.3.0
+msgpack==1.0.5
+multidict==6.0.4
+multiprocess==0.70.14
+networkx==3.1
+numba==0.57.0
+numpy==1.24.3
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+oauthlib==3.2.2
+packaging==23.1
+pandas==2.0.1
+pathtools==0.1.2
+pip==23.1.2
+pooch==1.6.0
+protobuf==4.22.3
+psutil==5.9.5
+pyarrow==12.0.0
+pyasn1-modules==0.3.0
+pyasn1==0.5.0
+pycparser==2.21
+python-dateutil==2.8.2
+pytz==2023.3
+pyyaml==6.0
+rapidfuzz==2.13.7
+regex==2023.5.4
+requests-oauthlib==1.3.1
+requests==2.29.0
+responses==0.18.0
+rsa==4.9
+scikit-learn==1.2.2
+scipy==1.10.1
+sentry-sdk==1.22.1
+setproctitle==1.3.2
+setuptools==67.7.2
+six==1.16.0
+smmap==5.0.0
+soundfile==0.12.1
+soxr==0.3.5
+sympy==1.11.1
+tensorboard-data-server==0.7.0
+tensorboard==2.12.3
+threadpoolctl==3.1.0
+tokenizers==0.13.3
+torch==2.0.0
+torchaudio==2.0.1
+tqdm==4.65.0
+transformers==4.29.0.dev0
+triton==2.0.0
+typing-extensions==4.5.0
+tzdata==2023.3
+urllib3==1.26.15
+wandb==0.15.2
+werkzeug==2.3.3
+wheel==0.40.0
+xxhash==3.2.0
+yarl==1.9.2
+zipp==3.15.0

wandb/run-20230506_113337-ysywp688/files/wandb-metadata.json

@@ -0,0 +1,369 @@
+{
+    "os": "Linux-3.10.0-957.27.2.el7.x86_64-x86_64-with-glibc2.17",
+    "python": "3.9.16",
+    "heartbeatAt": "2023-05-06T08:33:38.114072",
+    "startedAt": "2023-05-06T08:33:37.104716",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--model_name_or_path=openai/whisper-small",
+        "--dataset_name=mozilla-foundation/common_voice_11_0",
+        "--dataset_config_name=ar",
+        "--language=arabic",
+        "--train_split_name=train+validation",
+        "--eval_split_name=test",
+        "--model_index_name=Whisper Small Arabic",
+        "--max_steps=5000",
+        "--output_dir=./",
+        "--per_device_train_batch_size=32",
+        "--gradient_accumulation_steps=2",
+        "--per_device_eval_batch_size=32",
+        "--logging_steps=25",
+        "--learning_rate=1e-5",
+        "--warmup_steps=500",
+        "--evaluation_strategy=steps",
+        "--eval_steps=1000",
+        "--save_strategy=steps",
+        "--save_steps=1000",
+        "--generation_max_length=225",
+        "--length_column_name=input_length",
+        "--max_duration_in_seconds=30",
+        "--text_column_name=sentence",
+        "--freeze_feature_encoder=False",
+        "--report_to=tensorboard",
+        "--report_to=wandb",
+        "--metric_for_best_model=wer",
+        "--greater_is_better=False",
+        "--load_best_model_at_end",
+        "--gradient_checkpointing",
+        "--fp16",
+        "--overwrite_output_dir",
+        "--do_train",
+        "--do_eval",
+        "--predict_with_generate",
+        "--do_normalize_eval",
+        "--streaming",
+        "--use_auth_token",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py",
+    "codePath": "run_speech_recognition_seq2seq_streaming.py",
+    "git": {
+        "remote": "https://huggingface.co/danielizham/whisper-small-ar",
+        "commit": "33cfe8b27be49d1904070ffc4339ab1b4075c5b1"
+    },
+    "email": "[email protected]",
+    "root": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar",
+    "host": "crimv3mgpu025",
+    "username": "dizham",
+    "executable": "/home/local/QCRI/dizham/miniconda3/envs/whisper/bin/python",
+    "cpu_count": 28,
+    "cpu_count_logical": 56,
+    "cpu_freq": {
+        "current": 2201.0,
+        "min": 1000.0,
+        "max": 2201.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        }
+    ],
+    "disk": {
+        "total": 99.951171875,
+        "used": 19.748153686523438
+    },
+    "gpu": "Tesla V100-SXM2-32GB",
+    "gpu_count": 2,
+    "gpu_devices": [
+        {
+            "name": "Tesla V100-SXM2-32GB",
+            "memory_total": 34089730048
+        },
+        {
+            "name": "Tesla V100-SXM2-32GB",
+            "memory_total": 34089730048
+        }
+    ],
+    "memory": {
+        "total": 251.55353164672852
+    }
+}

wandb/run-20230506_113337-ysywp688/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 0.0517, "train/learning_rate": 8.893333333333333e-06, "train/epoch": 6.0, "train/global_step": 1000, "_timestamp": 1683392560.2236953, "_runtime": 30543.092183351517, "_step": 40, "eval/loss": 0.43406692147254944, "eval/wer": 54.476, "eval/runtime": 2259.524, "eval/samples_per_second": 4.62, "eval/steps_per_second": 0.073, "_wandb": {"runtime": 30558}}

wandb/run-20230506_113337-ysywp688/logs/debug.log

@@ -0,0 +1,28 @@
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Current SDK version is 0.15.2
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Configure stats pid to 59902
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/.config/wandb/settings
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/settings
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program': '/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py'}
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_init.py:_log_setup():507] Logging user logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230506_113337-ysywp688/logs/debug.log
+2023-05-06 11:33:37,123 INFO    MainThread:59902 [wandb_init.py:_log_setup():508] Logging internal logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230506_113337-ysywp688/logs/debug-internal.log
+2023-05-06 11:33:37,124 INFO    MainThread:59902 [wandb_init.py:init():547] calling init triggers
+2023-05-06 11:33:37,124 INFO    MainThread:59902 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
+config: {}
+2023-05-06 11:33:37,124 INFO    MainThread:59902 [wandb_init.py:init():596] starting backend
+2023-05-06 11:33:37,124 INFO    MainThread:59902 [wandb_init.py:init():600] setting up manager
+2023-05-06 11:33:37,127 INFO    MainThread:59902 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2023-05-06 11:33:37,131 INFO    MainThread:59902 [wandb_init.py:init():606] backend started and connected
+2023-05-06 11:33:37,133 INFO    MainThread:59902 [wandb_init.py:init():700] updated telemetry
+2023-05-06 11:33:37,202 INFO    MainThread:59902 [wandb_init.py:init():737] communicating run to backend with 60.0 second timeout
+2023-05-06 11:33:37,804 INFO    MainThread:59902 [wandb_run.py:_on_init():2177] communicating current version
+2023-05-06 11:33:38,081 INFO    MainThread:59902 [wandb_run.py:_on_init():2186] got version response 
+2023-05-06 11:33:38,081 INFO    MainThread:59902 [wandb_init.py:init():787] starting run threads in backend
+2023-05-06 11:33:47,905 INFO    MainThread:59902 [wandb_run.py:_console_start():2158] atexit reg
+2023-05-06 11:33:47,906 INFO    MainThread:59902 [wandb_run.py:_redirect():2013] redirect: SettingsConsole.WRAP_RAW
+2023-05-06 11:33:47,906 INFO    MainThread:59902 [wandb_run.py:_redirect():2078] Wrapping output streams.
+2023-05-06 11:33:47,906 INFO    MainThread:59902 [wandb_run.py:_redirect():2103] Redirects installed.
+2023-05-06 11:33:47,907 INFO    MainThread:59902 [wandb_init.py:init():829] run started, returning control to user process
+2023-05-06 11:33:47,925 INFO    MainThread:59902 [wandb_run.py:_config_callback():1286] config_cb None None {'vocab_size': 51865, 'num_mel_bins': 80, 'd_model': 768, 'encoder_layers': 12, 'encoder_attention_heads': 12, 'decoder_layers': 12, 'decoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'encoder_ffn_dim': 3072, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': False, 'num_hidden_layers': 12, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50257, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-small', 'transformers_version': '4.29.0.dev0', 'forced_decoder_ids': None, 'model_type': 'whisper', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 5000, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/May06_11-33-02_crimv3mgpu025', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 'None', 'save_safetensors': False, 'save_on_each_node': False, 'no_cuda': False, 'use_mps_device': False, 'seed': 42, 'data_seed': 'None', 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'cuda_amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': 0, 'ddp_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'fsdp': '[]', 'fsdp_min_num_params': 0, 'fsdp_config': "{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}", 'fsdp_transformer_layer_cls_to_wrap': 'None', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'optim_args': 'None', 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': 'None', 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': 'None', 'torch_compile_mode': 'None', 'xpu_backend': 'None', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': 'None', 'generation_config': 'None', 'train_batch_size': 64, 'eval_batch_size': 64}
+2023-05-06 20:03:08,523 WARNING MsgRouterThr:59902 [router.py:message_loop():77] message_loop has been closed

wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc04e94097f673d3a51da6ac65952f7e186c90757b4c6e65049e6316ed513737
+size 2828090

wandb/run-20230507_103405-9zf5xxpu/files/conda-environment.yaml

@@ -0,0 +1,133 @@
+name: whisper
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=h7f98852_4
+  - ca-certificates=2022.12.7=ha878542_0
+  - git-lfs=3.3.0=ha770c72_0
+  - ld_impl_linux-64=2.40=h41732ed_0
+  - libffi=3.4.2=h7f98852_5
+  - libgcc-ng=12.2.0=h65d4601_19
+  - libgomp=12.2.0=h65d4601_19
+  - libnsl=2.0.0=h7f98852_0
+  - libsqlite=3.40.0=h753d276_1
+  - libuuid=2.38.1=h0b41bf4_0
+  - libzlib=1.2.13=h166bdaf_4
+  - ncurses=6.3=h27087fc_1
+  - openssl=3.1.0=hd590300_3
+  - pip=23.1.2=pyhd8ed1ab_0
+  - python=3.9.16=h2782a2a_0_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=67.7.2=pyhd8ed1ab_0
+  - tk=8.6.12=h27826a3_0
+  - wheel=0.40.0=pyhd8ed1ab_0
+  - xz=5.2.6=h166bdaf_0
+  - pip:
+      - absl-py==1.4.0
+      - accelerate==0.18.0
+      - aiohttp==3.8.4
+      - aiosignal==1.3.1
+      - appdirs==1.4.4
+      - async-timeout==4.0.2
+      - attrs==23.1.0
+      - audioread==3.0.0
+      - cachetools==5.3.0
+      - certifi==2022.12.7
+      - cffi==1.15.1
+      - charset-normalizer==3.1.0
+      - click==8.1.3
+      - cmake==3.26.3
+      - datasets==2.12.1.dev0
+      - decorator==5.1.1
+      - dill==0.3.6
+      - docker-pycreds==0.4.0
+      - evaluate==0.4.0
+      - filelock==3.12.0
+      - frozenlist==1.3.3
+      - fsspec==2023.4.0
+      - gitdb==4.0.10
+      - gitpython==3.1.31
+      - google-auth==2.17.3
+      - google-auth-oauthlib==1.0.0
+      - grpcio==1.54.0
+      - huggingface-hub==0.14.1
+      - idna==3.4
+      - importlib-metadata==6.6.0
+      - jinja2==3.1.2
+      - jiwer==3.0.1
+      - joblib==1.2.0
+      - lazy-loader==0.2
+      - librosa==0.10.0.post2
+      - lit==16.0.2
+      - llvmlite==0.40.0
+      - markdown==3.4.3
+      - markupsafe==2.1.2
+      - more-itertools==9.1.0
+      - mpmath==1.3.0
+      - msgpack==1.0.5
+      - multidict==6.0.4
+      - multiprocess==0.70.14
+      - networkx==3.1
+      - numba==0.57.0
+      - numpy==1.24.3
+      - nvidia-cublas-cu11==11.10.3.66
+      - nvidia-cuda-cupti-cu11==11.7.101
+      - nvidia-cuda-nvrtc-cu11==11.7.99
+      - nvidia-cuda-runtime-cu11==11.7.99
+      - nvidia-cudnn-cu11==8.5.0.96
+      - nvidia-cufft-cu11==10.9.0.58
+      - nvidia-curand-cu11==10.2.10.91
+      - nvidia-cusolver-cu11==11.4.0.1
+      - nvidia-cusparse-cu11==11.7.4.91
+      - nvidia-nccl-cu11==2.14.3
+      - nvidia-nvtx-cu11==11.7.91
+      - oauthlib==3.2.2
+      - packaging==23.1
+      - pandas==2.0.1
+      - pathtools==0.1.2
+      - pooch==1.6.0
+      - protobuf==4.22.3
+      - psutil==5.9.5
+      - pyarrow==12.0.0
+      - pyasn1==0.5.0
+      - pyasn1-modules==0.3.0
+      - pycparser==2.21
+      - python-dateutil==2.8.2
+      - pytz==2023.3
+      - pyyaml==6.0
+      - rapidfuzz==2.13.7
+      - regex==2023.5.4
+      - requests==2.29.0
+      - requests-oauthlib==1.3.1
+      - responses==0.18.0
+      - rsa==4.9
+      - scikit-learn==1.2.2
+      - scipy==1.10.1
+      - sentry-sdk==1.22.1
+      - setproctitle==1.3.2
+      - six==1.16.0
+      - smmap==5.0.0
+      - soundfile==0.12.1
+      - soxr==0.3.5
+      - sympy==1.11.1
+      - tensorboard==2.12.3
+      - tensorboard-data-server==0.7.0
+      - threadpoolctl==3.1.0
+      - tokenizers==0.13.3
+      - torch==2.0.0
+      - torchaudio==2.0.1
+      - tqdm==4.65.0
+      - transformers==4.29.0.dev0
+      - triton==2.0.0
+      - typing-extensions==4.5.0
+      - tzdata==2023.3
+      - urllib3==1.26.15
+      - wandb==0.15.2
+      - werkzeug==2.3.3
+      - xxhash==3.2.0
+      - yarl==1.9.2
+      - zipp==3.15.0
+prefix: /home/local/QCRI/dizham/miniconda3/envs/whisper

wandb/run-20230507_103405-9zf5xxpu/files/config.yaml

@@ -0,0 +1,688 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.9.16
+    cli_version: 0.15.2
+    framework: huggingface
+    huggingface_version: 4.29.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1683444845.953953
+    t:
+      1:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      2:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      3:
+      - 7
+      - 23
+      4: 3.9.16
+      5: 0.15.2
+      6: 4.29.0.dev0
+      8:
+      - 5
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/wer
+      5: 1
+      6:
+      - 1
+    - 1: eval/runtime
+      5: 1
+      6:
+      - 1
+    - 1: eval/samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: eval/steps_per_second
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 51865
+num_mel_bins:
+  desc: null
+  value: 80
+d_model:
+  desc: null
+  value: 768
+encoder_layers:
+  desc: null
+  value: 12
+encoder_attention_heads:
+  desc: null
+  value: 12
+decoder_layers:
+  desc: null
+  value: 12
+decoder_attention_heads:
+  desc: null
+  value: 12
+decoder_ffn_dim:
+  desc: null
+  value: 3072
+encoder_ffn_dim:
+  desc: null
+  value: 3072
+dropout:
+  desc: null
+  value: 0.0
+attention_dropout:
+  desc: null
+  value: 0.0
+activation_dropout:
+  desc: null
+  value: 0.0
+activation_function:
+  desc: null
+  value: gelu
+init_std:
+  desc: null
+  value: 0.02
+encoder_layerdrop:
+  desc: null
+  value: 0.0
+decoder_layerdrop:
+  desc: null
+  value: 0.0
+use_cache:
+  desc: null
+  value: false
+num_hidden_layers:
+  desc: null
+  value: 12
+scale_embedding:
+  desc: null
+  value: false
+max_source_positions:
+  desc: null
+  value: 1500
+max_target_positions:
+  desc: null
+  value: 448
+classifier_proj_size:
+  desc: null
+  value: 256
+use_weighted_layer_sum:
+  desc: null
+  value: false
+apply_spec_augment:
+  desc: null
+  value: false
+mask_time_prob:
+  desc: null
+  value: 0.05
+mask_time_length:
+  desc: null
+  value: 10
+mask_time_min_masks:
+  desc: null
+  value: 2
+mask_feature_prob:
+  desc: null
+  value: 0.0
+mask_feature_length:
+  desc: null
+  value: 10
+mask_feature_min_masks:
+  desc: null
+  value: 0
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: float32
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: true
+is_encoder_decoder:
+  desc: null
+  value: true
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 448
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value:
+  - 220
+  - 50257
+architectures:
+  desc: null
+  value:
+  - WhisperForConditionalGeneration
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 50257
+pad_token_id:
+  desc: null
+  value: 50257
+eos_token_id:
+  desc: null
+  value: 50257
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: 50258
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: openai/whisper-small
+transformers_version:
+  desc: null
+  value: 4.29.0.dev0
+forced_decoder_ids:
+  desc: null
+  value: null
+model_type:
+  desc: null
+  value: whisper
+output_dir:
+  desc: null
+  value: ./
+overwrite_output_dir:
+  desc: null
+  value: true
+do_train:
+  desc: null
+  value: true
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+evaluation_strategy:
+  desc: null
+  value: steps
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 32
+per_device_eval_batch_size:
+  desc: null
+  value: 32
+per_gpu_train_batch_size:
+  desc: null
+  value: None
+per_gpu_eval_batch_size:
+  desc: null
+  value: None
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: None
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 1.0e-05
+weight_decay:
+  desc: null
+  value: 0.0
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 3.0
+max_steps:
+  desc: null
+  value: 5000
+lr_scheduler_type:
+  desc: null
+  value: linear
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 500
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/May07_10-33-38_crimv3mgpu025
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 25
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 1000
+save_total_limit:
+  desc: null
+  value: None
+save_safetensors:
+  desc: null
+  value: false
+save_on_each_node:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: None
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: false
+fp16:
+  desc: null
+  value: true
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: cuda_amp
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: None
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: None
+tpu_num_cores:
+  desc: null
+  value: None
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: '[]'
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: 1000
+dataloader_num_workers:
+  desc: null
+  value: 0
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: ./
+disable_tqdm:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+label_names:
+  desc: null
+  value: None
+load_best_model_at_end:
+  desc: null
+  value: true
+metric_for_best_model:
+  desc: null
+  value: wer
+greater_is_better:
+  desc: null
+  value: false
+ignore_data_skip:
+  desc: null
+  value: false
+sharded_ddp:
+  desc: null
+  value: '[]'
+fsdp:
+  desc: null
+  value: '[]'
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value: '{''fsdp_min_num_params'': 0, ''xla'': False, ''xla_fsdp_grad_ckpt'': False}'
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: None
+deepspeed:
+  desc: null
+  value: None
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_hf
+optim_args:
+  desc: null
+  value: None
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: input_length
+report_to:
+  desc: null
+  value: '[''wandb'']'
+ddp_find_unused_parameters:
+  desc: null
+  value: None
+ddp_bucket_cap_mb:
+  desc: null
+  value: None
+dataloader_pin_memory:
+  desc: null
+  value: true
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: true
+resume_from_checkpoint:
+  desc: null
+  value: None
+hub_model_id:
+  desc: null
+  value: None
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: true
+include_inputs_for_metrics:
+  desc: null
+  value: false
+fp16_backend:
+  desc: null
+  value: auto
+push_to_hub_model_id:
+  desc: null
+  value: None
+push_to_hub_organization:
+  desc: null
+  value: None
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: None
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: None
+torch_compile_mode:
+  desc: null
+  value: None
+xpu_backend:
+  desc: null
+  value: None
+sortish_sampler:
+  desc: null
+  value: false
+predict_with_generate:
+  desc: null
+  value: true
+generation_max_length:
+  desc: null
+  value: 225
+generation_num_beams:
+  desc: null
+  value: None
+generation_config:
+  desc: null
+  value: None
+train_batch_size:
+  desc: null
+  value: 64
+eval_batch_size:
+  desc: null
+  value: 64

wandb/run-20230507_103405-9zf5xxpu/files/output.log

@@ -0,0 +1,1079 @@
+  0%|          | 0/5000 [00:00<?, ?it/s]
+
+Reading metadata...: 10438it [00:00, 28290.14it/s]
+
+[INFO|trainer_utils.py:693] 2023-05-07 10:35:32,760 >> The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
+  warnings.warn('Was asked to gather along dimension 0, but all '
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  0%|          | 25/5000 [12:57<38:59:22, 28.21s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|          | 50/5000 [24:31<38:04:45, 27.69s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|▏         | 75/5000 [36:10<38:12:36, 27.93s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|▏         | 100/5000 [47:46<37:40:02, 27.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|▎         | 125/5000 [59:17<37:59:12, 28.05s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|▎         | 150/5000 [1:10:46<37:32:21, 27.86s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|▎         | 163/5000 [1:15:43<20:26:07, 15.21s/it]
+Reading metadata...: 23919it [00:01, 14960.32it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|▎         | 175/5000 [1:22:25<38:42:56, 28.89s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|▍         | 200/5000 [1:34:15<39:11:58, 29.40s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|▍         | 224/5000 [1:45:23<36:46:48, 27.72s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  5%|▍         | 249/5000 [1:57:07<37:05:48, 28.11s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  5%|▌         | 274/5000 [2:08:53<36:42:42, 27.97s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|▌         | 299/5000 [2:20:36<36:26:30, 27.91s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|▋         | 325/5000 [2:32:04<23:59:08, 18.47s/it]
+
+
+  7%|▋         | 327/5000 [2:32:23<17:43:56, 13.66s/it]
+
+
+Reading metadata...: 23979it [00:02, 8389.85it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|▋         | 350/5000 [2:45:20<38:18:16, 29.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|▋         | 374/5000 [2:56:51<36:29:03, 28.39s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|▊         | 400/5000 [3:09:27<37:45:36, 29.55s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|▊         | 424/5000 [3:21:03<36:39:46, 28.84s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  9%|▉         | 449/5000 [3:33:05<36:30:32, 28.88s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  9%|▉         | 474/5000 [3:44:57<36:23:20, 28.94s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|▉         | 490/5000 [3:51:29<19:35:34, 15.64s/it]
+
+
+Reading metadata...: 23848it [00:02, 13351.04it/s]
+
+
+
+
+
+
+
+
+
+
+
+ 10%|█         | 500/5000 [3:57:20<35:45:29, 28.61s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|█         | 525/5000 [4:09:00<34:54:55, 28.09s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 11%|█         | 550/5000 [4:20:30<34:27:46, 27.88s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 11%|█▏        | 574/5000 [4:31:36<34:02:43, 27.69s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█▏        | 600/5000 [4:43:33<34:06:44, 27.91s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█▎        | 625/5000 [4:55:08<33:43:52, 27.76s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 13%|█▎        | 650/5000 [5:06:34<31:39:01, 26.19s/it]
+
+
+
+ 13%|█▎        | 654/5000 [5:07:15<16:27:10, 13.63s/it]
+Reading metadata...: 10438it [00:00, 28332.17it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|█▎        | 675/5000 [5:18:11<33:22:09, 27.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|█▍        | 699/5000 [5:29:08<32:58:14, 27.60s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|█▍        | 725/5000 [5:41:16<32:59:03, 27.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 15%|█▍        | 749/5000 [5:52:28<32:45:54, 27.75s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|█▌        | 775/5000 [6:04:31<32:25:51, 27.63s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|█▌        | 800/5000 [6:16:05<31:52:14, 27.32s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|█▋        | 817/5000 [6:22:52<17:40:15, 15.21s/it]
+
+Reading metadata...: 10438it [00:00, 26121.88it/s]
+
+
+
+
+
+
+
+ 16%|█▋        | 824/5000 [6:27:10<33:50:30, 29.17s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 17%|█▋        | 849/5000 [6:38:45<32:12:00, 27.93s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█▊        | 875/5000 [6:50:44<31:43:20, 27.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█▊        | 900/5000 [7:02:26<31:53:22, 28.00s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█▊        | 925/5000 [7:14:00<31:27:54, 27.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 19%|█▉        | 950/5000 [7:25:24<29:51:57, 26.55s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|█▉        | 975/5000 [7:36:55<31:02:52, 27.77s/it]
+
+
+
+
+
+
+ 20%|█▉        | 981/5000 [7:38:26<15:15:07, 13.66s/it]
+Reading metadata...: 23329it [00:00, 27403.88it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|█▉        | 999/5000 [7:48:10<31:41:54, 28.52s/it]
+ 20%|██        | 1000/5000 [7:48:38<31:29:41, 28.35s/it][INFO|trainer.py:3138] 2023-05-07 18:22:49,172 >> ***** Running Evaluation *****
+[INFO|trainer.py:3142] 2023-05-07 18:22:49,172 >>   Num examples: Unknown
+[INFO|trainer.py:3143] 2023-05-07 18:22:49,172 >>   Batch size = 64
+
+
+[INFO|trainer_utils.py:693] 2023-05-07 18:23:04,305 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+{'eval_loss': 0.43405279517173767, 'eval_wer': 54.25600000000001, 'eval_runtime': 2248.2056, 'eval_samples_per_second': 4.644, 'eval_steps_per_second': 0.073, 'epoch': 6.0}
+ 20%|██        | 1000/5000 [8:26:06<31:29:41, 28.35s/it][INFO|trainer.py:2877] 2023-05-07 19:00:17,386 >> Saving model checkpoint to ./checkpoint-1000
+[INFO|configuration_utils.py:458] 2023-05-07 19:00:17,393 >> Configuration saved in ./checkpoint-1000/config.json
+[INFO|configuration_utils.py:364] 2023-05-07 19:00:17,398 >> Configuration saved in ./checkpoint-1000/generation_config.json
+[INFO|modeling_utils.py:1855] 2023-05-07 19:00:20,753 >> Model weights saved in ./checkpoint-1000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:369] 2023-05-07 19:00:20,758 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:369] 2023-05-07 19:00:30,115 >> Feature extractor saved in ./preprocessor_config.json
+Adding files tracked by Git LFS: ['wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb', 'wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb']. This may take a bit of time if the files are large.

wandb/run-20230507_103405-9zf5xxpu/files/requirements.txt

@@ -0,0 +1,107 @@
+absl-py==1.4.0
+accelerate==0.18.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+appdirs==1.4.4
+async-timeout==4.0.2
+attrs==23.1.0
+audioread==3.0.0
+cachetools==5.3.0
+certifi==2022.12.7
+cffi==1.15.1
+charset-normalizer==3.1.0
+click==8.1.3
+cmake==3.26.3
+datasets==2.12.1.dev0
+decorator==5.1.1
+dill==0.3.6
+docker-pycreds==0.4.0
+evaluate==0.4.0
+filelock==3.12.0
+frozenlist==1.3.3
+fsspec==2023.4.0
+gitdb==4.0.10
+gitpython==3.1.31
+google-auth-oauthlib==1.0.0
+google-auth==2.17.3
+grpcio==1.54.0
+huggingface-hub==0.14.1
+idna==3.4
+importlib-metadata==6.6.0
+jinja2==3.1.2
+jiwer==3.0.1
+joblib==1.2.0
+lazy-loader==0.2
+librosa==0.10.0.post2
+lit==16.0.2
+llvmlite==0.40.0
+markdown==3.4.3
+markupsafe==2.1.2
+more-itertools==9.1.0
+mpmath==1.3.0
+msgpack==1.0.5
+multidict==6.0.4
+multiprocess==0.70.14
+networkx==3.1
+numba==0.57.0
+numpy==1.24.3
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+oauthlib==3.2.2
+packaging==23.1
+pandas==2.0.1
+pathtools==0.1.2
+pip==23.1.2
+pooch==1.6.0
+protobuf==4.22.3
+psutil==5.9.5
+pyarrow==12.0.0
+pyasn1-modules==0.3.0
+pyasn1==0.5.0
+pycparser==2.21
+python-dateutil==2.8.2
+pytz==2023.3
+pyyaml==6.0
+rapidfuzz==2.13.7
+regex==2023.5.4
+requests-oauthlib==1.3.1
+requests==2.29.0
+responses==0.18.0
+rsa==4.9
+scikit-learn==1.2.2
+scipy==1.10.1
+sentry-sdk==1.22.1
+setproctitle==1.3.2
+setuptools==67.7.2
+six==1.16.0
+smmap==5.0.0
+soundfile==0.12.1
+soxr==0.3.5
+sympy==1.11.1
+tensorboard-data-server==0.7.0
+tensorboard==2.12.3
+threadpoolctl==3.1.0
+tokenizers==0.13.3
+torch==2.0.0
+torchaudio==2.0.1
+tqdm==4.65.0
+transformers==4.29.0.dev0
+triton==2.0.0
+typing-extensions==4.5.0
+tzdata==2023.3
+urllib3==1.26.15
+wandb==0.15.2
+werkzeug==2.3.3
+wheel==0.40.0
+xxhash==3.2.0
+yarl==1.9.2
+zipp==3.15.0

wandb/run-20230507_103405-9zf5xxpu/files/wandb-metadata.json

@@ -0,0 +1,369 @@
+{
+    "os": "Linux-3.10.0-957.27.2.el7.x86_64-x86_64-with-glibc2.17",
+    "python": "3.9.16",
+    "heartbeatAt": "2023-05-07T07:34:06.720314",
+    "startedAt": "2023-05-07T07:34:05.852018",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--model_name_or_path=openai/whisper-small",
+        "--dataset_name=mozilla-foundation/common_voice_11_0",
+        "--dataset_config_name=ar",
+        "--language=arabic",
+        "--train_split_name=train+validation",
+        "--eval_split_name=test",
+        "--model_index_name=Whisper Small Arabic",
+        "--max_steps=5000",
+        "--output_dir=./",
+        "--per_device_train_batch_size=32",
+        "--gradient_accumulation_steps=2",
+        "--per_device_eval_batch_size=32",
+        "--logging_steps=25",
+        "--learning_rate=1e-5",
+        "--warmup_steps=500",
+        "--evaluation_strategy=steps",
+        "--eval_steps=1000",
+        "--save_strategy=steps",
+        "--save_steps=1000",
+        "--generation_max_length=225",
+        "--length_column_name=input_length",
+        "--max_duration_in_seconds=30",
+        "--text_column_name=sentence",
+        "--freeze_feature_encoder=False",
+        "--report_to=tensorboard",
+        "--report_to=wandb",
+        "--metric_for_best_model=wer",
+        "--greater_is_better=False",
+        "--load_best_model_at_end",
+        "--gradient_checkpointing",
+        "--fp16",
+        "--overwrite_output_dir",
+        "--do_train",
+        "--do_eval",
+        "--predict_with_generate",
+        "--do_normalize_eval",
+        "--streaming",
+        "--use_auth_token",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py",
+    "codePath": "run_speech_recognition_seq2seq_streaming.py",
+    "git": {
+        "remote": "https://huggingface.co/danielizham/whisper-small-ar",
+        "commit": "33cfe8b27be49d1904070ffc4339ab1b4075c5b1"
+    },
+    "email": "[email protected]",
+    "root": "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar",
+    "host": "crimv3mgpu025",
+    "username": "dizham",
+    "executable": "/home/local/QCRI/dizham/miniconda3/envs/whisper/bin/python",
+    "cpu_count": 28,
+    "cpu_count_logical": 56,
+    "cpu_freq": {
+        "current": 2201.0,
+        "min": 1000.0,
+        "max": 2201.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        },
+        {
+            "current": 2201.0,
+            "min": 1000.0,
+            "max": 2201.0
+        }
+    ],
+    "disk": {
+        "total": 99.951171875,
+        "used": 19.748153686523438
+    },
+    "gpu": "Tesla V100-SXM2-32GB",
+    "gpu_count": 2,
+    "gpu_devices": [
+        {
+            "name": "Tesla V100-SXM2-32GB",
+            "memory_total": 34089730048
+        },
+        {
+            "name": "Tesla V100-SXM2-32GB",
+            "memory_total": 34089730048
+        }
+    ],
+    "memory": {
+        "total": 251.55353164672852
+    }
+}

wandb/run-20230507_103405-9zf5xxpu/files/wandb-summary.json

@@ -0,0 +1 @@
+{"eval/loss": 0.43405279517173767, "eval/wer": 54.25600000000001, "eval/runtime": 2248.2056, "eval/samples_per_second": 4.644, "eval/steps_per_second": 0.073, "_timestamp": 1683475217.3777876, "_runtime": 30371.4238345623, "_step": 40}

wandb/run-20230507_103405-9zf5xxpu/logs/debug.log

@@ -0,0 +1,27 @@
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Current SDK version is 0.15.2
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Configure stats pid to 12412
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/.config/wandb/settings
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Loading settings from /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/settings
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program': '/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py'}
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_init.py:_log_setup():507] Logging user logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230507_103405-9zf5xxpu/logs/debug.log
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_init.py:_log_setup():508] Logging internal logs to /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230507_103405-9zf5xxpu/logs/debug-internal.log
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_init.py:init():547] calling init triggers
+2023-05-07 10:34:05,926 INFO    MainThread:12412 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
+config: {}
+2023-05-07 10:34:05,927 INFO    MainThread:12412 [wandb_init.py:init():596] starting backend
+2023-05-07 10:34:05,927 INFO    MainThread:12412 [wandb_init.py:init():600] setting up manager
+2023-05-07 10:34:05,929 INFO    MainThread:12412 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2023-05-07 10:34:05,953 INFO    MainThread:12412 [wandb_init.py:init():606] backend started and connected
+2023-05-07 10:34:05,955 INFO    MainThread:12412 [wandb_init.py:init():700] updated telemetry
+2023-05-07 10:34:06,022 INFO    MainThread:12412 [wandb_init.py:init():737] communicating run to backend with 60.0 second timeout
+2023-05-07 10:34:06,586 INFO    MainThread:12412 [wandb_run.py:_on_init():2177] communicating current version
+2023-05-07 10:34:06,688 INFO    MainThread:12412 [wandb_run.py:_on_init():2186] got version response 
+2023-05-07 10:34:06,688 INFO    MainThread:12412 [wandb_init.py:init():787] starting run threads in backend
+2023-05-07 10:34:10,572 INFO    MainThread:12412 [wandb_run.py:_console_start():2158] atexit reg
+2023-05-07 10:34:10,573 INFO    MainThread:12412 [wandb_run.py:_redirect():2013] redirect: SettingsConsole.WRAP_RAW
+2023-05-07 10:34:10,573 INFO    MainThread:12412 [wandb_run.py:_redirect():2078] Wrapping output streams.
+2023-05-07 10:34:10,573 INFO    MainThread:12412 [wandb_run.py:_redirect():2103] Redirects installed.
+2023-05-07 10:34:10,574 INFO    MainThread:12412 [wandb_init.py:init():829] run started, returning control to user process
+2023-05-07 10:34:10,592 INFO    MainThread:12412 [wandb_run.py:_config_callback():1286] config_cb None None {'vocab_size': 51865, 'num_mel_bins': 80, 'd_model': 768, 'encoder_layers': 12, 'encoder_attention_heads': 12, 'decoder_layers': 12, 'decoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'encoder_ffn_dim': 3072, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': False, 'num_hidden_layers': 12, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50257, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-small', 'transformers_version': '4.29.0.dev0', 'forced_decoder_ids': None, 'model_type': 'whisper', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 5000, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/May07_10-33-38_crimv3mgpu025', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 'None', 'save_safetensors': False, 'save_on_each_node': False, 'no_cuda': False, 'use_mps_device': False, 'seed': 42, 'data_seed': 'None', 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'cuda_amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': 0, 'ddp_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'fsdp': '[]', 'fsdp_min_num_params': 0, 'fsdp_config': "{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}", 'fsdp_transformer_layer_cls_to_wrap': 'None', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'optim_args': 'None', 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': 'None', 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': 'None', 'torch_compile_mode': 'None', 'xpu_backend': 'None', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': 'None', 'generation_config': 'None', 'train_batch_size': 64, 'eval_batch_size': 64}

wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77d49c926099ac2b0f7a7e3b4e00ce2e9407dda9d529e412727a2fb9b212be2
+size 2787409