Whisper Languages.txt

Whisper Languages

ZIE:
https://github.com/openai/whisper/blob/main/whisper/tokenizer.py

LANGUAGES = {
    "en": "english",
    "zh": "chinese",
    "de": "german",
    "es": "spanish",
    "ru": "russian",
    "ko": "korean",
    "fr": "french",
    "ja": "japanese",
    "pt": "portuguese",
    "tr": "turkish",
    "pl": "polish",
    "ca": "catalan",
    "nl": "dutch",
    "ar": "arabic",
    "sv": "swedish",
    "it": "italian",
    "id": "indonesian",
    "hi": "hindi",
    "fi": "finnish",
    "vi": "vietnamese",
    "he": "hebrew",
    "uk": "ukrainian",
    "el": "greek",
    "ms": "malay",
    "cs": "czech",
    "ro": "romanian",
    "da": "danish",
    "hu": "hungarian",
    "ta": "tamil",
    "no": "norwegian",
    "th": "thai",
    "ur": "urdu",
    "hr": "croatian",
    "bg": "bulgarian",
    "lt": "lithuanian",
    "la": "latin",
    "mi": "maori",
    "ml": "malayalam",
    "cy": "welsh",
    "sk": "slovak",
    "te": "telugu",
    "fa": "persian",
    "lv": "latvian",
    "bn": "bengali",
    "sr": "serbian",
    "az": "azerbaijani",
    "sl": "slovenian",
    "kn": "kannada",
    "et": "estonian",
    "mk": "macedonian",
    "br": "breton",
    "eu": "basque",
    "is": "icelandic",
    "hy": "armenian",
    "ne": "nepali",
    "mn": "mongolian",
    "bs": "bosnian",
    "kk": "kazakh",
    "sq": "albanian",
    "sw": "swahili",
    "gl": "galician",
    "mr": "marathi",
    "pa": "punjabi",
    "si": "sinhala",
    "km": "khmer",
    "sn": "shona",
    "yo": "yoruba",
    "so": "somali",
    "af": "afrikaans",
    "oc": "occitan",
    "ka": "georgian",
    "be": "belarusian",
    "tg": "tajik",
    "sd": "sindhi",
    "gu": "gujarati",
    "am": "amharic",
    "yi": "yiddish",
    "lo": "lao",
    "uz": "uzbek",
    "fo": "faroese",
    "ht": "haitian creole",
    "ps": "pashto",
    "tk": "turkmen",
    "nn": "nynorsk",
    "mt": "maltese",
    "sa": "sanskrit",
    "lb": "luxembourgish",
    "my": "myanmar",
    "bo": "tibetan",
    "tl": "tagalog",
    "mg": "malagasy",
    "as": "assamese",
    "tt": "tatar",
    "haw": "hawaiian",
    "ln": "lingala",
    "ha": "hausa",
    "ba": "bashkir",
    "jw": "javanese",
    "su": "sundanese",
    "yue": "cantonese",
}

# language code lookup by name, with a few language aliases
TO_LANGUAGE_CODE = {
    **{language: code for code, language in LANGUAGES.items()},
    "burmese": "my",
    "valencian": "ca",
    "flemish": "nl",
    "haitian": "ht",
    "letzeburgesch": "lb",
    "pushto": "ps",
    "panjabi": "pa",
    "moldavian": "ro",
    "moldovan": "ro",
    "sinhalese": "si",
    "castilian": "es",
    "mandarin": "zh",
}



[
  [
    "fr",
    0.9877740740776062
  ],
  [
    "en",
    0.004565223585814238
  ],
  [
    "it",
    0.0013161455281078815
  ],
  [
    "de",
    0.0010678422404453158
  ],
  [
    "br",
    0.0010424673091620207
  ],
  [
    "la",
    0.0007281662547029555
  ],
  [
    "es",
    0.00047290409565903246
  ],
  [
    "ja",
    0.0003620732750277966
  ],
  [
    "pt",
    0.00025811095838434994
  ],
  [
    "nn",
    0.0002432575129205361
  ],
  [
    "pl",
    0.00021074499818496406
  ],
  [
    "nl",
    0.00020471173047553748
  ],
  [
    "ru",
    0.0002026906149694696
  ],
  [
    "cy",
    0.00018965611525345594
  ],
  [
    "oc",
    0.00017241497698705643
  ],
  [
    "km",
    0.00012158624303992838
  ],
  [
    "zh",
    0.00011692210682667792
  ],
  [
    "jw",
    0.00010178791853832081
  ],
  [
    "ro",
    0.00009590199624653906
  ],
  [
    "sv",
    0.00007909776468295604
  ],
  [
    "ar",
    0.0000725739446352236
  ],
  [
    "tr",
    0.000057220226153731346
  ],
  [
    "fi",
    0.00005474982754094526
  ],
  [
    "ko",
    0.00004248135883244686
  ],
  [
    "mi",
    0.00003786800516536459
  ],
  [
    "sn",
    0.000031534167646896094
  ],
  [
    "hu",
    0.000028775264581781812
  ],
  [
    "ht",
    0.000028651957109104842
  ],
  [
    "vi",
    0.000028335278329905123
  ],
  [
    "da",
    0.000027910642529604957
  ],
  [
    "el",
    0.000023526350560132414
  ],
  [
    "fa",
    0.000022600075681111775
  ],
  [
    "haw",
    0.00002183002288802527
  ],
  [
    "no",
    0.000019493931176839396
  ],
  [
    "cs",
    0.000016285941455862485
  ],
  [
    "he",
    0.00001463644457544433
  ],
  [
    "sa",
    0.000012327554941293783
  ],
  [
    "th",
    0.000010766526429506484
  ],
  [
    "ca",
    0.000008936658559832722
  ],
  [
    "bg",
    0.000007716189429629594
  ],
  [
    "ms",
    0.000007680522685404867
  ],
  [
    "yo",
    0.000006417556051019346
  ],
  [
    "gl",
    0.000006063059572625207
  ],
  [
    "ln",
    0.000006041265805833973
  ],
  [
    "si",
    0.000005011619577999227
  ],
  [
    "hi",
    0.000004941234692523722
  ],
  [
    "sk",
    0.000004815055945073254
  ],
  [
    "uk",
    0.000004419264769239817
  ],
  [
    "hy",
    0.000004105790594621794
  ],
  [
    "id",
    0.000003996842679043766
  ],
  [
    "tl",
    0.000003896923772117589
  ],
  [
    "ml",
    0.000003836657469946658
  ],
  [
    "hr",
    0.0000035950304209109163
  ],
  [
    "ta",
    0.0000031487393243878614
  ],
  [
    "ur",
    0.000002829937329806853
  ],
  [
    "yi",
    0.0000028043848487868672
  ],
  [
    "bs",
    0.000002576711949586752
  ],
  [
    "sl",
    0.0000025655576791905332
  ],
  [
    "eu",
    0.000002537221007514745
  ],
  [
    "sw",
    0.000002027671598625602
  ],
  [
    "bn",
    0.0000020110176137677627
  ],
  [
    "et",
    0.0000019163769593433244
  ],
  [
    "af",
    0.0000016607176576144411
  ],
  [
    "lb",
    0.0000015626893627995742
  ],
  [
    "fo",
    0.000001537753632874228
  ],
  [
    "mn",
    0.0000012066857379977591
  ],
  [
    "sq",
    0.0000010732701412052847
  ],
  [
    "te",
    0.0000010657946631908999
  ],
  [
    "pa",
    0.000001037814399751369
  ],
  [
    "sr",
    0.000001028694782689854
  ],
  [
    "my",
    9.428002840650151e-7
  ],
  [
    "bo",
    8.66582468006527e-7
  ],
  [
    "ne",
    8.636189363642188e-7
  ],
  [
    "lo",
    7.318710117942828e-7
  ],
  [
    "be",
    6.941849051145255e-7
  ],
  [
    "lv",
    6.265471483857254e-7
  ],
  [
    "az",
    6.14897032846784e-7
  ],
  [
    "sd",
    5.913773293286795e-7
  ],
  [
    "mr",
    5.441081043500162e-7
  ],
  [
    "ps",
    4.3055180753981404e-7
  ],
  [
    "is",
    3.4580702390485385e-7
  ],
  [
    "kk",
    3.0084689228715433e-7
  ],
  [
    "kn",
    1.7288991216446448e-7
  ],
  [
    "as",
    1.5110647666460864e-7
  ],
  [
    "am",
    1.2572900232044049e-7
  ],
  [
    "gu",
    1.2536465021639742e-7
  ],
  [
    "lt",
    1.1584211279114243e-7
  ],
  [
    "mt",
    9.117716359696715e-8
  ],
  [
    "mk",
    8.674353324522599e-8
  ],
  [
    "ka",
    8.111815219535856e-8
  ],
  [
    "ha",
    5.529446056584675e-8
  ],
  [
    "su",
    5.323035523474573e-8
  ],
  [
    "tg",
    4.645137252623499e-8
  ],
  [
    "tt",
    2.9631449294242884e-8
  ],
  [
    "so",
    5.109404455083677e-9
  ],
  [
    "uz",
    3.229358558343165e-9
  ],
  [
    "mg",
    3.0856159849435016e-9
  ],
  [
    "tk",
    4.514433618596492e-11
  ],
  [
    "ba",
    3.5637395812138095e-11
  ]
]