Spaces:
Sleeping
Sleeping
File size: 2,336 Bytes
e378a99 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
--[[
WhisperLanguages.lua - A list of languages supported by the Whisper API
]]--
WhisperLanguages = {
-- Copied from whisper.tokenizer.LANGUAGES
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'
},
LANGUAGE_CODES = {},
}
-- initialize LANGUAGE_CODES
(function()
for code, _ in pairs(WhisperLanguages.LANGUAGES) do
table.insert(WhisperLanguages.LANGUAGE_CODES, code)
end
table.sort(WhisperLanguages.LANGUAGE_CODES, function (a, b)
return WhisperLanguages.LANGUAGES[a] < WhisperLanguages.LANGUAGES[b]
end)
table.insert(WhisperLanguages.LANGUAGE_CODES, 1, '')
WhisperLanguages.LANGUAGES[''] = 'Detect'
end)()
|