label_encoder.txt
2.2 KB · 110 lines · plaintext Raw
1 'ab: Abkhazian' => 0
2 'af: Afrikaans' => 1
3 'am: Amharic' => 2
4 'ar: Arabic' => 3
5 'as: Assamese' => 4
6 'az: Azerbaijani' => 5
7 'ba: Bashkir' => 6
8 'be: Belarusian' => 7
9 'bg: Bulgarian' => 8
10 'bn: Bengali' => 9
11 'bo: Tibetan' => 10
12 'br: Breton' => 11
13 'bs: Bosnian' => 12
14 'ca: Catalan' => 13
15 'ceb: Cebuano' => 14
16 'cs: Czech' => 15
17 'cy: Welsh' => 16
18 'da: Danish' => 17
19 'de: German' => 18
20 'el: Greek' => 19
21 'en: English' => 20
22 'eo: Esperanto' => 21
23 'es: Spanish' => 22
24 'et: Estonian' => 23
25 'eu: Basque' => 24
26 'fa: Persian' => 25
27 'fi: Finnish' => 26
28 'fo: Faroese' => 27
29 'fr: French' => 28
30 'gl: Galician' => 29
31 'gn: Guarani' => 30
32 'gu: Gujarati' => 31
33 'gv: Manx' => 32
34 'ha: Hausa' => 33
35 'haw: Hawaiian' => 34
36 'hi: Hindi' => 35
37 'hr: Croatian' => 36
38 'ht: Haitian' => 37
39 'hu: Hungarian' => 38
40 'hy: Armenian' => 39
41 'ia: Interlingua' => 40
42 'id: Indonesian' => 41
43 'is: Icelandic' => 42
44 'it: Italian' => 43
45 'iw: Hebrew' => 44
46 'ja: Japanese' => 45
47 'jw: Javanese' => 46
48 'ka: Georgian' => 47
49 'kk: Kazakh' => 48
50 'km: Central Khmer' => 49
51 'kn: Kannada' => 50
52 'ko: Korean' => 51
53 'la: Latin' => 52
54 'lb: Luxembourgish' => 53
55 'ln: Lingala' => 54
56 'lo: Lao' => 55
57 'lt: Lithuanian' => 56
58 'lv: Latvian' => 57
59 'mg: Malagasy' => 58
60 'mi: Maori' => 59
61 'mk: Macedonian' => 60
62 'ml: Malayalam' => 61
63 'mn: Mongolian' => 62
64 'mr: Marathi' => 63
65 'ms: Malay' => 64
66 'mt: Maltese' => 65
67 'my: Burmese' => 66
68 'ne: Nepali' => 67
69 'nl: Dutch' => 68
70 'nn: Norwegian Nynorsk' => 69
71 'no: Norwegian' => 70
72 'oc: Occitan' => 71
73 'pa: Panjabi' => 72
74 'pl: Polish' => 73
75 'ps: Pushto' => 74
76 'pt: Portuguese' => 75
77 'ro: Romanian' => 76
78 'ru: Russian' => 77
79 'sa: Sanskrit' => 78
80 'sco: Scots' => 79
81 'sd: Sindhi' => 80
82 'si: Sinhala' => 81
83 'sk: Slovak' => 82
84 'sl: Slovenian' => 83
85 'sn: Shona' => 84
86 'so: Somali' => 85
87 'sq: Albanian' => 86
88 'sr: Serbian' => 87
89 'su: Sundanese' => 88
90 'sv: Swedish' => 89
91 'sw: Swahili' => 90
92 'ta: Tamil' => 91
93 'te: Telugu' => 92
94 'tg: Tajik' => 93
95 'th: Thai' => 94
96 'tk: Turkmen' => 95
97 'tl: Tagalog' => 96
98 'tr: Turkish' => 97
99 'tt: Tatar' => 98
100 'uk: Ukrainian' => 99
101 'ur: Urdu' => 100
102 'uz: Uzbek' => 101
103 'vi: Vietnamese' => 102
104 'war: Waray' => 103
105 'yi: Yiddish' => 104
106 'yo: Yoruba' => 105
107 'zh: Chinese' => 106
108 ================
109 'starting_index' => 0
110