mirror of
https://github.com/freedomofpress/dangerzone.git
synced 2025-04-28 18:02:38 +02:00
cbca9110ca
Switch to the tessdata-fast Tesseract model, instead of the tessdata one. The tessdata-fast Tesseract model is much smaller, and a bit faster than the other one. Also, it's the model that Debian/Fedora ship by default. Closes #545
125 lines
3 KiB
JSON
125 lines
3 KiB
JSON
{
|
|
"Afrikaans": "afr",
|
|
"Amharic": "amh",
|
|
"Arabic": "ara",
|
|
"Assamese": "asm",
|
|
"Azerbaijani": "aze",
|
|
"Azerbaijani (Cyrillic)": "aze_cyrl",
|
|
"Belarusian": "bel",
|
|
"Bengali": "ben",
|
|
"Tibetan Standard": "bod",
|
|
"Bosnian": "bos",
|
|
"Breton": "bre",
|
|
"Bulgarian": "bul",
|
|
"Catalan": "cat",
|
|
"Cebuano": "ceb",
|
|
"Czech": "ces",
|
|
"Chinese - Simplified": "chi_sim",
|
|
"Chinese - Simplified (vertical)": "chi_sim_vert",
|
|
"Chinese - Traditional": "chi_tra",
|
|
"Chinese - Traditional (vertical)": "chi_tra_vert",
|
|
"Cherokee": "chr",
|
|
"Corsican": "cos",
|
|
"Welsh": "cym",
|
|
"Danish": "dan",
|
|
"German": "deu",
|
|
"Divehi": "div",
|
|
"Dzongkha": "dzo",
|
|
"Greek": "ell",
|
|
"English": "eng",
|
|
"English, Middle (1100-1500)": "enm",
|
|
"Esperanto": "epo",
|
|
"Estonian": "est",
|
|
"Basque": "eus",
|
|
"Faroese": "fao",
|
|
"Persian": "fas",
|
|
"Filipino": "fil",
|
|
"Finnish": "fin",
|
|
"French": "fra",
|
|
"Frankish": "frk",
|
|
"French, Middle (ca.1400-1600)": "frm",
|
|
"Frisian (Western)": "fry",
|
|
"Gaelic (Scots)": "gla",
|
|
"Irish": "gle",
|
|
"Galician": "glg",
|
|
"Greek, Ancient (to 1453)": "grc",
|
|
"Gujarati": "guj",
|
|
"Hatian": "hat",
|
|
"Hebrew": "heb",
|
|
"Hindi": "hin",
|
|
"Croatian": "hrv",
|
|
"Hungarian": "hun",
|
|
"Armenian": "hye",
|
|
"Inuktitut": "iku",
|
|
"Indonesian": "ind",
|
|
"Icelandic": "isl",
|
|
"Italian": "ita",
|
|
"Italian - Old": "ita_old",
|
|
"Javanese": "jav",
|
|
"Japanese": "jpn",
|
|
"Japanese (vertical)": "jpn_vert",
|
|
"Kannada": "kan",
|
|
"Georgian": "kat",
|
|
"Old Georgian": "kat_old",
|
|
"Kazakh": "kaz",
|
|
"Khmer": "khm",
|
|
"Kyrgyz": "kir",
|
|
"Kurmanji (Kurdish - Latin Script)": "kmr",
|
|
"Korean": "kor",
|
|
"Korean (vertical)": "kor_vert",
|
|
"Lao": "lao",
|
|
"Latin": "lat",
|
|
"Latvian": "lav",
|
|
"Lithuanian": "lit",
|
|
"Luxembourgish": "ltz",
|
|
"Malayalam": "mal",
|
|
"Marathi": "mar",
|
|
"Macedonian": "mkd",
|
|
"Maltese": "mlt",
|
|
"Mongolian": "mon",
|
|
"Maori": "mri",
|
|
"Malay": "msa",
|
|
"Burmese": "mya",
|
|
"Nepali": "nep",
|
|
"Dutch": "nld",
|
|
"Norwegian": "nor",
|
|
"Occitan (post 1500)": "oci",
|
|
"Oriya": "ori",
|
|
"Punjabi": "pan",
|
|
"Polish": "pol",
|
|
"Portuguese": "por",
|
|
"Pashto": "pus",
|
|
"Quechua": "que",
|
|
"Romanian": "ron",
|
|
"Russian": "rus",
|
|
"Sanskrit": "san",
|
|
"Sinhala": "sin",
|
|
"Slovakian": "slk",
|
|
"Slovenian": "slv",
|
|
"Sindhi": "snd",
|
|
"Spanish": "spa",
|
|
"Spanish; Castilian - Old": "spa_old",
|
|
"Albanian": "sqi",
|
|
"Serbian": "srp",
|
|
"Serbian (Latin)": "srp_latn",
|
|
"Sundanese": "sun",
|
|
"Swahili": "swa",
|
|
"Swedish": "swe",
|
|
"Syriac": "syr",
|
|
"Tamil": "tam",
|
|
"Tatar": "tat",
|
|
"Telugu": "tel",
|
|
"Tajik": "tgk",
|
|
"Thai": "tha",
|
|
"Tigrinya": "tir",
|
|
"Tonga": "ton",
|
|
"Turkish": "tur",
|
|
"Uyghur": "uig",
|
|
"Ukrainian": "ukr",
|
|
"Urdu": "urd",
|
|
"Uzbek": "uzb",
|
|
"Uzbek (Cyrillic)": "uzb_cyrl",
|
|
"Vietnamese": "vie",
|
|
"Yiddish": "yid",
|
|
"Yoruba": "yor"
|
|
}
|