翻訳言語定義を YAML に移行しロード処理を実装
- 言語マッピングを src-python/models/translation/languages/languages.yml として追加 - translation_languages.py を全面リファクタ：YAML から読み込み、構造検証、スレッドロック、キャッシュ対応を導入 - config.py に loadTranslationLanguages のインポート/フォールバックを追加し、Config 初期化時に言語定義を読み込むよう変更 - PyYAML を requirements.txt / requirements_cuda.txt に追記 - PyInstaller spec (backend.spec / backend_cuda.spec) に言語ファイル配布先を追加 - translation_ollama.py の loadPromptConfig 呼び出しを修正（ファイル名を明示）
This commit is contained in:
misyaguziya
@@ -8,6 +8,7 @@ a = Analysis(
|
|||||||
datas=[
|
datas=[
|
||||||
('./src-python/models/overlay/fonts', 'fonts/'),
|
('./src-python/models/overlay/fonts', 'fonts/'),
|
||||||
('./src-python/models/translation/prompt', 'prompt/'),
|
('./src-python/models/translation/prompt', 'prompt/'),
|
||||||
|
('./src-python/models/translation/languages', 'languages/'),
|
||||||
('.venv/Lib/site-packages/zeroconf', 'zeroconf/'),
|
('.venv/Lib/site-packages/zeroconf', 'zeroconf/'),
|
||||||
('.venv/Lib/site-packages/openvr', 'openvr/'),
|
('.venv/Lib/site-packages/openvr', 'openvr/'),
|
||||||
('.venv/Lib/site-packages/faster_whisper', 'faster_whisper/'),
|
('.venv/Lib/site-packages/faster_whisper', 'faster_whisper/'),
|
||||||
|
|||||||
@@ -8,6 +8,7 @@ a = Analysis(
|
|||||||
datas=[
|
datas=[
|
||||||
('./src-python/models/overlay/fonts', 'fonts/'),
|
('./src-python/models/overlay/fonts', 'fonts/'),
|
||||||
('./src-python/models/translation/prompt', 'prompt/'),
|
('./src-python/models/translation/prompt', 'prompt/'),
|
||||||
|
('./src-python/models/translation/languages', 'languages/'),
|
||||||
('.venv_cuda/Lib/site-packages/zeroconf', 'zeroconf/'),
|
('.venv_cuda/Lib/site-packages/zeroconf', 'zeroconf/'),
|
||||||
('.venv_cuda/Lib/site-packages/openvr', 'openvr/'),
|
('.venv_cuda/Lib/site-packages/openvr', 'openvr/'),
|
||||||
('.venv_cuda/Lib/site-packages/faster_whisper', 'faster_whisper/'),
|
('.venv_cuda/Lib/site-packages/faster_whisper', 'faster_whisper/'),
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ transformers==4.40.2
|
|||||||
pillow == 10.0.0
|
pillow == 10.0.0
|
||||||
PyAudioWPatch == 0.2.12.6
|
PyAudioWPatch == 0.2.12.6
|
||||||
python-osc == 1.9.0
|
python-osc == 1.9.0
|
||||||
|
PyYAML==6.0.2
|
||||||
deepl == 1.22.0
|
deepl == 1.22.0
|
||||||
flashtext ==2.7
|
flashtext ==2.7
|
||||||
pyinstaller==6.10.0
|
pyinstaller==6.10.0
|
||||||
|
|||||||
@@ -6,6 +6,7 @@ transformers==4.40.2
|
|||||||
pillow == 10.0.0
|
pillow == 10.0.0
|
||||||
PyAudioWPatch == 0.2.12.6
|
PyAudioWPatch == 0.2.12.6
|
||||||
python-osc == 1.9.0
|
python-osc == 1.9.0
|
||||||
|
PyYAML==6.0.2
|
||||||
deepl == 1.22.0
|
deepl == 1.22.0
|
||||||
flashtext ==2.7
|
flashtext ==2.7
|
||||||
pyinstaller==6.10.0
|
pyinstaller==6.10.0
|
||||||
|
|||||||
@@ -16,9 +16,11 @@ except Exception: # pragma: no cover - optional runtime
|
|||||||
device_manager = None # type: ignore
|
device_manager = None # type: ignore
|
||||||
|
|
||||||
try:
|
try:
|
||||||
from models.translation.translation_languages import translation_lang
|
from models.translation.translation_languages import translation_lang, loadTranslationLanguages
|
||||||
except Exception: # pragma: no cover - optional runtime
|
except Exception: # pragma: no cover - optional runtime
|
||||||
translation_lang = {} # type: ignore
|
translation_lang = {} # type: ignore
|
||||||
|
def loadTranslationLanguages(path: str, force: bool = False) -> Dict[str, Any]:
|
||||||
|
return {}
|
||||||
|
|
||||||
try:
|
try:
|
||||||
from models.translation.translation_utils import ctranslate2_weights
|
from models.translation.translation_utils import ctranslate2_weights
|
||||||
@@ -1227,6 +1229,7 @@ class Config:
|
|||||||
# these external mappings may be empty dicts if the optional modules failed to import
|
# these external mappings may be empty dicts if the optional modules failed to import
|
||||||
self._SELECTABLE_CTRANSLATE2_WEIGHT_TYPE_LIST = getattr(ctranslate2_weights, 'keys', lambda: [])()
|
self._SELECTABLE_CTRANSLATE2_WEIGHT_TYPE_LIST = getattr(ctranslate2_weights, 'keys', lambda: [])()
|
||||||
self._SELECTABLE_WHISPER_WEIGHT_TYPE_LIST = getattr(whisper_models, 'keys', lambda: [])()
|
self._SELECTABLE_WHISPER_WEIGHT_TYPE_LIST = getattr(whisper_models, 'keys', lambda: [])()
|
||||||
|
translation_lang = loadTranslationLanguages(self.PATH_LOCAL)
|
||||||
self._SELECTABLE_TRANSLATION_ENGINE_LIST = getattr(translation_lang, 'keys', lambda: [])()
|
self._SELECTABLE_TRANSLATION_ENGINE_LIST = getattr(translation_lang, 'keys', lambda: [])()
|
||||||
try:
|
try:
|
||||||
# transcription_lang is nested dict; attempt to extract keys defensively
|
# transcription_lang is nested dict; attempt to extract keys defensively
|
||||||
|
|||||||
771
src-python/models/translation/languages/languages.yml
Normal file
771
src-python/models/translation/languages/languages.yml
Normal file
@@ -0,0 +1,771 @@
|
|||||||
|
# Translation Language Mappings
|
||||||
|
# Each backend defines source (input) and target (output) language codes
|
||||||
|
|
||||||
|
DeepL:
|
||||||
|
source: &deepl_langs
|
||||||
|
Arabic: ar
|
||||||
|
Bulgarian: bg
|
||||||
|
Czech: cs
|
||||||
|
Danish: da
|
||||||
|
German: de
|
||||||
|
Greek: el
|
||||||
|
English: en
|
||||||
|
Spanish: es
|
||||||
|
Estonian: et
|
||||||
|
Finnish: fi
|
||||||
|
French: fr
|
||||||
|
Irish: ga
|
||||||
|
Croatian: hr
|
||||||
|
Hungarian: hu
|
||||||
|
Indonesian: id
|
||||||
|
Italian: it
|
||||||
|
Japanese: ja
|
||||||
|
Korean: ko
|
||||||
|
Lithuanian: lt
|
||||||
|
Latvian: lv
|
||||||
|
Maltese: mt
|
||||||
|
Norwegian: 'no'
|
||||||
|
Dutch: nl
|
||||||
|
Polish: pl
|
||||||
|
Portuguese: pt
|
||||||
|
Romanian: ro
|
||||||
|
Russian: ru
|
||||||
|
Slovak: sk
|
||||||
|
Slovenian: sl
|
||||||
|
Swedish: sv
|
||||||
|
Turkish: tr
|
||||||
|
Ukrainian: uk
|
||||||
|
Chinese Simplified: zh
|
||||||
|
Chinese Traditional: zh
|
||||||
|
target: *deepl_langs
|
||||||
|
|
||||||
|
DeepL_API:
|
||||||
|
source:
|
||||||
|
Japanese: ja
|
||||||
|
English: en
|
||||||
|
Bulgarian: bg
|
||||||
|
Czech: cs
|
||||||
|
Danish: da
|
||||||
|
German: de
|
||||||
|
Greek: el
|
||||||
|
Spanish: es
|
||||||
|
Estonian: et
|
||||||
|
Finnish: fi
|
||||||
|
French: fr
|
||||||
|
Hungarian: hu
|
||||||
|
Indonesian: id
|
||||||
|
Italian: it
|
||||||
|
Korean: ko
|
||||||
|
Lithuanian: lt
|
||||||
|
Latvian: lv
|
||||||
|
Norwegian: 'no'
|
||||||
|
Dutch: nl
|
||||||
|
Polish: pl
|
||||||
|
Portuguese: pt
|
||||||
|
Romanian: ro
|
||||||
|
Russian: ru
|
||||||
|
Slovak: sk
|
||||||
|
Slovenian: sl
|
||||||
|
Swedish: sv
|
||||||
|
Turkish: tr
|
||||||
|
Ukrainian: uk
|
||||||
|
Chinese Simplified: zh
|
||||||
|
Chinese Traditional: zh
|
||||||
|
target:
|
||||||
|
Japanese: ja
|
||||||
|
English: en
|
||||||
|
English (American): en-US
|
||||||
|
English (British): en-GB
|
||||||
|
Bulgarian: bg
|
||||||
|
Czech: cs
|
||||||
|
Danish: da
|
||||||
|
German: de
|
||||||
|
Greek: el
|
||||||
|
Spanish: es
|
||||||
|
Estonian: et
|
||||||
|
Finnish: fi
|
||||||
|
French: fr
|
||||||
|
Hungarian: hu
|
||||||
|
Indonesian: id
|
||||||
|
Italian: it
|
||||||
|
Korean: ko
|
||||||
|
Lithuanian: lt
|
||||||
|
Latvian: lv
|
||||||
|
Norwegian: 'no'
|
||||||
|
Dutch: nl
|
||||||
|
Polish: pl
|
||||||
|
Portuguese (Brazilian): pt-BR
|
||||||
|
Portuguese (European): pt-PT
|
||||||
|
Romanian: ro
|
||||||
|
Russian: ru
|
||||||
|
Slovak: sk
|
||||||
|
Slovenian: sl
|
||||||
|
Swedish: sv
|
||||||
|
Turkish: tr
|
||||||
|
Ukrainian: uk
|
||||||
|
Chinese Simplified: zh
|
||||||
|
Chinese Traditional: zh
|
||||||
|
|
||||||
|
Google:
|
||||||
|
source: &google_langs
|
||||||
|
Japanese: ja
|
||||||
|
English: en
|
||||||
|
Chinese Simplified: zh
|
||||||
|
Chinese Traditional: zh-TW
|
||||||
|
Arabic: ar
|
||||||
|
Russian: ru
|
||||||
|
French: fr
|
||||||
|
German: de
|
||||||
|
Spanish: es
|
||||||
|
Portuguese: pt
|
||||||
|
Italian: it
|
||||||
|
Korean: ko
|
||||||
|
Greek: el
|
||||||
|
Dutch: nl
|
||||||
|
Hindi: hi
|
||||||
|
Turkish: tr
|
||||||
|
Malay: ms
|
||||||
|
Thai: th
|
||||||
|
Vietnamese: vi
|
||||||
|
Indonesian: id
|
||||||
|
Hebrew: he
|
||||||
|
Polish: pl
|
||||||
|
Mongolian: mn
|
||||||
|
Czech: cs
|
||||||
|
Hungarian: hu
|
||||||
|
Estonian: et
|
||||||
|
Bulgarian: bg
|
||||||
|
Danish: da
|
||||||
|
Finnish: fi
|
||||||
|
Romanian: ro
|
||||||
|
Swedish: sv
|
||||||
|
Slovenian: sl
|
||||||
|
Persian/Farsi: fa
|
||||||
|
Bosnian: bs
|
||||||
|
Serbian: sr
|
||||||
|
Croatian: hr
|
||||||
|
Slovak: sk
|
||||||
|
Albanian: sq
|
||||||
|
Lithuanian: lt
|
||||||
|
Latvian: lv
|
||||||
|
Macedonian: mk
|
||||||
|
Ukrainian: uk
|
||||||
|
Belarusian: be
|
||||||
|
Kazakh: kk
|
||||||
|
Uzbek: uz
|
||||||
|
Armenian: hy
|
||||||
|
Azerbaijani: az
|
||||||
|
Georgian: ka
|
||||||
|
Kyrgyz: ky
|
||||||
|
Tajik: tg
|
||||||
|
Turkmen: tk
|
||||||
|
Nepali: ne
|
||||||
|
Sinhala: si
|
||||||
|
Khmer: km
|
||||||
|
Lao: lo
|
||||||
|
Burmese: my
|
||||||
|
Malayalam: ml
|
||||||
|
Telugu: te
|
||||||
|
Tamil: ta
|
||||||
|
Kannada: kn
|
||||||
|
Marathi: mr
|
||||||
|
Gujarati: gu
|
||||||
|
Punjabi: pa
|
||||||
|
Bengali: bn
|
||||||
|
Odia: or
|
||||||
|
Assamese: as
|
||||||
|
Urdu: ur
|
||||||
|
Amharic: am
|
||||||
|
Tigrinya: ti
|
||||||
|
Oromo: om
|
||||||
|
Somali: so
|
||||||
|
Swahili: sw
|
||||||
|
Kinyarwanda: rw
|
||||||
|
Yoruba: yo
|
||||||
|
Zulu: zu
|
||||||
|
Xhosa: xh
|
||||||
|
Afrikaans: af
|
||||||
|
Sesotho: st
|
||||||
|
Chichewa: ny
|
||||||
|
Malagasy: mg
|
||||||
|
Esperanto: eo
|
||||||
|
Hawaiian: haw
|
||||||
|
Samoan: sm
|
||||||
|
Shona: sn
|
||||||
|
Sindhi: sd
|
||||||
|
Pashto: ps
|
||||||
|
Kurdish: ku
|
||||||
|
Hausa: ha
|
||||||
|
Igbo: ig
|
||||||
|
Maltese: mt
|
||||||
|
Welsh: cy
|
||||||
|
Luxembourgish: lb
|
||||||
|
Icelandic: is
|
||||||
|
Irish: ga
|
||||||
|
Scottish Gaelic: gd
|
||||||
|
Basque: eu
|
||||||
|
Galician: gl
|
||||||
|
Catalan: ca
|
||||||
|
Corsican: co
|
||||||
|
Latin: la
|
||||||
|
Maori: mi
|
||||||
|
Hmong: hmn
|
||||||
|
Cebuano: ceb
|
||||||
|
Filipino: tl
|
||||||
|
Javanese: jw
|
||||||
|
Sundanese: su
|
||||||
|
Yiddish: yi
|
||||||
|
Frisian: fy
|
||||||
|
target: *google_langs
|
||||||
|
|
||||||
|
Bing:
|
||||||
|
source: &bing_langs
|
||||||
|
Japanese: ja
|
||||||
|
English: en
|
||||||
|
Chinese Simplified: zh
|
||||||
|
Chinese Traditional: zh-Hant
|
||||||
|
Arabic: ar
|
||||||
|
Russian: ru
|
||||||
|
French: fr
|
||||||
|
German: de
|
||||||
|
Spanish: es
|
||||||
|
Portuguese: pt
|
||||||
|
Italian: it
|
||||||
|
Korean: ko
|
||||||
|
Greek: el
|
||||||
|
Dutch: nl
|
||||||
|
Hindi: hi
|
||||||
|
Turkish: tr
|
||||||
|
Malay: ms
|
||||||
|
Thai: th
|
||||||
|
Vietnamese: vi
|
||||||
|
Indonesian: id
|
||||||
|
Hebrew: he
|
||||||
|
Polish: pl
|
||||||
|
Czech: cs
|
||||||
|
Hungarian: hu
|
||||||
|
Estonian: et
|
||||||
|
Bulgarian: bg
|
||||||
|
Danish: da
|
||||||
|
Finnish: fi
|
||||||
|
Romanian: ro
|
||||||
|
Swedish: sv
|
||||||
|
Slovenian: sl
|
||||||
|
Persian/Farsi: fa
|
||||||
|
Bosnian: bs
|
||||||
|
Serbian: sr
|
||||||
|
Croatian: hr
|
||||||
|
Albanian: sq
|
||||||
|
Lithuanian: lt
|
||||||
|
Latvian: lv
|
||||||
|
Ukrainian: uk
|
||||||
|
Welsh: cy
|
||||||
|
Belarusian: be
|
||||||
|
Icelandic: is
|
||||||
|
Irish: ga
|
||||||
|
Maltese: mt
|
||||||
|
Yiddish: yi
|
||||||
|
Afrikaans: af
|
||||||
|
Norwegian: 'no'
|
||||||
|
Bengali: bn
|
||||||
|
Malagasy: mg
|
||||||
|
Samoan: sm
|
||||||
|
Slovak: sk
|
||||||
|
Swahili: sw
|
||||||
|
Filipino: tl
|
||||||
|
Urdu: ur
|
||||||
|
Haitian Creole: ht
|
||||||
|
Catalan: ca
|
||||||
|
Fijian: fj
|
||||||
|
Kiswahili: sw
|
||||||
|
Tahitian: ty
|
||||||
|
Tongan: to
|
||||||
|
Klingon: tlh
|
||||||
|
Queretaro Otomi: otl
|
||||||
|
Gujarati: gu
|
||||||
|
Tamil: ta
|
||||||
|
Telugu: te
|
||||||
|
Punjabi: pa
|
||||||
|
target: *bing_langs
|
||||||
|
|
||||||
|
Papago:
|
||||||
|
source: &papago_langs
|
||||||
|
German: de
|
||||||
|
English: en
|
||||||
|
Spanish: es
|
||||||
|
French: fr
|
||||||
|
Hindi: hi
|
||||||
|
Indonesian: id
|
||||||
|
Italian: it
|
||||||
|
Japanese: ja
|
||||||
|
Korean: ko
|
||||||
|
Portuguese: pt
|
||||||
|
Russian: ru
|
||||||
|
Thai: th
|
||||||
|
Vietnamese: vi
|
||||||
|
Chinese Simplified: zh-CN
|
||||||
|
Chinese Traditional: zh-TW
|
||||||
|
target: *papago_langs
|
||||||
|
|
||||||
|
CTranslate2:
|
||||||
|
m2m100_418M-ct2-int8:
|
||||||
|
source: &m2m100_langs
|
||||||
|
English: en
|
||||||
|
Chinese Simplified: zh
|
||||||
|
Chinese Traditional: zh
|
||||||
|
German: de
|
||||||
|
Spanish: es
|
||||||
|
Russian: ru
|
||||||
|
Korean: ko
|
||||||
|
French: fr
|
||||||
|
Japanese: ja
|
||||||
|
Portuguese: pt
|
||||||
|
Turkish: tr
|
||||||
|
Polish: pl
|
||||||
|
Catalan: ca
|
||||||
|
Dutch: nl
|
||||||
|
Arabic: ar
|
||||||
|
Swedish: sv
|
||||||
|
Italian: it
|
||||||
|
Indonesian: id
|
||||||
|
Hindi: hi
|
||||||
|
Finnish: fi
|
||||||
|
Vietnamese: vi
|
||||||
|
Hebrew: he
|
||||||
|
Ukrainian: uk
|
||||||
|
Greek: el
|
||||||
|
Malay: ms
|
||||||
|
Czech: cs
|
||||||
|
Romanian: ro
|
||||||
|
Danish: da
|
||||||
|
Hungarian: hu
|
||||||
|
Tamil: ta
|
||||||
|
Norwegian: 'no'
|
||||||
|
Thai: th
|
||||||
|
Urdu: ur
|
||||||
|
Croatian: hr
|
||||||
|
Bulgarian: bg
|
||||||
|
Lithuanian: lt
|
||||||
|
Latin: la
|
||||||
|
Maori: mi
|
||||||
|
Malayalam: ml
|
||||||
|
Welsh: cy
|
||||||
|
Slovak: sk
|
||||||
|
Telugu: te
|
||||||
|
Persian: fa
|
||||||
|
Latvian: lv
|
||||||
|
Bengali: bn
|
||||||
|
Serbian: sr
|
||||||
|
Azerbaijani: az
|
||||||
|
Slovenian: sl
|
||||||
|
Kannada: kn
|
||||||
|
Estonian: et
|
||||||
|
Macedonian: mk
|
||||||
|
Breton: br
|
||||||
|
Basque: eu
|
||||||
|
Icelandic: is
|
||||||
|
Armenian: hy
|
||||||
|
Nepali: ne
|
||||||
|
Mongolian: mn
|
||||||
|
Bosnian: bs
|
||||||
|
Kazakh: kk
|
||||||
|
Albanian: sq
|
||||||
|
Swahili: sw
|
||||||
|
Galician: gl
|
||||||
|
Marathi: mr
|
||||||
|
Punjabi: pa
|
||||||
|
Sinhala: si
|
||||||
|
Khmer: km
|
||||||
|
Shona: sn
|
||||||
|
Yoruba: yo
|
||||||
|
Somali: so
|
||||||
|
Afrikaans: af
|
||||||
|
Occitan: oc
|
||||||
|
Georgian: ka
|
||||||
|
Belarusian: be
|
||||||
|
Tajik: tg
|
||||||
|
Sindhi: sd
|
||||||
|
Gujarati: gu
|
||||||
|
Amharic: am
|
||||||
|
Yiddish: yi
|
||||||
|
Lao: lo
|
||||||
|
Uzbek: uz
|
||||||
|
Faroese: fo
|
||||||
|
Haitian creole: ht
|
||||||
|
Pashto: ps
|
||||||
|
Turkmen: tk
|
||||||
|
Nynorsk: nn
|
||||||
|
Maltese: mt
|
||||||
|
Sanskrit: sa
|
||||||
|
Luxembourgish: lb
|
||||||
|
Myanmar: my
|
||||||
|
Tibetan: bo
|
||||||
|
Filipino: tl
|
||||||
|
Malagasy: mg
|
||||||
|
Assamese: as
|
||||||
|
Tatar: tt
|
||||||
|
Hawaiian: haw
|
||||||
|
Lingala: ln
|
||||||
|
Hausa: ha
|
||||||
|
Bashkir: ba
|
||||||
|
Javanese: jw
|
||||||
|
Sundanese: su
|
||||||
|
target: *m2m100_langs
|
||||||
|
m2m100_1.2B-ct2-int8:
|
||||||
|
source: *m2m100_langs
|
||||||
|
target: *m2m100_langs
|
||||||
|
nllb-200-distilled-1.3B-ct2-int8:
|
||||||
|
source: &nllb_langs
|
||||||
|
Acehnese (Arabic script): ace_Arab
|
||||||
|
Acehnese (Latin script): ace_Latn
|
||||||
|
Mesopotamian Arabic: acm_Arab
|
||||||
|
Ta'izzi-Adeni Arabic: acq_Arab
|
||||||
|
Tunisian Arabic: aeb_Arab
|
||||||
|
Afrikaans: afr_Latn
|
||||||
|
South Levantine Arabic: ajp_Arab
|
||||||
|
Akan: aka_Latn
|
||||||
|
Amharic: amh_Ethi
|
||||||
|
North Levantine Arabic: apc_Arab
|
||||||
|
Standard Arabic: arb_Arab
|
||||||
|
Modern Standard Arabic (Romanized): arb_Latn
|
||||||
|
Najdi Arabic: ars_Arab
|
||||||
|
Moroccan Arabic: ary_Arab
|
||||||
|
Egyptian Arabic: arz_Arab
|
||||||
|
Assamese: asm_Beng
|
||||||
|
Asturian: ast_Latn
|
||||||
|
Awadhi: awa_Deva
|
||||||
|
Central Aymara: ayr_Latn
|
||||||
|
South Azerbaijani: azb_Arab
|
||||||
|
North Azerbaijani: azj_Latn
|
||||||
|
Bashkir: bak_Cyrl
|
||||||
|
Bambara: bam_Latn
|
||||||
|
Balinese: ban_Latn
|
||||||
|
Belarusian: bel_Cyrl
|
||||||
|
Bemba: bem_Latn
|
||||||
|
Bengali: ben_Beng
|
||||||
|
Bhojpuri: bho_Deva
|
||||||
|
Banjar (Arabic script): bjn_Arab
|
||||||
|
Banjar (Latin script): bjn_Latn
|
||||||
|
Standard Tibetan: bod_Tibt
|
||||||
|
Bosnian: bos_Latn
|
||||||
|
Buginese: bug_Latn
|
||||||
|
Bulgarian: bul_Cyrl
|
||||||
|
Catalan: cat_Latn
|
||||||
|
Cebuano: ceb_Latn
|
||||||
|
Czech: ces_Latn
|
||||||
|
Chokwe: cjk_Latn
|
||||||
|
Central Kurdish: ckb_Arab
|
||||||
|
Crimean Tatar: crh_Latn
|
||||||
|
Welsh: cym_Latn
|
||||||
|
Danish: dan_Latn
|
||||||
|
German: deu_Latn
|
||||||
|
Southwestern Dinka: dik_Latn
|
||||||
|
Dyula: dyu_Latn
|
||||||
|
Dzongkha: dzo_Tibt
|
||||||
|
Greek: ell_Grek
|
||||||
|
English: eng_Latn
|
||||||
|
Esperanto: epo_Latn
|
||||||
|
Estonian: est_Latn
|
||||||
|
Basque: eus_Latn
|
||||||
|
Ewe: ewe_Latn
|
||||||
|
Faroese: fao_Latn
|
||||||
|
Fijian: fij_Latn
|
||||||
|
Finnish: fin_Latn
|
||||||
|
Fon: fon_Latn
|
||||||
|
French: fra_Latn
|
||||||
|
Friulian: fur_Latn
|
||||||
|
Nigerian Fulfulde: fuv_Latn
|
||||||
|
Scottish Gaelic: gla_Latn
|
||||||
|
Irish: gle_Latn
|
||||||
|
Galician: glg_Latn
|
||||||
|
Guarani: grn_Latn
|
||||||
|
Gujarati: guj_Gujr
|
||||||
|
Haitian Creole: hat_Latn
|
||||||
|
Hausa: hau_Latn
|
||||||
|
Hebrew: heb_Hebr
|
||||||
|
Hindi: hin_Deva
|
||||||
|
Chhattisgarhi: hne_Deva
|
||||||
|
Croatian: hrv_Latn
|
||||||
|
Hungarian: hun_Latn
|
||||||
|
Armenian: hye_Armn
|
||||||
|
Igbo: ibo_Latn
|
||||||
|
Ilocano: ilo_Latn
|
||||||
|
Indonesian: ind_Latn
|
||||||
|
Icelandic: isl_Latn
|
||||||
|
Italian: ita_Latn
|
||||||
|
Javanese: jav_Latn
|
||||||
|
Japanese: jpn_Jpan
|
||||||
|
Kabyle: kab_Latn
|
||||||
|
Jingpho: kac_Latn
|
||||||
|
Kamba: kam_Latn
|
||||||
|
Kannada: kan_Knda
|
||||||
|
Kashmiri (Arabic script): kas_Arab
|
||||||
|
Kashmiri (Devanagari script): kas_Deva
|
||||||
|
Georgian: kat_Geor
|
||||||
|
Central Kanuri (Arabic script): knc_Arab
|
||||||
|
Central Kanuri (Latin script): knc_Latn
|
||||||
|
Kazakh: kaz_Cyrl
|
||||||
|
Kabiyè: kbp_Latn
|
||||||
|
Kabuverdianu: kea_Latn
|
||||||
|
Khmer: khm_Khmr
|
||||||
|
Kikuyu: kik_Latn
|
||||||
|
Kinyarwanda: kin_Latn
|
||||||
|
Kyrgyz: kir_Cyrl
|
||||||
|
Kimbundu: kmb_Latn
|
||||||
|
Northern Kurdish: kmr_Latn
|
||||||
|
Kikongo: kon_Latn
|
||||||
|
Korean: kor_Hang
|
||||||
|
Lao: lao_Laoo
|
||||||
|
Ligurian: lij_Latn
|
||||||
|
Limburgish: lim_Latn
|
||||||
|
Lingala: lin_Latn
|
||||||
|
Lithuanian: lit_Latn
|
||||||
|
Lombard: lmo_Latn
|
||||||
|
Latgalian: ltg_Latn
|
||||||
|
Luxembourgish: ltz_Latn
|
||||||
|
Luba-Kasai: lua_Latn
|
||||||
|
Ganda: lug_Latn
|
||||||
|
Luo: luo_Latn
|
||||||
|
Mizo: lus_Latn
|
||||||
|
Standard Latvian: lvs_Latn
|
||||||
|
Magahi: mag_Deva
|
||||||
|
Maithili: mai_Deva
|
||||||
|
Malayalam: mal_Mlym
|
||||||
|
Marathi: mar_Deva
|
||||||
|
Minangkabau (Arabic script): min_Arab
|
||||||
|
Minangkabau (Latin script): min_Latn
|
||||||
|
Macedonian: mkd_Cyrl
|
||||||
|
Plateau Malagasy: plt_Latn
|
||||||
|
Maltese: mlt_Latn
|
||||||
|
Meitei (Bengali script): mni_Beng
|
||||||
|
Halh Mongolian: khk_Cyrl
|
||||||
|
Mossi: mos_Latn
|
||||||
|
Maori: mri_Latn
|
||||||
|
Burmese: mya_Mymr
|
||||||
|
Dutch: nld_Latn
|
||||||
|
Norwegian Nynorsk: nno_Latn
|
||||||
|
Norwegian Bokmål: nob_Latn
|
||||||
|
Nepali: npi_Deva
|
||||||
|
Northern Sotho: nso_Latn
|
||||||
|
Nuer: nus_Latn
|
||||||
|
Nyanja: nya_Latn
|
||||||
|
Occitan: oci_Latn
|
||||||
|
West Central Oromo: gaz_Latn
|
||||||
|
Odia: ory_Orya
|
||||||
|
Pangasinan: pag_Latn
|
||||||
|
Eastern Panjabi: pan_Guru
|
||||||
|
Papiamento: pap_Latn
|
||||||
|
Western Persian: pes_Arab
|
||||||
|
Polish: pol_Latn
|
||||||
|
Portuguese: por_Latn
|
||||||
|
Dari: prs_Arab
|
||||||
|
Southern Pashto: pbt_Arab
|
||||||
|
Ayacucho Quechua: quy_Latn
|
||||||
|
Romanian: ron_Latn
|
||||||
|
Rundi: run_Latn
|
||||||
|
Russian: rus_Cyrl
|
||||||
|
Sango: sag_Latn
|
||||||
|
Sanskrit: san_Deva
|
||||||
|
Santali: sat_Olck
|
||||||
|
Sicilian: scn_Latn
|
||||||
|
Shan: shn_Mymr
|
||||||
|
Sinhala: sin_Sinh
|
||||||
|
Slovak: slk_Latn
|
||||||
|
Slovenian: slv_Latn
|
||||||
|
Samoan: smo_Latn
|
||||||
|
Shona: sna_Latn
|
||||||
|
Sindhi: snd_Arab
|
||||||
|
Somali: som_Latn
|
||||||
|
Southern Sotho: sot_Latn
|
||||||
|
Spanish: spa_Latn
|
||||||
|
Tosk Albanian: als_Latn
|
||||||
|
Sardinian: srd_Latn
|
||||||
|
Serbian: srp_Cyrl
|
||||||
|
Swati: ssw_Latn
|
||||||
|
Sundanese: sun_Latn
|
||||||
|
Swedish: swe_Latn
|
||||||
|
Swahili: swh_Latn
|
||||||
|
Silesian: szl_Latn
|
||||||
|
Tamil: tam_Taml
|
||||||
|
Tatar: tat_Cyrl
|
||||||
|
Telugu: tel_Telu
|
||||||
|
Tajik: tgk_Cyrl
|
||||||
|
Tagalog: tgl_Latn
|
||||||
|
Thai: tha_Thai
|
||||||
|
Tigrinya: tir_Ethi
|
||||||
|
Tamasheq (Latin script): taq_Latn
|
||||||
|
Tamasheq (Tifinagh script): taq_Tfng
|
||||||
|
Tok Pisin: tpi_Latn
|
||||||
|
Tswana: tsn_Latn
|
||||||
|
Tsonga: tso_Latn
|
||||||
|
Turkmen: tuk_Latn
|
||||||
|
Tumbuka: tum_Latn
|
||||||
|
Turkish: tur_Latn
|
||||||
|
Twi: twi_Latn
|
||||||
|
Central Atlas Tamazight: tzm_Tfng
|
||||||
|
Uyghur: uig_Arab
|
||||||
|
Ukrainian: ukr_Cyrl
|
||||||
|
Umbundu: umb_Latn
|
||||||
|
Urdu: urd_Arab
|
||||||
|
Northern Uzbek: uzn_Latn
|
||||||
|
Venetian: vec_Latn
|
||||||
|
Vietnamese: vie_Latn
|
||||||
|
Waray: war_Latn
|
||||||
|
Wolof: wol_Latn
|
||||||
|
Xhosa: xho_Latn
|
||||||
|
Eastern Yiddish: ydd_Hebr
|
||||||
|
Yoruba: yor_Latn
|
||||||
|
Yue Chinese: yue_Hant
|
||||||
|
Chinese Simplified: zho_Hans
|
||||||
|
Chinese Traditional: zho_Hant
|
||||||
|
Standard Malay: zsm_Latn
|
||||||
|
Zulu: zul_Latn
|
||||||
|
target: *nllb_langs
|
||||||
|
nllb-200-3.3B-ct2-int8:
|
||||||
|
source: *nllb_langs
|
||||||
|
target: *nllb_langs
|
||||||
|
|
||||||
|
Plamo_API:
|
||||||
|
source: &plamo_langs
|
||||||
|
English: English
|
||||||
|
Japanese: Japanese
|
||||||
|
Korean: Korean
|
||||||
|
French: French
|
||||||
|
German: German
|
||||||
|
Spanish: Spanish
|
||||||
|
Portuguese: Portuguese
|
||||||
|
Russian: Russian
|
||||||
|
Italian: Italian
|
||||||
|
Dutch: Dutch
|
||||||
|
Polish: Polish
|
||||||
|
Turkish: Turkish
|
||||||
|
Arabic: Arabic
|
||||||
|
Hindi: Hindi
|
||||||
|
Thai: Thai
|
||||||
|
Vietnamese: Vietnamese
|
||||||
|
Indonesian: Indonesian
|
||||||
|
Malay: Malay
|
||||||
|
Filipino: Filipino
|
||||||
|
Swedish: Swedish
|
||||||
|
Finnish: Finnish
|
||||||
|
Danish: Danish
|
||||||
|
Norwegian: Norwegian
|
||||||
|
Romanian: Romanian
|
||||||
|
Czech: Czech
|
||||||
|
Hungarian: Hungarian
|
||||||
|
Greek: Greek
|
||||||
|
Hebrew: Hebrew
|
||||||
|
Chinese Simplified: Simplified Chinese
|
||||||
|
Chinese Traditional: Traditional Chinese
|
||||||
|
target: *plamo_langs
|
||||||
|
|
||||||
|
Gemini_API:
|
||||||
|
source: &gemini_langs
|
||||||
|
Arabic: Arabic
|
||||||
|
Bengali: Bengali
|
||||||
|
Bulgarian: Bulgarian
|
||||||
|
Chinese Simplified: Simplified Chinese
|
||||||
|
Chinese Traditional: Traditional Chinese
|
||||||
|
Croatian: Croatian
|
||||||
|
Czech: Czech
|
||||||
|
Danish: Danish
|
||||||
|
Dutch: Dutch
|
||||||
|
English: English
|
||||||
|
Estonian: Estonian
|
||||||
|
Finnish: Finnish
|
||||||
|
French: French
|
||||||
|
German: German
|
||||||
|
Greek: Greek
|
||||||
|
Hebrew: Hebrew
|
||||||
|
Hindi: Hindi
|
||||||
|
Hungarian: Hungarian
|
||||||
|
Indonesian: Indonesian
|
||||||
|
Italian: Italian
|
||||||
|
Japanese: Japanese
|
||||||
|
Korean: Korean
|
||||||
|
Latvian: Latvian
|
||||||
|
Lithuanian: Lithuanian
|
||||||
|
Norwegian: Norwegian
|
||||||
|
Polish: Polish
|
||||||
|
Portuguese: Portuguese
|
||||||
|
Romanian: Romanian
|
||||||
|
Russian: Russian
|
||||||
|
Serbian: Serbian
|
||||||
|
Slovak: Slovak
|
||||||
|
Slovenian: Slovenian
|
||||||
|
Spanish: Spanish
|
||||||
|
Swedish: Swedish
|
||||||
|
Thai: Thai
|
||||||
|
Turkish: Turkish
|
||||||
|
Ukrainian: Ukrainian
|
||||||
|
Vietnamese: Vietnamese
|
||||||
|
target: *gemini_langs
|
||||||
|
|
||||||
|
OpenAI_API:
|
||||||
|
source: &openai_langs
|
||||||
|
Afrikaans: Afrikaans
|
||||||
|
Arabic: Arabic
|
||||||
|
Armenian: Armenian
|
||||||
|
Azerbaijani: Azerbaijani
|
||||||
|
Belarusian: Belarusian
|
||||||
|
Bosnian: Bosnian
|
||||||
|
Bulgarian: Bulgarian
|
||||||
|
Catalan: Catalan
|
||||||
|
Chinese: Chinese
|
||||||
|
Croatian: Croatian
|
||||||
|
Czech: Czech
|
||||||
|
Danish: Danish
|
||||||
|
Dutch: Dutch
|
||||||
|
English: English
|
||||||
|
Estonian: Estonian
|
||||||
|
Finnish: Finnish
|
||||||
|
French: French
|
||||||
|
Galician: Galician
|
||||||
|
German: German
|
||||||
|
Greek: Greek
|
||||||
|
Hebrew: Hebrew
|
||||||
|
Hindi: Hindi
|
||||||
|
Hungarian: Hungarian
|
||||||
|
Icelandic: Icelandic
|
||||||
|
Indonesian: Indonesian
|
||||||
|
Italian: Italian
|
||||||
|
Japanese: Japanese
|
||||||
|
Kannada: Kannada
|
||||||
|
Kazakh: Kazakh
|
||||||
|
Korean: Korean
|
||||||
|
Latvian: Latvian
|
||||||
|
Lithuanian: Lithuanian
|
||||||
|
Macedonian: Macedonian
|
||||||
|
Malay: Malay
|
||||||
|
Marathi: Marathi
|
||||||
|
Maori: Maori
|
||||||
|
Nepali: Nepali
|
||||||
|
Norwegian: Norwegian
|
||||||
|
Persian: Persian
|
||||||
|
Polish: Polish
|
||||||
|
Portuguese: Portuguese
|
||||||
|
Romanian: Romanian
|
||||||
|
Russian: Russian
|
||||||
|
Serbian: Serbian
|
||||||
|
Slovak: Slovak
|
||||||
|
Slovenian: Slovenian
|
||||||
|
Spanish: Spanish
|
||||||
|
Swahili: Swahili
|
||||||
|
Swedish: Swedish
|
||||||
|
Tagalog: Tagalog
|
||||||
|
Tamil: Tamil
|
||||||
|
Thai: Thai
|
||||||
|
Turkish: Turkish
|
||||||
|
Ukrainian: Ukrainian
|
||||||
|
Urdu: Urdu
|
||||||
|
Vietnamese: Vietnamese
|
||||||
|
Welsh: Welsh
|
||||||
|
target: *openai_langs
|
||||||
|
|
||||||
|
LMStudio:
|
||||||
|
source: *openai_langs
|
||||||
|
target: *openai_langs
|
||||||
|
|
||||||
|
Ollama:
|
||||||
|
source: *openai_langs
|
||||||
|
target: *openai_langs
|
||||||
@@ -1,713 +1,144 @@
|
|||||||
"""Language code mappings for supported translation backends.
|
"""Load translation language code mappings from YAML.
|
||||||
|
|
||||||
Provides `translation_lang` mapping keyed by backend name with `source` and
|
YAML ファイル: languages/languages.yml
|
||||||
`target` maps used by `Translator.getLanguageCode`.
|
構造:
|
||||||
|
<BackendName>:
|
||||||
|
source: { DisplayName: Code, ... }
|
||||||
|
target: { DisplayName: Code, ... }
|
||||||
|
CTranslate2:
|
||||||
|
<ModelName>:
|
||||||
|
source: {...}
|
||||||
|
target: {...}
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from typing import Dict
|
import os
|
||||||
|
import threading
|
||||||
|
from typing import Any, Dict
|
||||||
|
import yaml
|
||||||
|
try:
|
||||||
|
from utils import printLog, errorLogging
|
||||||
|
except ImportError:
|
||||||
|
def printLog(data, *args, **kwargs):
|
||||||
|
print(data, *args, **kwargs)
|
||||||
|
|
||||||
|
def errorLogging():
|
||||||
|
import traceback
|
||||||
|
traceback.print_exc()
|
||||||
|
|
||||||
|
|
||||||
|
# 型: translation_lang[backend][(model)?]['source'|'target'][display_name] = code
|
||||||
translation_lang: Dict[str, Dict[str, Dict[str, str]]] = {}
|
translation_lang: Dict[str, Dict[str, Dict[str, str]]] = {}
|
||||||
|
_loaded = False
|
||||||
|
_lock = threading.Lock()
|
||||||
|
|
||||||
dict_deepl_languages = {
|
|
||||||
"Arabic":"ar",
|
|
||||||
"Bulgarian":"bg",
|
|
||||||
"Czech":"cs",
|
|
||||||
"Danish":"da",
|
|
||||||
"German":"de",
|
|
||||||
"Greek":"el",
|
|
||||||
"English":"en",
|
|
||||||
"Spanish":"es",
|
|
||||||
"Estonian":"et",
|
|
||||||
"Finnish":"fi",
|
|
||||||
"French":"fr",
|
|
||||||
"Irish":"ga",
|
|
||||||
"Croatian":"hr",
|
|
||||||
"Hungarian":"hu",
|
|
||||||
"Indonesian":"id",
|
|
||||||
"Icelandic":"is",
|
|
||||||
"Italian":"it",
|
|
||||||
"Japanese":"ja",
|
|
||||||
"Korean":"ko",
|
|
||||||
"Lithuanian":"lt",
|
|
||||||
"Latvian":"lv",
|
|
||||||
"Maltese":"mt",
|
|
||||||
"Bokmal":"nb",
|
|
||||||
"Dutch":"nl",
|
|
||||||
"Norwegian":"no",
|
|
||||||
"Polish":"pl",
|
|
||||||
"Portuguese":"pt",
|
|
||||||
"Romanian":"ro",
|
|
||||||
"Russian":"ru",
|
|
||||||
"Slovak":"sk",
|
|
||||||
"Slovenian":"sl",
|
|
||||||
"Swedish":"sv",
|
|
||||||
"Turkish":"tr",
|
|
||||||
"Ukrainian":"uk",
|
|
||||||
"Chinese Simplified":"zh",
|
|
||||||
"Chinese Traditional":"zh"
|
|
||||||
}
|
|
||||||
translation_lang["DeepL"] = {"source": dict_deepl_languages, "target": dict_deepl_languages}
|
|
||||||
|
|
||||||
dict_deepl_api_source_languages = {
|
def _load_languages(path: str, filename: str) -> str:
|
||||||
"Japanese":"ja",
|
"""Get absolute path to resource file relative to this module.
|
||||||
"English":"en",
|
|
||||||
"Bulgarian":"bg",
|
|
||||||
"Czech":"cs",
|
|
||||||
"Danish":"da",
|
|
||||||
"German":"de",
|
|
||||||
"Greek":"el",
|
|
||||||
"Spanish":"es",
|
|
||||||
"Estonian":"et",
|
|
||||||
"Finnish":"fi",
|
|
||||||
"French":"fr",
|
|
||||||
"Hungarian":"hu",
|
|
||||||
"Indonesian":"id",
|
|
||||||
"Italian":"it",
|
|
||||||
"Korean":"ko",
|
|
||||||
"Lithuanian":"lt",
|
|
||||||
"Latvian":"lv",
|
|
||||||
"Norwegian":"nb",
|
|
||||||
"Dutch":"nl",
|
|
||||||
"Polish":"pl",
|
|
||||||
"Portuguese":"pt",
|
|
||||||
"Romanian":"ro",
|
|
||||||
"Russian":"ru",
|
|
||||||
"Slovak":"sk",
|
|
||||||
"Slovenian":"sl",
|
|
||||||
"Swedish":"sv",
|
|
||||||
"Turkish":"tr",
|
|
||||||
"Ukrainian":"uk",
|
|
||||||
"Chinese Simplified":"zh",
|
|
||||||
"Chinese Traditional":"zh"
|
|
||||||
}
|
|
||||||
dict_deepl_api_target_languages = {
|
|
||||||
"Japanese":"ja",
|
|
||||||
"English American":"en-US",
|
|
||||||
"English British":"en-GB",
|
|
||||||
"Bulgarian":"bg",
|
|
||||||
"Czech":"cs",
|
|
||||||
"Danish":"da",
|
|
||||||
"German":"de",
|
|
||||||
"Greek":"el",
|
|
||||||
"English":"en",
|
|
||||||
"Spanish":"es",
|
|
||||||
"Estonian":"et",
|
|
||||||
"Finnish":"fi",
|
|
||||||
"French":"fr",
|
|
||||||
"Hungarian":"hu",
|
|
||||||
"Indonesian":"id",
|
|
||||||
"Italian":"it",
|
|
||||||
"Korean":"ko",
|
|
||||||
"Lithuanian":"lt",
|
|
||||||
"Latvian":"lv",
|
|
||||||
"Norwegian":"nb",
|
|
||||||
"Dutch":"nl",
|
|
||||||
"Polish":"pl",
|
|
||||||
"Portuguese Brazilian":"pt-BR",
|
|
||||||
"Portuguese European":"pt-PT",
|
|
||||||
"Romanian":"ro",
|
|
||||||
"Russian":"ru",
|
|
||||||
"Slovak":"sk",
|
|
||||||
"Slovenian":"sl",
|
|
||||||
"Swedish":"sv",
|
|
||||||
"Turkish":"tr",
|
|
||||||
"Ukrainian":"uk",
|
|
||||||
"Chinese Simplified":"zh",
|
|
||||||
"Chinese Traditional":"zh"
|
|
||||||
}
|
|
||||||
translation_lang["DeepL_API"] = {"source": dict_deepl_api_source_languages, "target": dict_deepl_api_target_languages}
|
|
||||||
|
|
||||||
dict_google_languages = {
|
Args:
|
||||||
"Japanese":"ja",
|
filename: relative filename from this module's directory
|
||||||
"English":"en",
|
|
||||||
"Chinese Simplified":"zh",
|
|
||||||
"Chinese Traditional":"zh-TW",
|
|
||||||
"Arabic":"ar",
|
|
||||||
"Russian":"ru",
|
|
||||||
"French":"fr",
|
|
||||||
"German":"de",
|
|
||||||
"Spanish":"es",
|
|
||||||
"Portuguese":"pt",
|
|
||||||
"Italian":"it",
|
|
||||||
"Korean":"ko",
|
|
||||||
"Greek":"el",
|
|
||||||
"Dutch":"nl",
|
|
||||||
"Hindi":"hi",
|
|
||||||
"Turkish":"tr",
|
|
||||||
"Malay":"ms",
|
|
||||||
"Thai":"th",
|
|
||||||
"Vietnamese":"vi",
|
|
||||||
"Indonesian":"id",
|
|
||||||
"Hebrew":"he",
|
|
||||||
"Polish":"pl",
|
|
||||||
"Mongolian":"mn",
|
|
||||||
"Czech":"cs",
|
|
||||||
"Hungarian":"hu",
|
|
||||||
"Estonian":"et",
|
|
||||||
"Bulgarian":"bg",
|
|
||||||
"Danish":"da",
|
|
||||||
"Finnish":"fi",
|
|
||||||
"Romanian":"ro",
|
|
||||||
"Swedish":"sv",
|
|
||||||
"Slovenian":"sl",
|
|
||||||
"Persian/Farsi":"fa",
|
|
||||||
"Bosnian":"bs",
|
|
||||||
"Serbian":"sr",
|
|
||||||
"Filipino":"tl",
|
|
||||||
"Haitiancreole":"ht",
|
|
||||||
"Catalan":"ca",
|
|
||||||
"Croatian":"hr",
|
|
||||||
"Latvian":"lv",
|
|
||||||
"Lithuanian":"lt",
|
|
||||||
"Urdu":"ur",
|
|
||||||
"Ukrainian":"uk",
|
|
||||||
"Welsh":"cy",
|
|
||||||
"Swahili":"sw",
|
|
||||||
"Samoan":"sm",
|
|
||||||
"Slovak":"sk",
|
|
||||||
"Afrikaans":"af",
|
|
||||||
"Norwegian":"no",
|
|
||||||
"Bengali":"bn",
|
|
||||||
"Malagasy":"mg",
|
|
||||||
"Maltese":"mt",
|
|
||||||
"Gujarati":"gu",
|
|
||||||
"Tamil":"ta",
|
|
||||||
"Telugu":"te",
|
|
||||||
"Punjabi":"pa",
|
|
||||||
"Amharic":"am",
|
|
||||||
"Azerbaijani":"az",
|
|
||||||
"Belarusian":"be",
|
|
||||||
"Cebuano":"ceb",
|
|
||||||
"Esperanto":"eo",
|
|
||||||
# "Basque":"eu",
|
|
||||||
"Irish":"ga"
|
|
||||||
}
|
|
||||||
translation_lang["Google"] = {"source": dict_google_languages, "target": dict_google_languages}
|
|
||||||
|
|
||||||
dict_bing_languages = {
|
Returns:
|
||||||
"Japanese":"ja",
|
Absolute path to the resource file
|
||||||
"English":"en",
|
"""
|
||||||
"Chinese Simplified":"zh",
|
if os.path.exists(os.path.join(path, "_internal", "languages", "languages.yml")):
|
||||||
"Chinese Traditional":"zh-Hant",
|
languages_path = os.path.join(path, "_internal", "languages", "languages.yml")
|
||||||
"Arabic":"ar",
|
elif os.path.exists(os.path.join(os.path.dirname(os.path.abspath(__file__)), "models", "translation", "languages", "languages.yml")):
|
||||||
"Russian":"ru",
|
languages_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "models", "translation", "languages", "languages.yml")
|
||||||
"French":"fr",
|
elif os.path.exists(os.path.join(os.path.dirname(os.path.abspath(__file__)), "languages", "languages.yml")):
|
||||||
"German":"de",
|
languages_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "languages", "languages.yml")
|
||||||
"Spanish":"es",
|
else:
|
||||||
"Portuguese":"pt",
|
raise FileNotFoundError(f"Prompt file not found: {filename}")
|
||||||
"Italian":"it",
|
with open(languages_path, "r", encoding="utf-8") as f:
|
||||||
"Korean":"ko",
|
return yaml.safe_load(f)
|
||||||
"Greek":"el",
|
|
||||||
"Dutch":"nl",
|
|
||||||
"Hindi":"hi",
|
|
||||||
"Turkish":"tr",
|
|
||||||
"Malay":"ms",
|
|
||||||
"Thai":"th",
|
|
||||||
"Vietnamese":"vi",
|
|
||||||
"Indonesian":"id",
|
|
||||||
"Hebrew":"he",
|
|
||||||
"Polish":"pl",
|
|
||||||
"Czech":"cs",
|
|
||||||
"Hungarian":"hu",
|
|
||||||
"Estonian":"et",
|
|
||||||
"Bulgarian":"bg",
|
|
||||||
"Danish":"da",
|
|
||||||
"Finnish":"fi",
|
|
||||||
"Romanian":"ro",
|
|
||||||
"Swedish":"sv",
|
|
||||||
"Slovenian":"sl",
|
|
||||||
"Persian/Farsi":"fa",
|
|
||||||
"Bosnian":"bs",
|
|
||||||
"Serbian":"sr",
|
|
||||||
"Fijian":"fj",
|
|
||||||
"Filipino":"tl",
|
|
||||||
"Haitiancreole":"ht",
|
|
||||||
"Catalan":"ca",
|
|
||||||
"Croatian":"hr",
|
|
||||||
"Latvian":"lv",
|
|
||||||
"Lithuanian":"lt",
|
|
||||||
"Urdu":"ur",
|
|
||||||
"Ukrainian":"uk",
|
|
||||||
"Welsh":"cy",
|
|
||||||
"Tahiti":"ty",
|
|
||||||
"Tongan":"to",
|
|
||||||
"Swahili":"sw",
|
|
||||||
"Samoan":"sm",
|
|
||||||
"Slovak":"sk",
|
|
||||||
"Afrikaans":"af",
|
|
||||||
"Norwegian":"no",
|
|
||||||
"Bengali":"bn",
|
|
||||||
"Malagasy":"mg",
|
|
||||||
"Maltese":"mt",
|
|
||||||
"Queretaro otomi":"otq",
|
|
||||||
"Klingon/tlhingan Hol":"tlh",
|
|
||||||
"Gujarati":"gu",
|
|
||||||
"Tamil":"ta",
|
|
||||||
"Telugu":"te",
|
|
||||||
"Punjabi":"pa",
|
|
||||||
"Irish":"ga"
|
|
||||||
}
|
|
||||||
translation_lang["Bing"] = {"source": dict_bing_languages, "target": dict_bing_languages}
|
|
||||||
|
|
||||||
dict_papago_languages = {
|
def _validate_source_target(backend: str, mapping: Any) -> None:
|
||||||
"German": "de",
|
"""Validate that a backend mapping has proper source/target structure.
|
||||||
"English": "en",
|
|
||||||
"Spanish":"es",
|
|
||||||
"French": "fr",
|
|
||||||
"Hindi": "hi",
|
|
||||||
"Indonesian": "id",
|
|
||||||
"Italian": "it",
|
|
||||||
"Japanese": "ja",
|
|
||||||
"Korean": "ko",
|
|
||||||
"Portuguese": "pt",
|
|
||||||
"Russian": "ru",
|
|
||||||
"Thai": "th",
|
|
||||||
"Vietnamese": "vi",
|
|
||||||
"Chinese Simplified":"zh-CN",
|
|
||||||
"Chinese Traditional":"zh-TW",
|
|
||||||
}
|
|
||||||
|
|
||||||
translation_lang["Papago"] = {"source": dict_papago_languages, "target": dict_papago_languages}
|
Args:
|
||||||
|
backend: backend name for error messages
|
||||||
|
mapping: mapping to validate
|
||||||
|
|
||||||
dict_m2m100_languages = {
|
Raises:
|
||||||
"English": "en",
|
ValueError: If mapping structure is invalid
|
||||||
"Chinese Simplified": "zh",
|
"""
|
||||||
"Chinese Traditional":"zh",
|
if not isinstance(mapping, dict):
|
||||||
"German": "de",
|
raise ValueError(f"{backend}: 値は dict である必要があります。")
|
||||||
"Spanish": "es",
|
if "source" not in mapping or "target" not in mapping:
|
||||||
"Russian": "ru",
|
raise ValueError(f"{backend}: 'source' と 'target' が必要です。")
|
||||||
"Korean": "ko",
|
|
||||||
"French": "fr",
|
|
||||||
"Japanese": "ja",
|
|
||||||
"Portuguese": "pt",
|
|
||||||
"Turkish": "tr",
|
|
||||||
"Polish": "pl",
|
|
||||||
"Catalan": "ca",
|
|
||||||
"Dutch": "nl",
|
|
||||||
"Arabic": "ar",
|
|
||||||
"Swedish": "sv",
|
|
||||||
"Italian": "it",
|
|
||||||
"Indonesian": "id",
|
|
||||||
"Hindi": "hi",
|
|
||||||
"Finnish": "fi",
|
|
||||||
"Vietnamese": "vi",
|
|
||||||
"Hebrew": "he",
|
|
||||||
"Ukrainian": "uk",
|
|
||||||
"Greek": "el",
|
|
||||||
"Malay": "ms",
|
|
||||||
"Czech": "cs",
|
|
||||||
"Romanian": "ro",
|
|
||||||
"Danish": "da",
|
|
||||||
"Hungarian": "hu",
|
|
||||||
"Tamil": "ta",
|
|
||||||
"Norwegian": "no",
|
|
||||||
"Thai": "th",
|
|
||||||
"Urdu": "ur",
|
|
||||||
"Croatian": "hr",
|
|
||||||
"Bulgarian": "bg",
|
|
||||||
"Lithuanian": "lt",
|
|
||||||
"Latin": "la",
|
|
||||||
"Maori": "mi",
|
|
||||||
"Malayalam": "ml",
|
|
||||||
"Welsh": "cy",
|
|
||||||
"Slovak": "sk",
|
|
||||||
# "Telugu": "te",
|
|
||||||
"Persian": "fa",
|
|
||||||
"Latvian": "lv",
|
|
||||||
"Bengali": "bn",
|
|
||||||
"Serbian": "sr",
|
|
||||||
"Azerbaijani": "az",
|
|
||||||
"Slovenian": "sl",
|
|
||||||
"Kannada": "kn",
|
|
||||||
"Estonian": "et",
|
|
||||||
"Macedonian": "mk",
|
|
||||||
"Breton": "br",
|
|
||||||
# "Basque": "eu",
|
|
||||||
"Icelandic": "is",
|
|
||||||
"Armenian": "hy",
|
|
||||||
"Nepali": "ne",
|
|
||||||
"Mongolian": "mn",
|
|
||||||
"Bosnian": "bs",
|
|
||||||
"Kazakh": "kk",
|
|
||||||
"Albanian": "sq",
|
|
||||||
"Swahili": "sw",
|
|
||||||
"Galician": "gl",
|
|
||||||
"Marathi": "mr",
|
|
||||||
"Punjabi": "pa",
|
|
||||||
"Sinhala": "si",
|
|
||||||
"Khmer": "km",
|
|
||||||
"Shona": "sn",
|
|
||||||
"Yoruba": "yo",
|
|
||||||
"Somali": "so",
|
|
||||||
"Afrikaans": "af",
|
|
||||||
"Occitan": "oc",
|
|
||||||
"Georgian": "ka",
|
|
||||||
"Belarusian": "be",
|
|
||||||
"Tajik": "tg",
|
|
||||||
"Sindhi": "sd",
|
|
||||||
"Gujarati": "gu",
|
|
||||||
"Amharic": "am",
|
|
||||||
"Yiddish": "yi",
|
|
||||||
"Lao": "lo",
|
|
||||||
"Uzbek": "uz",
|
|
||||||
"Faroese": "fo",
|
|
||||||
"Haitian creole": "ht",
|
|
||||||
"Pashto": "ps",
|
|
||||||
"Turkmen": "tk",
|
|
||||||
"Nynorsk": "nn",
|
|
||||||
"Maltese": "mt",
|
|
||||||
"Sanskrit": "sa",
|
|
||||||
"Luxembourgish": "lb",
|
|
||||||
"Myanmar": "my",
|
|
||||||
"Tibetan": "bo",
|
|
||||||
"Filipino": "tl",
|
|
||||||
"Malagasy": "mg",
|
|
||||||
"Assamese": "as",
|
|
||||||
"Tatar": "tt",
|
|
||||||
"Hawaiian": "haw",
|
|
||||||
"Lingala": "ln",
|
|
||||||
"Hausa": "ha",
|
|
||||||
"Bashkir": "ba",
|
|
||||||
"Javanese": "jw",
|
|
||||||
"Sundanese": "su"
|
|
||||||
}
|
|
||||||
|
|
||||||
translation_lang["CTranslate2"] = {}
|
for key in ("source", "target"):
|
||||||
translation_lang["CTranslate2"]["m2m100_418M-ct2-int8"] = {"source":dict_m2m100_languages, "target":dict_m2m100_languages}
|
if not isinstance(mapping[key], dict):
|
||||||
translation_lang["CTranslate2"]["m2m100_1.2B-ct2-int8"] = {"source":dict_m2m100_languages, "target":dict_m2m100_languages}
|
raise ValueError(f"{backend}: '{key}' は dict である必要があります。")
|
||||||
|
# value は str を想定
|
||||||
|
for disp, code in mapping[key].items():
|
||||||
|
if not isinstance(disp, str) or not isinstance(code, str):
|
||||||
|
raise ValueError(
|
||||||
|
f"{backend}: '{key}' のエントリは str: str である必要があります。 ({disp} => {code})"
|
||||||
|
)
|
||||||
|
|
||||||
dict_nllb_languages = {
|
def loadTranslationLanguages(path: str, force: bool = False) -> Dict[str, Any]:
|
||||||
"Acehnese (Arabic script)": "ace_Arab",
|
"""Load translation language mappings from YAML file.
|
||||||
"Acehnese (Latin script)": "ace_Latn",
|
|
||||||
"Mesopotamian Arabic": "acm_Arab",
|
|
||||||
"Ta’izzi-Adeni Arabic": "acq_Arab",
|
|
||||||
"Tunisian Arabic": "aeb_Arab",
|
|
||||||
"Afrikaans": "afr_Latn",
|
|
||||||
"South Levantine Arabic": "ajp_Arab",
|
|
||||||
"Akan": "aka_Latn",
|
|
||||||
"Amharic": "amh_Ethi",
|
|
||||||
"North Levantine Arabic": "apc_Arab",
|
|
||||||
"Modern Standard Arabic": "arb_Arab",
|
|
||||||
"Modern Standard Arabic (Romanized)": "arb_Latn",
|
|
||||||
"Najdi Arabic": "ars_Arab",
|
|
||||||
"Moroccan Arabic": "ary_Arab",
|
|
||||||
"Egyptian Arabic": "arz_Arab",
|
|
||||||
"Assamese": "asm_Beng",
|
|
||||||
"Asturian": "ast_Latn",
|
|
||||||
"Awadhi": "awa_Deva",
|
|
||||||
"Central Aymara": "ayr_Latn",
|
|
||||||
"South Azerbaijani": "azb_Arab",
|
|
||||||
"North Azerbaijani": "azj_Latn",
|
|
||||||
"Bashkir": "bak_Cyrl",
|
|
||||||
"Bambara": "bam_Latn",
|
|
||||||
"Balinese": "ban_Latn",
|
|
||||||
"Belarusian": "bel_Cyrl",
|
|
||||||
"Bemba": "bem_Latn",
|
|
||||||
"Bengali": "ben_Beng",
|
|
||||||
"Bhojpuri": "bho_Deva",
|
|
||||||
"Banjar (Arabic script)": "bjn_Arab",
|
|
||||||
"Banjar (Latin script)": "bjn_Latn",
|
|
||||||
"Standard Tibetan": "bod_Tibt",
|
|
||||||
"Bosnian": "bos_Latn",
|
|
||||||
"Buginese": "bug_Latn",
|
|
||||||
"Bulgarian": "bul_Cyrl",
|
|
||||||
"Catalan": "cat_Latn",
|
|
||||||
"Cebuano": "ceb_Latn",
|
|
||||||
"Czech": "ces_Latn",
|
|
||||||
"Chokwe": "cjk_Latn",
|
|
||||||
"Central Kurdish": "ckb_Arab",
|
|
||||||
"Crimean Tatar": "crh_Latn",
|
|
||||||
"Welsh": "cym_Latn",
|
|
||||||
"Danish": "dan_Latn",
|
|
||||||
"German": "deu_Latn",
|
|
||||||
"Southwestern Dinka": "dik_Latn",
|
|
||||||
"Dyula": "dyu_Latn",
|
|
||||||
"Dzongkha": "dzo_Tibt",
|
|
||||||
"Greek": "ell_Grek",
|
|
||||||
"English": "eng_Latn",
|
|
||||||
"Esperanto": "epo_Latn",
|
|
||||||
"Estonian": "est_Latn",
|
|
||||||
"Basque": "eus_Latn",
|
|
||||||
"Ewe": "ewe_Latn",
|
|
||||||
"Faroese": "fao_Latn",
|
|
||||||
"Fijian": "fij_Latn",
|
|
||||||
"Finnish": "fin_Latn",
|
|
||||||
"Fon": "fon_Latn",
|
|
||||||
"French": "fra_Latn",
|
|
||||||
"Friulian": "fur_Latn",
|
|
||||||
"Nigerian Fulfulde": "fuv_Latn",
|
|
||||||
"Scottish Gaelic": "gla_Latn",
|
|
||||||
"Irish": "gle_Latn",
|
|
||||||
"Galician": "glg_Latn",
|
|
||||||
"Guarani": "grn_Latn",
|
|
||||||
"Gujarati": "guj_Gujr",
|
|
||||||
"Haitian Creole": "hat_Latn",
|
|
||||||
"Hausa": "hau_Latn",
|
|
||||||
"Hebrew": "heb_Hebr",
|
|
||||||
"Hindi": "hin_Deva",
|
|
||||||
"Chhattisgarhi": "hne_Deva",
|
|
||||||
"Croatian": "hrv_Latn",
|
|
||||||
"Hungarian": "hun_Latn",
|
|
||||||
"Armenian": "hye_Armn",
|
|
||||||
"Igbo": "ibo_Latn",
|
|
||||||
"Ilocano": "ilo_Latn",
|
|
||||||
"Indonesian": "ind_Latn",
|
|
||||||
"Icelandic": "isl_Latn",
|
|
||||||
"Italian": "ita_Latn",
|
|
||||||
"Javanese": "jav_Latn",
|
|
||||||
"Japanese": "jpn_Jpan",
|
|
||||||
"Kabyle": "kab_Latn",
|
|
||||||
"Jingpho": "kac_Latn",
|
|
||||||
"Kamba": "kam_Latn",
|
|
||||||
"Kannada": "kan_Knda",
|
|
||||||
"Kashmiri (Arabic script)": "kas_Arab",
|
|
||||||
"Kashmiri (Devanagari script)": "kas_Deva",
|
|
||||||
"Georgian": "kat_Geor",
|
|
||||||
"Central Kanuri (Arabic script)": "knc_Arab",
|
|
||||||
"Central Kanuri (Latin script)": "knc_Latn",
|
|
||||||
"Kazakh": "kaz_Cyrl",
|
|
||||||
"Kabiyè": "kbp_Latn",
|
|
||||||
"Kabuverdianu": "kea_Latn",
|
|
||||||
"Khmer": "khm_Khmr",
|
|
||||||
"Kikuyu": "kik_Latn",
|
|
||||||
"Kinyarwanda": "kin_Latn",
|
|
||||||
"Kyrgyz": "kir_Cyrl",
|
|
||||||
"Kimbundu": "kmb_Latn",
|
|
||||||
"Northern Kurdish": "kmr_Latn",
|
|
||||||
"Kikongo": "kon_Latn",
|
|
||||||
"Korean": "kor_Hang",
|
|
||||||
"Lao": "lao_Laoo",
|
|
||||||
"Ligurian": "lij_Latn",
|
|
||||||
"Limburgish": "lim_Latn",
|
|
||||||
"Lingala": "lin_Latn",
|
|
||||||
"Lithuanian": "lit_Latn",
|
|
||||||
"Lombard": "lmo_Latn",
|
|
||||||
"Latgalian": "ltg_Latn",
|
|
||||||
"Luxembourgish": "ltz_Latn",
|
|
||||||
"Luba-Kasai": "lua_Latn",
|
|
||||||
"Ganda": "lug_Latn",
|
|
||||||
"Luo": "luo_Latn",
|
|
||||||
"Mizo": "lus_Latn",
|
|
||||||
"Standard Latvian": "lvs_Latn",
|
|
||||||
"Magahi": "mag_Deva",
|
|
||||||
"Maithili": "mai_Deva",
|
|
||||||
"Malayalam": "mal_Mlym",
|
|
||||||
"Marathi": "mar_Deva",
|
|
||||||
"Minangkabau (Arabic script)": "min_Arab",
|
|
||||||
"Minangkabau (Latin script)": "min_Latn",
|
|
||||||
"Macedonian": "mkd_Cyrl",
|
|
||||||
"Plateau Malagasy": "plt_Latn",
|
|
||||||
"Maltese": "mlt_Latn",
|
|
||||||
"Meitei (Bengali script)": "mni_Beng",
|
|
||||||
"Halh Mongolian": "khk_Cyrl",
|
|
||||||
"Mossi": "mos_Latn",
|
|
||||||
"Maori": "mri_Latn",
|
|
||||||
"Burmese": "mya_Mymr",
|
|
||||||
"Dutch": "nld_Latn",
|
|
||||||
"Norwegian Nynorsk": "nno_Latn",
|
|
||||||
"Norwegian Bokmål": "nob_Latn",
|
|
||||||
"Nepali": "npi_Deva",
|
|
||||||
"Northern Sotho": "nso_Latn",
|
|
||||||
"Nuer": "nus_Latn",
|
|
||||||
"Nyanja": "nya_Latn",
|
|
||||||
"Occitan": "oci_Latn",
|
|
||||||
"West Central Oromo": "gaz_Latn",
|
|
||||||
"Odia": "ory_Orya",
|
|
||||||
"Pangasinan": "pag_Latn",
|
|
||||||
"Eastern Panjabi": "pan_Guru",
|
|
||||||
"Papiamento": "pap_Latn",
|
|
||||||
"Western Persian": "pes_Arab",
|
|
||||||
"Polish": "pol_Latn",
|
|
||||||
"Portuguese": "por_Latn",
|
|
||||||
"Dari": "prs_Arab",
|
|
||||||
"Southern Pashto": "pbt_Arab",
|
|
||||||
"Ayacucho Quechua": "quy_Latn",
|
|
||||||
"Romanian": "ron_Latn",
|
|
||||||
"Rundi": "run_Latn",
|
|
||||||
"Russian": "rus_Cyrl",
|
|
||||||
"Sango": "sag_Latn",
|
|
||||||
"Sanskrit": "san_Deva",
|
|
||||||
"Santali": "sat_Olck",
|
|
||||||
"Sicilian": "scn_Latn",
|
|
||||||
"Shan": "shn_Mymr",
|
|
||||||
"Sinhala": "sin_Sinh",
|
|
||||||
"Slovak": "slk_Latn",
|
|
||||||
"Slovenian": "slv_Latn",
|
|
||||||
"Samoan": "smo_Latn",
|
|
||||||
"Shona": "sna_Latn",
|
|
||||||
"Sindhi": "snd_Arab",
|
|
||||||
"Somali": "som_Latn",
|
|
||||||
"Southern Sotho": "sot_Latn",
|
|
||||||
"Spanish": "spa_Latn",
|
|
||||||
"Tosk Albanian": "als_Latn",
|
|
||||||
"Sardinian": "srd_Latn",
|
|
||||||
"Serbian": "srp_Cyrl",
|
|
||||||
"Swati": "ssw_Latn",
|
|
||||||
"Sundanese": "sun_Latn",
|
|
||||||
"Swedish": "swe_Latn",
|
|
||||||
"Swahili": "swh_Latn",
|
|
||||||
"Silesian": "szl_Latn",
|
|
||||||
"Tamil": "tam_Taml",
|
|
||||||
"Tatar": "tat_Cyrl",
|
|
||||||
"Telugu": "tel_Telu",
|
|
||||||
"Tajik": "tgk_Cyrl",
|
|
||||||
"Tagalog": "tgl_Latn",
|
|
||||||
"Thai": "tha_Thai",
|
|
||||||
"Tigrinya": "tir_Ethi",
|
|
||||||
"Tamasheq (Latin script)": "taq_Latn",
|
|
||||||
"Tamasheq (Tifinagh script)": "taq_Tfng",
|
|
||||||
"Tok Pisin": "tpi_Latn",
|
|
||||||
"Tswana": "tsn_Latn",
|
|
||||||
"Tsonga": "tso_Latn",
|
|
||||||
"Turkmen": "tuk_Latn",
|
|
||||||
"Tumbuka": "tum_Latn",
|
|
||||||
"Turkish": "tur_Latn",
|
|
||||||
"Twi": "twi_Latn",
|
|
||||||
"Central Atlas Tamazight": "tzm_Tfng",
|
|
||||||
"Uyghur": "uig_Arab",
|
|
||||||
"Ukrainian": "ukr_Cyrl",
|
|
||||||
"Umbundu": "umb_Latn",
|
|
||||||
"Urdu": "urd_Arab",
|
|
||||||
"Northern Uzbek": "uzn_Latn",
|
|
||||||
"Venetian": "vec_Latn",
|
|
||||||
"Vietnamese": "vie_Latn",
|
|
||||||
"Waray": "war_Latn",
|
|
||||||
"Wolof": "wol_Latn",
|
|
||||||
"Xhosa": "xho_Latn",
|
|
||||||
"Eastern Yiddish": "ydd_Hebr",
|
|
||||||
"Yoruba": "yor_Latn",
|
|
||||||
"Yue Chinese": "yue_Hant",
|
|
||||||
"Chinese Simplified": "zho_Hans",
|
|
||||||
"Chinese Traditional": "zho_Hant",
|
|
||||||
"Standard Malay": "zsm_Latn",
|
|
||||||
"Zulu": "zul_Latn"
|
|
||||||
}
|
|
||||||
|
|
||||||
translation_lang["CTranslate2"]["nllb-200-distilled-1.3B-ct2-int8"] = {"source":dict_nllb_languages, "target":dict_nllb_languages}
|
Args:
|
||||||
translation_lang["CTranslate2"]["nllb-200-3.3B-ct2-int8"] = {"source":dict_nllb_languages, "target":dict_nllb_languages}
|
path: Path to the YAML file
|
||||||
|
force: If True, reload even if already loaded
|
||||||
|
|
||||||
dict_plamo_languages = {
|
Returns:
|
||||||
"English": "English",
|
Dictionary of translation language mappings
|
||||||
"Japanese": "Japanese",
|
|
||||||
"Korean": "Korean",
|
|
||||||
"French": "French",
|
|
||||||
"German": "German",
|
|
||||||
"Spanish": "Spanish",
|
|
||||||
"Portuguese": "Portuguese",
|
|
||||||
"Russian": "Russian",
|
|
||||||
"Italian": "Italian",
|
|
||||||
"Dutch": "Dutch",
|
|
||||||
"Polish": "Polish",
|
|
||||||
"Turkish": "Turkish",
|
|
||||||
"Arabic": "Arabic",
|
|
||||||
"Hindi": "Hindi",
|
|
||||||
"Thai": "Thai",
|
|
||||||
"Vietnamese": "Vietnamese",
|
|
||||||
"Indonesian": "Indonesian",
|
|
||||||
"Malay": "Malay",
|
|
||||||
"Filipino": "Filipino",
|
|
||||||
"Swedish": "Swedish",
|
|
||||||
"Finnish": "Finnish",
|
|
||||||
"Danish": "Danish",
|
|
||||||
"Norwegian": "Norwegian",
|
|
||||||
"Romanian": "Romanian",
|
|
||||||
"Czech": "Czech",
|
|
||||||
"Hungarian": "Hungarian",
|
|
||||||
"Greek": "Greek",
|
|
||||||
"Hebrew": "Hebrew",
|
|
||||||
"Chinese Simplified":"Simplified Chinese",
|
|
||||||
"Chinese Traditional":"Traditional Chinese"
|
|
||||||
}
|
|
||||||
|
|
||||||
translation_lang["Plamo_API"] = {"source":dict_plamo_languages, "target":dict_plamo_languages}
|
Raises:
|
||||||
|
FileNotFoundError: If languages/languages.yml is not found
|
||||||
|
ValueError: If YAML structure is invalid
|
||||||
|
"""
|
||||||
|
global _loaded, translation_lang
|
||||||
|
if _loaded and not force:
|
||||||
|
return translation_lang
|
||||||
|
|
||||||
dict_gemini_languages = {
|
with _lock:
|
||||||
"Arabic": "Arabic",
|
if _loaded and not force:
|
||||||
"Bengali": "Bengali",
|
return translation_lang
|
||||||
"Bulgarian": "Bulgarian",
|
|
||||||
"Chinese Simplified": "Simplified Chinese",
|
|
||||||
"Chinese Traditional": "Traditional Chinese",
|
|
||||||
"Croatian": "Croatian",
|
|
||||||
"Czech": "Czech",
|
|
||||||
"Danish": "Danish",
|
|
||||||
"Dutch": "Dutch",
|
|
||||||
"English": "English",
|
|
||||||
"Estonian": "Estonian",
|
|
||||||
"Finnish": "Finnish",
|
|
||||||
"French": "French",
|
|
||||||
"German": "German",
|
|
||||||
"Greek": "Greek",
|
|
||||||
"Hebrew": "Hebrew",
|
|
||||||
"Hindi": "Hindi",
|
|
||||||
"Hungarian": "Hungarian",
|
|
||||||
"Indonesian": "Indonesian",
|
|
||||||
"Italian": "Italian",
|
|
||||||
"Japanese": "Japanese",
|
|
||||||
"Korean": "Korean",
|
|
||||||
"Latvian": "Latvian",
|
|
||||||
"Lithuanian": "Lithuanian",
|
|
||||||
"Norwegian": "Norwegian",
|
|
||||||
"Polish": "Polish",
|
|
||||||
"Portuguese": "Portuguese",
|
|
||||||
"Romanian": "Romanian",
|
|
||||||
"Russian": "Russian",
|
|
||||||
"Serbian": "Serbian",
|
|
||||||
"Slovak": "Slovak",
|
|
||||||
"Slovenian": "Slovenian",
|
|
||||||
"Spanish": "Spanish",
|
|
||||||
"Swahili": "Swahili",
|
|
||||||
"Swedish": "Swedish",
|
|
||||||
"Thai": "Thai",
|
|
||||||
"Turkish": "Turkish",
|
|
||||||
"Ukrainian": "Ukrainian",
|
|
||||||
"Vietnamese": "Vietnamese",
|
|
||||||
}
|
|
||||||
|
|
||||||
translation_lang["Gemini_API"] = {"source":dict_gemini_languages, "target":dict_gemini_languages}
|
data = _load_languages(path, "languages/languages.yml")
|
||||||
|
|
||||||
dict_openai_languages = {
|
if not isinstance(data, dict):
|
||||||
"Arabic": "Arabic",
|
raise ValueError(
|
||||||
"Bengali": "Bengali",
|
"languages/languages.yml のルートはマッピング(dict)である必要があります。"
|
||||||
"Bulgarian": "Bulgarian",
|
)
|
||||||
"Catalan": "Catalan",
|
|
||||||
"Chinese Simplified": "Simplified Chinese",
|
|
||||||
"Chinese Traditional": "Traditional Chinese",
|
|
||||||
"Croatian": "Croatian",
|
|
||||||
"Czech": "Czech",
|
|
||||||
"Danish": "Danish",
|
|
||||||
"Dutch": "Dutch",
|
|
||||||
"English": "English",
|
|
||||||
"Estonian": "Estonian",
|
|
||||||
"Finnish": "Finnish",
|
|
||||||
"French": "French",
|
|
||||||
"German": "German",
|
|
||||||
"Greek": "Greek",
|
|
||||||
"Hebrew": "Hebrew",
|
|
||||||
"Hindi": "Hindi",
|
|
||||||
"Hungarian": "Hungarian",
|
|
||||||
"Indonesian": "Indonesian",
|
|
||||||
"Italian": "Italian",
|
|
||||||
"Japanese": "Japanese",
|
|
||||||
"Korean": "Korean",
|
|
||||||
"Latvian": "Latvian",
|
|
||||||
"Lithuanian": "Lithuanian",
|
|
||||||
"Norwegian": "Norwegian",
|
|
||||||
"Polish": "Polish",
|
|
||||||
"Portuguese": "Portuguese",
|
|
||||||
"Romanian": "Romanian",
|
|
||||||
"Russian": "Russian",
|
|
||||||
"Serbian": "Serbian",
|
|
||||||
"Slovak": "Slovak",
|
|
||||||
"Slovenian": "Slovenian",
|
|
||||||
"Spanish": "Spanish",
|
|
||||||
"Swahili": "Swahili",
|
|
||||||
"Swedish": "Swedish",
|
|
||||||
"Thai": "Thai",
|
|
||||||
"Turkish": "Turkish",
|
|
||||||
"Ukrainian": "Ukrainian",
|
|
||||||
"Vietnamese": "Vietnamese",
|
|
||||||
}
|
|
||||||
|
|
||||||
translation_lang["OpenAI_API"] = {"source": dict_openai_languages, "target": dict_openai_languages}
|
# 検証と正規化
|
||||||
translation_lang["LMStudio"] = {"source": dict_openai_languages, "target": dict_openai_languages}
|
validated: Dict[str, Dict[str, Dict[str, str]]] = {}
|
||||||
translation_lang["Ollama"] = {"source": dict_openai_languages, "target": dict_openai_languages}
|
for backend, value in data.items():
|
||||||
|
if backend == "CTranslate2":
|
||||||
|
# NOTE: CTranslate2 はモデルごとに異なる言語セットを持つ
|
||||||
|
if not isinstance(value, dict):
|
||||||
|
raise ValueError(
|
||||||
|
"CTranslate2 の値はモデル名→ {source:, target:} の dict である必要があります。"
|
||||||
|
)
|
||||||
|
validated["CTranslate2"] = {}
|
||||||
|
for model_name, model_map in value.items():
|
||||||
|
_validate_source_target(
|
||||||
|
backend=f"CTranslate2/{model_name}", mapping=model_map
|
||||||
|
)
|
||||||
|
validated["CTranslate2"][model_name] = {
|
||||||
|
"source": model_map["source"],
|
||||||
|
"target": model_map["target"],
|
||||||
|
}
|
||||||
|
else:
|
||||||
|
_validate_source_target(backend=backend, mapping=value)
|
||||||
|
validated[backend] = {
|
||||||
|
"source": value["source"],
|
||||||
|
"target": value["target"],
|
||||||
|
}
|
||||||
|
|
||||||
|
translation_lang = validated
|
||||||
|
_loaded = True
|
||||||
|
return translation_lang
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
try:
|
||||||
|
langs = loadTranslationLanguages(path=".", force=True)
|
||||||
|
printLog("Loaded translation languages:")
|
||||||
|
printLog(langs)
|
||||||
|
except Exception:
|
||||||
|
errorLogging()
|
||||||
@@ -42,7 +42,7 @@ class OllamaClient:
|
|||||||
self.model = None
|
self.model = None
|
||||||
self.base_url = "http://localhost:11434"
|
self.base_url = "http://localhost:11434"
|
||||||
|
|
||||||
prompt_config = loadPromptConfig(root_path)
|
prompt_config = loadPromptConfig(root_path, "translation_ollama.yml")
|
||||||
self.supported_languages = prompt_config["supported_languages"]
|
self.supported_languages = prompt_config["supported_languages"]
|
||||||
self.prompt_template = prompt_config["system_prompt"]
|
self.prompt_template = prompt_config["system_prompt"]
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user