dolphin-small-onnx / config.json
Jarbas's picture
Language and region are predicted when no language is given
9e4775f verified
Raw
History Blame Contribute Delete
2.17 kB
{
"model_type": "espnet-aed",
"preprocessor": "identity",
"subsampling_factor": 4,
"max_sequence_length": 200,
"sos_token": "<sos>",
"eos_token": "<eos>",
"prompt_tokens": [
"{language}",
"{region}",
"<asr>",
"<notimestamp>"
],
"languages": [
"zh-CN",
"zh-TW",
"zh-WU",
"zh-SICHUAN",
"zh-SHANXI",
"zh-ANHUI",
"zh-TIANJIN",
"zh-NINGXIA",
"zh-SHAANXI",
"zh-HEBEI",
"zh-SHANDONG",
"zh-GUANGDONG",
"zh-SHANGHAI",
"zh-HUBEI",
"zh-LIAONING",
"zh-GANSU",
"zh-FUJIAN",
"zh-HUNAN",
"zh-HENAN",
"zh-YUNNAN",
"zh-MINNAN",
"zh-WENZHOU",
"ja-JP",
"th-TH",
"ru-RU",
"ko-KR",
"id-ID",
"vi-VN",
"ct-NULL",
"ct-HK",
"ct-GZ",
"hi-IN",
"ur-IN",
"ur-PK",
"ms-MY",
"uz-UZ",
"ar-MA",
"ar-GLA",
"ar-SA",
"ar-EG",
"ar-KW",
"ar-LY",
"ar-JO",
"ar-AE",
"ar-LVT",
"fa-IR",
"bn-BD",
"ta-SG",
"ta-LK",
"ta-IN",
"ta-MY",
"te-IN",
"ug-NULL",
"ug-CN",
"gu-IN",
"my-MM",
"tl-PH",
"kk-KZ",
"or-IN",
"ne-NP",
"mn-MN",
"km-KH",
"jv-ID",
"lo-LA",
"si-LK",
"fil-PH",
"ps-AF",
"pa-IN",
"kab-NULL",
"ba-NULL",
"ks-IN",
"tg-TJ",
"su-ID",
"mr-IN",
"ky-KG",
"az-AZ"
],
"language_aliases": {
"zh": "zh-CN",
"ja": "ja-JP",
"th": "th-TH",
"ru": "ru-RU",
"ko": "ko-KR",
"id": "id-ID",
"vi": "vi-VN",
"ct": "ct-NULL",
"hi": "hi-IN",
"ur": "ur-IN",
"ms": "ms-MY",
"uz": "uz-UZ",
"ar": "ar-MA",
"fa": "fa-IR",
"bn": "bn-BD",
"ta": "ta-SG",
"te": "te-IN",
"ug": "ug-NULL",
"gu": "gu-IN",
"my": "my-MM",
"tl": "tl-PH",
"kk": "kk-KZ",
"or": "or-IN",
"ne": "ne-NP",
"mn": "mn-MN",
"km": "km-KH",
"jv": "jv-ID",
"lo": "lo-LA",
"si": "si-LK",
"fil": "fil-PH",
"ps": "ps-AF",
"pa": "pa-IN",
"kab": "kab-NULL",
"ba": "ba-NULL",
"ks": "ks-IN",
"tg": "tg-TJ",
"su": "su-ID",
"mr": "mr-IN",
"ky": "ky-KG",
"az": "az-AZ"
}
}