Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- multilingual
|
| 5 |
+
library_name: gliner
|
| 6 |
+
datasets:
|
| 7 |
+
- urchade/pile-mistral-v0.1
|
| 8 |
+
- thegenerativegeneration/custom_PII_wisperlanguages
|
| 9 |
+
pipeline_tag: token-classification
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
Finetuned for way too short on the following categories:
|
| 13 |
+
|
| 14 |
+
```python
|
| 15 |
+
PII_CATEGORIES3 = [
|
| 16 |
+
"identifying person name", "non-identifying person name",
|
| 17 |
+
"identifying company name", "non-identifying company name",
|
| 18 |
+
"identifying address", "non-identifying address",
|
| 19 |
+
"identifying city", "non-identifying city", "identifying postal code", "non-identifying postal code",
|
| 20 |
+
"identifying gender", "non-identifying gender",
|
| 21 |
+
"identifying religious belief", "non-identifying religious belief",
|
| 22 |
+
"identifying nationality", "non-identifying nationality",
|
| 23 |
+
"identifying age", "non-identifying age", "other identifying information",
|
| 24 |
+
]
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
On these languages (the ones contained in Whisper):
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
LANGUAGES = {
|
| 31 |
+
"en": "english",
|
| 32 |
+
"zh": "chinese",
|
| 33 |
+
"de": "german",
|
| 34 |
+
"es": "spanish",
|
| 35 |
+
"ru": "russian",
|
| 36 |
+
"ko": "korean",
|
| 37 |
+
"fr": "french",
|
| 38 |
+
"ja": "japanese",
|
| 39 |
+
"pt": "portuguese",
|
| 40 |
+
"tr": "turkish",
|
| 41 |
+
"pl": "polish",
|
| 42 |
+
"ca": "catalan",
|
| 43 |
+
"nl": "dutch",
|
| 44 |
+
"ar": "arabic",
|
| 45 |
+
"sv": "swedish",
|
| 46 |
+
"it": "italian",
|
| 47 |
+
"id": "indonesian",
|
| 48 |
+
"hi": "hindi",
|
| 49 |
+
"fi": "finnish",
|
| 50 |
+
"vi": "vietnamese",
|
| 51 |
+
"he": "hebrew",
|
| 52 |
+
"uk": "ukrainian",
|
| 53 |
+
"el": "greek",
|
| 54 |
+
"ms": "malay",
|
| 55 |
+
"cs": "czech",
|
| 56 |
+
"ro": "romanian",
|
| 57 |
+
"da": "danish",
|
| 58 |
+
"hu": "hungarian",
|
| 59 |
+
"ta": "tamil",
|
| 60 |
+
"no": "norwegian",
|
| 61 |
+
"th": "thai",
|
| 62 |
+
"ur": "urdu",
|
| 63 |
+
"hr": "croatian",
|
| 64 |
+
"bg": "bulgarian",
|
| 65 |
+
"lt": "lithuanian",
|
| 66 |
+
"la": "latin",
|
| 67 |
+
"mi": "maori",
|
| 68 |
+
"ml": "malayalam",
|
| 69 |
+
"cy": "welsh",
|
| 70 |
+
"sk": "slovak",
|
| 71 |
+
"te": "telugu",
|
| 72 |
+
"fa": "persian",
|
| 73 |
+
"lv": "latvian",
|
| 74 |
+
"bn": "bengali",
|
| 75 |
+
"sr": "serbian",
|
| 76 |
+
"az": "azerbaijani",
|
| 77 |
+
"sl": "slovenian",
|
| 78 |
+
"kn": "kannada",
|
| 79 |
+
"et": "estonian",
|
| 80 |
+
"mk": "macedonian",
|
| 81 |
+
"br": "breton",
|
| 82 |
+
"eu": "basque",
|
| 83 |
+
"is": "icelandic",
|
| 84 |
+
"hy": "armenian",
|
| 85 |
+
"ne": "nepali",
|
| 86 |
+
"mn": "mongolian",
|
| 87 |
+
"bs": "bosnian",
|
| 88 |
+
"kk": "kazakh",
|
| 89 |
+
"sq": "albanian",
|
| 90 |
+
"sw": "swahili",
|
| 91 |
+
"gl": "galician",
|
| 92 |
+
"mr": "marathi",
|
| 93 |
+
"pa": "punjabi",
|
| 94 |
+
"si": "sinhala",
|
| 95 |
+
"km": "khmer",
|
| 96 |
+
"sn": "shona",
|
| 97 |
+
"yo": "yoruba",
|
| 98 |
+
"so": "somali",
|
| 99 |
+
"af": "afrikaans",
|
| 100 |
+
"oc": "occitan",
|
| 101 |
+
"ka": "georgian",
|
| 102 |
+
"be": "belarusian",
|
| 103 |
+
"tg": "tajik",
|
| 104 |
+
"sd": "sindhi",
|
| 105 |
+
"gu": "gujarati",
|
| 106 |
+
"am": "amharic",
|
| 107 |
+
"yi": "yiddish",
|
| 108 |
+
"lo": "lao",
|
| 109 |
+
"uz": "uzbek",
|
| 110 |
+
"fo": "faroese",
|
| 111 |
+
"ht": "haitian creole",
|
| 112 |
+
"ps": "pashto",
|
| 113 |
+
"tk": "turkmen",
|
| 114 |
+
"nn": "nynorsk",
|
| 115 |
+
"mt": "maltese",
|
| 116 |
+
"sa": "sanskrit",
|
| 117 |
+
"lb": "luxembourgish",
|
| 118 |
+
"my": "myanmar",
|
| 119 |
+
"bo": "tibetan",
|
| 120 |
+
"tl": "tagalog",
|
| 121 |
+
"mg": "malagasy",
|
| 122 |
+
"as": "assamese",
|
| 123 |
+
"tt": "tatar",
|
| 124 |
+
"haw": "hawaiian",
|
| 125 |
+
"ln": "lingala",
|
| 126 |
+
"ha": "hausa",
|
| 127 |
+
"ba": "bashkir",
|
| 128 |
+
"jw": "javanese",
|
| 129 |
+
"su": "sundanese",
|
| 130 |
+
"yue": "cantonese",
|
| 131 |
+
}
|
| 132 |
+
```
|