Add model files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,35 @@
 ---
+library_name: Spacy
 license: mit
+tags:
+- Spacy
+language:
+- 'lat'
+​version:
+- 'Spacy v2'
 ---
+
+## Model description
+​
+The model has been trained using the Spacy v2 library on the [HOME-Alcar](https://zenodo.org/record/5600884) document annotations. The model is compatible with version 2.3.5 of Spacy and incompatible with versions 3.x.x
+​
+# Cite us!
+​
+```bibtex
+@inproceedings{10.1007/978-3-031-06555-2_29,
+    author = {Monroc, Claire Bizon and Miret, Blanche and Bonhomme, Marie-Laurence and Kermorvant, Christopher},
+    title = {A Comprehensive Study Of Open-Source Libraries For Named Entity Recognition On Handwritten Historical Documents},
+    year = {2022},
+    isbn = {978-3-031-06554-5},
+    publisher = {Springer-Verlag},
+    address = {Berlin, Heidelberg},
+    url = {https://doi.org/10.1007/978-3-031-06555-2_29},
+    doi = {10.1007/978-3-031-06555-2_29},
+    abstract = {In this paper, we propose an evaluation of several state-of-the-art open-source natural language processing (NLP) libraries for named entity recognition (NER) on handwritten historical documents: spaCy, Stanza and Flair. The comparison is carried out on three low-resource multilingual datasets of handwritten historical documents: HOME (a multilingual corpus of medieval charters), Balsac (a corpus of parish records from Quebec), and Esposalles (a corpus of marriage records in Catalan). We study the impact of the document recognition processes (text line detection and handwriting recognition) on the performance of the NER. We show that current off-the-shelf NER libraries yield state-of-the-art results, even on low-resource languages or multilingual documents using multilingual models. We show, in an end-to-end evaluation, that text line detection errors have a greater impact than handwriting recognition errors. Finally, we also report state-of-the-art results on the public Esposalles dataset.},
+    booktitle = {Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22–25, 2022, Proceedings},
+    pages = {429–444},
+    numpages = {16},
+    keywords = {Text line detection, Named entity recognition, Handwritten historical documents},
+    location = {La Rochelle, France}
+}
+```

meta.json

@@ -0,0 +1,44 @@
+{
+  "lang":"xx",
+  "pipeline":[
+    "ner"
+  ],
+  "spacy_version":">=2.3.5<3.0",
+  "speed":{
+    "nwords":737404,
+    "cpu":15715.5042896057,
+    "gpu":null
+  },
+  "accuracy":{
+    "ents_f":99.862424388,
+    "ents_p":99.8471615721,
+    "ents_r":99.8776918709,
+    "ents_per_type":{
+      "LOC":{
+        "p":99.8644527279,
+        "r":99.9039493757,
+        "f":99.8841971473
+      },
+      "PERS":{
+        "p":99.836263971,
+        "r":99.8611457258,
+        "f":99.8487032983
+      }
+    },
+    "token_acc":100.0
+  },
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":"spacy_pretrained_vectors"
+  },
+  "name":"model0",
+  "version":"0.0.0",
+  "labels":{
+    "ner":[
+      "LOC",
+      "PERS"
+    ]
+  }
+}

ner/cfg

@@ -0,0 +1,18 @@
+{
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":1.0,
+  "cnn_maxout_pieces":3,
+  "nr_feature_tokens":6,
+  "nr_class":10,
+  "hidden_depth":1,
+  "token_vector_width":96,
+  "hidden_width":64,
+  "maxout_pieces":2,
+  "pretrained_vectors":null,
+  "bilstm_depth":0,
+  "self_attn_depth":0,
+  "conv_depth":4,
+  "conv_window":1,
+  "embed_size":2000
+}

ner/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf71f4619ef49f166ed161a01cc4fb5c189ef474516f9effd535b727d14dd410
+size 4003764

ner/moves

@@ -0,0 +1 @@
+��movesٔ{"0":{},"1":{"PERS":61908,"LOC":24382},"2":{"PERS":61908,"LOC":24382},"3":{"PERS":61908,"LOC":24382},"4":{"PERS":61908,"LOC":24382,"":1},"5":{"":1}}

tokenizer

@@ -0,0 +1,3 @@
+��prefix_search��^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^？|^！|^，|^、|^；|^：|^～|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^（|^）|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^[¦©®°҂֍֎؎؏۞۩۽۾߶৺୰௳-௸௺౿൏൹༁-༃༓༕-༗༚-༟༴༶༸྾-࿅࿇-࿌࿎࿏࿕-࿘႞႟᎐-᎙᥀᧞-᧿᭡-᭪᭴-᭼℀℁℃-℆℈℉℔№℗℞-℣℥℧℩℮℺℻⅊⅌⅍⅏↊↋↕-↙↜-↟↡↢↤↥↧-↭↯-⇍⇐⇑⇓⇕-⇳⌀-⌇⌌-⌟⌢-⌨⌫-⍻⍽-⎚⎴-⏛⏢-␦⑀-⑊⒜-ⓩ─-▶▸-◀◂-◷☀-♮♰-❧➔-➿⠀-⣿⬀-⬯⭅⭆⭍-⭳⭶-⮕⮘-⯈⯊-⯾⳥-⳪⺀-⺙⺛-⻳⼀-⿕⿰-⿻〄〒〓〠〶〷〾〿㆐㆑㆖-㆟㇀-㇣㈀-㈞㈪-㉇㉐㉠-㉿㊊-㊰㋀-㋾㌀-㏿䷀-䷿꒐-꓆꠨-꠫꠶꠷꠹꩷-꩹﷽￤￨￭￮�𐄷-𐄿𐅹-𐆉𐆌-𐆎𐆐-𐆛𐆠𐇐-𐇼𐡷𐡸𐫈𑜿𖬼-𖬿𖭅𛲜𝀀-𝃵𝄀-𝄦𝄩-𝅘𝅥𝅲𝅪-𝅬𝆃𝆄𝆌-𝆩𝆮-𝇨𝈀-𝉁𝉅𝌀-𝍖𝠀-𝧿𝨷-𝨺𝩭-𝩴𝩶-𝪃𝪅𝪆𞲬🀀-🀫🀰-🂓🂠-🂮🂱-🂿🃁-🃏🃑-🃵🄐-🅫🅰-🆬🇦-🈂🈐-🈻🉀-🉈🉐🉑🉠-🉥🌀-🏺🐀-🛔🛠-🛬🛰-🛹🜀-🝳🞀-🟘🠀-🠋🠐-🡇🡐-🡙🡠-🢇🢐-🢭🤀-🤋🤐-🤾🥀-🥰🥳-🥶🥺🥼-🦢🦰-🦹🧀-🧂🧐-🧿🩠-🩭]�suffix_search��…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|？$|！$|，$|、$|；$|：$|～$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|（$|）$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[¦©®°҂֍֎؎؏۞۩۽۾߶৺୰௳-௸௺౿൏൹༁-༃༓༕-༗༚-༟༴༶༸྾-࿅࿇-࿌࿎࿏࿕-࿘႞႟᎐-᎙᥀᧞-᧿᭡-᭪᭴-᭼℀℁℃-℆℈℉℔№℗℞-℣℥℧℩℮℺℻⅊⅌⅍⅏↊↋↕-↙↜-↟↡↢↤↥↧-↭↯-⇍⇐⇑⇓⇕-⇳⌀-⌇⌌-⌟⌢-⌨⌫-⍻⍽-⎚⎴-⏛⏢-␦⑀-⑊⒜-ⓩ─-▶▸-◀◂-◷☀-♮♰-❧➔-➿⠀-⣿⬀-⬯⭅⭆⭍-⭳⭶-⮕⮘-⯈⯊-⯾⳥-⳪⺀-⺙⺛-⻳⼀-⿕⿰-⿻〄〒〓〠〶〷〾〿㆐㆑㆖-㆟㇀-㇣㈀-㈞㈪-㉇㉐㉠-㉿㊊-㊰㋀-㋾㌀-㏿䷀-䷿꒐-꓆꠨-꠫꠶꠷꠹꩷-꩹﷽￤￨￭￮�𐄷-𐄿𐅹-𐆉𐆌-𐆎𐆐-𐆛𐆠𐇐-𐇼𐡷𐡸𐫈𑜿𖬼-𖬿𖭅𛲜𝀀-𝃵𝄀-𝄦𝄩-𝅘𝅥𝅲𝅪-𝅬𝆃𝆄𝆌-𝆩𝆮-𝇨𝈀-𝉁𝉅𝌀-𝍖𝠀-𝧿𝨷-𝨺𝩭-𝩴𝩶-𝪃𝪅𝪆𞲬🀀-🀫🀰-🂓🂠-🂮🂱-🂿🃁-🃏🃑-🃵🄐-🅫🅰-🆬🇦-🈂🈐-🈻🉀-🉈🉐🉑🉠-🉥🌀-🏺🐀-🛔🛠-🛬🛰-🛹🜀-🝳🞀-🟘🠀-🠋🠐-🡇🡐-🡙🡠-🢇🢐-🢭🤀-🤋🤐-🤾🥀-🥰🥳-🥶🥺🥼-🦢🦰-🦹🧀-🧂🧐-🧿🩠-🩭]$|'s$|'S$|’s$|’S$|—$|–$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[0-9a-zａ-ｚß-öø-ÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙ-ƛƞơƣƥƨƪƫƭưƴƶƹƺƽ-ƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳ-ȹȼȿɀɂɇɉɋɍɏⱡⱥⱦⱨⱪⱬⱱⱳⱴⱶ-ⱻꜣꜥꜧꜩꜫꜭꜯ-ꜱꜳꜵꜷꜹꜻꜽꜿꝁꝃꝅꝇꝉꝋꝍꝏꝑꝓꝕꝗꝙꝛꝝꝟꝡꝣꝥꝧꝩꝫꝭꝯꝱ-ꝸꝺꝼꝿꞁꞃꞅꞇꞌꞎꞑꞓ-ꞕꞗꞙꞛꞝꞟꞡꞣꞥꞧꞩꞯꞵꞷꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕ-ẝẟạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹỻỽỿёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|？|！|，|、|；|：|～|·|।|،|۔|��|٪(?:\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉)])\.$|(?<=[A-ZＡ-ＺÀ-ÖØ-ÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉ-ƋƎ-ƑƓƔƖ-ƘƜƝƟƠƢƤƦƧƩƬƮƯƱ-ƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶ-ǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁɃ-ɆɈɊɌɎⱠⱢ-ⱤⱧⱩⱫⱭ-ⱰⱲⱵⱾⱿꜢꜤꜦꜨꜪꜬꜮꜲꜴꜶꜸꜺꜼꜾꝀꝂꝄꝆꝈꝊꝌꝎꝐꝒꝔꝖꝘꝚꝜꝞꝠꝢꝤꝦꝨꝪꝬꝮꝹꝻꝽꝾꞀꞂꞄꞆꞋꞍꞐꞒꞖꞘꞚꞜꞞꞠꞢꞤꞦꞨꞪ-ꞮꞰ-ꞴꞶꞸḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẞẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸỺỼỾЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟][A-ZＡ-ＺÀ-ÖØ-ÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉ-ƋƎ-ƑƓƔƖ-ƘƜƝƟƠƢƤƦƧƩƬƮƯƱ-ƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶ-ǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁɃ-ɆɈɊɌɎⱠⱢ-ⱤⱧⱩⱫⱭ-ⱰⱲⱵⱾⱿꜢꜤꜦꜨꜪꜬꜮꜲꜴꜶꜸꜺꜼꜾꝀꝂꝄꝆꝈꝊꝌꝎꝐꝒꝔꝖꝘꝚꝜꝞꝠꝢꝤꝦꝨꝪꝬꝮꝹꝻꝽꝾꞀꞂꞄꞆꞋꞍꞐꞒꞖꞘꞚꞜꞞꞠꞢꞤꞦꞨꞪ-ꞮꞰ-ꞴꞶꞸḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẞẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸỺỼỾЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟])\.$�infix_finditer�s\.\.+|…|[¦©®°҂֍֎؎؏۞۩۽۾߶৺୰௳-௸௺౿൏൹༁-༃༓༕-༗༚-༟༴༶༸྾-࿅࿇-࿌࿎࿏࿕-࿘႞႟᎐-᎙᥀᧞-᧿᭡-᭪᭴-᭼℀℁℃-℆℈℉℔№℗℞-℣℥℧℩℮℺℻⅊⅌⅍⅏↊↋↕-↙↜-↟↡↢↤↥↧-↭↯-⇍⇐⇑⇓⇕-⇳⌀-⌇⌌-⌟⌢-⌨⌫-⍻⍽-⎚⎴-⏛⏢-␦⑀-⑊⒜-ⓩ─-▶▸-◀◂-◷☀-♮♰-❧➔-➿⠀-⣿⬀-⬯⭅⭆⭍-⭳⭶-⮕⮘-⯈⯊-⯾⳥-⳪⺀-⺙⺛-⻳⼀-⿕⿰-⿻〄〒〓〠〶〷〾〿㆐㆑㆖-㆟㇀-㇣㈀-㈞㈪-㉇㉐㉠-㉿㊊-㊰㋀-㋾㌀-㏿䷀-䷿꒐-꓆꠨-꠫꠶꠷꠹꩷-꩹﷽￤￨￭￮�𐄷-𐄿𐅹-𐆉𐆌-𐆎𐆐-𐆛𐆠𐇐-𐇼𐡷𐡸𐫈𑜿𖬼-𖬿𖭅𛲜𝀀-𝃵𝄀-𝄦𝄩-𝅘𝅥𝅲𝅪-𝅬𝆃𝆄𝆌-𝆩𝆮-𝇨𝈀-𝉁𝉅𝌀-𝍖𝠀-𝧿𝨷-𝨺𝩭-𝩴𝩶-𝪃𝪅𝪆𞲬🀀-🀫🀰-🂓🂠-🂮🂱-🂿🃁-🃏🃑-🃵🄐-🅫🅰-🆬🇦-🈂🈐-🈻🉀-🉈🉐🉑🉠-🉥🌀-🏺🐀-🛔🛠-🛬🛰-🛹🜀-🝳🞀-🟘🠀-🠋🠐-🡇🡐-🡙🡠-🢇🢐-🢭🤀-🤋🤐-🤾🥀-🥰🥳-🥶🥺🥼-🦢🦰-🦹🧀-🧂🧐-🧿🩠-🩭]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[a-zａ-ｚß-öø-ÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙ-ƛƞơƣƥƨƪƫƭưƴƶƹƺƽ-ƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳ-ȹȼȿɀɂɇɉɋɍɏⱡⱥⱦⱨⱪⱬⱱⱳⱴⱶ-ⱻꜣꜥꜧꜩꜫꜭꜯ-ꜱꜳꜵꜷꜹꜻꜽꜿꝁꝃꝅꝇꝉꝋꝍꝏꝑꝓꝕꝗꝙꝛꝝꝟꝡꝣꝥꝧꝩꝫꝭꝯꝱ-ꝸꝺꝼꝿꞁꞃꞅꞇꞌꞎꞑꞓ-ꞕꞗꞙꞛꞝꞟꞡꞣꞥꞧꞩꞯꞵꞷꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕ-ẝẟạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹỻỽỿёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉])\.(?=[A-ZＡ-ＺÀ-ÖØ-ÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉ-ƋƎ-ƑƓƔƖ-ƘƜƝƟƠƢƤƦƧƩƬƮƯƱ-ƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶ-ǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁɃ-ɆɈɊɌɎⱠⱢ-ⱤⱧⱩⱫⱭ-ⱰⱲⱵⱾⱿꜢꜤꜦꜨꜪꜬꜮꜲꜴꜶꜸꜺꜼꜾꝀꝂꝄꝆꝈꝊꝌꝎꝐꝒꝔꝖꝘꝚꝜꝞꝠꝢꝤꝦꝨꝪꝬꝮꝹꝻꝽꝾꞀꞂꞄꞆꞋꞍꞐꞒꞖꞘꞚꞜꞞꞠꞢꞤꞦꞨꞪ-ꞮꞰ-ꞴꞶꞸḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẞẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸỺỼỾЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉])|(?<=[A-Za-zＡ-Ｚａ-ｚÀ-ÖØ-öø-ÿĀ-ſƀ-ƿDŽ-ɏⱠ-ⱻⱾⱿꜢ-ꝯꝱ-ꞇꞋ-ꞎꞐ-ꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḀ-ỿёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟]),(?=[A-Za-zＡ-Ｚａ-ｚÀ-ÖØ-öø-ÿĀ-ſƀ-ƿDŽ-ɏⱠ-ⱻⱾⱿꜢ-ꝯꝱ-ꞇꞋ-ꞎꞐ-ꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḀ-ỿёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟])|(?<=[A-Za-zＡ-Ｚａ-ｚÀ-ÖØ-öø-ÿĀ-ſƀ-ƿDŽ-ɏⱠ-ⱻⱾⱿꜢ-ꝯꝱ-ꞇꞋ-ꞎꞐ-ꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḀ-ỿёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟])(?:-|–|—|--|---|——|~)(?=[A-Za-zＡ-Ｚａ-ｚÀ-ÖØ-öø-ÿĀ-ſƀ-ƿDŽ-ɏⱠ-ⱻⱾⱿꜢ-ꝯꝱ-ꞇꞋ-ꞎꞐ-ꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḀ-ỿёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟])|(?<=[A-Za-zＡ-Ｚａ-ｚÀ-ÖØ-öø-ÿĀ-ſƀ-ƿDŽ-ɏⱠ-ⱻⱾⱿꜢ-ꝯꝱ-ꞇꞋ-ꞎꞐ-ꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḀ-ỿёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟0-9])[:<>=/](?=[A-Za-zＡ-Ｚａ-ｚÀ-ÖØ-öø-ÿĀ-ſƀ-ƿDŽ-ɏⱠ-ⱻⱾⱿꜢ-ꝯꝱ-ꞇꞋ-ꞎꞐ-ꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḀ-ỿёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟])�token_match��url_match�(?u)^(?:(?:[\w\+\-\.]{2,})://)?(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[A-Za-z0-9¡-￿][A-Za-z0-9¡-￿_-]{0,62})?[A-Za-z0-9¡-￿]\.)+(?:[a-zａ-ｚß-öø-ÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙ-ƛƞơƣƥƨƪƫƭưƴƶƹƺƽ-ƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳ-ȹȼȿɀɂɇɉɋɍɏⱡⱥⱦⱨⱪⱬⱱⱳⱴⱶ-ⱻꜣꜥꜧꜩꜫꜭꜯ-ꜱꜳꜵꜷꜹꜻꜽꜿꝁꝃꝅꝇꝉꝋꝍꝏꝑꝓꝕꝗꝙꝛꝝꝟꝡꝣꝥꝧꝩꝫꝭꝯꝱ-ꝸꝺꝼꝿꞁꞃꞅꞇꞌꞎꞑꞓ-ꞕꞗꞙꞛꞝꞟꞡꞣꞥꞧꞩꞯꞵꞷꞹꟺꬰ-ꭚꭠ-ꭤɐ-ʯᴀ-ᴥᵫ-ᵷᵹ-ᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕ-ẝẟạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹỻỽỿёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґঀ-৿֑-״יִ-ﭏؠ-يٮ-ەۥ-ۿݐ-ݿࢠ-ࢽﭐ-ﮱﯓ-ﴽﵐ-ﷇﷰ-ﷻﹰ-ﻼ𞸀-𞺻඀-෿ऀ-ॿಀ-೿஀-௿ఀ-౿가-힯ᄀ-ᇿ一-拿挀-矿砀-賿贀-鿿㐀-䶿𠀀-𡗿𡘀-𣃿𣄀-𤗿𤘀-𦃿𦄀-𧗿𧘀-𩃿𩄀-𪛟𪜀-𫜿𫝀-𫠟𫠠-𬺯𬺰-𮯯⺀-⻿⼀-⿟⿰-⿿　-〿㇀-㇯㈀-㋿㌀-㏿豈-﫿︰-﹏🈀-🋿丽-𯨟]{2,63}))(?::\d{2,5})?(?:[/?#]\S*)?$�exceptions���	��A�	JgK�_SP�
+��A�
+JgK�_SP� ��A� JgK�_SP�")��A�")�'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°）╯︵┻━┻��A�(╯°□°）╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�._.��A�._.�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�:’(��A�:’(�:’)��A�:’)�:’-(��A�:’-(�:’-)��A�:’-)�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�\")��A�\")�\n��A�\nJgK�_SP�\t��A�\tJgK�_SP�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�f.��A�f.�g.��A�g.�h.��A�h.�i.��A�i.�j.��A�j.�k.��A�k.�l.��A�l.�m.��A�m.�n.��A�n.�o.��A�o.�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�p.��A�p.�q.��A�q.�r.��A�r.�s.��A�s.�t.��A�t.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� JgI�  K�_SP�¯\(ツ)/¯��A�¯\(ツ)/¯�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�’��A�’�’’��A�’’

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bac7887f37e66e55721c09112b3ccbe56866fe1969146df08fc41cb86a4b18f
+size 14

vocab/lookups_extra.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479d77559672b791f58e372a4e000da8efb92f443b6964d82684bbe2d324d28b
+size 47