Spaces:

huspacy
/

example-applications

Runtime error

App Files Files Community

oroszgy commited on Jun 24, 2022

Commit

539b929

•

2 Parent(s): b27f1b3 265d133

Merge pull request #3 from huspacy/relation

Browse files

Files changed (10) hide show

README.md +1 -1
app.py +3 -2
examples/anon.py +29 -19
examples/common.py +1 -29
examples/keyphrases.py +31 -3
examples/relation.py +53 -0
poetry.lock +391 -129
pyproject.toml +1 -1
requirements.txt +17 -10
resources/triples.py +125 -0

README.md CHANGED Viewed

@@ -19,4 +19,4 @@ This repository presents some practical examples on using HuSpaCy for various te
 To start the demo: `poetry run python app.py`
-If you upgrade dependencies via poetry don't forget to update `requirements.txt` with ` poetry export --without-hashes > requirements.txt`


19
20	To start the demo: `poetry run python app.py`
21
22	+ If you upgrade dependencies via poetry don't forget to update `requirements.txt` with `poetry export --without-hashes > requirements.txt`

app.py CHANGED Viewed

@@ -1,14 +1,15 @@
 import gradio as gr
 from examples.keyphrases import demo as keyphrases_demo
 from examples.anon import demo as anon_demo
 demo = gr.Blocks()
 with demo:
     gr.Markdown("# HuSpaCy Examples")
     gr.TabbedInterface(
-        interface_list=[keyphrases_demo, anon_demo],
-        tab_names=["Keyphrase extraction", "Text anonymization"],
     )
 if __name__ == '__main__':

 import gradio as gr
 from examples.keyphrases import demo as keyphrases_demo
 from examples.anon import demo as anon_demo
+from examples.relation import demo as relation_demo
 demo = gr.Blocks()
 with demo:
     gr.Markdown("# HuSpaCy Examples")
     gr.TabbedInterface(
+        interface_list=[keyphrases_demo, anon_demo, relation_demo],
+        tab_names=["Keyphrase extraction", "Text anonymization", "Relation Extraction"],
     )
 if __name__ == '__main__':

examples/anon.py CHANGED Viewed

@@ -1,26 +1,26 @@
 from typing import Tuple, List
 import gradio as gr
 from presidio_analyzer import AnalyzerEngine
-from presidio_analyzer.nlp_engine import NlpEngineProvider
 from presidio_anonymizer import AnonymizerEngine
-from faker import Faker
 from presidio_anonymizer.entities.engine import OperatorConfig
-def process(text: str, fake_data: bool, entities: List) -> Tuple[str, List]:
-    configuration = {
-        "nlp_engine_name": "spacy",
-        "models": [{"lang_code": "hu", "model_name": "hu_core_news_lg", }],
-    }
-    provider = NlpEngineProvider(nlp_configuration=configuration)
-    nlp_engine = provider.create_engine()
-    analyzer = AnalyzerEngine(nlp_engine=nlp_engine,
-                              supported_languages=["hu"],)
     results = analyzer.analyze(
         text=text, entities=entities, language="hu")
@@ -42,17 +42,25 @@ def process(text: str, fake_data: bool, entities: List) -> Tuple[str, List]:
     anonymizer = AnonymizerEngine()
     anonymized_text = anonymizer.anonymize(
-        text=text, analyzer_results=results, operators=fake_operators) if fake_data else anonymizer.anonymize(text=text, analyzer_results=results)
     return anonymized_text.text, anonymized_text.items
 EXAMPLES = [
-    ["Vespucci 1450-es években született Firenzében, és 1497 és 1504 között legalább két felfedező úton vett részt – az egyiket spanyol, a másikat portugál támogatással.", False, ["PERSON", "LOCATION"]],
-    ["Elon Musk 1971-ben született a Dél-afrikai Köztársaságban, anyja Maye Musk (született: Haldeman) modell, apja Errol Musk mérnök, pilóta.", True, [
         "PERSON", "LOCATION"]],
-    ["Vespucci 1450-es években született Firenzében, és 1497 és 1504 között legalább két felfedező úton vett részt. Bárorító leveleket a vespucci@deojeda.es email-címre várt, mellette működött egy hangrögzítője is a +3903827802737 telefonszámon. Adományokat a bitcoin tárcájába (1Fsb3io3hj1jKaRCTRQ89Du88Dp7NxgEcU), bankkártyájára (5200 8282 8282 8210) és IBAN számlaszámára (ES8201289482186115378819) fogadott. Utazási blogja a https://firenze.it/vespucci címen volt elérhető. Legutóbb 1503-03-15-én publikált, ezt a 192.168.0.1 ip-címről tette meg.", True,
-     ["PERSON", "LOCATION", "EMAIL_ADDRESS", "PHONE_NUMBER", "CRYPTO", "IP_ADDRESS", "URL", "DATE_TIME", "CREDIT_CARD", "IBAN_CODE"]],
 ]
 demo = gr.Interface(
@@ -60,7 +68,9 @@ demo = gr.Interface(
     inputs=[gr.Textbox(value=EXAMPLES[0][0], lines=10, label="Input text", show_label=True),
             gr.Checkbox(value=EXAMPLES[0][1],
                         label="Apply de-identification", show_label=True),
-            gr.CheckboxGroup(['PERSON', 'LOCATION', 'DATE_TIME', 'IP_ADDRESS', 'URL', 'EMAIL_ADDRESS', 'PHONE_NUMBER', 'CREDIT_CARD', 'IBAN_CODE', 'CRYPTO'], label="Entities", show_label=True, value=EXAMPLES[0][2])],
     outputs=[gr.Textbox(label="Anonymized text", show_label=True),
              gr.Textbox(label="Tags", show_label=True)],
     examples=EXAMPLES,

 from typing import Tuple, List
 import gradio as gr
+from faker import Faker
 from presidio_analyzer import AnalyzerEngine
+from presidio_analyzer.nlp_engine import SpacyNlpEngine
 from presidio_anonymizer import AnonymizerEngine
 from presidio_anonymizer.entities.engine import OperatorConfig
+from spacy import Language
+from examples.common import NLP
+# noinspection PyMissingConstructor
+class HuSpaCyNlpEngine(SpacyNlpEngine):
+    def __init__(self, nlp: Language):
+        self.nlp = {"hu": nlp}
+def process(text: str, fake_data: bool, entities: List) -> Tuple[str, List]:
+    nlp_engine = HuSpaCyNlpEngine(NLP)
+    analyzer = AnalyzerEngine(nlp_engine=nlp_engine, supported_languages=["hu"])
     results = analyzer.analyze(
         text=text, entities=entities, language="hu")
     anonymizer = AnonymizerEngine()
     anonymized_text = anonymizer.anonymize(
+        text=text, analyzer_results=results, operators=fake_operators) if fake_data else anonymizer.anonymize(text=text,
+                                                                                                              analyzer_results=results)
     return anonymized_text.text, anonymized_text.items
 EXAMPLES = [
+    [
+        "Vespucci 1450-es években született Firenzében, és 1497 és 1504 között legalább két felfedező úton vett részt – az egyiket spanyol, a másikat portugál támogatással.",
+        False, ["PERSON", "LOCATION"]],
+    [
+        "Elon Musk 1971-ben született a Dél-afrikai Köztársaságban, anyja Maye Musk (született: Haldeman) modell, apja Errol Musk mérnök, pilóta.",
+        True, [
         "PERSON", "LOCATION"]],
+    [
+        "Vespucci 1450-es években született Firenzében, és 1497 és 1504 között legalább két felfedező úton vett részt. Bárorító leveleket a vespucci@deojeda.es email-címre várt, mellette működött egy hangrögzítője is a +3903827802737 telefonszámon. Adományokat a bitcoin tárcájába (1Fsb3io3hj1jKaRCTRQ89Du88Dp7NxgEcU), bankkártyájára (5200 8282 8282 8210) és IBAN számlaszámára (ES8201289482186115378819) fogadott. Utazási blogja a https://firenze.it/vespucci címen volt elérhető. Legutóbb 1503-03-15-én publikált, ezt a 192.168.0.1 ip-címről tette meg.",
+        True,
+        ["PERSON", "LOCATION", "EMAIL_ADDRESS", "PHONE_NUMBER", "CRYPTO", "IP_ADDRESS", "URL", "DATE_TIME",
+         "CREDIT_CARD", "IBAN_CODE"]],
 ]
 demo = gr.Interface(
     inputs=[gr.Textbox(value=EXAMPLES[0][0], lines=10, label="Input text", show_label=True),
             gr.Checkbox(value=EXAMPLES[0][1],
                         label="Apply de-identification", show_label=True),
+            gr.CheckboxGroup(
+                ['PERSON', 'LOCATION', 'DATE_TIME', 'IP_ADDRESS', 'URL', 'EMAIL_ADDRESS', 'PHONE_NUMBER', 'CREDIT_CARD',
+                 'IBAN_CODE', 'CRYPTO'], label="Entities", show_label=True, value=EXAMPLES[0][2])],
     outputs=[gr.Textbox(label="Anonymized text", show_label=True),
              gr.Textbox(label="Tags", show_label=True)],
     examples=EXAMPLES,

examples/common.py CHANGED Viewed

@@ -5,7 +5,7 @@ from typing import Dict, List
 import spacy
 from spacy import Language
-NLP: Language = spacy.load("hu_core_news_lg")
 def _compute_idf(freq_file: Path) -> Dict[str, float]:
@@ -26,31 +26,3 @@ def _compute_idf(freq_file: Path) -> Dict[str, float]:
 IDF: Dict[str, float] = _compute_idf(Path(__file__).parent.parent / "resources" / "freq.list")
-NEWS_EXAMPLES = [
-    """A magyar futballválogatott negyedik Nemzetek Ligája mérkőzésén másodszor nyert, a hazai 1-0-s siker után idegenben 4-0-val megsemmisítette Angliát. Nagy győzelem volt, az enervált angolokat a saját közönségük fütyülte ki, miután a második félidőben el sem találták a kaput. 96 éve nem kaptak ekkora verést az angolok hazai pályán.
-Az angol kapitány, Gareth Southgate kilenc helyen változtatott azon a csapaton, amelyik az olaszok ellen gól nélküli döntetlent játszott szombaton. Marco Rossi a kapuban cserélt, Dibusz Dénes állt a gólvonalon, Schäfer András visszatért a középpályára, miután a németek ellen letöltötte eltiltását. A 3-4-2-1-es felállás ezúttal sem változott. Ha végig akarja nézni helyszíni közvetítésünket, mit műveltek az angolok a Himnusz alatt, itt megteheti.
-Az első helyzetre a hatodik percig kellett várni, akkor Kane passzából James húzott el a bal oldalon, középre adta a labdát, Bowen fejelt, Nagy Zsolt a helyén volt, és mentett.
-Az első magyar lövés rögtön a kapuban landolt.
-Szoboszlai ívelt be szabadrúgást a tizenhatoson belülre, Lang és Stone ugrott fel fejelni, a magyar védő megelőzte ellenfelét. A labda Kane talpa alatt elcsúszott, Sallai combbal átvette, azonnal lőtt 7 méterről, mielőtt még Phillips odaért volna, Ramsdale ugyan beleért, de kiütni már nem tudta. Szoboszlainak volt egy másik, sokkal közelebbről elvégzett szabadrúgása, amit igen veszélyesen lőtt be a kapu elé, James a gólvonalról mentett, Szalai Attila elől. A kipattanóból az angolok egy gyors kontrát vezettek, de a magyar tízes visszafutott, és a tizenhatoson belül szerelni tudott.
-A magyar válogatott nem volt nagy nyomás alatt, az angolok akkor jártak legközelebb a gólhoz, amikor Orbán a 36. percben a saját kapuja felé fejelt, de Dibusz akkor is a helyén volt. A hazai szögletek veszélyesek voltak, de egyik sem annyira, hogy a szívünkhöz kellett volna kapnunk.
-A második félidőben az angolok felgyorsították a játékukat, de igazán komoly helyzetet nem tudtak kialakítani, Rossi pedig már az 55. percben érezte, hogy frissíteni kell, és Szoboszlai helyére Gazdag, Styles helyére pedig Nagy Ádám állt.
-Mivel a válogatott visszaállt, és fegyelmezetten zárta le a területeket, az angolok ötlettelen, olykor lassú adogatása veszélytelen volt. A csapat ezúttal is igazolta, mennyire képes megnehezíteni, megkeseríteni a riválisai dolgát.
-A hajrában jött a varázslat Most azonban azt is igazolta, hogy egy pillanat alatt a kapu elé tud kerülni. A Szalai helyére beálló Ádám Martin megharcolt egy labdáért, megtartotta a térfél közepén, majd tökéletesen szöktette Sallait, aki a tizenhatoson belül állítgatás nélkül jobb külsővel elrúgta a labdát Ramsdale lába mellett.
-A 77. percben Kane használható labdát kapott a szélről, kilenc méterről fejelt, a kapufáról pattant vissza a labda a mezőnybe, a center megpróbálta átvenni, de másodszorra már nem tudta, így odalett a helyzet. A 81. percben Magyarország berúgta a harmadik gólt.
-Nego fejesét még hárították a védők, a kipattanót készítette le Ádám Martin a támadást kísérő Nagy Zsolt elé, aki 17 méterről külsővel, állítgatás nélkül, pazarul lőtte ki a jobb alsó sarkot. A 29 éves felcsúti védő ennek a 11 napnak a legnagyobb felfedezettje, mert a németek ellen is eredményes volt szombaton.
-Stonest a hajrában még kiállították, a mieink nem törekedtek még jobban a gólkülönbség javítására, de magabiztosan passzolgattak, így Angliának esélye sem volt a szépítésre, miután alig volt náluk a labda. Hogy teljes legyen az angol KO, arról Gazdag Dániel gondoskodott, amikor egy nagy sprint után lazán átpörgette a labdát a kimozduló kapus felett.
-Ha Anglia nem is veszi komolyan ezt a sorozatot, mert a novemberi vb-re készül, és egy fárasztó szezon végén már a legszívesebben pihennének a klasszisai, négy gólt biztosan nem akart kapni, mert így könnyen ki is eshetnek az A divízióból. Tavaly szeptemberben Eb-selejtezőn Anglia ugyanilyen arányban verte a mieinket a Puskás Arénában, ez most egy méltó visszavágás volt.
-A csoport másik meccsén a németek 5-2-vel küldték haza az olaszokat, és ezzel feljöttek a második helyre.""",
-    """A megszokott menetrenden kívül és váratlanul nagy mértékben emelt a jegybank az irányadó rátán. A forint a hírre 395 alá erősödött az euróval szemben.
-7,25 százalékos kamattal hirdette meg a Magyar Nemzeti Bank (MNB) az egyhetes betéti tenderét – derül ki a jegybank által közzétett adatokból. Az egyhetes betét azt jelenti, hogy a bankok ezzel a rátával parkoltathatják a pénzüket egy hétig az MNB-ben. Mivel az egyhetes betéti eszköz kamata jelenleg magasabb, mint az alapkamat, valójában ez az irányadó ráta.
-A kamatemelés váratlan, mind időzítését, mind mértékét tekintve. A jegybank ugyan kommunikációja szerint nyitva tartja a lehetőségét, hogy bármikor emeljen az egyhetes betét kamatán, azon a Monetáris Tanács havi kamatdöntő ülései után szokott emelni. A cél az, hogy idővel az alapkamat és az egyhetes betét kamata újra összezárjon. A kamatemelés így a bevett menetrenden kívüli. A mértéke is nagyobb a megszokottnál, az emelés 0,5 százalékpontos, miközben a jegybank egy ideje 0,3 százalékpontos lépésekkel haladt felfelé. Legutóbb márciusban volt 0,5 százalékpontos emelés, ekkor a ráta 5,35 százalékról 5,85 százalékra nőtt.
-A Monetáris Tanács legutóbb május végén emelt az alapkamat szintjén, 5,4-ről 5,9 százalékra. Addig kell a kamatokat emelni, amíg az szükséges, hogy az inflációs célt fenntartható módon el tudjuk érni – mondta Virág Barnabás alelnök az alapkamat-emelés után. Az alelnök szerint a következő hónapokban várhatóan még tovább nő az infláció az áprilisi 9,5 százalékról, Virág elhúzódó infláció elleni harcot, a szigorúbb monetáris kondíciók tartós fenntartását ígérte.
-A forint árfolyama mindenesetre jól reagált az egyhetesbetétkamat-emelésre, az euróval szemben a napi nyitó árfolyam 397,5 környékéről 395 alá erősödött. A megelőző napokban a forint sorra döntögette a negatív árfolyamrekordokat, az euróval szemben többször 400 fölött is járt. Jelenleg a történelmi mélypont 402,96.
-""",
-    """Jövőre nem lesz "ledolgozós" hétvége
-2023-ban egyetlen szombati munkanap sem lesz.
-Jövőre kétszer (húsvétkor és karácsonykor) lesz négynapos a hétvége. Emellett négyszer lesz háromnapos hosszú hétvége, mivel május 1-én, pünkösdkor, október 23-án, és az újévkor is egy-egy hétfővel bővülnek majd a hétvégi szabadnapok - ezt Koncz Zsófia, a Technológiai és Ipari Minisztérium új parlamenti államtitkára közölte egy Facebook-bejegyzésben, hangsúlyozva, hogy a munkarendet meghatározó minisztériumuk úgy döntött, hogy 2023-ban egyetlen egynapos, "ledolgozós” hétvége sem lesz.
-Hogy mennyit ér egy munkanap, arról csak becsléseket lehet készíteni, és a statisztikusok legszívesebben erről is lebeszélnék a kísérletező kedvűeket. Nagyon leegyszerűsítve mondhatjuk azt: a GDP-t leosztva a munkanapok számával 160 milliárd forintot ér egy munkanap, de akkor még azt sem vettük figyelembe, hogy van munka azért hétvégéken is.
-"""
-]

 import spacy
 from spacy import Language
+NLP: Language = spacy.load("hu_core_news_trf")
 def _compute_idf(freq_file: Path) -> Dict[str, float]:
 IDF: Dict[str, float] = _compute_idf(Path(__file__).parent.parent / "resources" / "freq.list")

examples/keyphrases.py CHANGED Viewed

@@ -4,7 +4,7 @@ import gradio as gr
 import pandas as pd
 from textacy.extract.keyterms.sgrank import sgrank as keywords
-from examples.common import NLP, IDF, NEWS_EXAMPLES
 def process(text: str) -> pd.DataFrame:
@@ -16,10 +16,38 @@ def process(text: str) -> pd.DataFrame:
                          if all(other == term or term not in other for other in term_set)])
 demo = gr.Interface(
     fn=process,
-    inputs=gr.Textbox(value=NEWS_EXAMPLES[0], lines=10, label="Input text", show_label=True),
     outputs=gr.DataFrame(label="Keywords", show_label=False, max_cols=2, max_rows=10),
-    examples=NEWS_EXAMPLES,
     # cache_examples=True,
 )

 import pandas as pd
 from textacy.extract.keyterms.sgrank import sgrank as keywords
+from examples.common import NLP, IDF
 def process(text: str) -> pd.DataFrame:
                          if all(other == term or term not in other for other in term_set)])
+EXAMPLES = [
+    """A magyar futballválogatott negyedik Nemzetek Ligája mérkőzésén másodszor nyert, a hazai 1-0-s siker után idegenben 4-0-val megsemmisítette Angliát. Nagy győzelem volt, az enervált angolokat a saját közönségük fütyülte ki, miután a második félidőben el sem találták a kaput. 96 éve nem kaptak ekkora verést az angolok hazai pályán.
+Az angol kapitány, Gareth Southgate kilenc helyen változtatott azon a csapaton, amelyik az olaszok ellen gól nélküli döntetlent játszott szombaton. Marco Rossi a kapuban cserélt, Dibusz Dénes állt a gólvonalon, Schäfer András visszatért a középpályára, miután a németek ellen letöltötte eltiltását. A 3-4-2-1-es felállás ezúttal sem változott. Ha végig akarja nézni helyszíni közvetítésünket, mit műveltek az angolok a Himnusz alatt, itt megteheti.
+Az első helyzetre a hatodik percig kellett várni, akkor Kane passzából James húzott el a bal oldalon, középre adta a labdát, Bowen fejelt, Nagy Zsolt a helyén volt, és mentett.
+Az első magyar lövés rögtön a kapuban landolt.
+Szoboszlai ívelt be szabadrúgást a tizenhatoson belülre, Lang és Stone ugrott fel fejelni, a magyar védő megelőzte ellenfelét. A labda Kane talpa alatt elcsúszott, Sallai combbal átvette, azonnal lőtt 7 méterről, mielőtt még Phillips odaért volna, Ramsdale ugyan beleért, de kiütni már nem tudta. Szoboszlainak volt egy másik, sokkal közelebbről elvégzett szabadrúgása, amit igen veszélyesen lőtt be a kapu elé, James a gólvonalról mentett, Szalai Attila elől. A kipattanóból az angolok egy gyors kontrát vezettek, de a magyar tízes visszafutott, és a tizenhatoson belül szerelni tudott.
+A magyar válogatott nem volt nagy nyomás alatt, az angolok akkor jártak legközelebb a gólhoz, amikor Orbán a 36. percben a saját kapuja felé fejelt, de Dibusz akkor is a helyén volt. A hazai szögletek veszélyesek voltak, de egyik sem annyira, hogy a szívünkhöz kellett volna kapnunk.
+A második félidőben az angolok felgyorsították a játékukat, de igazán komoly helyzetet nem tudtak kialakítani, Rossi pedig már az 55. percben érezte, hogy frissíteni kell, és Szoboszlai helyére Gazdag, Styles helyére pedig Nagy Ádám állt.
+Mivel a válogatott visszaállt, és fegyelmezetten zárta le a területeket, az angolok ötlettelen, olykor lassú adogatása veszélytelen volt. A csapat ezúttal is igazolta, mennyire képes megnehezíteni, megkeseríteni a riválisai dolgát.
+A hajrában jött a varázslat Most azonban azt is igazolta, hogy egy pillanat alatt a kapu elé tud kerülni. A Szalai helyére beálló Ádám Martin megharcolt egy labdáért, megtartotta a térfél közepén, majd tökéletesen szöktette Sallait, aki a tizenhatoson belül állítgatás nélkül jobb külsővel elrúgta a labdát Ramsdale lába mellett.
+A 77. percben Kane használható labdát kapott a szélről, kilenc méterről fejelt, a kapufáról pattant vissza a labda a mezőnybe, a center megpróbálta átvenni, de másodszorra már nem tudta, így odalett a helyzet. A 81. percben Magyarország berúgta a harmadik gólt.
+Nego fejesét még hárították a védők, a kipattanót készítette le Ádám Martin a támadást kísérő Nagy Zsolt elé, aki 17 méterről külsővel, állítgatás nélkül, pazarul lőtte ki a jobb alsó sarkot. A 29 éves felcsúti védő ennek a 11 napnak a legnagyobb felfedezettje, mert a németek ellen is eredményes volt szombaton.
+Stonest a hajrában még kiállították, a mieink nem törekedtek még jobban a gólkülönbség javítására, de magabiztosan passzolgattak, így Angliának esélye sem volt a szépítésre, miután alig volt náluk a labda. Hogy teljes legyen az angol KO, arról Gazdag Dániel gondoskodott, amikor egy nagy sprint után lazán átpörgette a labdát a kimozduló kapus felett.
+Ha Anglia nem is veszi komolyan ezt a sorozatot, mert a novemberi vb-re készül, és egy fárasztó szezon végén már a legszívesebben pihennének a klasszisai, négy gólt biztosan nem akart kapni, mert így könnyen ki is eshetnek az A divízióból. Tavaly szeptemberben Eb-selejtezőn Anglia ugyanilyen arányban verte a mieinket a Puskás Arénában, ez most egy méltó visszavágás volt.
+A csoport másik meccsén a németek 5-2-vel küldték haza az olaszokat, és ezzel feljöttek a második helyre.""",
+    """A megszokott menetrenden kívül és váratlanul nagy mértékben emelt a jegybank az irányadó rátán. A forint a hírre 395 alá erősödött az euróval szemben.
+7,25 százalékos kamattal hirdette meg a Magyar Nemzeti Bank (MNB) az egyhetes betéti tenderét – derül ki a jegybank által közzétett adatokból. Az egyhetes betét azt jelenti, hogy a bankok ezzel a rátával parkoltathatják a pénzüket egy hétig az MNB-ben. Mivel az egyhetes betéti eszköz kamata jelenleg magasabb, mint az alapkamat, valójában ez az irányadó ráta.
+A kamatemelés váratlan, mind időzítését, mind mértékét tekintve. A jegybank ugyan kommunikációja szerint nyitva tartja a lehetőségét, hogy bármikor emeljen az egyhetes betét kamatán, azon a Monetáris Tanács havi kamatdöntő ülései után szokott emelni. A cél az, hogy idővel az alapkamat és az egyhetes betét kamata újra összezárjon. A kamatemelés így a bevett menetrenden kívüli. A mértéke is nagyobb a megszokottnál, az emelés 0,5 százalékpontos, miközben a jegybank egy ideje 0,3 százalékpontos lépésekkel haladt felfelé. Legutóbb márciusban volt 0,5 százalékpontos emelés, ekkor a ráta 5,35 százalékról 5,85 százalékra nőtt.
+A Monetáris Tanács legutóbb május végén emelt az alapkamat szintjén, 5,4-ről 5,9 százalékra. Addig kell a kamatokat emelni, amíg az szükséges, hogy az inflációs célt fenntartható módon el tudjuk érni – mondta Virág Barnabás alelnök az alapkamat-emelés után. Az alelnök szerint a következő hónapokban várhatóan még tovább nő az infláció az áprilisi 9,5 százalékról, Virág elhúzódó infláció elleni harcot, a szigorúbb monetáris kondíciók tartós fenntartását ígérte.
+A forint árfolyama mindenesetre jól reagált az egyhetesbetétkamat-emelésre, az euróval szemben a napi nyitó árfolyam 397,5 környékéről 395 alá erősödött. A megelőző napokban a forint sorra döntögette a negatív árfolyamrekordokat, az euróval szemben többször 400 fölött is járt. Jelenleg a történelmi mélypont 402,96.
+""",
+    """Jövőre nem lesz "ledolgozós" hétvége
+2023-ban egyetlen szombati munkanap sem lesz.
+Jövőre kétszer (húsvétkor és karácsonykor) lesz négynapos a hétvége. Emellett négyszer lesz háromnapos hosszú hétvége, mivel május 1-én, pünkösdkor, október 23-án, és az újévkor is egy-egy hétfővel bővülnek majd a hétvégi szabadnapok - ezt Koncz Zsófia, a Technológiai és Ipari Minisztérium új parlamenti államtitkára közölte egy Facebook-bejegyzésben, hangsúlyozva, hogy a munkarendet meghatározó minisztériumuk úgy döntött, hogy 2023-ban egyetlen egynapos, "ledolgozós” hétvége sem lesz.
+Hogy mennyit ér egy munkanap, arról csak becsléseket lehet készíteni, és a statisztikusok legszívesebben erről is lebeszélnék a kísérletező kedvűeket. Nagyon leegyszerűsítve mondhatjuk azt: a GDP-t leosztva a munkanapok számával 160 milliárd forintot ér egy munkanap, de akkor még azt sem vettük figyelembe, hogy van munka azért hétvégéken is.
+"""
+]
 demo = gr.Interface(
     fn=process,
+    inputs=gr.Textbox(value=EXAMPLES[0], lines=10, label="Input text", show_label=True),
     outputs=gr.DataFrame(label="Keywords", show_label=False, max_cols=2, max_rows=10),
+    examples=EXAMPLES,
     # cache_examples=True,
 )

examples/relation.py ADDED Viewed

	@@ -0,0 +1,53 @@

+import gradio as gr
+import pandas as pd
+from examples.common import NLP
+from resources import triples
+def process(text: str) -> pd.DataFrame:
+    doc = NLP(text)
+    tuples_to_list = list()
+    tuples = triples.subject_verb_object_triples(doc)
+    if tuples:
+        tuples_to_list = list(tuples)
+    subject = ""
+    verb = ""
+    object = ""
+    if len(tuples_to_list) == 0:
+        return pd.DataFrame([["-", "-", "-"]], columns=['Subject', 'Verb', 'Object'])
+    for sub_multiple in tuples_to_list[0][0]:
+        subject += str(sub_multiple) + ", "
+    subject = subject[:-2]
+    for verb_multiple in tuples_to_list[0][1]:
+        verb += str(verb_multiple) + ", "
+    verb = verb[:-2]
+    for obj_multiple in tuples_to_list[0][2]:
+        object += str(obj_multiple) + ", "
+    object = object[:-2]
+    relation_list = [[subject, verb, object]]
+    return pd.DataFrame(relation_list, columns=['Subject', 'Verb', 'Object'])
+EXAMPLES = [
+    "Anna éppen most házat épít magának.",
+    "Noémi gulyáslevest szeret főzni, ha éhes.",
+    "Balázs jéghideg helyi ananászlevet ivott Hawaii fehér homokos partján.",
+    "Júliska fagyit árul a nyáron teljes állásban.",
+    "Einstein megmutatta a házát építés közben.",
+    "Hawking nyilatkozott egy levelet, miszerint a felfedezései az élete legizgalmasabb eseményei voltak."
+]
+demo = gr.Interface(
+    fn=process,
+    inputs=gr.Textbox(value=EXAMPLES[0], lines=10, label="Input text", show_label=True),
+    outputs=gr.DataFrame(label="Keywords", show_label=False, max_cols=3, max_rows=1),
+    examples=EXAMPLES,
+    # cache_examples=True,
+)

poetry.lock CHANGED Viewed

@@ -60,8 +60,8 @@ idna = ">=2.8"
 sniffio = ">=1.1"
 [package.extras]
-test = ["coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "contextlib2", "uvloop (<0.15)", "mock (>=4)", "uvloop (>=0.15)"]
 doc = ["packaging", "sphinx-rtd-theme", "sphinx-autodoc-typehints (>=1.2.0)"]
 trio = ["trio (>=0.16)"]
 [[package]]
@@ -92,10 +92,10 @@ optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 [package.extras]
 docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
 tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
 tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "cloudpickle"]
-dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
 [[package]]
 name = "backoff"
@@ -117,8 +117,8 @@ python-versions = ">=3.6"
 cffi = ">=1.1"
 [package.extras]
-typecheck = ["mypy"]
 tests = ["pytest (>=3.2.1,!=3.3.0)"]
 [[package]]
 name = "beautifulsoup4"
@@ -132,8 +132,8 @@ python-versions = ">=3.6.0"
 soupsieve = ">1.2"
 [package.extras]
-lxml = ["lxml"]
 html5lib = ["html5lib"]
 [[package]]
 name = "blis"
@@ -194,11 +194,11 @@ unicode_backport = ["unicodedata2"]
 [[package]]
 name = "click"
-version = "8.1.3"
 description = "Composable command line interface toolkit"
 category = "main"
 optional = false
-python-versions = ">=3.7"
 [package.dependencies]
 colorama = {version = "*", markers = "platform_system == \"Windows\""}
@@ -223,11 +223,11 @@ python-versions = ">=3.6"
 cffi = ">=1.12"
 [package.extras]
-pep8test = ["black", "flake8", "flake8-import-order", "pep8-naming"]
 docstest = ["pyenchant (>=1.6.11)", "twine (>=1.12.0)", "sphinxcontrib-spelling (>=4.0.1)"]
 sdist = ["setuptools_rust (>=0.11.4)"]
 ssh = ["bcrypt (>=3.1.5)"]
-docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx-rtd-theme"]
 test = ["pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-subtests", "pytest-xdist", "pretend", "iso8601", "pytz", "hypothesis (>=1.11.4,!=3.79.2)"]
 [[package]]
@@ -292,10 +292,10 @@ pydantic = ">=1.6.2,<1.7 || >1.7,<1.7.1 || >1.7.1,<1.7.2 || >1.7.2,<1.7.3 || >1.
 starlette = "0.19.1"
 [package.extras]
-test = ["pytest (>=6.2.4,<7.0.0)", "pytest-cov (>=2.12.0,<4.0.0)", "mypy (==0.910)", "flake8 (>=3.8.3,<4.0.0)", "black (==22.3.0)", "isort (>=5.0.6,<6.0.0)", "requests (>=2.24.0,<3.0.0)", "httpx (>=0.14.0,<0.19.0)", "email_validator (>=1.1.1,<2.0.0)", "sqlalchemy (>=1.3.18,<1.5.0)", "peewee (>=3.13.3,<4.0.0)", "databases[sqlite] (>=0.3.2,<0.6.0)", "orjson (>=3.2.1,<4.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "flask (>=1.1.2,<3.0.0)", "anyio[trio] (>=3.2.1,<4.0.0)", "types-ujson (==4.2.1)", "types-orjson (==3.6.2)", "types-dataclasses (==0.6.5)"]
-doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)", "mkdocs-markdownextradata-plugin (>=0.1.7,<0.3.0)", "typer (>=0.4.1,<0.5.0)", "pyyaml (>=5.3.1,<7.0.0)"]
 all = ["requests (>=2.24.0,<3.0.0)", "jinja2 (>=2.11.2,<4.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "itsdangerous (>=1.1.0,<3.0.0)", "pyyaml (>=5.3.1,<7.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "orjson (>=3.2.1,<4.0.0)", "email_validator (>=1.1.1,<2.0.0)", "uvicorn[standard] (>=0.12.0,<0.18.0)"]
 dev = ["python-jose[cryptography] (>=3.3.0,<4.0.0)", "passlib[bcrypt] (>=1.7.2,<2.0.0)", "autoflake (>=1.4.0,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)", "uvicorn[standard] (>=0.12.0,<0.18.0)", "pre-commit (>=2.17.0,<3.0.0)"]
 [[package]]
 name = "feedfinder2"
@@ -350,18 +350,18 @@ optional = false
 python-versions = ">=3.7"
 [package.extras]
-plot = ["matplotlib"]
 all = ["fs (>=2.2.0,<3)", "lxml (>=4.0,<5)", "zopfli (>=0.1.4)", "lz4 (>=1.7.4.2)", "matplotlib", "sympy", "skia-pathops (>=0.5.0)", "uharfbuzz (>=0.23.0)", "brotlicffi (>=0.8.0)", "scipy", "brotli (>=1.0.1)", "munkres", "unicodedata2 (>=14.0.0)", "xattr"]
-lxml = ["lxml (>=4.0,<5)"]
 interpolatable = ["scipy", "munkres"]
-ufo = ["fs (>=2.2.0,<3)"]
 pathops = ["skia-pathops (>=0.5.0)"]
-woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
-symfont = ["sympy"]
-graphite = ["lz4 (>=1.7.4.2)"]
-unicode = ["unicodedata2 (>=14.0.0)"]
 repacker = ["uharfbuzz (>=0.23.0)"]
 type1 = ["xattr"]
 [[package]]
 name = "frozenlist"
@@ -380,27 +380,27 @@ optional = false
 python-versions = ">=3.7"
 [package.extras]
-oci = ["ocifs"]
-hdfs = ["pyarrow (>=1)"]
 entrypoints = ["importlib-metadata"]
 git = ["pygit2"]
 gs = ["gcsfs"]
-s3 = ["s3fs"]
 gui = ["panel"]
-sftp = ["paramiko"]
-github = ["requests"]
-gcs = ["gcsfs"]
-fuse = ["fusepy"]
-tqdm = ["tqdm"]
-ssh = ["paramiko"]
-arrow = ["pyarrow (>=1)"]
-dropbox = ["dropboxdrivefs", "requests", "dropbox"]
-abfs = ["adlfs"]
 http = ["requests", "aiohttp"]
-adl = ["adlfs"]
 libarchive = ["libarchive-c"]
-dask = ["dask", "distributed"]
 smb = ["smbprotocol"]
 [[package]]
 name = "gradio"
@@ -439,19 +439,46 @@ optional = false
 python-versions = ">=3.6"
 [[package]]
-name = "hu-core-news-lg"
-version = "3.3.0"
-description = "Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner"
 category = "main"
 optional = false
 python-versions = "*"
 [package.dependencies]
-spacy = ">=3.3.0,<3.4.0"
 [package.source]
 type = "url"
-url = "https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl"
 [[package]]
 name = "idna"
 version = "3.3"
@@ -529,10 +556,10 @@ python-versions = ">=3.6"
 uc-micro-py = "*"
 [package.extras]
-test = ["coverage", "pytest", "pytest-cov"]
-doc = ["sphinx", "sphinx-book-theme", "myst-parser"]
 benchmark = ["pytest", "pytest-benchmark"]
 dev = ["pre-commit", "isort", "flake8", "black"]
 [[package]]
 name = "lxml"
@@ -543,10 +570,10 @@ optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
 [package.extras]
-source = ["Cython (>=0.29.7)"]
 cssselect = ["cssselect (>=0.7)"]
 html5 = ["html5lib"]
 htmlsoup = ["beautifulsoup4"]
 [[package]]
 name = "markdown-it-py"
@@ -562,14 +589,14 @@ mdit-py-plugins = {version = "*", optional = true, markers = "extra == \"plugins
 mdurl = ">=0.1,<1.0"
 [package.extras]
-rtd = ["attrs", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx-book-theme"]
 compare = ["commonmark (>=0.9.1,<0.10.0)", "markdown (>=3.3.6,<3.4.0)", "mistletoe (>=0.8.1,<0.9.0)", "mistune (>=2.0.2,<2.1.0)", "panflute (>=2.1.3,<2.2.0)"]
 profiling = ["gprof2dot"]
-code_style = ["pre-commit (==2.6)"]
 testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
-plugins = ["mdit-py-plugins"]
-linkify = ["linkify-it-py (>=1.0,<2.0)"]
-benchmarking = ["psutil", "pytest", "pytest-benchmark (>=3.2,<4.0)"]
 [[package]]
 name = "markupsafe"
@@ -610,8 +637,8 @@ python-versions = "~=3.6"
 markdown-it-py = ">=1.0.0,<3.0.0"
 [package.extras]
-rtd = ["myst-parser (>=0.14.0,<0.15.0)", "sphinx-book-theme (>=0.1.0,<0.2.0)"]
 code_style = ["pre-commit (==2.6)"]
 testing = ["coverage", "pytest (>=3.6,<4)", "pytest-cov", "pytest-regressions"]
 [[package]]
@@ -656,10 +683,10 @@ python-versions = ">=3.8"
 [package.extras]
 default = ["numpy (>=1.19)", "scipy (>=1.8)", "matplotlib (>=3.4)", "pandas (>=1.3)"]
-doc = ["sphinx (>=5)", "pydata-sphinx-theme (>=0.9)", "sphinx-gallery (>=0.10)", "numpydoc (>=1.4)", "pillow (>=9.1)", "nb2plots (>=0.6)", "texext (>=0.6.6)"]
-test = ["pytest (>=7.1)", "pytest-cov (>=3.0)", "codecov (>=2.1)"]
 developer = ["pre-commit (>=2.19)", "mypy (>=0.960)"]
 extra = ["lxml (>=4.6)", "pygraphviz (>=1.9)", "pydot (>=1.4.2)", "sympy (>=1.10)"]
 [[package]]
 name = "newspaper3k"
@@ -699,12 +726,12 @@ regex = ">=2021.8.3"
 tqdm = "*"
 [package.extras]
-plot = ["matplotlib"]
 all = ["numpy", "pyparsing", "scipy", "matplotlib", "twython", "requests", "scikit-learn", "python-crfsuite"]
-twitter = ["twython"]
-tgrep = ["pyparsing"]
-machine_learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
 corenlp = ["requests"]
 [[package]]
 name = "numpy"
@@ -768,8 +795,8 @@ pynacl = ">=1.0.1"
 six = "*"
 [package.extras]
-ed25519 = ["pynacl (>=1.0.1)", "bcrypt (>=3.1.3)"]
 all = ["pyasn1 (>=0.1.7)", "pynacl (>=1.0.1)", "bcrypt (>=3.1.3)", "invoke (>=1.3)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
 gssapi = ["pyasn1 (>=0.1.7)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
 invoke = ["invoke (>=1.3)"]
@@ -786,10 +813,10 @@ smart-open = ">=5.0.0,<6.0.0"
 typer = ">=0.3.0,<1.0.0"
 [package.extras]
-s3 = ["boto3"]
-test = ["pytest", "pytest-coverage", "mock", "typer-cli"]
 all = ["google-cloud-storage (>=1.26.0,<2.0.0)", "boto3", "pytest", "pytest-coverage", "mock", "typer-cli"]
 gcs = ["google-cloud-storage (>=1.26.0,<2.0.0)"]
 [[package]]
 name = "phonenumbers"
@@ -923,8 +950,8 @@ optional = false
 python-versions = ">=3.7"
 [package.extras]
-test = ["pytest", "pytest-cov", "pytest-flake8", "pytest-isort", "coverage"]
 doc = ["sphinx", "sphinx-rtd-theme"]
 [[package]]
 name = "python-dateutil"
@@ -987,8 +1014,8 @@ idna = ">=2.5,<4"
 urllib3 = ">=1.21.1,<1.27"
 [package.extras]
-use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 [[package]]
 name = "requests-file"
@@ -1017,10 +1044,10 @@ scipy = ">=1.3.2"
 threadpoolctl = ">=2.0.0"
 [package.extras]
-docs = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)", "memory-profiler (>=0.57.0)", "sphinx (>=4.0.1)", "sphinx-gallery (>=0.7.0)", "numpydoc (>=1.2.0)", "Pillow (>=7.1.2)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
-tests = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "pytest (>=5.0.1)", "pytest-cov (>=2.9.0)", "flake8 (>=3.8.2)", "black (>=22.3.0)", "mypy (>=0.770)", "pyamg (>=4.0.0)", "numpydoc (>=1.2.0)"]
 benchmark = ["matplotlib (>=3.1.2)", "pandas (>=1.0.5)", "memory-profiler (>=0.57.0)"]
 examples = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)"]
 [[package]]
 name = "scipy"
@@ -1075,12 +1102,12 @@ python-versions = ">=3.6,<4.0"
 [package.extras]
 all = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests"]
-http = ["requests"]
-s3 = ["boto3"]
-webhdfs = ["requests"]
 azure = ["azure-storage-blob", "azure-common", "azure-core"]
 gcs = ["google-cloud-storage"]
 test = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests", "moto[server] (==1.3.14)", "pathlib2", "responses", "paramiko", "parameterizedtestcase", "pytest", "pytest-rerunfailures"]
 [[package]]
 name = "sniffio"
@@ -1100,7 +1127,7 @@ python-versions = ">=3.6"
 [[package]]
 name = "spacy"
-version = "3.3.1"
 description = "Industrial-strength Natural Language Processing (NLP) in Python"
 category = "main"
 optional = false
@@ -1109,6 +1136,7 @@ python-versions = ">=3.6"
 [package.dependencies]
 blis = ">=0.4.0,<0.8.0"
 catalogue = ">=2.0.6,<2.1.0"
 cymem = ">=2.0.2,<2.1.0"
 jinja2 = "*"
 langcodes = ">=3.2.0,<4.0.0"
@@ -1119,36 +1147,58 @@ pathy = ">=0.3.5"
 preshed = ">=3.0.2,<3.1.0"
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<1.9.0"
 requests = ">=2.13.0,<3.0.0"
-spacy-legacy = ">=3.0.9,<3.1.0"
 spacy-loggers = ">=1.0.0,<2.0.0"
-srsly = ">=2.4.3,<3.0.0"
-thinc = ">=8.0.14,<8.1.0"
 tqdm = ">=4.38.0,<5.0.0"
 typer = ">=0.3.0,<0.5.0"
-wasabi = ">=0.9.1,<1.1.0"
 [package.extras]
-lookups = ["spacy-lookups-data (>=1.0.3,<1.1.0)"]
-transformers = ["spacy-transformers (>=1.1.2,<1.2.0)"]
 apple = ["thinc-apple-ops (>=0.0.4,<1.0.0)"]
-cuda90 = ["cupy-cuda90 (>=5.0.0b4,<11.0.0)"]
-cuda91 = ["cupy-cuda91 (>=5.0.0b4,<11.0.0)"]
-cuda92 = ["cupy-cuda92 (>=5.0.0b4,<11.0.0)"]
-cuda115 = ["cupy-cuda115 (>=5.0.0b4,<11.0.0)"]
-ko = ["natto-py (==0.9.0)"]
 cuda102 = ["cupy-cuda102 (>=5.0.0b4,<11.0.0)"]
-ja = ["sudachipy (>=0.5.2,!=0.6.1)", "sudachidict-core (>=20211220)"]
-cuda112 = ["cupy-cuda112 (>=5.0.0b4,<11.0.0)"]
-cuda113 = ["cupy-cuda113 (>=5.0.0b4,<11.0.0)"]
 cuda110 = ["cupy-cuda110 (>=5.0.0b4,<11.0.0)"]
 cuda111 = ["cupy-cuda111 (>=5.0.0b4,<11.0.0)"]
-cuda101 = ["cupy-cuda101 (>=5.0.0b4,<11.0.0)"]
-cuda100 = ["cupy-cuda100 (>=5.0.0b4,<11.0.0)"]
-th = ["pythainlp (>=2.0)"]
-cuda80 = ["cupy-cuda80 (>=5.0.0b4,<11.0.0)"]
-cuda = ["cupy (>=5.0.0b4,<11.0.0)"]
 cuda114 = ["cupy-cuda114 (>=5.0.0b4,<11.0.0)"]
 ray = ["spacy-ray (>=0.1.0,<1.0.0)"]
 [[package]]
 name = "spacy-legacy"
@@ -1169,6 +1219,34 @@ python-versions = ">=3.6"
 [package.dependencies]
 wasabi = ">=0.8.1,<1.1.0"
 [[package]]
 name = "srsly"
 version = "2.4.3"
@@ -1219,11 +1297,11 @@ spacy = ">=3.0.0"
 tqdm = ">=4.19.6"
 [package.extras]
-viz = ["matplotlib (>=3.0.0)"]
-docs = ["recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)"]
 build_and_test = ["build", "pytest (>=6.0,<7.0)", "pytest-cov", "twine (>=3.0.0)", "wheel"]
 dev = ["black", "build", "flake8 (>=3.8.0)", "mypy (>=0.900)", "recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)", "pytest (>=6.0,<7.0)", "pytest-cov", "twine (>=3.0.0)", "wheel"]
 lint_and_format = ["black", "flake8 (>=3.8.0)", "mypy (>=0.900)"]
 [[package]]
 name = "thinc"
@@ -1245,24 +1323,24 @@ srsly = ">=2.4.0,<3.0.0"
 wasabi = ">=0.8.1,<1.1.0"
 [package.extras]
-datasets = ["ml-datasets (>=0.2.0,<0.3.0)"]
-mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
-cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
-cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
-cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
-torch = ["torch (>=1.6.0)"]
 cuda112 = ["cupy-cuda112 (>=5.0.0b4)"]
 cuda113 = ["cupy-cuda113 (>=5.0.0b4)"]
-cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
-cuda115 = ["cupy-cuda115 (>=5.0.0b4)"]
-cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
-cuda = ["cupy (>=5.0.0b4)"]
 cuda114 = ["cupy-cuda114 (>=5.0.0b4)"]
 cuda80 = ["cupy-cuda80 (>=5.0.0b4)"]
 tensorflow = ["tensorflow (>=2.0.0,<2.6.0)"]
-cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
-cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
-cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
 [[package]]
 name = "threadpoolctl"
@@ -1294,6 +1372,18 @@ idna = "*"
 requests = ">=2.1.0"
 requests-file = ">=1.4"
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -1310,6 +1400,17 @@ category = "main"
 optional = false
 python-versions = ">=3.5"
 [[package]]
 name = "tqdm"
 version = "4.64.0"
@@ -1322,10 +1423,70 @@ python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
 colorama = {version = "*", markers = "platform_system == \"Windows\""}
 [package.extras]
-telegram = ["requests"]
 notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
-dev = ["py-make (>=0.1.0)", "twine", "wheel"]
 [[package]]
 name = "typer"
@@ -1339,10 +1500,10 @@ python-versions = ">=3.6"
 click = ">=7.1.1,<9.0.0"
 [package.extras]
-test = ["shellingham (>=1.3.0,<2.0.0)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "coverage (>=5.2,<6.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "mypy (==0.910)", "black (>=22.3.0,<23.0.0)", "isort (>=5.0.6,<6.0.0)"]
-doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)"]
 all = ["colorama (>=0.4.3,<0.5.0)", "shellingham (>=1.3.0,<2.0.0)"]
 dev = ["autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)"]
 [[package]]
 name = "typing-extensions"
@@ -1415,7 +1576,7 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "1.1"
 python-versions = "~3.8"
-content-hash = "f2bf888b325ef9d3f418a6cdcbd951892aeebf16eff5cbad5fc73088a0b3b36f"
 [metadata.files]
 aiohttp = [
@@ -1627,8 +1788,8 @@ charset-normalizer = [
     {file = "charset_normalizer-2.0.12-py3-none-any.whl", hash = "sha256:6881edbebdb17b39b4eaaa821b438bf6eddffb4468cf344f09f89def34a8b1df"},
 ]
 click = [
-    {file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
-    {file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
 ]
 colorama = [
     {file = "colorama-0.4.5-py2.py3-none-any.whl", hash = "sha256:854bf444933e37f5824ae7bfc1e98d5bce2ebe4160d46b5edf346a89358e99da"},
@@ -1668,7 +1829,6 @@ cycler = [
 ]
 cymem = [
     {file = "cymem-2.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:700540b68e96a7056d0691d467df2bbaaf0934a3e6fe2383669998cbee19580a"},
-    {file = "cymem-2.0.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a261f51796a2705f3900ed22b8442519a0f230f50a816fb5bd89cb9b027dc5ac"},
     {file = "cymem-2.0.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:971cf0a8437dfb4185c3049c086e463612fe849efadc0f5cc153fc81c501da7d"},
     {file = "cymem-2.0.6-cp310-cp310-win_amd64.whl", hash = "sha256:6b0d1a6b0a1296f31fa9e4b7ae5ea49394084ecc883b1ae6fec4844403c43468"},
     {file = "cymem-2.0.6-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:b8e1c18bb00800425576710468299153caad20c64ddb6819d40a6a34e21ee21c"},
@@ -1678,11 +1838,9 @@ cymem = [
     {file = "cymem-2.0.6-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd52d8a81881804625df88453611175ab7e0099b34f52204da1f6940cf2e83c9"},
     {file = "cymem-2.0.6-cp37-cp37m-win_amd64.whl", hash = "sha256:4749f220e4c06ec44eb10de13794ff0508cdc4f8eff656cf49cab2cdb3122c0c"},
     {file = "cymem-2.0.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2aa3fa467d906cd2c27fa0a2e2952dd7925f5fcc7973fab6d815ef6acb25aad8"},
-    {file = "cymem-2.0.6-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:228bd261a85d92d870ed358f263ee028ac026302304f2186827377a3895c5819"},
     {file = "cymem-2.0.6-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea535f74ab6024e7416f93de564e5c81fb7c0964b96280de66f60aeb05f0cf53"},
     {file = "cymem-2.0.6-cp38-cp38-win_amd64.whl", hash = "sha256:4f87fe087f2ae36c3e20e2b1a29d7f76a28c035372d0a97655f26223d975235a"},
     {file = "cymem-2.0.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:a93fba62fe79dbf6fc4d5b6d804a6e114b44af3ff3d40a28833ee39f21bd336b"},
-    {file = "cymem-2.0.6-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5d631239bfb07293ee444b269656308da952b6b003b12332ccb1c624dbfcda4b"},
     {file = "cymem-2.0.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04676d696596b0db3f3c5a3936bab12fb6f24278921a6622bb185e61765b2b4d"},
     {file = "cymem-2.0.6-cp39-cp39-win_amd64.whl", hash = "sha256:c59293b232b53ebb47427f16cf648e937022f489cff36c11d1d8a1f0075b6609"},
     {file = "cymem-2.0.6.tar.gz", hash = "sha256:169725b5816959d34de2545b33fee6a8021a6e08818794a426c5a4f981f17e5e"},
@@ -1789,7 +1947,11 @@ h11 = [
     {file = "h11-0.13.0-py3-none-any.whl", hash = "sha256:8ddd78563b633ca55346c8cd41ec0af27d3c79931828beffb46ce70a379e7442"},
     {file = "h11-0.13.0.tar.gz", hash = "sha256:70813c1135087a248a4d38cc0e1a0181ffab2188141a93eaf567940c3957ff06"},
 ]
-hu-core-news-lg = []
 idna = [
     {file = "idna-3.3-py3-none-any.whl", hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff"},
     {file = "idna-3.3.tar.gz", hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d"},
@@ -2267,7 +2429,6 @@ pillow = [
 ]
 preshed = [
     {file = "preshed-3.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:66a71ced487516cf81fd0431a3a843514262ae2f33e9a7688b87562258fa75d5"},
-    {file = "preshed-3.0.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9fb3d1da40abe3d99a9ee28c0df7090c1bab7c09042421d3cade7dc12e868c70"},
     {file = "preshed-3.0.6-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c98f725d8478f3ade4ab1ea00f50a92d2d9406d37276bc46fd8bab1d47452c4"},
     {file = "preshed-3.0.6-cp310-cp310-win_amd64.whl", hash = "sha256:ea8aa9610837e907e8442e79300df0a861bfdb4dcaf026a5d9642a688ad04815"},
     {file = "preshed-3.0.6-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:e03ae3eee961106a517fcd827b5a7c51f7317236b3e665c989054ab8dc381d28"},
@@ -2277,11 +2438,9 @@ preshed = [
     {file = "preshed-3.0.6-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61b2ea656cb1c38d544cc774f1c2ad1cdab23167b46b35310a7e211d4ba9c6d0"},
     {file = "preshed-3.0.6-cp37-cp37m-win_amd64.whl", hash = "sha256:87e1add41b7f6236a3ccc34788f47ab8682bc28e8a2d369089062e274494c1a0"},
     {file = "preshed-3.0.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a279c138ad1d5be02547b1545254929588414b01571fe637016367f6a1aa11de"},
-    {file = "preshed-3.0.6-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ab8b5232255ebf7ee96e3cb4f1bedaace6ae0925d1113d4ede9d44c78f088ef2"},
     {file = "preshed-3.0.6-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3af09f4cfcdaca085fd87dac8107617c4e2bb0ad1458f953841b71e9728287f5"},
     {file = "preshed-3.0.6-cp38-cp38-win_amd64.whl", hash = "sha256:f92e752a868ea2690e1b38c4b775251a145e0fce36b9bdd972539e8271b7a23a"},
     {file = "preshed-3.0.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:eaffbc71fdb8625f9aac4fe7e19e20bf318d1421ea05903bebe3e6ffef27b587"},
-    {file = "preshed-3.0.6-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9c7809491e26a41bd6e4e2e93ddf3e8989cff256c3829a7953b57c97a8268a6c"},
     {file = "preshed-3.0.6-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cfe1495fcfc7f479de840ddc4f426dbb55351e218ae5c8712c1269183a4d0060"},
     {file = "preshed-3.0.6-cp39-cp39-win_amd64.whl", hash = "sha256:92a8f49d17a63537a8beed48a049b62ef168ca07e0042a5b2bcdf178a1fb5d48"},
     {file = "preshed-3.0.6.tar.gz", hash = "sha256:fb3b7588a3a0f2f2f1bf3fe403361b2b031212b73a37025aea1df7215af3772a"},
@@ -2575,25 +2734,64 @@ soupsieve = [
     {file = "soupsieve-2.3.2.post1.tar.gz", hash = "sha256:fc53893b3da2c33de295667a0e19f078c14bf86544af307354de5fcf12a3f30d"},
 ]
 spacy = [
-    {file = "spacy-3.3.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d2e9510ad67fef328bbec01673d6e65f5670ccbb9434dfe0deaa7edffcc900a6"},
-    {file = "spacy-3.3.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:192baa97dfb90b9c59c8c5e90448284ea3810d4a9422f514f2d3eae78f97aa14"},
-    {file = "spacy-3.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5916b1e43b848680e01619963c2dd6ec0c1d99b5a5665c9b9b761f65c5adf18e"},
-    {file = "spacy-3.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:ad3c6726b92723d16c15dc7ecc48abbb6495ef7b4c30d7cf4948c1195162a272"},
-    {file = "spacy-3.3.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:ee876b2036e8500b6dd315347eb2fc0345be097806bfe6857c7347beb759169a"},
-    {file = "spacy-3.3.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b18ed499fc8d848bb9026b294dc78128028c58a73ba0ae547d42fc6d471628a8"},
-    {file = "spacy-3.3.1-cp36-cp36m-win_amd64.whl", hash = "sha256:7b58cd4e27d6ae29e23b47e9ba6b8ca4e02fc69d65b57b2a9c7072c3a187b4ba"},
-    {file = "spacy-3.3.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:ae06825f2e349e035fae602e2a48ba1453b8eed9238144e36e1b09a741744c6e"},
-    {file = "spacy-3.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5fd1e3abab9df2e113d29d1bcf16700b68b125504a2b477b49eb7b6c7b5225ea"},
-    {file = "spacy-3.3.1-cp37-cp37m-win_amd64.whl", hash = "sha256:eea5d066f472261a37e43aa6b5002af5a9232da66a83ea5b7b590b905f00a5bb"},
-    {file = "spacy-3.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:dfbd15084f7b49fed1160999ef2986f2769cbcc50ab240bf026fa82337500ace"},
-    {file = "spacy-3.3.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:618f3cd983aa37bb448bdd554e1abf1d82106fc3163959786a2ca1fe01dc4f1b"},
-    {file = "spacy-3.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1581ba49a6f687a5e0ad8291129793af8e3c4bb02ffbc8857b34acfa7ed3049f"},
-    {file = "spacy-3.3.1-cp38-cp38-win_amd64.whl", hash = "sha256:b652cc9fcd1e07f733a5de9c89fef300852d0129240f0eb11513d03bba470609"},
-    {file = "spacy-3.3.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9af33d170d8a697f50556b612be5468fdd4134759846c54415f8fc9f87ca1c25"},
-    {file = "spacy-3.3.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6971e37234395c6157a514ef1c1f15d27f91042df4e7fc8aefcc6e0d79a3cb8b"},
-    {file = "spacy-3.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:747a99fd2712e60325ff00b6b3131e4aef4c67b2f4433b9ffbd44833889a313d"},
-    {file = "spacy-3.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:787bd8546ae4feed088fb712f3baf5239197cedfe9e1ce9d8906b3e3ef2f10bc"},
-    {file = "spacy-3.3.1.tar.gz", hash = "sha256:7f87dbdb104d851ae6ba5fd3a76a2e14e22e048135903e98baf08571a3aa81c0"},
 ]
 spacy-legacy = [
     {file = "spacy-legacy-3.0.9.tar.gz", hash = "sha256:4f7dcbc4e6c8e8cb4eadbb009f9c0a1a2a67442e0032c8d6776c9470c3759903"},
@@ -2603,6 +2801,10 @@ spacy-loggers = [
     {file = "spacy-loggers-1.0.2.tar.gz", hash = "sha256:e75d44f4cf99e6763d7132ca7c8c420e0a92790222a08bc8eb9e24ea2c13536e"},
     {file = "spacy_loggers-1.0.2-py3-none-any.whl", hash = "sha256:d48c9313a577ad1818da961cf6db71a73fd1e556ae47e6e68d7e28b541d11e18"},
 ]
 srsly = [
     {file = "srsly-2.4.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2d0236feafe3805b384532221596e6749a54d0ff10ba022b333dc1de7aa1b2f7"},
     {file = "srsly-2.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f96af9fde9f58d5923091fa723fa0fed58a83781b98e143a5d1fac5e738b9f0d"},
@@ -2664,6 +2866,41 @@ tldextract = [
     {file = "tldextract-3.3.0-py3-none-any.whl", hash = "sha256:5d88321b1b528ebb8f678c72ab023f37caf6381f6af9576b4e60fd266cff178c"},
     {file = "tldextract-3.3.0.tar.gz", hash = "sha256:adcd24abf21ce3450417cd5a00f23b7e57554ce8ae827334dd12bfcbb6274cf1"},
 ]
 tomli = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
@@ -2672,10 +2909,35 @@ toolz = [
     {file = "toolz-0.11.2-py3-none-any.whl", hash = "sha256:a5700ce83414c64514d82d60bcda8aabfde092d1c1a8663f9200c07fdcc6da8f"},
     {file = "toolz-0.11.2.tar.gz", hash = "sha256:6b312d5e15138552f1bda8a4e66c30e236c831b612b2bf0005f8a1df10a4bc33"},
 ]
 tqdm = [
     {file = "tqdm-4.64.0-py2.py3-none-any.whl", hash = "sha256:74a2cdefe14d11442cedf3ba4e21a3b84ff9a2dbdc6cfae2c34addb2a14a5ea6"},
     {file = "tqdm-4.64.0.tar.gz", hash = "sha256:40be55d30e200777a307a7585aee69e4eabb46b4ec6a4b4a5f2d9f11e7d5408d"},
 ]
 typer = [
     {file = "typer-0.4.1-py3-none-any.whl", hash = "sha256:e8467f0ebac0c81366c2168d6ad9f888efdfb6d4e1d3d5b4a004f46fa444b5c3"},
     {file = "typer-0.4.1.tar.gz", hash = "sha256:5646aef0d936b2c761a10393f0384ee6b5c7fe0bb3e5cd710b17134ca1d99cff"},

 sniffio = ">=1.1"
 [package.extras]
 doc = ["packaging", "sphinx-rtd-theme", "sphinx-autodoc-typehints (>=1.2.0)"]
+test = ["coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "contextlib2", "uvloop (<0.15)", "mock (>=4)", "uvloop (>=0.15)"]
 trio = ["trio (>=0.16)"]
 [[package]]
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 [package.extras]
+dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
 docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
 tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
 tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "cloudpickle"]
 [[package]]
 name = "backoff"
 cffi = ">=1.1"
 [package.extras]
 tests = ["pytest (>=3.2.1,!=3.3.0)"]
+typecheck = ["mypy"]
 [[package]]
 name = "beautifulsoup4"
 soupsieve = ">1.2"
 [package.extras]
 html5lib = ["html5lib"]
+lxml = ["lxml"]
 [[package]]
 name = "blis"
 [[package]]
 name = "click"
+version = "8.0.4"
 description = "Composable command line interface toolkit"
 category = "main"
 optional = false
+python-versions = ">=3.6"
 [package.dependencies]
 colorama = {version = "*", markers = "platform_system == \"Windows\""}
 cffi = ">=1.12"
 [package.extras]
+docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx-rtd-theme"]
 docstest = ["pyenchant (>=1.6.11)", "twine (>=1.12.0)", "sphinxcontrib-spelling (>=4.0.1)"]
+pep8test = ["black", "flake8", "flake8-import-order", "pep8-naming"]
 sdist = ["setuptools_rust (>=0.11.4)"]
 ssh = ["bcrypt (>=3.1.5)"]
 test = ["pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-subtests", "pytest-xdist", "pretend", "iso8601", "pytz", "hypothesis (>=1.11.4,!=3.79.2)"]
 [[package]]
 starlette = "0.19.1"
 [package.extras]
 all = ["requests (>=2.24.0,<3.0.0)", "jinja2 (>=2.11.2,<4.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "itsdangerous (>=1.1.0,<3.0.0)", "pyyaml (>=5.3.1,<7.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "orjson (>=3.2.1,<4.0.0)", "email_validator (>=1.1.1,<2.0.0)", "uvicorn[standard] (>=0.12.0,<0.18.0)"]
 dev = ["python-jose[cryptography] (>=3.3.0,<4.0.0)", "passlib[bcrypt] (>=1.7.2,<2.0.0)", "autoflake (>=1.4.0,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)", "uvicorn[standard] (>=0.12.0,<0.18.0)", "pre-commit (>=2.17.0,<3.0.0)"]
+doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)", "mkdocs-markdownextradata-plugin (>=0.1.7,<0.3.0)", "typer (>=0.4.1,<0.5.0)", "pyyaml (>=5.3.1,<7.0.0)"]
+test = ["pytest (>=6.2.4,<7.0.0)", "pytest-cov (>=2.12.0,<4.0.0)", "mypy (==0.910)", "flake8 (>=3.8.3,<4.0.0)", "black (==22.3.0)", "isort (>=5.0.6,<6.0.0)", "requests (>=2.24.0,<3.0.0)", "httpx (>=0.14.0,<0.19.0)", "email_validator (>=1.1.1,<2.0.0)", "sqlalchemy (>=1.3.18,<1.5.0)", "peewee (>=3.13.3,<4.0.0)", "databases[sqlite] (>=0.3.2,<0.6.0)", "orjson (>=3.2.1,<4.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "flask (>=1.1.2,<3.0.0)", "anyio[trio] (>=3.2.1,<4.0.0)", "types-ujson (==4.2.1)", "types-orjson (==3.6.2)", "types-dataclasses (==0.6.5)"]
 [[package]]
 name = "feedfinder2"
 python-versions = ">=3.7"
 [package.extras]
 all = ["fs (>=2.2.0,<3)", "lxml (>=4.0,<5)", "zopfli (>=0.1.4)", "lz4 (>=1.7.4.2)", "matplotlib", "sympy", "skia-pathops (>=0.5.0)", "uharfbuzz (>=0.23.0)", "brotlicffi (>=0.8.0)", "scipy", "brotli (>=1.0.1)", "munkres", "unicodedata2 (>=14.0.0)", "xattr"]
+graphite = ["lz4 (>=1.7.4.2)"]
 interpolatable = ["scipy", "munkres"]
+lxml = ["lxml (>=4.0,<5)"]
 pathops = ["skia-pathops (>=0.5.0)"]
+plot = ["matplotlib"]
 repacker = ["uharfbuzz (>=0.23.0)"]
+symfont = ["sympy"]
 type1 = ["xattr"]
+ufo = ["fs (>=2.2.0,<3)"]
+unicode = ["unicodedata2 (>=14.0.0)"]
+woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
 [[package]]
 name = "frozenlist"
 python-versions = ">=3.7"
 [package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+dropbox = ["dropboxdrivefs", "requests", "dropbox"]
 entrypoints = ["importlib-metadata"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
 git = ["pygit2"]
+github = ["requests"]
 gs = ["gcsfs"]
 gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
 http = ["requests", "aiohttp"]
 libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
 smb = ["smbprotocol"]
+ssh = ["paramiko"]
+tqdm = ["tqdm"]
 [[package]]
 name = "gradio"
 python-versions = ">=3.6"
 [[package]]
+name = "hu-core-news-trf"
+version = "3.2.2"
+description = "Hungarian transformer pipeline (huBert) for HuSpaCy. Components: transformer, senter, tagger, morphologizer, lemmatizer, parser, ner"
 category = "main"
 optional = false
 python-versions = "*"
 [package.dependencies]
+spacy = ">=3.2.4,<3.3.0"
+spacy-experimental = "0.4.0"
+spacy-transformers = ">=1.1.4,<1.2.0"
 [package.source]
 type = "url"
+url = "https://huggingface.co/huspacy/hu_core_news_trf/resolve/main/hu_core_news_trf-any-py3-none-any.whl"
+[[package]]
+name = "huggingface-hub"
+version = "0.8.1"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+[package.dependencies]
+filelock = "*"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = "*"
+typing-extensions = ">=3.7.4.3"
+[package.extras]
+all = ["pytest", "pytest-cov", "datasets", "soundfile", "black (>=22.0,<23.0)", "isort (>=5.5.4)", "flake8 (>=3.8.3)"]
+dev = ["pytest", "pytest-cov", "datasets", "soundfile", "black (>=22.0,<23.0)", "isort (>=5.5.4)", "flake8 (>=3.8.3)"]
+fastai = ["toml", "fastai (>=2.4)", "fastcore (>=1.3.27)"]
+quality = ["black (>=22.0,<23.0)", "isort (>=5.5.4)", "flake8 (>=3.8.3)"]
+tensorflow = ["tensorflow", "pydot", "graphviz"]
+testing = ["pytest", "pytest-cov", "datasets", "soundfile"]
+torch = ["torch"]
 [[package]]
 name = "idna"
 version = "3.3"
 uc-micro-py = "*"
 [package.extras]
 benchmark = ["pytest", "pytest-benchmark"]
 dev = ["pre-commit", "isort", "flake8", "black"]
+doc = ["sphinx", "sphinx-book-theme", "myst-parser"]
+test = ["coverage", "pytest", "pytest-cov"]
 [[package]]
 name = "lxml"
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
 [package.extras]
 cssselect = ["cssselect (>=0.7)"]
 html5 = ["html5lib"]
 htmlsoup = ["beautifulsoup4"]
+source = ["Cython (>=0.29.7)"]
 [[package]]
 name = "markdown-it-py"
 mdurl = ">=0.1,<1.0"
 [package.extras]
+benchmarking = ["psutil", "pytest", "pytest-benchmark (>=3.2,<4.0)"]
+code_style = ["pre-commit (==2.6)"]
 compare = ["commonmark (>=0.9.1,<0.10.0)", "markdown (>=3.3.6,<3.4.0)", "mistletoe (>=0.8.1,<0.9.0)", "mistune (>=2.0.2,<2.1.0)", "panflute (>=2.1.3,<2.2.0)"]
+linkify = ["linkify-it-py (>=1.0,<2.0)"]
+plugins = ["mdit-py-plugins"]
 profiling = ["gprof2dot"]
+rtd = ["attrs", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx-book-theme"]
 testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
 [[package]]
 name = "markupsafe"
 markdown-it-py = ">=1.0.0,<3.0.0"
 [package.extras]
 code_style = ["pre-commit (==2.6)"]
+rtd = ["myst-parser (>=0.14.0,<0.15.0)", "sphinx-book-theme (>=0.1.0,<0.2.0)"]
 testing = ["coverage", "pytest (>=3.6,<4)", "pytest-cov", "pytest-regressions"]
 [[package]]
 [package.extras]
 default = ["numpy (>=1.19)", "scipy (>=1.8)", "matplotlib (>=3.4)", "pandas (>=1.3)"]
 developer = ["pre-commit (>=2.19)", "mypy (>=0.960)"]
+doc = ["sphinx (>=5)", "pydata-sphinx-theme (>=0.9)", "sphinx-gallery (>=0.10)", "numpydoc (>=1.4)", "pillow (>=9.1)", "nb2plots (>=0.6)", "texext (>=0.6.6)"]
 extra = ["lxml (>=4.6)", "pygraphviz (>=1.9)", "pydot (>=1.4.2)", "sympy (>=1.10)"]
+test = ["pytest (>=7.1)", "pytest-cov (>=3.0)", "codecov (>=2.1)"]
 [[package]]
 name = "newspaper3k"
 tqdm = "*"
 [package.extras]
 all = ["numpy", "pyparsing", "scipy", "matplotlib", "twython", "requests", "scikit-learn", "python-crfsuite"]
 corenlp = ["requests"]
+machine_learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
+plot = ["matplotlib"]
+tgrep = ["pyparsing"]
+twitter = ["twython"]
 [[package]]
 name = "numpy"
 six = "*"
 [package.extras]
 all = ["pyasn1 (>=0.1.7)", "pynacl (>=1.0.1)", "bcrypt (>=3.1.3)", "invoke (>=1.3)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
+ed25519 = ["pynacl (>=1.0.1)", "bcrypt (>=3.1.3)"]
 gssapi = ["pyasn1 (>=0.1.7)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
 invoke = ["invoke (>=1.3)"]
 typer = ">=0.3.0,<1.0.0"
 [package.extras]
 all = ["google-cloud-storage (>=1.26.0,<2.0.0)", "boto3", "pytest", "pytest-coverage", "mock", "typer-cli"]
 gcs = ["google-cloud-storage (>=1.26.0,<2.0.0)"]
+s3 = ["boto3"]
+test = ["pytest", "pytest-coverage", "mock", "typer-cli"]
 [[package]]
 name = "phonenumbers"
 python-versions = ">=3.7"
 [package.extras]
 doc = ["sphinx", "sphinx-rtd-theme"]
+test = ["pytest", "pytest-cov", "pytest-flake8", "pytest-isort", "coverage"]
 [[package]]
 name = "python-dateutil"
 urllib3 = ">=1.21.1,<1.27"
 [package.extras]
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
 [[package]]
 name = "requests-file"
 threadpoolctl = ">=2.0.0"
 [package.extras]
 benchmark = ["matplotlib (>=3.1.2)", "pandas (>=1.0.5)", "memory-profiler (>=0.57.0)"]
+docs = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)", "memory-profiler (>=0.57.0)", "sphinx (>=4.0.1)", "sphinx-gallery (>=0.7.0)", "numpydoc (>=1.2.0)", "Pillow (>=7.1.2)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
 examples = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)"]
+tests = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "pytest (>=5.0.1)", "pytest-cov (>=2.9.0)", "flake8 (>=3.8.2)", "black (>=22.3.0)", "mypy (>=0.770)", "pyamg (>=4.0.0)", "numpydoc (>=1.2.0)"]
 [[package]]
 name = "scipy"
 [package.extras]
 all = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests"]
 azure = ["azure-storage-blob", "azure-common", "azure-core"]
 gcs = ["google-cloud-storage"]
+http = ["requests"]
+s3 = ["boto3"]
 test = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests", "moto[server] (==1.3.14)", "pathlib2", "responses", "paramiko", "parameterizedtestcase", "pytest", "pytest-rerunfailures"]
+webhdfs = ["requests"]
 [[package]]
 name = "sniffio"
 [[package]]
 name = "spacy"
+version = "3.2.4"
 description = "Industrial-strength Natural Language Processing (NLP) in Python"
 category = "main"
 optional = false
 [package.dependencies]
 blis = ">=0.4.0,<0.8.0"
 catalogue = ">=2.0.6,<2.1.0"
+click = "<8.1.0"
 cymem = ">=2.0.2,<2.1.0"
 jinja2 = "*"
 langcodes = ">=3.2.0,<4.0.0"
 preshed = ">=3.0.2,<3.1.0"
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<1.9.0"
 requests = ">=2.13.0,<3.0.0"
+spacy-legacy = ">=3.0.8,<3.1.0"
 spacy-loggers = ">=1.0.0,<2.0.0"
+srsly = ">=2.4.1,<3.0.0"
+thinc = ">=8.0.12,<8.1.0"
 tqdm = ">=4.38.0,<5.0.0"
 typer = ">=0.3.0,<0.5.0"
+wasabi = ">=0.8.1,<1.1.0"
 [package.extras]
 apple = ["thinc-apple-ops (>=0.0.4,<1.0.0)"]
+cuda = ["cupy (>=5.0.0b4,<11.0.0)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4,<11.0.0)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4,<11.0.0)"]
 cuda102 = ["cupy-cuda102 (>=5.0.0b4,<11.0.0)"]
 cuda110 = ["cupy-cuda110 (>=5.0.0b4,<11.0.0)"]
 cuda111 = ["cupy-cuda111 (>=5.0.0b4,<11.0.0)"]
+cuda112 = ["cupy-cuda112 (>=5.0.0b4,<11.0.0)"]
+cuda113 = ["cupy-cuda113 (>=5.0.0b4,<11.0.0)"]
 cuda114 = ["cupy-cuda114 (>=5.0.0b4,<11.0.0)"]
+cuda115 = ["cupy-cuda115 (>=5.0.0b4,<11.0.0)"]
+cuda80 = ["cupy-cuda80 (>=5.0.0b4,<11.0.0)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4,<11.0.0)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4,<11.0.0)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4,<11.0.0)"]
+ja = ["sudachipy (>=0.5.2,!=0.6.1)", "sudachidict-core (>=20211220)"]
+ko = ["natto-py (==0.9.0)"]
+lookups = ["spacy-lookups-data (>=1.0.3,<1.1.0)"]
 ray = ["spacy-ray (>=0.1.0,<1.0.0)"]
+th = ["pythainlp (>=2.0)"]
+transformers = ["spacy-transformers (>=1.1.2,<1.2.0)"]
+[[package]]
+name = "spacy-alignments"
+version = "0.8.5"
+description = "A spaCy package for the Rust tokenizations library"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+[[package]]
+name = "spacy-experimental"
+version = "0.4.0"
+description = "Cutting-edge experimental spaCy components and features"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+[package.dependencies]
+spacy = ">=3.2.0,<3.3.0"
+[package.extras]
+torch = ["torch (>=1.5.0)"]
 [[package]]
 name = "spacy-legacy"
 [package.dependencies]
 wasabi = ">=0.8.1,<1.1.0"
+[[package]]
+name = "spacy-transformers"
+version = "1.1.6"
+description = "spaCy pipelines for pre-trained BERT and other transformers"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+[package.dependencies]
+spacy = ">=3.1.3,<4.0.0"
+spacy-alignments = ">=0.7.2,<1.0.0"
+srsly = ">=2.4.0,<3.0.0"
+torch = ">=1.6.0"
+transformers = ">=3.4.0,<4.20.0"
+[package.extras]
+cuda = ["cupy (>=5.0.0b4)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
+cuda112 = ["cupy-cuda112 (>=5.0.0b4)"]
+cuda80 = ["cupy-cuda80 (>=5.0.0b4)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
 [[package]]
 name = "srsly"
 version = "2.4.3"
 tqdm = ">=4.19.6"
 [package.extras]
 build_and_test = ["build", "pytest (>=6.0,<7.0)", "pytest-cov", "twine (>=3.0.0)", "wheel"]
 dev = ["black", "build", "flake8 (>=3.8.0)", "mypy (>=0.900)", "recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)", "pytest (>=6.0,<7.0)", "pytest-cov", "twine (>=3.0.0)", "wheel"]
+docs = ["recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)"]
 lint_and_format = ["black", "flake8 (>=3.8.0)", "mypy (>=0.900)"]
+viz = ["matplotlib (>=3.0.0)"]
 [[package]]
 name = "thinc"
 wasabi = ">=0.8.1,<1.1.0"
 [package.extras]
+cuda = ["cupy (>=5.0.0b4)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
 cuda112 = ["cupy-cuda112 (>=5.0.0b4)"]
 cuda113 = ["cupy-cuda113 (>=5.0.0b4)"]
 cuda114 = ["cupy-cuda114 (>=5.0.0b4)"]
+cuda115 = ["cupy-cuda115 (>=5.0.0b4)"]
 cuda80 = ["cupy-cuda80 (>=5.0.0b4)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
+datasets = ["ml-datasets (>=0.2.0,<0.3.0)"]
+mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
 tensorflow = ["tensorflow (>=2.0.0,<2.6.0)"]
+torch = ["torch (>=1.6.0)"]
 [[package]]
 name = "threadpoolctl"
 requests = ">=2.1.0"
 requests-file = ">=1.4"
+[[package]]
+name = "tokenizers"
+version = "0.12.1"
+description = "Fast and Customizable Tokenizers"
+category = "main"
+optional = false
+python-versions = "*"
+[package.extras]
+docs = ["sphinx", "sphinx-rtd-theme", "setuptools-rust"]
+testing = ["pytest", "requests", "numpy", "datasets"]
 [[package]]
 name = "tomli"
 version = "2.0.1"
 optional = false
 python-versions = ">=3.5"
+[[package]]
+name = "torch"
+version = "1.11.0"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+[package.dependencies]
+typing-extensions = "*"
 [[package]]
 name = "tqdm"
 version = "4.64.0"
 colorama = {version = "*", markers = "platform_system == \"Windows\""}
 [package.extras]
+dev = ["py-make (>=0.1.0)", "twine", "wheel"]
 notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
+telegram = ["requests"]
+[[package]]
+name = "transformers"
+version = "4.19.4"
+description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+[package.dependencies]
+filelock = "*"
+huggingface-hub = ">=0.1.0,<1.0"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pyyaml = ">=5.1"
+regex = "!=2019.12.17"
+requests = "*"
+tokenizers = ">=0.11.1,<0.11.3 || >0.11.3,<0.13"
+tqdm = ">=4.27"
+[package.extras]
+all = ["tensorflow (>=2.3)", "onnxconverter-common", "tf2onnx", "torch (>=1.0)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "flax (>=0.3.5)", "optax (>=0.0.8)", "sentencepiece (>=0.1.91,!=0.1.92)", "protobuf (<=3.20.1)", "tokenizers (>=0.11.1,!=0.11.3,<0.13)", "torchaudio", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer", "pillow", "optuna", "ray", "sigopt", "timm", "codecarbon (==1.2.0)"]
+audio = ["librosa", "pyctcdecode (>=0.3.0)", "phonemizer"]
+codecarbon = ["codecarbon (==1.2.0)"]
+deepspeed = ["deepspeed (>=0.6.4)"]
+deepspeed-testing = ["deepspeed (>=0.6.4)", "pytest", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets", "pytest-timeout", "black (>=22.0,<23.0)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score", "nltk", "GitPython (<3.1.19)", "hf-doc-builder (>=0.3.0)", "protobuf (<=3.20.1)", "sacremoses", "rjieba", "faiss-cpu", "cookiecutter (==1.7.3)", "optuna"]
+dev = ["tensorflow (>=2.3)", "onnxconverter-common", "tf2onnx", "torch (>=1.0)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "flax (>=0.3.5)", "optax (>=0.0.8)", "sentencepiece (>=0.1.91,!=0.1.92)", "protobuf (<=3.20.1)", "tokenizers (>=0.11.1,!=0.11.3,<0.13)", "torchaudio", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer", "pillow", "optuna", "ray", "sigopt", "timm", "codecarbon (==1.2.0)", "pytest", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets", "pytest-timeout", "black (>=22.0,<23.0)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score", "nltk", "GitPython (<3.1.19)", "hf-doc-builder (>=0.3.0)", "sacremoses", "rjieba", "faiss-cpu", "cookiecutter (==1.7.3)", "isort (>=5.5.4)", "flake8 (>=3.8.3)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "unidic-lite (>=1.0.7)", "unidic (>=1.0.2)", "hf-doc-builder", "scikit-learn"]
+dev-tensorflow = ["pytest", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets", "pytest-timeout", "black (>=22.0,<23.0)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score", "nltk", "GitPython (<3.1.19)", "hf-doc-builder (>=0.3.0)", "protobuf (<=3.20.1)", "sacremoses", "rjieba", "faiss-cpu", "cookiecutter (==1.7.3)", "tensorflow (>=2.3)", "onnxconverter-common", "tf2onnx", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.13)", "pillow", "isort (>=5.5.4)", "flake8 (>=3.8.3)", "hf-doc-builder", "scikit-learn", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer"]
+dev-torch = ["pytest", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets", "pytest-timeout", "black (>=22.0,<23.0)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score", "nltk", "GitPython (<3.1.19)", "hf-doc-builder (>=0.3.0)", "protobuf (<=3.20.1)", "sacremoses", "rjieba", "faiss-cpu", "cookiecutter (==1.7.3)", "torch (>=1.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.13)", "torchaudio", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer", "pillow", "optuna", "ray", "sigopt", "timm", "codecarbon (==1.2.0)", "isort (>=5.5.4)", "flake8 (>=3.8.3)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "unidic-lite (>=1.0.7)", "unidic (>=1.0.2)", "hf-doc-builder", "scikit-learn", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+docs = ["tensorflow (>=2.3)", "onnxconverter-common", "tf2onnx", "torch (>=1.0)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "flax (>=0.3.5)", "optax (>=0.0.8)", "sentencepiece (>=0.1.91,!=0.1.92)", "protobuf (<=3.20.1)", "tokenizers (>=0.11.1,!=0.11.3,<0.13)", "torchaudio", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer", "pillow", "optuna", "ray", "sigopt", "timm", "codecarbon (==1.2.0)", "hf-doc-builder"]
+docs_specific = ["hf-doc-builder"]
+fairscale = ["fairscale (>0.3)"]
+flax = ["jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "flax (>=0.3.5)", "optax (>=0.0.8)"]
+flax-speech = ["librosa", "pyctcdecode (>=0.3.0)", "phonemizer"]
+ftfy = ["ftfy"]
+integrations = ["optuna", "ray", "sigopt"]
+ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "unidic-lite (>=1.0.7)", "unidic (>=1.0.2)"]
+modelcreation = ["cookiecutter (==1.7.3)"]
+onnx = ["onnxconverter-common", "tf2onnx", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+optuna = ["optuna"]
+quality = ["black (>=22.0,<23.0)", "isort (>=5.5.4)", "flake8 (>=3.8.3)", "GitPython (<3.1.19)", "hf-doc-builder (>=0.3.0)"]
+ray = ["ray"]
+retrieval = ["faiss-cpu", "datasets"]
+sagemaker = ["sagemaker (>=2.31.0)"]
+sentencepiece = ["sentencepiece (>=0.1.91,!=0.1.92)", "protobuf (<=3.20.1)"]
+serving = ["pydantic", "uvicorn", "fastapi", "starlette"]
+sigopt = ["sigopt"]
+sklearn = ["scikit-learn"]
+speech = ["torchaudio", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer"]
+testing = ["pytest", "pytest-xdist", "timeout-decorator", "parameterized", "psutil", "datasets", "pytest-timeout", "black (>=22.0,<23.0)", "sacrebleu (>=1.4.12,<2.0.0)", "rouge-score", "nltk", "GitPython (<3.1.19)", "hf-doc-builder (>=0.3.0)", "protobuf (<=3.20.1)", "sacremoses", "rjieba", "faiss-cpu", "cookiecutter (==1.7.3)"]
+tf = ["tensorflow (>=2.3)", "onnxconverter-common", "tf2onnx"]
+tf-cpu = ["tensorflow-cpu (>=2.3)", "onnxconverter-common", "tf2onnx"]
+tf-speech = ["librosa", "pyctcdecode (>=0.3.0)", "phonemizer"]
+timm = ["timm"]
+tokenizers = ["tokenizers (>=0.11.1,!=0.11.3,<0.13)"]
+torch = ["torch (>=1.0)"]
+torch-speech = ["torchaudio", "librosa", "pyctcdecode (>=0.3.0)", "phonemizer"]
+torchhub = ["filelock", "huggingface-hub (>=0.1.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf (<=3.20.1)", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.0)", "tokenizers (>=0.11.1,!=0.11.3,<0.13)", "tqdm (>=4.27)"]
+vision = ["pillow"]
 [[package]]
 name = "typer"
 click = ">=7.1.1,<9.0.0"
 [package.extras]
 all = ["colorama (>=0.4.3,<0.5.0)", "shellingham (>=1.3.0,<2.0.0)"]
 dev = ["autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)"]
+doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)"]
+test = ["shellingham (>=1.3.0,<2.0.0)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "coverage (>=5.2,<6.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "mypy (==0.910)", "black (>=22.3.0,<23.0.0)", "isort (>=5.0.6,<6.0.0)"]
 [[package]]
 name = "typing-extensions"
 [metadata]
 lock-version = "1.1"
 python-versions = "~3.8"
+content-hash = "6eddc3d82625c70609c7d662f96be93f68188162ab16c1b708812a1ce1bcc64f"
 [metadata.files]
 aiohttp = [
     {file = "charset_normalizer-2.0.12-py3-none-any.whl", hash = "sha256:6881edbebdb17b39b4eaaa821b438bf6eddffb4468cf344f09f89def34a8b1df"},
 ]
 click = [
+    {file = "click-8.0.4-py3-none-any.whl", hash = "sha256:6a7a62563bbfabfda3a38f3023a1db4a35978c0abd76f6c9605ecd6554d6d9b1"},
+    {file = "click-8.0.4.tar.gz", hash = "sha256:8458d7b1287c5fb128c90e23381cf99dcde74beaf6c7ff6384ce84d6fe090adb"},
 ]
 colorama = [
     {file = "colorama-0.4.5-py2.py3-none-any.whl", hash = "sha256:854bf444933e37f5824ae7bfc1e98d5bce2ebe4160d46b5edf346a89358e99da"},
 ]
 cymem = [
     {file = "cymem-2.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:700540b68e96a7056d0691d467df2bbaaf0934a3e6fe2383669998cbee19580a"},
     {file = "cymem-2.0.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:971cf0a8437dfb4185c3049c086e463612fe849efadc0f5cc153fc81c501da7d"},
     {file = "cymem-2.0.6-cp310-cp310-win_amd64.whl", hash = "sha256:6b0d1a6b0a1296f31fa9e4b7ae5ea49394084ecc883b1ae6fec4844403c43468"},
     {file = "cymem-2.0.6-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:b8e1c18bb00800425576710468299153caad20c64ddb6819d40a6a34e21ee21c"},
     {file = "cymem-2.0.6-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd52d8a81881804625df88453611175ab7e0099b34f52204da1f6940cf2e83c9"},
     {file = "cymem-2.0.6-cp37-cp37m-win_amd64.whl", hash = "sha256:4749f220e4c06ec44eb10de13794ff0508cdc4f8eff656cf49cab2cdb3122c0c"},
     {file = "cymem-2.0.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2aa3fa467d906cd2c27fa0a2e2952dd7925f5fcc7973fab6d815ef6acb25aad8"},
     {file = "cymem-2.0.6-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea535f74ab6024e7416f93de564e5c81fb7c0964b96280de66f60aeb05f0cf53"},
     {file = "cymem-2.0.6-cp38-cp38-win_amd64.whl", hash = "sha256:4f87fe087f2ae36c3e20e2b1a29d7f76a28c035372d0a97655f26223d975235a"},
     {file = "cymem-2.0.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:a93fba62fe79dbf6fc4d5b6d804a6e114b44af3ff3d40a28833ee39f21bd336b"},
     {file = "cymem-2.0.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04676d696596b0db3f3c5a3936bab12fb6f24278921a6622bb185e61765b2b4d"},
     {file = "cymem-2.0.6-cp39-cp39-win_amd64.whl", hash = "sha256:c59293b232b53ebb47427f16cf648e937022f489cff36c11d1d8a1f0075b6609"},
     {file = "cymem-2.0.6.tar.gz", hash = "sha256:169725b5816959d34de2545b33fee6a8021a6e08818794a426c5a4f981f17e5e"},
     {file = "h11-0.13.0-py3-none-any.whl", hash = "sha256:8ddd78563b633ca55346c8cd41ec0af27d3c79931828beffb46ce70a379e7442"},
     {file = "h11-0.13.0.tar.gz", hash = "sha256:70813c1135087a248a4d38cc0e1a0181ffab2188141a93eaf567940c3957ff06"},
 ]
+hu-core-news-trf = []
+huggingface-hub = [
+    {file = "huggingface_hub-0.8.1-py3-none-any.whl", hash = "sha256:a11fb8d696a26f927833d46b7633105fd864fd92a2beb1140cbf1b2f703dedb3"},
+    {file = "huggingface_hub-0.8.1.tar.gz", hash = "sha256:75c70797da54b849f06c2cbf7ba2217250ee217230b9f65547d5db3c5bd84bb5"},
+]
 idna = [
     {file = "idna-3.3-py3-none-any.whl", hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff"},
     {file = "idna-3.3.tar.gz", hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d"},
 ]
 preshed = [
     {file = "preshed-3.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:66a71ced487516cf81fd0431a3a843514262ae2f33e9a7688b87562258fa75d5"},
     {file = "preshed-3.0.6-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c98f725d8478f3ade4ab1ea00f50a92d2d9406d37276bc46fd8bab1d47452c4"},
     {file = "preshed-3.0.6-cp310-cp310-win_amd64.whl", hash = "sha256:ea8aa9610837e907e8442e79300df0a861bfdb4dcaf026a5d9642a688ad04815"},
     {file = "preshed-3.0.6-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:e03ae3eee961106a517fcd827b5a7c51f7317236b3e665c989054ab8dc381d28"},
     {file = "preshed-3.0.6-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61b2ea656cb1c38d544cc774f1c2ad1cdab23167b46b35310a7e211d4ba9c6d0"},
     {file = "preshed-3.0.6-cp37-cp37m-win_amd64.whl", hash = "sha256:87e1add41b7f6236a3ccc34788f47ab8682bc28e8a2d369089062e274494c1a0"},
     {file = "preshed-3.0.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a279c138ad1d5be02547b1545254929588414b01571fe637016367f6a1aa11de"},
     {file = "preshed-3.0.6-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3af09f4cfcdaca085fd87dac8107617c4e2bb0ad1458f953841b71e9728287f5"},
     {file = "preshed-3.0.6-cp38-cp38-win_amd64.whl", hash = "sha256:f92e752a868ea2690e1b38c4b775251a145e0fce36b9bdd972539e8271b7a23a"},
     {file = "preshed-3.0.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:eaffbc71fdb8625f9aac4fe7e19e20bf318d1421ea05903bebe3e6ffef27b587"},
     {file = "preshed-3.0.6-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cfe1495fcfc7f479de840ddc4f426dbb55351e218ae5c8712c1269183a4d0060"},
     {file = "preshed-3.0.6-cp39-cp39-win_amd64.whl", hash = "sha256:92a8f49d17a63537a8beed48a049b62ef168ca07e0042a5b2bcdf178a1fb5d48"},
     {file = "preshed-3.0.6.tar.gz", hash = "sha256:fb3b7588a3a0f2f2f1bf3fe403361b2b031212b73a37025aea1df7215af3772a"},
     {file = "soupsieve-2.3.2.post1.tar.gz", hash = "sha256:fc53893b3da2c33de295667a0e19f078c14bf86544af307354de5fcf12a3f30d"},
 ]
 spacy = [
+    {file = "spacy-3.2.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7e20c63ba47eaa33ebd4b2cc6eefa3e8906505273799138ad8ab231b146d8875"},
+    {file = "spacy-3.2.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc9184973c9052e1bb9eeb975801e6906aacbe0c009533ec0c34f443832473fd"},
+    {file = "spacy-3.2.4-cp310-cp310-win_amd64.whl", hash = "sha256:0168d97e7fbbddd3258016e4d3c10d1593b7129dddff146c14f3b103ade6b1cd"},
+    {file = "spacy-3.2.4-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:cff47cdaa824802cd38ae94fe98af9cde6810d86334cd283659c868e0011831a"},
+    {file = "spacy-3.2.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:400af3490c36c1b6c895de526ec06f6c7655af5ca595743c07e09e9bc8f378ea"},
+    {file = "spacy-3.2.4-cp36-cp36m-win_amd64.whl", hash = "sha256:87bd072ccacedbf8bc5a692fea1d5c320abd26821c63af157a7c95baa47dc36d"},
+    {file = "spacy-3.2.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:36e9ef5a32834383d37bbd27fca49388e31e9b53f77c91ba8ccbf19af10e3aef"},
+    {file = "spacy-3.2.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e9a98999b0fce03d4f483112837ac7111378449ace069c7cd050908f0fa5d9f"},
+    {file = "spacy-3.2.4-cp37-cp37m-win_amd64.whl", hash = "sha256:89be328ff378e4cdcfb4dcf38ca2fad740f87213825ed10e8ce9f54b822277b8"},
+    {file = "spacy-3.2.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ed29278fc89f07c1999ceca5f6702b379589c8e884a57816bdaeb05a1a7b2bbb"},
+    {file = "spacy-3.2.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:090e684eec551b5b7d56d9242cea18742515a706191ad158e32e16e8f2fe15ac"},
+    {file = "spacy-3.2.4-cp38-cp38-win_amd64.whl", hash = "sha256:2053cb78bcf4eec38aa266890a5700167a284d1a26197f851710d29f3d7071b3"},
+    {file = "spacy-3.2.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6db861f69f18ba5e00d0bd44744cf1662e00cc3b564d17a1ccdc4625ec3d5c3d"},
+    {file = "spacy-3.2.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac2288e87de1066ad65676e930f53978d6ee97c34044dca4d24f64a24e2a88b6"},
+    {file = "spacy-3.2.4-cp39-cp39-win_amd64.whl", hash = "sha256:e759e27da39e469b6367b82281a10eb4e50de04260ba49d42091cbdfe2d99633"},
+    {file = "spacy-3.2.4.tar.gz", hash = "sha256:3e4c6f298d54044582daca1142b082ee38831bb3d7bb931d2ee601e8b8dce64f"},
+]
+spacy-alignments = [
+    {file = "spacy-alignments-0.8.5.tar.gz", hash = "sha256:94ecb48f884ab8fa479d9929997281ebe0dc5b98fb8b5e53ebc252e88b023e21"},
+    {file = "spacy_alignments-0.8.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:96d0df4bbd88a840ac136cb9b191e64fb21faa893afc6dd4dd7061242095f254"},
+    {file = "spacy_alignments-0.8.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4a0793ddd98ef840ac60be3583a096e0168c99f4604b01d3060ecd578f9920d2"},
+    {file = "spacy_alignments-0.8.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:095ac0b876ca823b1a44a4779c0de47d73d643601b934c4d996d79329440f40b"},
+    {file = "spacy_alignments-0.8.5-cp310-cp310-win_amd64.whl", hash = "sha256:d33e3f02753e0febb469f7700750eb726bb008025efb6e553b6f86c02bc98e67"},
+    {file = "spacy_alignments-0.8.5-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:4f4ac27b1f2a5a4a5f3c43ee171fadf10a24220a5921846cd6b92514bd7f46e2"},
+    {file = "spacy_alignments-0.8.5-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c7eb900cdcbb4ce83f81e7b36fd6b4b05ce305b693f17e5b385ebfb9e859f473"},
+    {file = "spacy_alignments-0.8.5-cp36-cp36m-win_amd64.whl", hash = "sha256:4591d02a8fbf697fe3142d2b8278fcf28f7fb19c1a527a4876b281d7525ccea0"},
+    {file = "spacy_alignments-0.8.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:6bf4c27615ddbb50d7920e870157400acdae15a0d5bd43694432dd668798b018"},
+    {file = "spacy_alignments-0.8.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a15cc4ec3251feaddf5ccd404e1691717594b05e8cd4957baca46f1ce6c3723f"},
+    {file = "spacy_alignments-0.8.5-cp37-cp37m-win_amd64.whl", hash = "sha256:60a659fc8fdac78f28def69155ccabdf63ff7578e15d79b9a20821f96c9c4744"},
+    {file = "spacy_alignments-0.8.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:57a142679f609994fe5609aea1e0d779857277f116f71f34891c879d7cec8166"},
+    {file = "spacy_alignments-0.8.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:efa040247a82f46dd285e8144b86d1b06e757543d757a5a98157516a36526df2"},
+    {file = "spacy_alignments-0.8.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64c6bde918394ed772a9c10997fe6e4c28dd8d093f51c94eeecaeed3c9fb3230"},
+    {file = "spacy_alignments-0.8.5-cp38-cp38-win_amd64.whl", hash = "sha256:9288d6ab901d183a9f4c5037a5a20477936d62d8222bd026a15c044bddd20b6f"},
+    {file = "spacy_alignments-0.8.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:24642819c1068215c07d1de036a22b00d136050bb6f9de4f898cfb18f4e4ef0f"},
+    {file = "spacy_alignments-0.8.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:46956d142b1972dd992577aca5c1d32b49b6621768ec8f272e73b8c0dba805fd"},
+    {file = "spacy_alignments-0.8.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2c209d8aa4b0aa07ba4b98f51de679f2e415a1e069cc4caf1efb7bd0f6059ac"},
+    {file = "spacy_alignments-0.8.5-cp39-cp39-win_amd64.whl", hash = "sha256:176c0cc59da7789daf7a313c0bcbc61d1dde5539068a24c8aba728917e481a2d"},
+]
+spacy-experimental = [
+    {file = "spacy-experimental-0.4.0.tar.gz", hash = "sha256:0739e8350c103076e221bcaec019d5a55dbb1f6d26125d2e59b1ca91743b3799"},
+    {file = "spacy_experimental-0.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0f3dd83241ea86ddcd2ea99f5d346460570e10349c7fc6d7446d84c709ff9f1a"},
+    {file = "spacy_experimental-0.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:df5a969adf3de3befe3e7b916ac2adc5f11f0a1af9ad07349382f2496da89b07"},
+    {file = "spacy_experimental-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:35d63e2aba04c047c9a1fa5274221ef86608885eaae3745f65ab75ead1e6b6e8"},
+    {file = "spacy_experimental-0.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:45b0dafe2e68cf5443a4b443868daf64fa14f537ee290c22988a0ad9d560697b"},
+    {file = "spacy_experimental-0.4.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:16da4a4a16d8abc41c6b9eb505903a8714c9de755b9125df75d4291eda322395"},
+    {file = "spacy_experimental-0.4.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0eb41150d4893afee25e6b1796fd7b760a632ff8eb219cb82ae5a2e7d3478d1c"},
+    {file = "spacy_experimental-0.4.0-cp36-cp36m-win_amd64.whl", hash = "sha256:b8c820a6e1671cd33a46099e97193f39e7f551bdb1e13af7edde6ff07832a759"},
+    {file = "spacy_experimental-0.4.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:f8c667a21a54af11a00346a8e89f6c1ba45a0af25fb1f3967c27ac9dcaf7a2a0"},
+    {file = "spacy_experimental-0.4.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99a163765edbfccca36f60b1e1ac101f1bb54991d0d66eedc364422bf25f55fe"},
+    {file = "spacy_experimental-0.4.0-cp37-cp37m-win_amd64.whl", hash = "sha256:347d8901d3a1c592f7b4365cbfa10c5198ab0764b0acafaaf17577d1b4f3c366"},
+    {file = "spacy_experimental-0.4.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:226e5ae003130b22d3df9699f4ec891d897bf94b42d11f14cc30cdc57e70c795"},
+    {file = "spacy_experimental-0.4.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:150279a0a2da42ce2cc87e16cc70deadcdde66fe60c4b3a49609c6f052b4e58e"},
+    {file = "spacy_experimental-0.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31ae583f41cb316e6bc120e401de192e01ab84a9d10a1443e7c8185bfd7ce9a7"},
+    {file = "spacy_experimental-0.4.0-cp38-cp38-win_amd64.whl", hash = "sha256:95438909caaeb66beab25643f559b64447f15fe1994d3739ba5c6c64c9daa739"},
+    {file = "spacy_experimental-0.4.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:90ffbbda69330a5e7b195dbafa44a50ce9beff7d4d60026b62f1305a3f34d334"},
+    {file = "spacy_experimental-0.4.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:523bf9a0ca419c7232bc0bd70b85f4bff07c1de5b52817faa618a839a05e70e7"},
+    {file = "spacy_experimental-0.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2068d052082d157b7de0fe05282107aed4203198357648bd9619581f2b0fba0a"},
+    {file = "spacy_experimental-0.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:cb68325f9b656e543b010d4270ad5e793d31f5c8ec135e62c5baa77297be5f19"},
 ]
 spacy-legacy = [
     {file = "spacy-legacy-3.0.9.tar.gz", hash = "sha256:4f7dcbc4e6c8e8cb4eadbb009f9c0a1a2a67442e0032c8d6776c9470c3759903"},
     {file = "spacy-loggers-1.0.2.tar.gz", hash = "sha256:e75d44f4cf99e6763d7132ca7c8c420e0a92790222a08bc8eb9e24ea2c13536e"},
     {file = "spacy_loggers-1.0.2-py3-none-any.whl", hash = "sha256:d48c9313a577ad1818da961cf6db71a73fd1e556ae47e6e68d7e28b541d11e18"},
 ]
+spacy-transformers = [
+    {file = "spacy-transformers-1.1.6.tar.gz", hash = "sha256:7a05a172b7d1f01ea5ee38b428ecee333d7c6197a935bfd9433e52d11128f477"},
+    {file = "spacy_transformers-1.1.6-py2.py3-none-any.whl", hash = "sha256:370a51d6b2eeae9f6fe0b90c76fb6602579173659acd7f68c1a6dd6b2655f5dc"},
+]
 srsly = [
     {file = "srsly-2.4.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2d0236feafe3805b384532221596e6749a54d0ff10ba022b333dc1de7aa1b2f7"},
     {file = "srsly-2.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f96af9fde9f58d5923091fa723fa0fed58a83781b98e143a5d1fac5e738b9f0d"},
     {file = "tldextract-3.3.0-py3-none-any.whl", hash = "sha256:5d88321b1b528ebb8f678c72ab023f37caf6381f6af9576b4e60fd266cff178c"},
     {file = "tldextract-3.3.0.tar.gz", hash = "sha256:adcd24abf21ce3450417cd5a00f23b7e57554ce8ae827334dd12bfcbb6274cf1"},
 ]
+tokenizers = [
+    {file = "tokenizers-0.12.1-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:d737df0f8f26e093a82bfb106b6cfb510a0e9302d35834568e5b20b73ddc5a9c"},
+    {file = "tokenizers-0.12.1-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f1271224acafb27639c432e1ce4e7d38eab40305ba1c546e871d5c8a32f4f195"},
+    {file = "tokenizers-0.12.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cdeba37c2fb44e1aec8a72af4cb369655b59ba313181b1b4b8183f08e759c49c"},
+    {file = "tokenizers-0.12.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:53b5f4012ce3ffddd5b00827441b80dc7a0f6b41f4fc5248ae6d36e7d3920c6d"},
+    {file = "tokenizers-0.12.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5188e13fc09edfe05712ca3ae5a44e7f2b0137927b1ca210d0fad90d3e58315a"},
+    {file = "tokenizers-0.12.1-cp310-cp310-win32.whl", hash = "sha256:eff5ff411f18a201eec137b7b32fcb55e0c48b372d370bd24f965f5bad471fa4"},
+    {file = "tokenizers-0.12.1-cp310-cp310-win_amd64.whl", hash = "sha256:bdbca79726fe883c696088ea163715b2f902aec638a8e24bcf9790ff8fa45019"},
+    {file = "tokenizers-0.12.1-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:28825dade9e52ad464164020758f9d49eb7251c32b6ae146601c506a23c67c0e"},
+    {file = "tokenizers-0.12.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91906d725cb84d8ee71ce05fbb155d39d494849622b4f9349e5176a8eb01c49b"},
+    {file = "tokenizers-0.12.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:230f51a0a82ca7b90077eaca2415f12ff9bd144607888b9c50c2ee543452322e"},
+    {file = "tokenizers-0.12.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d4339c376b695de2ad8ccaebffa75e4dc1d7857be1103d80e7925b34af8cf78"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-macosx_10_11_x86_64.whl", hash = "sha256:27d93b712aa2d4346aa506ecd4ec9e94edeebeaf2d484357b482cdeffc02b5f5"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7f4cb68dc538b52240d1986d2034eb0a6373be2ab5f0787d1be3ad1444ce71b7"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ae6c04b629ac2cd2f695739988cb70b9bd8d5e7f849f5b14c4510e942bee5770"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6a38b2019d4807d42afeff603a119094ee00f63bea2921136524c8814e9003f8"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fde8dccb9033fa344ffce3ee1837939a50e7a210a768f1cf2059beeafa755481"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-win32.whl", hash = "sha256:38625595b2fd37bfcce64ff9bfb6868c07e9a7b7f205c909d94a615ce9472287"},
+    {file = "tokenizers-0.12.1-cp37-cp37m-win_amd64.whl", hash = "sha256:01abe6fbfe55e4131ca0c4c3d1a9d7ef5df424a8d536e998d2a4fc0bc57935f4"},
+    {file = "tokenizers-0.12.1-cp38-cp38-macosx_10_11_x86_64.whl", hash = "sha256:7c5c54080a7d5c89c990e0d478e0882dbac88926d43323a3aa236492a3c9455f"},
+    {file = "tokenizers-0.12.1-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:419d113e3bcc4fe20a313afc47af81e62906306b08fe1601e1443d747d46af1f"},
+    {file = "tokenizers-0.12.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9779944559cb7ace6a8516e402895f239b0d9d3c833c67dbaec496310e7e206"},
+    {file = "tokenizers-0.12.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7d43de14b4469b57490dbaf136a31c266cb676fa22320f01f230af9219ae9034"},
+    {file = "tokenizers-0.12.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:258873634406bd1d438c799993a5e44bbc0132ff055985c03c4fe30f702e9a33"},
+    {file = "tokenizers-0.12.1-cp38-cp38-win32.whl", hash = "sha256:3f2647cc256d6a53d18b9dcd71d377828e9f8991fbcbd6fcd8ca2ceb174552b0"},
+    {file = "tokenizers-0.12.1-cp38-cp38-win_amd64.whl", hash = "sha256:62a723bd4b18bc55121f5c34cd8efd6c651f2d3b81f81dd50e5351fb65b8a617"},
+    {file = "tokenizers-0.12.1-cp39-cp39-macosx_10_11_x86_64.whl", hash = "sha256:411ebc89228f30218ffa9d9c49d414864b0df5026a47c24820431821c4360460"},
+    {file = "tokenizers-0.12.1-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:619728df2551bdfe6f96ff177f9ded958e7ed9e2af94c8d5ac2834d1eb06d112"},
+    {file = "tokenizers-0.12.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8cea98f3f9577d1541b7bb0f7a3308a911751067e1d83e01485c9d3411bbf087"},
+    {file = "tokenizers-0.12.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:664f36f0a0d409c24f2201d495161fec4d8bc93e091fbb78814eb426f29905a3"},
+    {file = "tokenizers-0.12.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0bf2380ad59c50222959a9b6f231339200a826fc5cb2be09ff96d8a59f65fc5e"},
+    {file = "tokenizers-0.12.1-cp39-cp39-win32.whl", hash = "sha256:6a7a106d04154c2159db6cd7d042af2e2e0e53aee432f872fe6c8be45100436a"},
+    {file = "tokenizers-0.12.1-cp39-cp39-win_amd64.whl", hash = "sha256:2158baf80cbc09259bfd6e0e0fc4597b611e7a72ad5443dad63918a90f1dd304"},
+    {file = "tokenizers-0.12.1.tar.gz", hash = "sha256:070746f86efa6c873db341e55cf17bb5e7bdd5450330ca8eca542f5c3dab2c66"},
+]
 tomli = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
     {file = "toolz-0.11.2-py3-none-any.whl", hash = "sha256:a5700ce83414c64514d82d60bcda8aabfde092d1c1a8663f9200c07fdcc6da8f"},
     {file = "toolz-0.11.2.tar.gz", hash = "sha256:6b312d5e15138552f1bda8a4e66c30e236c831b612b2bf0005f8a1df10a4bc33"},
 ]
+torch = [
+    {file = "torch-1.11.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:62052b50fffc29ca7afc0c04ef8206b6f1ca9d10629cb543077e12967e8d0398"},
+    {file = "torch-1.11.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:866bfba29ac98dec35d893d8e17eaec149d0ac7a53be7baae5c98069897db667"},
+    {file = "torch-1.11.0-cp310-cp310-win_amd64.whl", hash = "sha256:951640fb8db308a59d9b510e7d1ad910aff92913323bbe4bc75435347ddd346d"},
+    {file = "torch-1.11.0-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:5d77b5ece78fdafa5c7f42995ff9474399d22571cd6b2de21a5d666306a2ff8c"},
+    {file = "torch-1.11.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:b5a38682769b544c875ecc34bcb81fbad5c922139b61319aacffcfd8a32f528c"},
+    {file = "torch-1.11.0-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:f82d77695a60626f2b7382d85bc566de8a6b3e50d32080755abc040db802e419"},
+    {file = "torch-1.11.0-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:b96654d42566080a134e784705f33f8536b3b95b5dcde357ed7879b1692a5f78"},
+    {file = "torch-1.11.0-cp37-cp37m-win_amd64.whl", hash = "sha256:8ee7c2e8d7f7020d5bfbc1bb91b9591044c26bbd0cee5e4f694cfd7ed8649260"},
+    {file = "torch-1.11.0-cp37-none-macosx_10_9_x86_64.whl", hash = "sha256:6860b1d1bf0bb0b67a6bd47f85a0e4c825b518eea13b5d6101999dbbcbd5bc0c"},
+    {file = "torch-1.11.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:4322aa29f50da7f404db06cdf30896ea67b09f673af4a985afc7162bc897864d"},
+    {file = "torch-1.11.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:e4d2e0ddd652f30e94cff750220324ec45705d4ecc69658f773b3cb1c7a28dd0"},
+    {file = "torch-1.11.0-cp38-cp38-win_amd64.whl", hash = "sha256:34ce5ea4d8d85da32cdbadb50d4585106901e9f8a3527991daa70c13a09de1f7"},
+    {file = "torch-1.11.0-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:0ccc85cd06227a3edf809e2c795fd5762c3d4e8a38b5c9f744c6e7cf841361bb"},
+    {file = "torch-1.11.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:c1554e49d74f1b2c3e7202d77056ba2dd7465437585bac64062b580f714a44e9"},
+    {file = "torch-1.11.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:58c7814502b1c129a650d7092033bbb0bbd64faf1a7941631aaa1aeaddc37570"},
+    {file = "torch-1.11.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:831cf588f01dda9409e75576741d2823453990dee2983d670f2584b37a01adf7"},
+    {file = "torch-1.11.0-cp39-cp39-win_amd64.whl", hash = "sha256:44a1d02fd20f827f0f36dc26fdcfc45e793806a6ad52769a22260655a77a4369"},
+    {file = "torch-1.11.0-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:50fd9bf85c578c871c28f1cb0ace9dfc6024401c7f399b174fb0f370899f4454"},
+    {file = "torch-1.11.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:0e48af66ad755f0f9c5f2664028a414f57c49d6adc37e77e06fe0004da4edb61"},
+]
 tqdm = [
     {file = "tqdm-4.64.0-py2.py3-none-any.whl", hash = "sha256:74a2cdefe14d11442cedf3ba4e21a3b84ff9a2dbdc6cfae2c34addb2a14a5ea6"},
     {file = "tqdm-4.64.0.tar.gz", hash = "sha256:40be55d30e200777a307a7585aee69e4eabb46b4ec6a4b4a5f2d9f11e7d5408d"},
 ]
+transformers = [
+    {file = "transformers-4.19.4-py3-none-any.whl", hash = "sha256:572d8ecbff29ec53769e0459b4334ebd1038f75ad25119a3006f8816643dccc4"},
+    {file = "transformers-4.19.4.tar.gz", hash = "sha256:b8c0f9816b4c4c2f0265b24d0a0b9d4ae8b7b98fc779d63f92e3c121c4c2d483"},
+]
 typer = [
     {file = "typer-0.4.1-py3-none-any.whl", hash = "sha256:e8467f0ebac0c81366c2168d6ad9f888efdfb6d4e1d3d5b4a004f46fa444b5c3"},
     {file = "typer-0.4.1.tar.gz", hash = "sha256:5646aef0d936b2c761a10393f0384ee6b5c7fe0bb3e5cd710b17134ca1d99cff"},

pyproject.toml CHANGED Viewed

@@ -8,13 +8,13 @@ license = "Apache 2.0"
 [tool.poetry.dependencies]
 python = "~3.8"
 textacy = "^0.12.0"
-hu-core-news-lg = {url = "https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl"}
 scipy = "~1.8.0"
 newspaper3k = "^0.2.8"
 gradio = "^3.0.18"
 Faker = "^13.13.0"
 presidio-analyzer = "^2.2.28"
 presidio-anonymizer = "^2.2.28"
 [tool.poetry.dev-dependencies]

 [tool.poetry.dependencies]
 python = "~3.8"
 textacy = "^0.12.0"
 scipy = "~1.8.0"
 newspaper3k = "^0.2.8"
 gradio = "^3.0.18"
 Faker = "^13.13.0"
 presidio-analyzer = "^2.2.28"
 presidio-anonymizer = "^2.2.28"
+hu-core-news-trf = {url = "https://huggingface.co/huspacy/hu_core_news_trf/resolve/main/hu_core_news_trf-any-py3-none-any.whl"}
 [tool.poetry.dev-dependencies]

requirements.txt CHANGED Viewed

@@ -14,7 +14,7 @@ catalogue==2.0.7; python_version >= "3.8"
 certifi==2022.6.15; python_version >= "3.8" and python_version < "4"
 cffi==1.15.0; python_version >= "3.7"
 charset-normalizer==2.0.12; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.5.0"
-click==8.1.3; python_version >= "3.8"
 colorama==0.4.5; python_version >= "3.8" and python_full_version < "3.0.0" and platform_system == "Windows" or python_full_version >= "3.5.0" and python_version >= "3.8" and platform_system == "Windows"
 cryptography==37.0.2; python_version >= "3.7"
 cssselect==1.1.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0"
@@ -26,13 +26,14 @@ fastapi==0.78.0; python_full_version >= "3.6.1" and python_version >= "3.7"
 feedfinder2==0.0.4
 feedparser==6.0.10; python_version >= "3.6"
 ffmpy==0.3.0; python_version >= "3.7"
-filelock==3.7.1; python_version >= "3.7"
 fonttools==4.33.3; python_version >= "3.7"
 frozenlist==1.3.0; python_version >= "3.7"
 fsspec==2022.5.0; python_version >= "3.7"
 gradio==3.0.18; python_version >= "3.7"
 h11==0.13.0; python_version >= "3.7"
-hu-core-news-lg @ https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl
 idna==3.3; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.6.2"
 jellyfish==0.9.0; python_version >= "3.8"
 jieba3k==0.35.1
@@ -55,7 +56,7 @@ newspaper3k==0.2.8
 nltk==3.7; python_version >= "3.7"
 numpy==1.22.4
 orjson==3.7.2; python_version >= "3.7"
-packaging==21.3; python_version >= "3.8"
 pandas==1.4.2; python_version >= "3.8"
 paramiko==2.11.0; python_version >= "3.7"
 pathy==0.6.1; python_version >= "3.8"
@@ -74,10 +75,10 @@ pyphen==0.12.0; python_version >= "3.8"
 python-dateutil==2.8.2; python_version >= "3.8" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.8"
 python-multipart==0.0.5; python_version >= "3.7"
 pytz==2022.1; python_version >= "3.8"
-pyyaml==6.0; python_version >= "3.6"
-regex==2022.6.2; python_version >= "3.7"
 requests-file==1.5.1; python_version >= "3.7"
-requests==2.28.0; python_version >= "3.8" and python_version < "4"
 scikit-learn==1.1.1; python_version >= "3.8"
 scipy==1.8.1; python_version >= "3.8" and python_version < "3.11"
 setuptools-scm==6.4.2; python_version >= "3.7"
@@ -86,9 +87,12 @@ six==1.16.0; python_version >= "3.7" and python_full_version < "3.0.0" or python
 smart-open==5.2.1; python_version >= "3.8" and python_version < "4.0"
 sniffio==1.2.0; python_full_version >= "3.6.2" and python_version >= "3.7"
 soupsieve==2.3.2.post1; python_version >= "3.6" and python_full_version >= "3.6.0"
 spacy-legacy==3.0.9; python_version >= "3.8"
 spacy-loggers==1.0.2; python_version >= "3.8"
-spacy==3.3.1; python_version >= "3.8"
 srsly==2.4.3; python_version >= "3.8"
 starlette==0.19.1; python_full_version >= "3.6.1" and python_version >= "3.7"
 textacy==0.12.0; python_version >= "3.8"
@@ -96,11 +100,14 @@ thinc==8.0.17; python_version >= "3.8"
 threadpoolctl==3.1.0; python_version >= "3.8"
 tinysegmenter==0.3
 tldextract==3.3.0; python_version >= "3.7"
 tomli==2.0.1; python_version >= "3.7"
 toolz==0.11.2; python_version >= "3.8"
-tqdm==4.64.0; python_version >= "3.8" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.8"
 typer==0.4.1; python_version >= "3.8"
-typing-extensions==4.2.0; python_full_version >= "3.6.1" and python_version >= "3.8" and python_version < "3.10"
 uc-micro-py==1.0.1; python_version >= "3.7"
 urllib3==1.26.9; python_version >= "3.8" and python_full_version < "3.0.0" and python_version < "4" or python_full_version >= "3.5.0" and python_version < "4" and python_version >= "3.8"
 uvicorn==0.17.6; python_version >= "3.7"

 certifi==2022.6.15; python_version >= "3.8" and python_version < "4"
 cffi==1.15.0; python_version >= "3.7"
 charset-normalizer==2.0.12; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.5.0"
+click==8.0.4; python_version >= "3.8"
 colorama==0.4.5; python_version >= "3.8" and python_full_version < "3.0.0" and platform_system == "Windows" or python_full_version >= "3.5.0" and python_version >= "3.8" and platform_system == "Windows"
 cryptography==37.0.2; python_version >= "3.7"
 cssselect==1.1.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0"
 feedfinder2==0.0.4
 feedparser==6.0.10; python_version >= "3.6"
 ffmpy==0.3.0; python_version >= "3.7"
+filelock==3.7.1; python_full_version >= "3.7.0" and python_version >= "3.7"
 fonttools==4.33.3; python_version >= "3.7"
 frozenlist==1.3.0; python_version >= "3.7"
 fsspec==2022.5.0; python_version >= "3.7"
 gradio==3.0.18; python_version >= "3.7"
 h11==0.13.0; python_version >= "3.7"
+hu-core-news-trf @ https://huggingface.co/huspacy/hu_core_news_trf/resolve/main/hu_core_news_trf-any-py3-none-any.whl
+huggingface-hub==0.8.1; python_full_version >= "3.7.0" and python_version >= "3.6"
 idna==3.3; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.6.2"
 jellyfish==0.9.0; python_version >= "3.8"
 jieba3k==0.35.1
 nltk==3.7; python_version >= "3.7"
 numpy==1.22.4
 orjson==3.7.2; python_version >= "3.7"
+packaging==21.3; python_full_version >= "3.7.0" and python_version >= "3.8"
 pandas==1.4.2; python_version >= "3.8"
 paramiko==2.11.0; python_version >= "3.7"
 pathy==0.6.1; python_version >= "3.8"
 python-dateutil==2.8.2; python_version >= "3.8" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.8"
 python-multipart==0.0.5; python_version >= "3.7"
 pytz==2022.1; python_version >= "3.8"
+pyyaml==6.0; python_full_version >= "3.7.0" and python_version >= "3.6"
+regex==2022.6.2; python_full_version >= "3.7.0" and python_version >= "3.7"
 requests-file==1.5.1; python_version >= "3.7"
+requests==2.28.0; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.7.0"
 scikit-learn==1.1.1; python_version >= "3.8"
 scipy==1.8.1; python_version >= "3.8" and python_version < "3.11"
 setuptools-scm==6.4.2; python_version >= "3.7"
 smart-open==5.2.1; python_version >= "3.8" and python_version < "4.0"
 sniffio==1.2.0; python_full_version >= "3.6.2" and python_version >= "3.7"
 soupsieve==2.3.2.post1; python_version >= "3.6" and python_full_version >= "3.6.0"
+spacy-alignments==0.8.5; python_version >= "3.6"
+spacy-experimental==0.4.0; python_version >= "3.6"
 spacy-legacy==3.0.9; python_version >= "3.8"
 spacy-loggers==1.0.2; python_version >= "3.8"
+spacy-transformers==1.1.6; python_version >= "3.6"
+spacy==3.2.4; python_version >= "3.8"
 srsly==2.4.3; python_version >= "3.8"
 starlette==0.19.1; python_full_version >= "3.6.1" and python_version >= "3.7"
 textacy==0.12.0; python_version >= "3.8"
 threadpoolctl==3.1.0; python_version >= "3.8"
 tinysegmenter==0.3
 tldextract==3.3.0; python_version >= "3.7"
+tokenizers==0.12.1; python_full_version >= "3.7.0" and python_version >= "3.6"
 tomli==2.0.1; python_version >= "3.7"
 toolz==0.11.2; python_version >= "3.8"
+torch==1.11.0; python_full_version >= "3.7.0" and python_version >= "3.6"
+tqdm==4.64.0; python_full_version >= "3.7.0" and python_version >= "3.8"
+transformers==4.19.4; python_full_version >= "3.7.0" and python_version >= "3.6"
 typer==0.4.1; python_version >= "3.8"
+typing-extensions==4.2.0; python_full_version >= "3.7.0" and python_version >= "3.8" and python_version < "3.10"
 uc-micro-py==1.0.1; python_version >= "3.7"
 urllib3==1.26.9; python_version >= "3.8" and python_full_version < "3.0.0" and python_version < "4" or python_full_version >= "3.5.0" and python_version < "4" and python_version >= "3.8"
 uvicorn==0.17.6; python_version >= "3.7"

resources/triples.py ADDED Viewed

	@@ -0,0 +1,125 @@

+"""
+Triples
+-------
+:mod:`textacy.extract.triples`: Extract structured triples from a document or sentence
+through rule-based pattern-matching of the annotated tokens.
+"""
+from __future__ import annotations
+import collections
+from operator import attrgetter
+from typing import Iterable, List, Tuple
+from spacy.symbols import (
+    AUX, VERB,
+    agent, attr, aux, auxpass, csubj, csubjpass, dobj, neg, nsubj, nsubjpass, obj, pobj, xcomp,
+)
+from spacy.tokens import Span, Token
+from textacy import types
+_NOMINAL_SUBJ_DEPS = {nsubj, nsubjpass}
+_CLAUSAL_SUBJ_DEPS = {csubj, csubjpass}
+_ACTIVE_SUBJ_DEPS = {csubj, nsubj}
+_VERB_MODIFIER_DEPS = {aux, auxpass, neg}
+SVOTriple: Tuple[List[Token], List[Token], List[Token]] = collections.namedtuple(
+    "SVOTriple", ["subject", "verb", "object"]
+)
+def subject_verb_object_triples(doclike: types.DocLike) -> Iterable[SVOTriple]:
+    """
+    Extract an ordered sequence of subject-verb-object triples from a document
+    or sentence.
+    Args:
+        doclike
+    Yields:
+        Next SVO triple as (subject, verb, object), in approximate order of appearance.
+    """
+    if isinstance(doclike, Span):
+        sents = [doclike]
+    else:
+        sents = doclike.sents
+    for sent in sents:
+        # connect subjects/objects to direct verb heads
+        # and expand them to include conjuncts, compound nouns, ...
+        verb_sos = collections.defaultdict(lambda: collections.defaultdict(set))
+        for tok in sent:
+            head = tok.head
+            # ensure entry for all verbs, even if empty
+            # to catch conjugate verbs without direct subject/object deps
+            if tok.pos == VERB:
+                _ = verb_sos[tok]
+            # nominal subject of active or passive verb
+            if tok.dep in _NOMINAL_SUBJ_DEPS:
+                if head.pos == VERB:
+                    verb_sos[head]["subjects"].update(expand_noun(tok))
+            # clausal subject of active or passive verb
+            elif tok.dep in _CLAUSAL_SUBJ_DEPS:
+                if head.pos == VERB:
+                    verb_sos[head]["subjects"].update(tok.subtree)
+            # nominal direct object of transitive verb
+            elif tok.dep == obj:
+                if head.pos == VERB:
+                    verb_sos[head]["objects"].update(expand_noun(tok))
+            # prepositional object acting as agent of passive verb
+            elif tok.dep == pobj:
+                if head.dep == agent and head.head.pos == VERB:
+                    verb_sos[head.head]["objects"].update(expand_noun(tok))
+            # open clausal complement, but not as a secondary predicate
+            elif tok.dep == xcomp:
+                if (
+                    head.pos == VERB
+                    and not any(child.dep == obj for child in head.children)
+                ):
+                    # TODO: just the verb, or the whole tree?
+                    # verb_sos[verb]["objects"].update(expand_verb(tok))
+                    verb_sos[head]["objects"].update(tok.subtree)
+        # fill in any indirect relationships connected via verb conjuncts
+        for verb, so_dict in verb_sos.items():
+            conjuncts = verb.conjuncts
+            if so_dict.get("subjects"):
+                for conj in conjuncts:
+                    conj_so_dict = verb_sos.get(conj)
+                    if conj_so_dict and not conj_so_dict.get("subjects"):
+                        conj_so_dict["subjects"].update(so_dict["subjects"])
+            if not so_dict.get("objects"):
+                so_dict["objects"].update(
+                    obj
+                    for conj in conjuncts
+                    for obj in verb_sos.get(conj, {}).get("objects", [])
+                )
+        # expand verbs and restructure into svo triples
+        for verb, so_dict in verb_sos.items():
+            if so_dict["subjects"] and so_dict["objects"]:
+                yield SVOTriple(
+                    subject=sorted(so_dict["subjects"], key=attrgetter("i")),
+                    verb=sorted(expand_verb(verb), key=attrgetter("i")),
+                    object=sorted(so_dict["objects"], key=attrgetter("i")),
+                )
+def expand_noun(tok: Token) -> List[Token]:
+    """Expand a noun token to include all associated conjunct and compound nouns."""
+    tok_and_conjuncts = [tok] + list(tok.conjuncts)
+    compounds = [
+        child
+        for tc in tok_and_conjuncts
+        for child in tc.children
+        # TODO: why doesn't compound import from spacy.symbols?
+        if child.dep_ == "compound"
+    ]
+    return tok_and_conjuncts + compounds
+def expand_verb(tok: Token) -> List[Token]:
+    """Expand a verb token to include all associated auxiliary and negation tokens."""
+    verb_modifiers = [
+        child for child in tok.children if child.dep in _VERB_MODIFIER_DEPS
+    ]
+    return [tok] + verb_modifiers