Upload 2 files

500_unigram.vocab

@@ -0,0 +1,500 @@
+<unk>	0
+S	-2.88235
+▁	-3.58593
+E	-3.63853
+▁DE	-3.77958
+'	-3.82185
+T	-4.01718
+R	-4.15337
+U	-4.29558
+▁LA	-4.30786
+▁L	-4.32102
+I	-4.37497
+A	-4.41527
+É	-4.41611
+N	-4.49243
+▁LE	-4.50752
+▁EST	-4.51213
+O	-4.51599
+C	-4.52696
+P	-4.58634
+▁IL	-4.66918
+▁D	-4.67445
+▁A	-4.67767
+G	-4.74767
+▁À	-4.82041
+ON	-4.86261
+▁ET	-4.91762
+▁S	-4.96847
+▁EN	-4.97547
+L	-5.01103
+▁C	-5.06597
+D	-5.11056
+▁LES	-5.14526
+ER	-5.14566
+Y	-5.17062
+IN	-5.18296
+▁UN	-5.19802
+B	-5.20758
+RE	-5.2828
+▁DU	-5.2896
+RI	-5.30488
+▁PAR	-5.30893
+▁B	-5.31085
+▁F	-5.31184
+IT	-5.32316
+ES	-5.32465
+LE	-5.32593
+IS	-5.35872
+▁SE	-5.38259
+RA	-5.38444
+H	-5.41167
+▁DES	-5.41401
+▁RE	-5.42134
+ANT	-5.44528
+▁AU	-5.44806
+F	-5.45871
+V	-5.46102
+AL	-5.4841
+TE	-5.49683
+▁P	-5.51025
+▁UNE	-5.5194
+UR	-5.5579
+ENT	-5.581
+M	-5.60816
+▁G	-5.62046
+ME	-5.64809
+▁DANS	-5.66453
+▁CON	-5.69161
+▁ELLE	-5.6936
+ATION	-5.71252
+MENT	-5.71409
+AN	-5.72102
+OU	-5.72679
+LI	-5.73299
+▁T	-5.73797
+OR	-5.76793
+ÉE	-5.79042
+TI	-5.8224
+Z	-5.82256
+▁MA	-5.83768
+▁N	-5.83972
+È	-5.84262
+CE	-5.84544
+▁SA	-5.8523
+RO	-5.86178
+NT	-5.8713
+▁CE	-5.91471
+▁IN	-5.91896
+NE	-5.92129
+▁SON	-5.94746
+CH	-5.95192
+ND	-5.96537
+▁POUR	-5.9695
+K	-5.9824
+LA	-6.02599
+▁PRO	-6.02791
+DE	-6.04618
+▁CA	-6.0462
+▁DÉ	-6.05555
+▁É	-6.05778
+DI	-6.05955
+QUE	-6.06501
+IQUE	-6.06704
+X	-6.07622
+AR	-6.11457
+▁SONT	-6.1192
+▁RÉ	-6.13304
+CI	-6.13426
+TRE	-6.13855
+▁QU	-6.14164
+CHE	-6.14986
+▁SUR	-6.15805
+▁MO	-6.18156
+IE	-6.18812
+UL	-6.20546
+AIRE	-6.21351
+LO	-6.21908
+J	-6.23926
+▁PO	-6.23973
+▁O	-6.26682
+AIT	-6.27285
+RÉ	-6.27809
+OL	-6.29914
+MA	-6.30134
+TA	-6.31335
+▁VI	-6.31508
+EL	-6.3174
+ION	-6.32013
+TÉ	-6.32774
+▁AR	-6.34714
+INE	-6.36038
+ÈRE	-6.3619
+▁QUE	-6.371
+▁PAS	-6.37325
+▁DI	-6.38812
+▁SU	-6.41595
+MP	-6.41732
+▁M	-6.41997
+MI	-6.42651
+IR	-6.4273
+▁CH	-6.43151
+CETTE	-6.43506
+ALE	-6.45147
+US	-6.453
+▁CHA	-6.45476
+▁PLUS	-6.45728
+ILLE	-6.45808
+VI	-6.46049
+GE	-6.46082
+UT	-6.46994
+▁EX	-6.47734
+IL	-6.48259
+EN	-6.49679
+TH	-6.49802
+▁NE	-6.50831
+EUR	-6.50998
+EMENT	-6.51878
+▁RO	-6.52846
+ELLE	-6.53664
+QU	-6.5376
+▁BA	-6.54094
+IM	-6.5457
+AGE	-6.54969
+▁DEUX	-6.57041
+▁VO	-6.57223
+VE	-6.57948
+▁AVEC	-6.57986
+▁CO	-6.60067
+AT	-6.60556
+IC	-6.6181
+ITÉ	-6.61908
+▁AV	-6.62056
+VER	-6.62304
+OIS	-6.62726
+TO	-6.63003
+SSE	-6.64601
+PORT	-6.64613
+MB	-6.65251
+PH	-6.6632
+▁SOU	-6.66778
+FF	-6.67198
+NA	-6.67383
+▁COMME	-6.67454
+▁QUI	-6.67976
+TION	-6.6854
+▁JE	-6.69969
+▁OU	-6.72334
+▁MAR	-6.73709
+▁ÉTÉ	-6.74273
+CT	-6.74319
+PE	-6.76167
+CTION	-6.76333
+▁RA	-6.77337
+LU	-6.78706
+LL	-6.78859
+NI	-6.79663
+AIS	-6.80207
+ARD	-6.80999
+▁MI	-6.8109
+TER	-6.81362
+DU	-6.82466
+▁ÉTAIT	-6.8266
+NÉ	-6.8287
+IGN	-6.8389
+▁Y	-6.84139
+TIQUE	-6.84801
+▁AC	-6.84965
+ISTE	-6.85066
+▁DO	-6.85549
+▁TRA	-6.85828
+MÉ	-6.86299
+▁FA	-6.87082
+▁COM	-6.87536
+ORD	-6.87594
+MO	-6.87603
+▁APP	-6.88329
+▁ÉT	-6.88783
+IF	-6.89103
+▁ÉGALEMENT	-6.89553
+CO	-6.90035
+▁ME	-6.9063
+LÉ	-6.90695
+▁PA	-6.90754
+IER	-6.91361
+AUX	-6.91387
+UE	-6.92254
+▁VA	-6.92313
+▁SES	-6.92795
+RES	-6.93183
+▁AN	-6.93375
+Ô	-6.93809
+W	-6.94651
+▁K	-6.95481
+ANG	-6.96591
+ÉRI	-6.97936
+▁NOM	-6.98496
+▁MAIS	-6.99944
+▁COMP	-7.00146
+TU	-7.00669
+ANCE	-7.01429
+ENCE	-7.02238
+DA	-7.02419
+MAN	-7.02747
+▁FAIT	-7.04633
+IVE	-7.05796
+TEUR	-7.06357
+▁TOUT	-7.06502
+IÈRE	-7.06521
+ITE	-7.07067
+▁SI	-7.07304
+AND	-7.07585
+▁FOR	-7.08095
+▁TO	-7.081
+MIN	-7.08145
+▁PLA	-7.08465
+EUX	-7.08495
+TURE	-7.09304
+POS	-7.09586
+ABLE	-7.09867
+IRE	-7.09979
+▁AUX	-7.09981
+▁HA	-7.11286
+Ç	-7.11559
+▁AUSSI	-7.11898
+UV	-7.11936
+ÉES	-7.11971
+LES	-7.13175
+▁ON	-7.13296
+OIR	-7.14552
+EAU	-7.15293
+▁MON	-7.15342
+ENS	-7.15369
+ÉS	-7.15465
+ONNE	-7.15874
+▁JA	-7.16225
+▁CENT	-7.16805
+▁GRAND	-7.17051
+▁DIS	-7.17198
+ID	-7.17358
+▁ÉC	-7.1791
+▁NO	-7.18726
+▁PRÉ	-7.18739
+▁RU	-7.19007
+TTE	-7.20017
+TRO	-7.20057
+Î	-7.20252
+TEN	-7.20663
+VEN	-7.2103
+▁DÉC	-7.21551
+▁LUI	-7.2163
+TRI	-7.21733
+ILL	-7.21896
+▁MÉ	-7.22109
+RIE	-7.23107
+VENT	-7.23539
+▁MU	-7.23879
+ÊT	-7.24886
+AGN	-7.25827
+▁FUT	-7.2602
+Â	-7.26194
+AIENT	-7.26197
+AM	-7.26341
+▁PRI	-7.2645
+▁ALORS	-7.26735
+GUE	-7.27135
+TRA	-7.27415
+▁ONT	-7.27417
+▁TROIS	-7.28166
+VA	-7.29358
+▁PER	-7.29723
+▁NA	-7.30002
+BA	-7.30448
+URE	-7.31045
+▁AB	-7.3198
+▁LEUR	-7.32503
+▁W	-7.33534
+ÈS	-7.33801
+▁ÊTRE	-7.34348
+▁MÊME	-7.3782
+IDE	-7.3802
+▁FIN	-7.38171
+▁APRÈS	-7.38685
+▁LI	-7.39557
+VÉ	-7.3999
+▁SAINT	-7.40109
+▁COUR	-7.42135
+▁JU	-7.42573
+▁PEU	-7.4398
+PAR	-7.44043
+▁CES	-7.44276
+NO	-7.45503
+IEN	-7.45928
+CUL	-7.46271
+▁VILLE	-7.46905
+▁JO	-7.47826
+▁ENTRE	-7.48849
+▁INTER	-7.48866
+▁VOUS	-7.49951
+▁PARTIE	-7.51989
+TIN	-7.5199
+▁PLUSIEURS	-7.53102
+▁TE	-7.53839
+▁OB	-7.54149
+▁SITUÉ	-7.54248
+▁HO	-7.55305
+▁HE	-7.56954
+IENNE	-7.58441
+TRÈS	-7.58443
+▁TOUR	-7.58863
+▁FRANC	-7.61136
+HUI	-7.62457
+▁SÉ	-7.63425
+▁PREMIER	-7.63436
+▁QUATRE	-7.65199
+▁CLA	-7.65268
+▁ATT	-7.66519
+VIENT	-7.66895
+▁PEUT	-7.67363
+STRU	-7.67523
+▁COMMUNE	-7.67992
+▁ANNÉE	-7.68895
+▁ÉV	-7.70477
+OMM	-7.72235
+FORM	-7.72527
+À	-7.74379
+▁BIEN	-7.7443
+Ê	-7.74557
+▁MONT	-7.75343
+▁AUTRES	-7.7543
+▁PI	-7.75838
+▁JOUR	-7.76397
+ATEUR	-7.77242
+IBLE	-7.79082
+▁UTILIS	-7.79271
+VRE	-7.79324
+ISSE	-7.79641
+▁PREMIÈRE	-7.79925
+▁TROUVE	-7.80535
+▁CINQ	-7.81071
+LEMENT	-7.81922
+▁EU	-7.83251
+▁DONC	-7.84492
+▁JOUE	-7.84639
+▁VERS	-7.85405
+▁GROUPE	-7.85474
+▁ESPÈCE	-7.875
+▁EMP	-7.88279
+▁FRANÇAIS	-7.88906
+▁ÉTAT	-7.8932
+▁PETIT	-7.9135
+▁ENSUITE	-7.91658
+EUSE	-7.9191
+▁LORS	-7.92133
+▁PUIS	-7.92306
+▁AINSI	-7.93635
+▁EFF	-7.93758
+▁NOUS	-7.93803
+▁TRAVAIL	-7.93972
+▁LIEU	-7.94473
+▁RENCONTRE	-7.96101
+▁ÉQUIPE	-7.96747
+▁CERTAIN	-7.96747
+▁FAMILLE	-7.97161
+▁PRÉSENT	-7.97185
+▁COLL	-7.97715
+▁FILS	-7.9893
+▁VINGT	-8.0125
+▁GÉNÉRAL	-8.0161
+▁PAYS	-8.05267
+Ï	-8.05537
+▁ANCIEN	-8.05638
+▁ÉGLISE	-8.0708
+▁PRINCIPAL	-8.07248
+▁GUERRE	-8.09234
+▁ESP	-8.09582
+▁CEPENDANT	-8.14452
+▁RESTE	-8.15609
+▁PENDANT	-8.17858
+▁TEMPS	-8.18712
+▁RÉGION	-8.19917
+▁JEUNE	-8.20441
+▁HABIT	-8.20661
+Û	-8.21411
+▁ENFANT	-8.21569
+▁CLUB	-8.21786
+▁MEMBRE	-8.22277
+▁AGIT	-8.22427
+▁HOMME	-8.25242
+▁SUCC	-8.25812
+▁VILLAGE	-8.26046
+BERT	-8.26082
+▁DEPUIS	-8.26399
+▁RÉALIS	-8.29354
+▁ENCORE	-8.30531
+Ù	-8.31422
+▁AUJOURD	-8.32929
+▁SECOND	-8.32975
+UNIVERSITÉ	-8.33426
+▁HISTOIRE	-8.33582
+▁UVRE	-8.33654
+POSITION	-8.33667
+▁IMPORTANT	-8.34553
+▁REPRÉSENT	-8.34616
+▁NOUVELLE	-8.34869
+▁ORGANIS	-8.34932
+▁FRÈRE	-8.35086
+▁ORIGINE	-8.35217
+▁FILM	-8.36806
+▁ÎLE	-8.37963
+▁PARTICIP	-8.39558
+▁FEMME	-8.41497
+▁ÉCOLE	-8.41794
+▁DERNIER	-8.42586
+▁PERMET	-8.44089
+▁JUSQU	-8.44195
+▁CARRIÈRE	-8.44651
+▁NOMBREUX	-8.46373
+▁MONSIEUR	-8.46657
+Á	-9.05535
+Í	-9.39349
+Ö	-9.39528
+Ü	-9.40978
+Ë	-9.42357
+Ó	-9.54652
+Q	-9.59991
+Ä	-10.0889
+Ñ	-10.8423
+Ú	-10.9386
+Ã	-11.3242
+Æ	-11.4494
+Å	-11.4635
+Ý	-12.2897
+Ð	-12.3745
+Ò	-12.4479
+Õ	-13.2952
+Ì	-13.3882
+Þ	-13.7344
+А	-15.1526
+Ј	-15.486
+І	-15.986
+Е	-15.986
+Р	-15.986
+К	-16.9858
+Г	-16.9859
+Ø	-16.986
+́	-16.986
+Є	-16.986
+Џ	-16.986
+З	-16.986
+И	-16.986
+М	-16.986
+Н	-16.986
+П	-16.986
+С	-16.986
+Ц	-16.986
+Ч	-16.986
+Э	-16.986
+Я	-16.986
+Ҫ	-16.986
+Ӌ	-16.986

normalizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a981c379f2602425c7fe56f670c9321f5dbc6a930cc988ef236930f9548265f
+size 1779