test7_balanced_and_sentence / added_tokens.json
adriansanz's picture
Training in progress, epoch 1
324c592 verified
{
"2022": 50408,
"2023": 50497,
"acc茅s": 50303,
"actuaci贸": 50462,
"adjunt": 50292,
"adjunto": 50405,
"adre莽ar": 50540,
"aix铆": 50399,
"aix貌": 50357,
"alg煤": 50360,
"all铆": 50495,
"al莽ada": 50395,
"aparcar": 50520,
"aqu铆": 50373,
"atenci贸": 50348,
"atentament": 50472,
"autoritzaci贸": 50541,
"aviat": 50457,
"balc贸": 50288,
"bancari": 50544,
"banda": 50333,
"benvolguts": 50470,
"bisbe": 50455,
"bonificaci贸": 50508,
"bordeta": 50323,
"borsa": 50406,
"bressol": 50324,
"brossa": 50359,
"bruticia": 50356,
"brut铆cia": 50298,
"caducada": 50313,
"caldre": 50274,
"cami": 50483,
"cami贸": 50476,
"cam铆": 50362,
"canviar": 50445,
"cappont": 50381,
"caure": 50290,
"certificat": 50376,
"ciutad脿": 50459,
"client": 50379,
"club": 50428,
"cobrar": 50488,
"colom": 50524,
"comentar": 50501,
"comen莽ar": 50372,
"comercial": 50280,
"comer莽": 50463,
"complir": 50275,
"comportar": 50444,
"comprar": 50297,
"compte": 50393,
"comunicaci贸": 50409,
"comunicar": 50416,
"concretament": 50454,
"condici贸": 50522,
"constant": 50453,
"constar": 50439,
"construcci贸": 50486,
"consultar": 50436,
"contactar": 50469,
"contacte": 50415,
"contenidor": 50358,
"continuar": 50448,
"cordial": 50337,
"corrent": 50402,
"corresponent": 50451,
"correu": 50481,
"costat": 50494,
"cotxe": 50446,
"crear": 50512,
"creure": 50365,
"darrer": 50518,
"degut": 50404,
"deixalla": 50509,
"demanar": 50308,
"denuncia": 50426,
"departament": 50473,
"descans": 50382,
"desde": 50291,
"despr茅s": 50413,
"diferent": 50277,
"directament": 50528,
"disposar": 50320,
"disposici贸": 50388,
"diuar": 50502,
"divendres": 50389,
"dni": 50377,
"doctor": 50269,
"documentaci贸": 50397,
"domicili": 50490,
"dormir": 50384,
"educaci贸": 50521,
"educatiu": 50513,
"embornal": 50266,
"embossat": 50267,
"etc猫tera": 50429,
"facilitar": 50434,
"factura": 50531,
"familia": 50300,
"fam铆lia": 50332,
"farola": 50500,
"fa莽ana": 50318,
"feina": 50410,
"finca": 50479,
"finestra": 50353,
"fotografia": 50305,
"funcionar": 50437,
"generar": 50447,
"gestionar": 50546,
"gesti贸": 50343,
"gracia": 50344,
"gracies": 50272,
"gr脿cia": 50310,
"gr脿cies": 50371,
"gu脿rdia": 50432,
"ibi": 50489,
"incid猫ncia": 50424,
"indigents": 50458,
"informaci贸": 50339,
"interseccio": 50499,
"itv": 50312,
"jard铆": 50378,
"jugar": 50355,
"lamentable": 50450,
"llarg": 50471,
"lleida": 50316,
"manera": 50460,
"manteniment": 50301,
"mariola": 50304,
"mar莽": 50533,
"mateixa": 50423,
"matricula": 50315,
"mat铆": 50293,
"mesura": 50361,
"meus": 50340,
"missatge": 50325,
"mitjan莽ant": 50262,
"mitj脿": 50331,
"molestar": 50433,
"mol猫stia": 50400,
"moment": 50441,
"mosquit": 50552,
"motiu": 50427,
"multa": 50350,
"m茅s": 50289,
"m煤sica": 50386,
"necessari": 50411,
"necessitar": 50383,
"necessitat": 50354,
"neteja": 50352,
"netejar": 50364,
"ning煤": 50403,
"nom茅s": 50328,
"normativa": 50456,
"nostre": 50287,
"notificaci贸": 50553,
"numero": 50270,
"n煤m": 50468,
"n煤mero": 50282,
"ocasi贸": 50363,
"opci贸": 50496,
"ordenan莽a": 50449,
"paeria": 50419,
"pagament": 50349,
"parc": 50295,
"pardinyes": 50517,
"particular": 50412,
"partida": 50485,
"partir": 50525,
"passeig": 50515,
"pati": 50487,
"patinet": 50555,
"patir": 50417,
"pavell贸": 50535,
"pendent": 50474,
"pensar": 50440,
"perill": 50279,
"perill贸s": 50368,
"perm铆s": 50366,
"perqu猫": 50306,
"per貌": 50276,
"petici贸": 50374,
"pista": 50542,
"plaga": 50551,
"plaques": 50314,
"pla莽a": 50345,
"possible": 50342,
"pregar": 50478,
"prego": 50538,
"preguntar": 50319,
"presentar": 50491,
"problem脿tica": 50545,
"procedir": 50554,
"produir": 50422,
"proper": 50530,
"propietari": 50414,
"propietaris": 50537,
"propietat": 50543,
"proposta": 50526,
"provocar": 50519,
"p煤blic": 50335,
"quant": 50443,
"quedar": 50284,
"queixa": 50321,
"queixar": 50390,
"qu猫": 50273,
"realitzar": 50294,
"rebre": 50480,
"rebut": 50322,
"reclamaci贸": 50532,
"recollida": 50370,
"recollir": 50369,
"referent": 50438,
"refer猫ncia": 50505,
"registre": 50452,
"relaci贸": 50442,
"resident": 50281,
"resoluci贸": 50511,
"resposta": 50420,
"revisin": 50493,
"roman": 50271,
"ronda": 50516,
"roure": 50523,
"sabar": 50461,
"saber": 50265,
"salubritat": 50510,
"salutacions": 50425,
"salutaci贸": 50338,
"sector": 50547,
"seguretat": 50302,
"semblar": 50264,
"sentir": 50387,
"sentit": 50336,
"senyal": 50503,
"senyor": 50465,
"servir": 50484,
"setmana": 50351,
"sin贸": 50534,
"situaci贸": 50307,
"situat": 50268,
"socials": 50466,
"solar": 50550,
"sollicitar": 50504,
"sollicito": 50529,
"solucionar": 50475,
"soluci贸": 50309,
"sol路licitar": 50467,
"sol路licitud": 50539,
"soroll": 50380,
"sortida": 50536,
"sortir": 50398,
"subvenci贸": 50549,
"suggeriment": 50492,
"supermercat": 50548,
"suposar": 50299,
"tambe": 50317,
"tamb茅": 50278,
"tancar": 50385,
"tancat": 50401,
"tarda": 50296,
"taxa": 50507,
"tel猫fon": 50514,
"terme": 50327,
"terrassa": 50286,
"terreny": 50346,
"tocar": 50435,
"tractar": 50527,
"treballador": 50329,
"trobar": 50375,
"trucar": 50431,
"tr脿mit": 50421,
"t猫cnic": 50392,
"urbana": 50263,
"urb脿": 50391,
"vegada": 50283,
"vehicle": 50311,
"vehicles": 50396,
"veins": 50430,
"velocitat": 50506,
"ve铆": 50367,
"vianant": 50418,
"vidre": 50285,
"vivent": 50477,
"vivir": 50498,
"voldria": 50407,
"voldriar": 50341,
"voler": 50326,
"voliar": 50334,
"voltant": 50464,
"vorera": 50394,
"vostr": 50347,
"vost猫": 50482,
"煤nic": 50330
}