{
 "lignes_total": 2632,
 "lignes_vides": 122,
 "lignes_utiles": 2510,
 "sources_total": 87,
 "caracteres": 191782,
 "octets_utf8": 209035,
 "longueur_entree": {
  "min": 1,
  "max": 42906,
  "moyenne": 76.4,
  "mediane": 20,
  "p90": 87
 },
 "tranches_longueur_entree": [
  {
   "min": 0,
   "max": 10,
   "n": 612
  },
  {
   "min": 10,
   "max": 25,
   "n": 821
  },
  {
   "min": 25,
   "max": 50,
   "n": 627
  },
  {
   "min": 50,
   "max": 100,
   "n": 246
  },
  {
   "min": 100,
   "max": 200,
   "n": 120
  },
  {
   "min": 200,
   "max": 500,
   "n": 41
  },
  {
   "min": 500,
   "max": null,
   "n": 43
  }
 ],
 "mots_total": 36501,
 "mots_uniques": 5287,
 "richesse_lexicale": 0.1448,
 "mots_par_entree": 14.5,
 "bigrammes_uniques": 20307,
 "trigrammes_uniques": 26960,
 "hapax": 2954,
 "hapax_pourcent": 55.9,
 "longueur_mot_moyenne": 3.91,
 "top_mots": [
  {
   "mot": "ka",
   "n": 1800,
   "pourcent": 4.93
  },
  {
   "mot": "an",
   "n": 1388,
   "pourcent": 3.8
  },
  {
   "mot": "sé",
   "n": 885,
   "pourcent": 2.42
  },
  {
   "mot": "on",
   "n": 833,
   "pourcent": 2.28
  },
  {
   "mot": "pou",
   "n": 727,
   "pourcent": 1.99
  },
  {
   "mot": "té",
   "n": 726,
   "pourcent": 1.99
  },
  {
   "mot": "pa",
   "n": 664,
   "pourcent": 1.82
  },
  {
   "mot": "yo",
   "n": 638,
   "pourcent": 1.75
  },
  {
   "mot": "nou",
   "n": 633,
   "pourcent": 1.73
  },
  {
   "mot": "ou",
   "n": 611,
   "pourcent": 1.67
  },
  {
   "mot": "ki",
   "n": 548,
   "pourcent": 1.5
  },
  {
   "mot": "la",
   "n": 481,
   "pourcent": 1.32
  },
  {
   "mot": "ni",
   "n": 408,
   "pourcent": 1.12
  },
  {
   "mot": "fè",
   "n": 404,
   "pourcent": 1.11
  },
  {
   "mot": "sa",
   "n": 401,
   "pourcent": 1.1
  },
  {
   "mot": "mwen",
   "n": 400,
   "pourcent": 1.1
  },
  {
   "mot": "ké",
   "n": 337,
   "pourcent": 0.92
  },
  {
   "mot": "moun",
   "n": 267,
   "pourcent": 0.73
  },
  {
   "mot": "di",
   "n": 251,
   "pourcent": 0.69
  },
  {
   "mot": "pé",
   "n": 244,
   "pourcent": 0.67
  },
  {
   "mot": "si",
   "n": 218,
   "pourcent": 0.6
  },
  {
   "mot": "kon",
   "n": 214,
   "pourcent": 0.59
  },
  {
   "mot": "lè",
   "n": 211,
   "pourcent": 0.58
  },
  {
   "mot": "tout",
   "n": 206,
   "pourcent": 0.56
  },
  {
   "mot": "adan",
   "n": 202,
   "pourcent": 0.55
  }
 ],
 "top_bigrammes": [
  {
   "suite": "té ka",
   "n": 184
  },
  {
   "suite": "ka fè",
   "n": 161
  },
  {
   "suite": "ou ka",
   "n": 145
  },
  {
   "suite": "an ka",
   "n": 142
  },
  {
   "suite": "yo ka",
   "n": 116
  },
  {
   "suite": "té ké",
   "n": 111
  },
  {
   "suite": "an mwen",
   "n": 106
  },
  {
   "suite": "an té",
   "n": 99
  },
  {
   "suite": "ni on",
   "n": 91
  },
  {
   "suite": "pa ka",
   "n": 87
  },
  {
   "suite": "an nou",
   "n": 82
  },
  {
   "suite": "sé on",
   "n": 81
  },
  {
   "suite": "nou ka",
   "n": 73
  },
  {
   "suite": "pa té",
   "n": 68
  },
  {
   "suite": "ka di",
   "n": 66
  },
  {
   "suite": "pa ni",
   "n": 63
  },
  {
   "suite": "ki té",
   "n": 60
  },
  {
   "suite": "ka pran",
   "n": 59
  },
  {
   "suite": "ka vwè",
   "n": 59
  },
  {
   "suite": "pè pyè",
   "n": 59
  }
 ],
 "top_trigrammes": [
  {
   "suite": "an té ké",
   "n": 49
  },
  {
   "suite": "ou ka fè",
   "n": 29
  },
  {
   "suite": "té ké vlé",
   "n": 26
  },
  {
   "suite": "ki té ka",
   "n": 25
  },
  {
   "suite": "ka fè pou",
   "n": 25
  },
  {
   "suite": "té ké pé",
   "n": 21
  },
  {
   "suite": "sa ou ka",
   "n": 19
  },
  {
   "suite": "ou té ké",
   "n": 19
  },
  {
   "suite": "yo ka fè",
   "n": 17
  },
  {
   "suite": "té ké enmé",
   "n": 17
  },
  {
   "suite": "mèsi pou sa",
   "n": 16
  },
  {
   "suite": "pou sa ou",
   "n": 16
  },
  {
   "suite": "an sé moun",
   "n": 16
  },
  {
   "suite": "té ni on",
   "n": 15
  },
  {
   "suite": "an-mwen ka fè-mwen",
   "n": 15
  },
  {
   "suite": "ka fè-mwen mal",
   "n": 15
  },
  {
   "suite": "yo té ka",
   "n": 14
  },
  {
   "suite": "kou pou kou",
   "n": 14
  },
  {
   "suite": "té ka fè",
   "n": 13
  },
  {
   "suite": "pa té ka",
   "n": 13
  }
 ],
 "couverture": {
  "50": 73,
  "75": 522,
  "90": 1985,
  "95": 3462,
  "99": 4922
 },
 "mots_longs": [
  {
   "mot": "diz-nèf-san-swasannsèt",
   "lettres": 22,
   "n": 1
  },
  {
   "mot": "sèvis-ladministrasyon",
   "lettres": 21,
   "n": 1
  },
  {
   "mot": "rèsponsabilité-lasa",
   "lettres": 19,
   "n": 1
  },
  {
   "mot": "lagyè-lendépandans",
   "lettres": 18,
   "n": 1
  },
  {
   "mot": "katrè-d-laprémidi",
   "lettres": 17,
   "n": 1
  },
  {
   "mot": "konkou-agrégasyon",
   "lettres": 17,
   "n": 1
  },
  {
   "mot": "propriyétè-fonsyé",
   "lettres": 17,
   "n": 1
  },
  {
   "mot": "twazè-d-laprémidi",
   "lettres": 17,
   "n": 1
  },
  {
   "mot": "bazil-lanmòsibit",
   "lettres": 16,
   "n": 1
  },
  {
   "mot": "fanm-laplenn-lin",
   "lettres": 16,
   "n": 1
  },
  {
   "mot": "konsititisyon-la",
   "lettres": 16,
   "n": 1
  },
  {
   "mot": "lawa-a-gran-tété",
   "lettres": 16,
   "n": 1
  },
  {
   "mot": "pawòl-senk-é-kat",
   "lettres": 16,
   "n": 1
  },
  {
   "mot": "toutmoun-bouliki",
   "lettres": 16,
   "n": 1
  },
  {
   "mot": "kréyòl-gwadloup",
   "lettres": 15,
   "n": 4
  },
  {
   "mot": "véridik-véritab",
   "lettres": 15,
   "n": 2
  },
  {
   "mot": "charlottesville",
   "lettres": 15,
   "n": 1
  },
  {
   "mot": "dèmen-spéra-dyé",
   "lettres": 15,
   "n": 1
  },
  {
   "mot": "jiwomon-malanga",
   "lettres": 15,
   "n": 1
  },
  {
   "mot": "konstitisyon-la",
   "lettres": 15,
   "n": 1
  }
 ],
 "longueur_mots": [
  {
   "lettres": 2,
   "mots": 102
  },
  {
   "lettres": 3,
   "mots": 417
  },
  {
   "lettres": 4,
   "mots": 727
  },
  {
   "lettres": 5,
   "mots": 919
  },
  {
   "lettres": 6,
   "mots": 932
  },
  {
   "lettres": 7,
   "mots": 720
  },
  {
   "lettres": 8,
   "mots": 527
  },
  {
   "lettres": 9,
   "mots": 372
  },
  {
   "lettres": 10,
   "mots": 232
  },
  {
   "lettres": 11,
   "mots": 129
  },
  {
   "lettres": 12,
   "mots": 89
  },
  {
   "lettres": 13,
   "mots": 71
  },
  {
   "lettres": 14,
   "mots": 23
  },
  {
   "lettres": 15,
   "mots": 13
  },
  {
   "lettres": 16,
   "mots": 6
  },
  {
   "lettres": 17,
   "mots": 4
  },
  {
   "lettres": 18,
   "mots": 1
  },
  {
   "lettres": 19,
   "mots": 1
  },
  {
   "lettres": 21,
   "mots": 1
  },
  {
   "lettres": 22,
   "mots": 1
  }
 ],
 "composes": {
  "mots": 1089,
  "pourcent": 20.6,
  "occurrences": 2323,
  "occurrences_pourcent": 6.4,
  "exemples": [
   {
    "mot": "a-y",
    "n": 130
   },
   {
    "mot": "an-mwen",
    "n": 88
   },
   {
    "mot": "a-w",
    "n": 60
   },
   {
    "mot": "an-nou",
    "n": 34
   },
   {
    "mot": "a-yo",
    "n": 34
   },
   {
    "mot": "ba-w",
    "n": 26
   },
   {
    "mot": "fi-la",
    "n": 26
   },
   {
    "mot": "ban-mwen",
    "n": 25
   },
   {
    "mot": "fè-mwen",
    "n": 21
   },
   {
    "mot": "kaz-la",
    "n": 20
   },
   {
    "mot": "rann-nou",
    "n": 19
   },
   {
    "mot": "di-mwen",
    "n": 18
   }
  ],
  "segments": [
   {
    "segments": 2,
    "mots": 1030
   },
   {
    "segments": 3,
    "mots": 53
   },
   {
    "segments": 4,
    "mots": 6
   }
  ]
 },
 "mots_10_lettres": {
  "mots": 571,
  "pourcent": 10.8,
  "avec_trait_union": 392,
  "hapax": 443
 },
 "tma": [
  {
   "marqueur": "ka",
   "fonction": "Aspect progressif ou habituel",
   "n": 1800,
   "pourcent": 4.93,
   "collocations": [
    {
     "mot": "fè",
     "n": 161
    },
    {
     "mot": "di",
     "n": 66
    },
    {
     "mot": "pran",
     "n": 59
    }
   ]
  },
  {
   "marqueur": "té",
   "fonction": "Passé",
   "n": 726,
   "pourcent": 1.99,
   "collocations": [
    {
     "mot": "ka",
     "n": 184
    },
    {
     "mot": "ké",
     "n": 111
    },
    {
     "mot": "ni",
     "n": 47
    }
   ]
  },
  {
   "marqueur": "ké",
   "fonction": "Futur",
   "n": 337,
   "pourcent": 0.92,
   "collocations": [
    {
     "mot": "pé",
     "n": 36
    },
    {
     "mot": "vlé",
     "n": 27
    },
    {
     "mot": "enmé",
     "n": 17
    }
   ]
  },
  {
   "marqueur": "kay",
   "fonction": "Futur proche",
   "n": 31,
   "pourcent": 0.08,
   "collocations": [
    {
     "mot": "òwganizé",
     "n": 4
    },
    {
     "mot": "bengné",
     "n": 3
    },
    {
     "mot": "palé",
     "n": 2
    }
   ]
  },
  {
   "marqueur": "pé",
   "fonction": "Possibilité",
   "n": 244,
   "pourcent": 0.67,
   "collocations": [
    {
     "mot": "ké",
     "n": 29
    },
    {
     "mot": "pa",
     "n": 21
    },
    {
     "mot": "fè",
     "n": 17
    }
   ]
  },
  {
   "marqueur": "ja",
   "fonction": "Accompli",
   "n": 97,
   "pourcent": 0.27,
   "collocations": [
    {
     "mot": "ka",
     "n": 15
    },
    {
     "mot": "ni",
     "n": 5
    },
    {
     "mot": "byen",
     "n": 4
    }
   ]
  },
  {
   "marqueur": "pa",
   "fonction": "Négation",
   "n": 664,
   "pourcent": 1.82,
   "collocations": [
    {
     "mot": "ka",
     "n": 87
    },
    {
     "mot": "té",
     "n": 68
    },
    {
     "mot": "ni",
     "n": 63
    }
   ]
  }
 ],
 "tma_combinaisons": [
  {
   "suite": "té ka",
   "n": 184
  },
  {
   "suite": "té ké",
   "n": 111
  },
  {
   "suite": "pa ka",
   "n": 87
  },
  {
   "suite": "pa té",
   "n": 68
  },
  {
   "suite": "ké pé",
   "n": 36
  },
  {
   "suite": "pé ké",
   "n": 29
  },
  {
   "suite": "pé pa",
   "n": 21
  },
  {
   "suite": "té ja",
   "n": 18
  },
  {
   "suite": "té pé",
   "n": 16
  },
  {
   "suite": "ja ka",
   "n": 15
  }
 ],
 "tma_part": 10.7,
 "top_sources": [
  {
   "source": "Soni RUPAIRE SOMANBIL, Pyès téyat, 3 LAK, « gran parad … ti kou baton », Edisyon PARABOLE, 1971",
   "court": "Soni RUPAIRE SOMANBIL, Pyès téyat, 3 LAK, «…",
   "mots": 7958,
   "lignes": 1,
   "caracteres": 42906
  },
  {
   "source": "POTOMITAN/potomitan-gcf-fr-translation (traduction FR)",
   "court": "POTOMITAN/potomitan-gcf-fr-translation…",
   "mots": 5587,
   "lignes": 1605,
   "caracteres": 28532
  },
  {
   "source": "Bel poveb kréyol, potomitan.info (collecte Jid)",
   "court": "Bel poveb kréyol, potomitan.info (collecte…",
   "mots": 2638,
   "lignes": 156,
   "caracteres": 12581
  },
  {
   "source": "Dialogue entre Léontin, Dèdèt, René, Ejèni, et Man Azoé",
   "court": "Dialogue entre Léontin, Dèdèt, René, Ejèni…",
   "mots": 2531,
   "lignes": 47,
   "caracteres": 12613
  },
  {
   "source": "Marga ANZALA, Zyé a Mangrov'la",
   "court": "Marga ANZALA, Zyé a Mangrov'la",
   "mots": 973,
   "lignes": 51,
   "caracteres": 4868
  },
  {
   "source": "Alain Rutil, Les belles paroles d'Albert Gaspard, 1987, Les Éditions Caribéennes, pp 59-61",
   "court": "Alain Rutil, Les belles paroles d'Albert…",
   "mots": 643,
   "lignes": 2,
   "caracteres": 3544
  },
  {
   "source": "Textes en créole de Romy Geneviève",
   "court": "Textes en créole de Romy Geneviève",
   "mots": 622,
   "lignes": 2,
   "caracteres": 3178
  },
  {
   "source": "Mé 67, Mové Doukou, Max Rippon, 31/12/2007",
   "court": "Mé 67, Mové Doukou, Max Rippon, 31/12/2007",
   "mots": 586,
   "lignes": 3,
   "caracteres": 2994
  },
  {
   "source": "Sonny Rupaire, Cette igname brisée qu'est ma terre natale, Editions Caribéennes, 1982.",
   "court": "Sonny Rupaire, Cette igname brisée qu'est…",
   "mots": 548,
   "lignes": 219,
   "caracteres": 2767
  },
  {
   "source": "Kon andidan papay …",
   "court": "Kon andidan papay …",
   "mots": 546,
   "lignes": 1,
   "caracteres": 2796
  },
  {
   "source": "Max Rippon, Pègmèl, 2013",
   "court": "Max Rippon, Pègmèl, 2013",
   "mots": 539,
   "lignes": 1,
   "caracteres": 2948
  },
  {
   "source": "La Jamaïque est mon Afrique, Gerty DAMBURY, Les Editions du Manguier, 2015",
   "court": "La Jamaïque est mon Afrique, Gerty DAMBURY…",
   "mots": 538,
   "lignes": 1,
   "caracteres": 2979
  },
  {
   "source": "Sa nou yé, Fleurs d'insomnies, Alain Verin, 2020",
   "court": "Sa nou yé, Fleurs d'insomnies, Alain Verin…",
   "mots": 528,
   "lignes": 1,
   "caracteres": 2721
  },
  {
   "source": "Contes créoles, Jean Juraver, 1985",
   "court": "Contes créoles, Jean Juraver, 1985",
   "mots": 503,
   "lignes": 1,
   "caracteres": 2832
  },
  {
   "source": "Marga ANZALA, plodari pou mangwòvla",
   "court": "Marga ANZALA, plodari pou mangwòvla",
   "mots": 489,
   "lignes": 22,
   "caracteres": 2373
  }
 ],
 "part_top10_sources": 62.0,
 "top_lettres": [
  {
   "lettre": "a",
   "n": 19559,
   "pourcent": 13.66
  },
  {
   "lettre": "n",
   "n": 15289,
   "pourcent": 10.68
  },
  {
   "lettre": "o",
   "n": 11262,
   "pourcent": 7.86
  },
  {
   "lettre": "é",
   "n": 9968,
   "pourcent": 6.96
  },
  {
   "lettre": "i",
   "n": 8449,
   "pourcent": 5.9
  },
  {
   "lettre": "t",
   "n": 7138,
   "pourcent": 4.98
  },
  {
   "lettre": "k",
   "n": 6739,
   "pourcent": 4.71
  },
  {
   "lettre": "l",
   "n": 6639,
   "pourcent": 4.64
  },
  {
   "lettre": "s",
   "n": 5736,
   "pourcent": 4.01
  },
  {
   "lettre": "u",
   "n": 5521,
   "pourcent": 3.86
  },
  {
   "lettre": "p",
   "n": 5339,
   "pourcent": 3.73
  },
  {
   "lettre": "m",
   "n": 5126,
   "pourcent": 3.58
  }
 ],
 "accents": [
  {
   "lettre": "é",
   "n": 9968
  },
  {
   "lettre": "è",
   "n": 4886
  },
  {
   "lettre": "ò",
   "n": 1753
  },
  {
   "lettre": "à",
   "n": 23
  },
  {
   "lettre": "ô",
   "n": 4
  },
  {
   "lettre": "ó",
   "n": 3
  },
  {
   "lettre": "â",
   "n": 1
  },
  {
   "lettre": "ê",
   "n": 1
  },
  {
   "lettre": "í",
   "n": 1
  },
  {
   "lettre": "á",
   "n": 1
  }
 ],
 "accents_pourcent": 11.62,
 "modele": {
  "cles": 8846,
  "cles_1mot": 4595,
  "cles_2mots": 4251,
  "contextes_ecartes": 14910,
  "candidats_moyen": 2.11
 },
 "contextes_frequents": [
  {
   "contexte": "ka",
   "suite": "fè",
   "probabilite": 0.089,
   "occurrences": 1800,
   "candidats": 5
  },
  {
   "contexte": "an",
   "suite": "ka",
   "probabilite": 0.102,
   "occurrences": 1388,
   "candidats": 5
  },
  {
   "contexte": "sé",
   "suite": "on",
   "probabilite": 0.092,
   "occurrences": 885,
   "candidats": 5
  },
  {
   "contexte": "on",
   "suite": "ti",
   "probabilite": 0.035,
   "occurrences": 833,
   "candidats": 5
  },
  {
   "contexte": "pou",
   "suite": "nou",
   "probabilite": 0.067,
   "occurrences": 727,
   "candidats": 5
  },
  {
   "contexte": "té",
   "suite": "ka",
   "probabilite": 0.253,
   "occurrences": 726,
   "candidats": 5
  },
  {
   "contexte": "pa",
   "suite": "ka",
   "probabilite": 0.131,
   "occurrences": 664,
   "candidats": 5
  },
  {
   "contexte": "yo",
   "suite": "ka",
   "probabilite": 0.182,
   "occurrences": 638,
   "candidats": 5
  },
  {
   "contexte": "nou",
   "suite": "ka",
   "probabilite": 0.115,
   "occurrences": 633,
   "candidats": 5
  },
  {
   "contexte": "ou",
   "suite": "ka",
   "probabilite": 0.237,
   "occurrences": 611,
   "candidats": 5
  },
  {
   "contexte": "ki",
   "suite": "té",
   "probabilite": 0.109,
   "occurrences": 548,
   "candidats": 5
  },
  {
   "contexte": "la",
   "suite": "ka",
   "probabilite": 0.108,
   "occurrences": 481,
   "candidats": 5
  },
  {
   "contexte": "ni",
   "suite": "on",
   "probabilite": 0.223,
   "occurrences": 408,
   "candidats": 5
  },
  {
   "contexte": "fè",
   "suite": "pou",
   "probabilite": 0.082,
   "occurrences": 404,
   "candidats": 5
  },
  {
   "contexte": "sa",
   "suite": "ki",
   "probabilite": 0.097,
   "occurrences": 401,
   "candidats": 5
  }
 ],
 "clavier": {
  "dictionnaire_mots": 5296,
  "ngrams_cles": 8852,
  "francais_mots": 662
 },
 "dataset": "POTOMITAN/PawolKreyol-gfc",
 "dataset_url": "https://huggingface.co/datasets/POTOMITAN/PawolKreyol-gfc",
 "source_donnees": "huggingface",
 "parquet_octets": 139578,
 "dataset_revision": "bcdf1d4ec2ba6e54cc7a70b90a2bb836c924c6d6",
 "dataset_revision_parquet": "e9ac8f8e9ad766cfc4f9306bb33b23ab54dd5098",
 "dataset_derniere_modification": "2026-10-01T09:43:50.000Z"
}