Skip to content

Instantly share code, notes, and snippets.

@graphemecluster
Created July 16, 2024 11:24
Show Gist options
  • Save graphemecluster/e59634a18d1d2927293aa7f40bb060e5 to your computer and use it in GitHub Desktop.
Save graphemecluster/e59634a18d1d2927293aa7f40bb060e5 to your computer and use it in GitHub Desktop.

Statistics

Input Letter Count (Case-Insensitive)

{
  "s": 117445,
  "e": 112183,
  "i": 84399,
  "a": 81719,
  "r": 73395,
  "n": 72052,
  "t": 66536,
  "o": 63243,
  "l": 52256,
  "c": 40521,
  "d": 35263,
  "'": 33990,
  "u": 33372,
  "m": 28651,
  "p": 28097,
  "g": 27974,
  "h": 24545,
  "b": 20299,
  "y": 16298,
  "f": 13454,
  "k": 10624,
  "v": 10094,
  "w": 9552,
  "x": 2726,
  "z": 2512,
  "j": 2358,
  "q": 1917
}

Input Letter Count (Case-Sensitive)

{
  "s": 115447,
  "e": 111387,
  "i": 83858,
  "a": 79913,
  "r": 72465,
  "n": 71326,
  "t": 65411,
  "o": 62676,
  "l": 51152,
  "c": 38579,
  "d": 34218,
  "'": 33990,
  "u": 33150,
  "g": 27009,
  "p": 26826,
  "m": 26641,
  "h": 23477,
  "b": 18622,
  "y": 16113,
  "f": 12766,
  "k": 9899,
  "v": 9656,
  "w": 8930,
  "x": 2656,
  "z": 2334,
  "M": 2010,
  "S": 1998,
  "C": 1942,
  "A": 1806,
  "q": 1805,
  "j": 1770,
  "B": 1677,
  "P": 1271,
  "T": 1125,
  "L": 1104,
  "H": 1068,
  "D": 1045,
  "G": 965,
  "R": 930,
  "E": 796,
  "N": 726,
  "K": 725,
  "F": 688,
  "W": 622,
  "J": 588,
  "O": 567,
  "I": 541,
  "V": 438,
  "U": 222,
  "Y": 185,
  "Z": 178,
  "Q": 112,
  "X": 70
}

Transcription Phoneme Count

{
  "ˈ": 123732,
  "ɪ": 92136,
  "s": 61957,
  "n": 57406,
  "t": 55604,
  "z": 54644,
  "ə": 53920,
  "l": 39681,
  "k": 39415,
  "ɹ": 39268,
  "d": 32606,
  "ˌ": 28926,
  "m": 27537,
  "p": 24561,
  "æ": 21964,
  "ɛ": 20920,
  "b": 19518,
  "e͡ɪ": 16683,
  "ɒ": 15180,
  "f": 14199,
  "ŋ": 13267,
  "ə͡ʊ": 12988,
  "ɐ": 12596,
  "a͡ɪ": 11924,
  "ʌ": 11408,
  "iː": 11271,
  "ɡ": 11190,
  "ʃ": 10418,
  "v": 10073,
  "uː": 9960,
  "ɔː": 8744,
  "ɑː": 8712,
  "w": 7844,
  "d͡ʒ": 7213,
  "h": 6959,
  "ə͡l": 6787,
  "j": 6761,
  "ɜː": 5416,
  "t͡ʃ": 4662,
  "i͡ə": 4060,
  "a͡ʊ": 3269,
  "θ": 2911,
  "ʊ": 2461,
  "e͡ə": 1660,
  "ɔ͡ɪ": 1303,
  "a͡ɪ͡ə": 1019,
  "ð": 673,
  "ʒ": 501,
  " ": 242,
  "x": 36
}

Phoneme Cluster Counts

  • Syllable and morpheme boundaries are unmarked in the data, so a cluster might spread across them.
  • ə͡l are counted as two separate phonemes.
  • Since there are plenty of redundant words in the list (like those end with 's), it may not reflect the actual usage.
  • Illegal English clusters do appear in the data. They are not cleansed.

Consonant Cluster Count (Long List!)

{
  "z": 31938,
  "l": 23602,
  "s": 21976,
  "n": 21906,
  "t": 21566,
  "ɹ": 20353,
  "k": 18198,
  "d": 18126,
  "m": 17242,
  "b": 11641,
  "p": 11405,
  "f": 8016,
  "nz": 7992,
  "ʃ": 7837,
  "ŋ": 7755,
  "v": 7570,
  "st": 6868,
  "d͡ʒ": 5650,
  "h": 5575,
  "ɡ": 5178,
  "nt": 4847,
  "w": 3999,
  "nd": 3995,
  "lz": 3914,
  "ts": 3884,
  "ks": 3346,
  "ns": 3328,
  "t͡ʃ": 3055,
  "pɹ": 2930,
  "tɹ": 2490,
  "dz": 2092,
  "mz": 2001,
  "kɹ": 2000,
  "ɡɹ": 1999,
  "kl": 1942,
  "sk": 1858,
  "kt": 1804,
  "bɹ": 1641,
  "sp": 1586,
  "θ": 1546,
  "nts": 1484,
  "bl": 1474,
  "ŋz": 1416,
  "sts": 1412,
  "ld": 1360,
  "sl": 1330,
  "ŋk": 1328,
  "pl": 1279,
  "mp": 1255,
  "kw": 1224,
  "ps": 1203,
  "fl": 1125,
  "j": 1076,
  "stɹ": 1070,
  "fɹ": 1061,
  "sn": 1053,
  "dɹ": 986,
  "mb": 949,
  "nj": 784,
  "kj": 764,
  "lt": 761,
  "ɡz": 730,
  "nd͡ʒ": 696,
  "pt": 684,
  "ɡl": 642,
  "ŋɡ": 635,
  "nf": 619,
  "kʃ": 576,
  "nʃ": 563,
  "sw": 563,
  "ð": 563,
  "ntɹ": 548,
  "vz": 545,
  "ndz": 544,
  "sm": 540,
  "zd": 529,
  "mj": 524,
  "kz": 520,
  "nv": 497,
  "dl": 484,
  "tl": 484,
  "nt͡ʃ": 482,
  "tj": 445,
  "skɹ": 443,
  "ft": 441,
  "ʒ": 430,
  "bz": 411,
  "ɡn": 405,
  "dj": 403,
  "nst": 390,
  "nl": 370,
  "ln": 363,
  "lm": 359,
  "pj": 357,
  "fs": 352,
  "tw": 341,
  "tz": 305,
  "mpl": 295,
  "bj": 289,
  "kst": 288,
  "nh": 285,
  "ŋl": 284,
  "ksp": 279,
  "ls": 273,
  "nm": 271,
  "lb": 270,
  "lk": 269,
  "lf": 264,
  "tn": 264,
  "md": 262,
  "dn": 252,
  "ntl": 252,
  "nɹ": 251,
  "vl": 249,
  "nb": 248,
  "vn": 247,
  "sf": 243,
  "θɹ": 241,
  "lv": 240,
  "fj": 240,
  "skw": 231,
  "lj": 227,
  "mn": 220,
  "ŋks": 216,
  "kts": 208,
  "ndɹ": 207,
  "spɹ": 199,
  "mpɹ": 198,
  "bs": 197,
  "tm": 196,
  "sb": 192,
  "ml": 187,
  "nw": 185,
  "nstɹ": 184,
  "dw": 183,
  "ŋɡɹ": 183,
  "tf": 182,
  "ɡj": 180,
  "ldz": 180,
  "kn": 180,
  "hj": 177,
  "θz": 176,
  "dm": 175,
  "zm": 172,
  "d͡ʒz": 170,
  "ʃn": 165,
  "ŋkl": 163,
  "kt͡ʃ": 162,
  "pʃ": 161,
  "ktɹ": 158,
  "lp": 154,
  "mf": 154,
  "ʃt": 151,
  "spl": 150,
  "mps": 149,
  "np": 148,
  "dv": 147,
  "lts": 141,
  "tb": 141,
  "bd": 135,
  "mpt": 135,
  "nsp": 135,
  "lɡ": 131,
  "ŋkɹ": 129,
  "ŋɡl": 128,
  "d͡ʒd": 128,
  "nfl": 128,
  "nn": 126,
  "nθ": 125,
  "ɡm": 125,
  "kstɹ": 125,
  "ʃɹ": 125,
  "st͡ʃ": 124,
  "t͡ʃt": 124,
  "ndl": 121,
  "θs": 121,
  "ŋkw": 120,
  "stj": 120,
  "lw": 119,
  "vd": 119,
  "th": 118,
  "ŋkt": 118,
  "kb": 117,
  "ɡw": 116,
  "mbl": 116,
  "ʃm": 114,
  "vj": 113,
  "mbɹ": 109,
  "fts": 106,
  "lh": 105,
  "lɹ": 105,
  "fz": 103,
  "db": 102,
  "lt͡ʃ": 101,
  "ʃl": 100,
  "dh": 98,
  "tk": 98,
  "sɹ": 96,
  "ld͡ʒ": 93,
  "nfɹ": 93,
  "sj": 92,
  "lst": 89,
  "ɡd": 88,
  "ds": 88,
  "ms": 88,
  "bst": 88,
  "pz": 87,
  "ltɹ": 86,
  "kh": 84,
  "skj": 82,
  "dk": 80,
  "lʃ": 78,
  "θl": 76,
  "mpj": 76,
  "sd": 74,
  "tp": 73,
  "stm": 73,
  "stl": 72,
  "kspl": 72,
  "t͡ʃm": 71,
  "sh": 70,
  "ŋɡw": 68,
  "nsm": 68,
  "km": 67,
  "nsl": 67,
  "bd͡ʒ": 67,
  "mɹ": 65,
  "zl": 65,
  "ndj": 65,
  "ŋkʃ": 65,
  "mw": 64,
  "θw": 64,
  "ndb": 63,
  "pst": 62,
  "ksk": 62,
  "mst": 61,
  "pm": 60,
  "nsj": 59,
  "dst": 59,
  "nsk": 57,
  "npɹ": 57,
  "nθɹ": 56,
  "ŋh": 56,
  "nskɹ": 56,
  "stf": 56,
  "sks": 55,
  "dp": 54,
  "pts": 54,
  "pt͡ʃ": 54,
  "pk": 53,
  "dʃ": 53,
  "ʃw": 52,
  "df": 52,
  "pw": 52,
  "ndm": 52,
  "kf": 50,
  "kp": 49,
  "d͡ʒm": 49,
  "nsf": 49,
  "bstɹ": 49,
  "sɡ": 48,
  "bm": 48,
  "lθ": 47,
  "zw": 47,
  "stb": 47,
  "nds": 45,
  "mbj": 45,
  "kd": 45,
  "spj": 45,
  "bt": 45,
  "ŋɡj": 45,
  "pn": 45,
  "ŋt": 44,
  "zb": 44,
  "tʃ": 44,
  "ŋkj": 44,
  "pb": 43,
  "ŋd": 43,
  "vɹ": 43,
  "nfj": 43,
  "sθ": 43,
  "ntm": 43,
  "nd͡ʒd": 43,
  "d͡ʒj": 42,
  "ndh": 42,
  "bk": 42,
  "ɡh": 41,
  "lkj": 40,
  "mk": 40,
  "ŋkt͡ʃ": 40,
  "skl": 40,
  "ðz": 39,
  "kspɹ": 39,
  "θf": 39,
  "ndw": 38,
  "bn": 37,
  "ntj": 37,
  "tst": 37,
  "ndn": 36,
  "ʃb": 36,
  "ŋb": 36,
  "fb": 35,
  "ldɹ": 35,
  "mh": 35,
  "mt": 35,
  "zz": 35,
  "zn": 35,
  "kst͡ʃ": 35,
  "t͡ʃb": 35,
  "nt͡ʃt": 35,
  "stw": 34,
  "zj": 34,
  "pd": 34,
  "tsk": 33,
  "pf": 33,
  "lvz": 33,
  "npl": 33,
  "ʃk": 32,
  "t͡ʃw": 32,
  "mpʃ": 32,
  "tɡ": 32,
  "ndp": 32,
  "btɹ": 32,
  "stn": 31,
  "fn": 31,
  "lfɹ": 30,
  "ŋst": 30,
  "sd͡ʒ": 30,
  "lks": 30,
  "tsm": 29,
  "ktn": 29,
  "kskɹ": 29,
  "ndf": 29,
  "d͡ʒn": 29,
  "ph": 29,
  "θj": 28,
  "bv": 28,
  "ndst": 27,
  "ll": 27,
  "t͡ʃl": 26,
  "ksl": 26,
  "sps": 26,
  "vm": 26,
  "dzm": 26,
  "ðd": 26,
  "nsw": 25,
  "nbɹ": 25,
  "ɡb": 25,
  "lsp": 25,
  "kskl": 25,
  "bskɹ": 25,
  "tsw": 24,
  "zk": 24,
  "ŋf": 24,
  "bw": 24,
  "mʃ": 24,
  "ŋθ": 24,
  "lfs": 23,
  "nθz": 23,
  "bh": 23,
  "ntn": 23,
  "bf": 23,
  "tkɹ": 23,
  "lɡɹ": 22,
  "ŋn": 22,
  "sbɹ": 22,
  "θm": 22,
  "ɡf": 21,
  "td": 21,
  "lbɹ": 21,
  "fd": 21,
  "tsp": 21,
  "t͡ʃd": 21,
  "ksm": 21,
  "nθs": 21,
  "sʃ": 21,
  "nsn": 21,
  "θn": 21,
  "skz": 20,
  "d͡ʒɹ": 20,
  "fθ": 20,
  "ktl": 20,
  "nd͡ʒm": 20,
  "ldl": 20,
  "tbɹ": 20,
  "lps": 19,
  "psk": 19,
  "ldf": 19,
  "skt": 19,
  "fɡ": 18,
  "ntw": 18,
  "ŋʃ": 18,
  "sv": 18,
  "ʒz": 18,
  "fh": 18,
  "ɡzj": 18,
  "fk": 17,
  "lmz": 17,
  "vw": 17,
  "tt": 17,
  "vsk": 17,
  "dɡ": 17,
  "zɹ": 17,
  "dt": 17,
  "mv": 17,
  "nzm": 17,
  "ss": 17,
  "ɡp": 17,
  "lvd": 17,
  "tstɹ": 17,
  "sɡɹ": 17,
  "ndk": 17,
  "ŋkf": 16,
  "nt͡ʃm": 16,
  "ʃj": 16,
  "ksh": 16,
  "ldw": 15,
  "nbl": 15,
  "lpl": 15,
  "nθj": 15,
  "tpɹ": 15,
  "ŋkn": 15,
  "θt": 15,
  "nʒ": 15,
  "d͡ʒh": 15,
  "tpl": 15,
  "sst": 15,
  "ssp": 15,
  "bskj": 15,
  "mstɹ": 14,
  "stk": 14,
  "t͡ʃp": 14,
  "ksf": 14,
  "d͡ʒl": 14,
  "ptn": 14,
  "t͡ʃf": 14,
  "kk": 14,
  "zp": 14,
  "mfl": 14,
  "ktf": 14,
  "ɡst": 14,
  "stp": 14,
  "ŋm": 14,
  "ɡt": 14,
  "ɡʒ": 14,
  "tkl": 14,
  "lsk": 13,
  "dstɹ": 13,
  "sth": 13,
  "fw": 13,
  "lkɹ": 13,
  "dθ": 13,
  "lkw": 13,
  "ŋw": 13,
  "fst": 13,
  "t͡ʃh": 13,
  "ksw": 13,
  "ptj": 13,
  "ŋkh": 13,
  "ndbɹ": 13,
  "kbɹ": 13,
  "ldk": 13,
  "ndʃ": 13,
  "md͡ʒ": 12,
  "ɡs": 12,
  "lkl": 12,
  "mm": 12,
  "nsv": 12,
  "nth": 12,
  "ldn": 12,
  "mpt͡ʃ": 12,
  "ksts": 12,
  "ndsk": 12,
  "lpt": 12,
  "θp": 12,
  "pɡ": 12,
  "zt": 11,
  "tv": 11,
  "ŋs": 11,
  "t͡ʃn": 11,
  "ftw": 11,
  "td͡ʒ": 11,
  "dsw": 11,
  "nd͡ʒj": 11,
  "bd͡ʒj": 11,
  "ndzm": 11,
  "nθl": 11,
  "bsl": 11,
  "lbl": 11,
  "lfl": 11,
  "θb": 11,
  "ʃp": 11,
  "bb": 11,
  "pfɹ": 11,
  "sfl": 11,
  "kθ": 10,
  "ŋstɹ": 10,
  "nhj": 10,
  "dsl": 10,
  "dbɹ": 10,
  "ldb": 10,
  "t͡ʃk": 10,
  "hw": 10,
  "ntb": 10,
  "t͡ʃs": 10,
  "d͡ʒw": 10,
  "mpts": 10,
  "dt͡ʃ": 10,
  "psj": 10,
  "mft": 10,
  "ftsm": 10,
  "ftn": 10,
  "nʃɹ": 10,
  "ntf": 10,
  "kskj": 10,
  "ndt͡ʃ": 10,
  "bdj": 10,
  "zf": 10,
  "pbɹ": 10,
  "nsɡɹ": 10,
  "x": 9,
  "xs": 9,
  "xt": 9,
  "msk": 9,
  "kɡ": 9,
  "dsp": 9,
  "tt͡ʃ": 9,
  "bsk": 9,
  "tfl": 9,
  "kd͡ʒ": 9,
  "ŋkts": 9,
  "lkt": 9,
  "ftl": 9,
  "ɡk": 9,
  "ɡʃ": 9,
  "ktm": 9,
  "skm": 9,
  "ndbl": 9,
  "nspl": 9,
  "pdɹ": 9,
  "lkm": 8,
  "d͡ʒp": 8,
  "t͡ʃz": 8,
  "ldm": 8,
  "mt͡ʃ": 8,
  "ŋkz": 8,
  "lstɹ": 8,
  "mpk": 8,
  "ldh": 8,
  "vt": 8,
  "nsʃ": 8,
  "skn": 8,
  "sfɹ": 8,
  "ŋktn": 8,
  "dfl": 8,
  "mfz": 8,
  "sbl": 8,
  "ldbɹ": 8,
  "nt͡ʃb": 8,
  "tdɹ": 8,
  "tɡɹ": 8,
  "std": 8,
  "dbl": 8,
  "pɡɹ": 8,
  "nsmj": 8,
  "θdɹ": 8,
  "lfz": 7,
  "ltm": 7,
  "zɡ": 7,
  "nt͡ʃl": 7,
  "ŋɡz": 7,
  "nt͡ʃw": 7,
  "ldsm": 7,
  "lbz": 7,
  "ŋd͡ʒ": 7,
  "ɡsk": 7,
  "ldj": 7,
  "ksn": 7,
  "t͡ʃj": 7,
  "ʃd": 7,
  "ptl": 7,
  "ðst": 7,
  "ŋkm": 7,
  "t͡ʃɡ": 7,
  "mskɹ": 7,
  "spt": 7,
  "lpɹ": 7,
  "ftb": 7,
  "vzdɹ": 7,
  "dpl": 7,
  "dsk": 7,
  "ŋkst": 7,
  "ndsl": 7,
  "pstɹ": 7,
  "nsfj": 7,
  "zv": 6,
  "tsks": 6,
  "fp": 6,
  "nsb": 6,
  "lsw": 6,
  "tsb": 6,
  "fm": 6,
  "mfɹ": 6,
  "dkl": 6,
  "ʒw": 6,
  "ŋksɡ": 6,
  "nzd": 6,
  "vb": 6,
  "stz": 6,
  "kɡɹ": 6,
  "ŋkb": 6,
  "ŋkk": 6,
  "ʒd": 6,
  "ʃf": 6,
  "θst": 6,
  "ðn": 6,
  "tskɹ": 6,
  "kpl": 6,
  "nd͡ʒl": 6,
  "msp": 6,
  "ptɹ": 6,
  "lsl": 6,
  "ftsw": 6,
  "tθɹ": 6,
  "mpn": 6,
  "ltl": 6,
  "ʃkl": 6,
  "vst": 6,
  "lpf": 6,
  "mbsk": 6,
  "nt͡ʃp": 6,
  "t͡ʃst": 6,
  "btj": 6,
  "fʃ": 6,
  "nʃj": 6,
  "lpt͡ʃ": 6,
  "ndpɹ": 6,
  "bpɹ": 6,
  "mtɹ": 5,
  "lkh": 5,
  "lsm": 5,
  "hz": 5,
  "nsks": 5,
  "ŋɡd": 5,
  "tsɹ": 5,
  "t͡ʃd͡ʒ": 5,
  "vh": 5,
  "hɹ": 5,
  "ɡd͡ʒ": 5,
  "ʃtɹ": 5,
  "ʃh": 5,
  "tbj": 5,
  "dɡɹ": 5,
  "bsp": 5,
  "ntd͡ʒ": 5,
  "θsk": 5,
  "vp": 5,
  "ŋp": 5,
  "pd͡ʒ": 5,
  "ksb": 5,
  "bɡ": 5,
  "lbj": 5,
  "dθs": 5,
  "nspɹ": 5,
  "ltw": 5,
  "dkɹ": 5,
  "kfɹ": 5,
  "dsm": 5,
  "lθz": 5,
  "bɡɹ": 5,
  "mpm": 5,
  "ɡtɹ": 5,
  "vk": 5,
  "ndɡ": 5,
  "lsn": 5,
  "ltf": 5,
  "lmd": 5,
  "mkɹ": 5,
  "ntsm": 5,
  "ndkl": 5,
  "mdɹ": 5,
  "ndkɹ": 5,
  "dkw": 5,
  "lθf": 5,
  "nnj": 5,
  "bsw": 5,
  "stpɹ": 5,
  "lzm": 5,
  "dtɹ": 5,
  "bkj": 5,
  "ðh": 5,
  "lph": 4,
  "msl": 4,
  "ʃɡ": 4,
  "ɡsb": 4,
  "xts": 4,
  "lsb": 4,
  "fsk": 4,
  "dsd": 4,
  "vsks": 4,
  "msd": 4,
  "t͡ʃkj": 4,
  "nzb": 4,
  "ŋʒ": 4,
  "ʃv": 4,
  "psw": 4,
  "ŋzt": 4,
  "nt͡ʃj": 4,
  "ntɡ": 4,
  "lsbɹ": 4,
  "stɡ": 4,
  "tsd": 4,
  "nzw": 4,
  "θk": 4,
  "lʃm": 4,
  "lth": 4,
  "kkl": 4,
  "t͡ʃfɹ": 4,
  "dspɹ": 4,
  "lt͡ʃt": 4,
  "ðs": 4,
  "tbl": 4,
  "ksɹ": 4,
  "dθz": 4,
  "ld͡ʒd": 4,
  "ldpɹ": 4,
  "ntd": 4,
  "lft": 4,
  "mpst": 4,
  "kskw": 4,
  "tsl": 4,
  "bsm": 4,
  "vs": 4,
  "ndsw": 4,
  "dskɹ": 4,
  "mpb": 4,
  "ðm": 4,
  "nsd": 4,
  "nd͡ʒf": 4,
  "mθ": 4,
  "ŋɹ": 4,
  "bp": 4,
  "bsj": 4,
  "pθɹ": 4,
  "θʃ": 3,
  "d͡ʒs": 3,
  "bfɹ": 3,
  "wz": 3,
  "ŋj": 3,
  "lθj": 3,
  "thz": 3,
  "mdz": 3,
  "dd͡ʒ": 3,
  "bdz": 3,
  "ftm": 3,
  "msh": 3,
  "t͡ʃdj": 3,
  "kdɹ": 3,
  "θh": 3,
  "sʃj": 3,
  "θd": 3,
  "θpl": 3,
  "ðl": 3,
  "dfɹ": 3,
  "kθɹ": 3,
  "stpl": 3,
  "ststɹ": 3,
  "bdɹ": 3,
  "mpf": 3,
  "mpɡɹ": 3,
  "mpd": 3,
  "ðsh": 3,
  "ðsl": 3,
  "ðsp": 3,
  "kkɹ": 3,
  "psm": 3,
  "kssw": 3,
  "t͡ʃʃ": 3,
  "θbl": 3,
  "θtɹ": 3,
  "ŋktl": 3,
  "vʃ": 3,
  "θkw": 3,
  "ɡpl": 3,
  "lsh": 3,
  "lmstɹ": 3,
  "mθɹ": 3,
  "ʃkj": 3,
  "flj": 3,
  "ksɡl": 3,
  "ŋpl": 3,
  "ŋkɡ": 3,
  "pv": 3,
  "mzm": 3,
  "mkh": 3,
  "ndspɹ": 3,
  "ddɹ": 3,
  "dʃɹ": 3,
  "lmzm": 3,
  "lpm": 3,
  "ndkw": 3,
  "ɡsh": 3,
  "lnd": 3,
  "ŋkbl": 3,
  "lvm": 3,
  "sθm": 3,
  "kkn": 3,
  "mkw": 3,
  "mbk": 3,
  "ŋθz": 3,
  "ŋθs": 3,
  "ltd": 3,
  "lkʃ": 3,
  "nt͡ʃk": 3,
  "zɡɹ": 3,
  "zst": 3,
  "fpɹ": 3,
  "ldst": 3,
  "nd͡ʒn": 3,
  "tspɹ": 3,
  "d͡ʒb": 3,
  "ntbɹ": 3,
  "pskw": 3,
  "ðsm": 3,
  "stɡɹ": 3,
  "stskɹ": 3,
  "lskl": 3,
  "lsɡ": 3,
  "ltb": 3,
  "ltʃ": 3,
  "ŋktj": 3,
  "lptɹ": 3,
  "mpstɹ": 3,
  "tfɹ": 3,
  "lkskɹ": 3,
  "ndtɹ": 3,
  "ndθɹ": 3,
  "nt͡ʃn": 3,
  "bbɹ": 3,
  "bhj": 3,
  "bpl": 3,
  "lfj": 3,
  "t͡ʃbl": 3,
  "mptɹ": 3,
  "kstb": 3,
  "mbpɹ": 3,
  "mbskɹ": 3,
  "mbt": 3,
  "θbɹ": 3,
  "t͡ʃskɹ": 3,
  "nsdj": 3,
  "nsd͡ʒ": 3,
  "pskɹ": 3,
  "ʃst": 3,
  "lspɹ": 3,
  "ldfl": 3,
  "ndfl": 3,
  "ndskɹ": 3,
  "ŋsp": 3,
  "ŋspɹ": 3,
  "lfh": 3,
  "kfl": 3,
  "ldvj": 3,
  "mmn": 2,
  "ɡnj": 2,
  "xm": 2,
  "khm": 2,
  "ʃkɹ": 2,
  "ʃkh": 2,
  "ztl": 2,
  "ld͡ʒj": 2,
  "msbɹ": 2,
  "ltzm": 2,
  "ʒn": 2,
  "nzv": 2,
  "nszv": 2,
  "szv": 2,
  "ŋt͡ʃ": 2,
  "t͡ʃnj": 2,
  "bt͡ʃ": 2,
  "stt͡ʃ": 2,
  "tmn": 2,
  "lds": 2,
  "nzbɹ": 2,
  "kwj": 2,
  "ʃts": 2,
  "tsd͡ʒ": 2,
  "ntst": 2,
  "nzz": 2,
  "lbv": 2,
  "d͡ʒt": 2,
  "ztɹ": 2,
  "tzk": 2,
  "sz": 2,
  "skd͡ʒ": 2,
  "psb": 2,
  "ptm": 2,
  "ŋd͡ʒj": 2,
  "lmh": 2,
  "ltz": 2,
  "tsspɹ": 2,
  "d͡ʒk": 2,
  "hnhn": 2,
  "θɡ": 2,
  "vf": 2,
  "khn": 2,
  "mzt": 2,
  "sfs": 2,
  "hs": 2,
  "khst": 2,
  "jj": 2,
  "xw": 2,
  "pfs": 2,
  "ksv": 2,
  "kʃm": 2,
  "ŋmj": 2,
  "blj": 2,
  "vkɹ": 2,
  "mfj": 2,
  "ntk": 2,
  "ntp": 2,
  "nt͡ʃh": 2,
  "vɡ": 2,
  "ksz": 2,
  "lmst": 2,
  "msks": 2,
  "lmb": 2,
  "ntt͡ʃ": 2,
  "hŋkw": 2,
  "t͡ʃθ": 2,
  "zkɹ": 2,
  "ltsk": 2,
  "msf": 2,
  "ɹj": 2,
  "lsf": 2,
  "zdz": 2,
  "lzn": 2,
  "dzz": 2,
  "ɡfɹ": 2,
  "lʒ": 2,
  "ŋhj": 2,
  "dʒ": 2,
  "lmj": 2,
  "lksv": 2,
  "lfɡ": 2,
  "wk": 2,
  "ŋts": 2,
  "ɡdɹ": 2,
  "knz": 2,
  "vdz": 2,
  "ŋsɡ": 2,
  "ʃstɹ": 2,
  "lkz": 2,
  "zkl": 2,
  "nls": 2,
  "spbɹ": 2,
  "spn": 2,
  "lftw": 2,
  "ɡsl": 2,
  "stʃ": 2,
  "tθ": 2,
  "tθz": 2,
  "tθs": 2,
  "lfm": 2,
  "lsj": 2,
  "ldsp": 2,
  "ldzm": 2,
  "mbz": 2,
  "msm": 2,
  "ɡlj": 2,
  "lndz": 2,
  "bʃ": 2,
  "d͡ʒʃ": 2,
  "lnz": 2,
  "mpbl": 2,
  "fbl": 2,
  "fsp": 2,
  "vt͡ʃ": 2,
  "lnj": 2,
  "nʒt": 2,
  "dd": 2,
  "lkts": 2,
  "zfl": 2,
  "zh": 2,
  "zpɹ": 2,
  "fspɹ": 2,
  "ksbl": 2,
  "sthj": 2,
  "mptn": 2,
  "lpw": 2,
  "ʃt͡ʃ": 2,
  "vdn": 2,
  "d͡ʒbɹ": 2,
  "lsɹ": 2,
  "ltp": 2,
  "ŋfɹ": 2,
  "tsj": 2,
  "tskw": 2,
  "kbdz": 2,
  "ksʃ": 2,
  "t͡ʃɹ": 2,
  "ɡfl": 2,
  "ntʃ": 2,
  "psp": 2,
  "d͡ʒdz": 2,
  "t͡ʃstɹ": 2,
  "t͡ʃkɹ": 2,
  "fdk": 1,
  "kbz": 1,
  "lsks": 1,
  "ntz": 1,
  "bhz": 1,
  "nbz": 1,
  "nsts": 1,
  "fsl": 1,
  "lsts": 1,
  "ldt": 1,
  "ldts": 1,
  "ntzv": 1,
  "ntszv": 1,
  "mnʃ": 1,
  "nsbɹ": 1,
  "mts": 1,
  "sɡz": 1,
  "pks": 1,
  "szt": 1,
  "szts": 1,
  "t͡ʃtz": 1,
  "bsts": 1,
  "xst": 1,
  "bts": 1,
  "kv": 1,
  "skɡ": 1,
  "zmk": 1,
  "lʃw": 1,
  "lff": 1,
  "lffs": 1,
  "dvt": 1,
  "lð": 1,
  "ŋsts": 1,
  "vdp": 1,
  "ðdz": 1,
  "ðɹ": 1,
  "ldbl": 1,
  "lθs": 1,
  "nt͡ʃz": 1,
  "ftsp": 1,
  "lfts": 1,
  "pθ": 1,
  "pθz": 1,
  "pθs": 1,
  "dnt": 1,
  "mfs": 1,
  "fθz": 1,
  "fθl": 1,
  "fθs": 1,
  "knj": 1,
  "ɡsp": 1,
  "lθk": 1,
  "t͡ʃɡw": 1,
  "mɡɹ": 1,
  "dmp": 1,
  "sθmj": 1,
  "mbsw": 1,
  "ŋθw": 1,
  "ff": 1,
  "vnd": 1,
  "vnz": 1,
  "fd͡ʒ": 1,
  "dsts": 1,
  "tsv": 1,
  "pɡz": 1,
  "lktf": 1,
  "nð": 1,
  "ftɹ": 1,
  "ftt": 1,
  "ɡsw": 1,
  "ntbl": 1,
  "mptl": 1,
  "ksps": 1,
  "wd": 1,
  "wdz": 1,
  "lpts": 1,
  "kpɹ": 1,
  "kbd": 1,
  "dspl": 1,
  "ksθ": 1,
  "ksθz": 1,
  "ksθs": 1,
  "ftk": 1,
  "fth": 1,
  "bbd": 1,
  "bkl": 1,
  "nbd": 1,
  "nbdz": 1,
  "ptb": 1,
  "skb": 1,
  "ndθ": 1,
  "ndθz": 1,
  "ndθs": 1,
  "pfl": 1,
  "lfθ": 1,
  "lfθz": 1,
  "lfθs": 1,
  "nmj": 1,
  "lvl": 1,
  "lvj": 1,
  "ltst": 1,
  "mθz": 1,
  "vfɹ": 1
}

Vowel Cluster Count

{
  "ɪ": 85277,
  "ə": 57826,
  "æ": 21370,
  "ɛ": 20417,
  "e͡ɪ": 15317,
  "ɒ": 14691,
  "ə͡ʊ": 11537,
  "ʌ": 11370,
  "ɐ": 11282,
  "a͡ɪ": 10924,
  "iː": 9864,
  "ɔː": 8647,
  "ɑː": 8549,
  "uː": 8484,
  "ɜː": 5400,
  "i͡ə": 4052,
  "a͡ʊ": 2904,
  "ʊ": 2453,
  "e͡ə": 1618,
  "ɔ͡ɪ": 1123,
  "ɪə": 1026,
  "a͡ɪ͡ə": 1019,
  "ɪɪ": 871,
  "ɪɐ": 868,
  "uːə": 650,
  "ɪe͡ɪ": 471,
  "ɪə͡ʊ": 419,
  "a͡ɪə": 371,
  "uːɪ": 363,
  "ɪɒ": 303,
  "ɪæ": 301,
  "ə͡ʊɪ": 301,
  "iːɪ": 278,
  "a͡ʊə": 230,
  "iːɛ": 218,
  "iːə": 197,
  "e͡ɪɪ": 195,
  "uːe͡ɪ": 173,
  "a͡ɪɪ": 169,
  "e͡ɪə": 166,
  "iːɐ": 151,
  "iːə͡ʊ": 143,
  "ə͡ʊə": 133,
  "iːe͡ɪ": 113,
  "a͡ɪə͡ʊ": 102,
  "ɔ͡ɪə": 90,
  "iːæ": 90,
  "ɪɛ": 89,
  "a͡ɪæ": 85,
  "a͡ɪɒ": 81,
  "uːɛ": 68,
  "ɪɔː": 62,
  "ɪɑː": 61,
  "ə͡ʊɐ": 58,
  "uːɐ": 57,
  "e͡ɪɐ": 51,
  "a͡ɪɐ": 50,
  "iːɑː": 50,
  "a͡ʊɐ": 48,
  "uːæ": 47,
  "ə͡ʊɛ": 43,
  "ə͡ʊæ": 41,
  "ɔ͡ɪɪ": 40,
  "a͡ʊɪ": 38,
  "e͡ɪə͡ʊ": 37,
  "ɪe͡ə": 34,
  "e͡ɪɛ": 32,
  "iːɒ": 32,
  "e͡ɪɒ": 27,
  "ə͡ʊɒ": 27,
  "uːiː": 24,
  "a͡ɪɛ": 22,
  "ə͡ʊɔː": 20,
  "a͡ɪiː": 19,
  "e͡ɪɑː": 18,
  "a͡ʊɛ": 17,
  "ɔ͡ɪɐ": 17,
  "uːə͡ʊ": 17,
  "uːɒ": 17,
  "iːa͡ɪ": 16,
  "ɪʌ": 14,
  "e͡ɪæ": 13,
  "a͡ɪe͡ɪ": 13,
  "uːɑː": 12,
  "a͡ɪɑː": 11,
  "ɪiː": 11,
  "a͡ɪʌ": 11,
  "ə͡ʊɜː": 10,
  "ə͡ʊiː": 9,
  "ɔ͡ɪə͡ʊ": 9,
  "ə͡ʊe͡ɪ": 8,
  "ə͡ʊʌ": 8,
  "uːe͡ɪə": 7,
  "ə͡ʊɑː": 7,
  "ɪa͡ɪ": 7,
  "iːiː": 6,
  "a͡ɪə͡ʊə": 6,
  "ʊæ": 6,
  "a͡ɪa͡ʊ": 6,
  "e͡ɪa͡ʊ": 6,
  "ɛɪ": 5,
  "e͡ɪiː": 5,
  "a͡ɪuː": 5,
  "uːɪɪ": 5,
  "a͡ʊiː": 5,
  "ə͡ʊɪɐ": 5,
  "ə͡ʊɪɪ": 5,
  "ɔ͡ɪe͡ɪ": 5,
  "ɪə͡ʊæ": 5,
  "ə͡ʊi͡ə": 5,
  "ə͡ʊə͡ʊ": 4,
  "uːɔː": 4,
  "ɔ͡ɪɑː": 4,
  "ɪuː": 4,
  "iːe͡ə": 4,
  "e͡ɪɔː": 4,
  "uːɪɐ": 4,
  "uːa͡ʊ": 4,
  "iːa͡ʊ": 4,
  "iːɔː": 4,
  "e͡ɪa͡ɪ": 3,
  "iːa͡ɪe͡ɪ": 3,
  "e͡ɪuː": 3,
  "uːɜː": 3,
  "a͡ɪi͡ə": 3,
  "ɪɜː": 3,
  "ə͡ʊa͡ʊ": 3,
  "ə͡ʊe͡ə": 3,
  "ɔ͡ɪɛ": 3,
  "ɔ͡ɪiː": 3,
  "e͡ɪʌ": 3,
  "ɪɔ͡ɪ": 3,
  "a͡ɪɔː": 3,
  "ɪə͡ʊa͡ɪ": 3,
  "e͡ɪə͡ʊɛ": 2,
  "æɪ": 2,
  "iːiːə͡ʊ": 2,
  "uːʊ": 2,
  "ɪə͡ʊə": 2,
  "ɔ͡ɪæ": 2,
  "ɔ͡ɪɒ": 2,
  "a͡ʊuː": 2,
  "ɔ͡ɪʌ": 2,
  "iːuː": 2,
  "a͡ɪə͡ʊɛ": 2,
  "ɪə͡ʊɪ": 2,
  "e͡ɪe͡ɪe͡ɪ": 1,
  "uːe͡ɪɐ": 1,
  "iːa͡ɪɐ": 1,
  "iːa͡ɪə": 1,
  "æiːɐ": 1,
  "æiːə": 1,
  "a͡ɪa͡ɪ": 1,
  "a͡ɪiːiːiː": 1,
  "ɪə͡ʊɐ": 1,
  "iːə͡ʊe͡ɪ": 1,
  "a͡ɪə͡ʊa͡ɪ": 1,
  "uːa͡ɪ": 1,
  "uːe͡ə": 1,
  "ɪa͡ʊ": 1,
  "e͡ɪɪɐ": 1,
  "e͡ɪɪɪ": 1,
  "ɛə": 1,
  "iːə͡ʊɛ": 1,
  "e͡ɪə͡ʊɪ": 1,
  "iːa͡ʊɪ": 1,
  "ə͡ʊa͡ɪ": 1
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment