geolip-bytelex / btx_e003 /instruments /codebook_d5_states.json
AbstractPhil's picture
btx-e003 I-5 codebooks: codebook_d5_states.json
d825814 verified
Raw History Blame Contribute Delete
1.98 kB
[
{
"text": "is",
"count": 264000,
"n_bytes": 2,
"class": "word"
},
{
"text": "If",
"count": 120000,
"n_bytes": 2,
"class": "Name"
},
{
"text": "So",
"count": 120000,
"n_bytes": 2,
"class": "Name"
},
{
"text": "are",
"count": 120000,
"n_bytes": 3,
"class": "word"
},
{
"text": "someone",
"count": 120000,
"n_bytes": 7,
"class": "word"
},
{
"text": "then",
"count": 120000,
"n_bytes": 4,
"class": "word"
},
{
"text": "they",
"count": 120000,
"n_bytes": 4,
"class": "word"
},
{
"text": "tovi",
"count": 32270,
"n_bytes": 4,
"class": "word"
},
{
"text": "marn",
"count": 32175,
"n_bytes": 4,
"class": "word"
},
{
"text": "trell",
"count": 32173,
"n_bytes": 5,
"class": "word"
},
{
"text": "dorn",
"count": 32077,
"n_bytes": 4,
"class": "word"
},
{
"text": "vint",
"count": 32048,
"n_bytes": 4,
"class": "word"
},
{
"text": "yast",
"count": 32038,
"n_bytes": 4,
"class": "word"
},
{
"text": "kresp",
"count": 32024,
"n_bytes": 5,
"class": "word"
},
{
"text": "brulk",
"count": 31999,
"n_bytes": 5,
"class": "word"
},
{
"text": "sorb",
"count": 31975,
"n_bytes": 4,
"class": "word"
},
{
"text": "plim",
"count": 31953,
"n_bytes": 4,
"class": "word"
},
{
"text": "glent",
"count": 31848,
"n_bytes": 5,
"class": "word"
},
{
"text": "senn",
"count": 31420,
"n_bytes": 4,
"class": "word"
},
{
"text": "Cora",
"count": 24348,
"n_bytes": 4,
"class": "Name"
},
{
"text": "Zev",
"count": 24048,
"n_bytes": 3,
"class": "Name"
},
{
"text": "Wren",
"count": 24030,
"n_bytes": 4,
"class": "Name"
},
{
"text": "Suki",
"count": 24006,
"n_bytes": 4,
"class": "Name"
},
{
"text": "What",
"count": 24000,
"n_bytes": 4,
"class": "Name"
},
{
"text": "follows",
"count": 24000,
"n_bytes": 7,
"class": "word"
},
{
"text": "Nils",
"count": 23898,
"n_bytes": 4,
"class": "Name"
},
{
"text": "Beto",
"count": 23670,
"n_bytes": 4,
"class": "Name"
}
]