remote-rdr / src /samples /sample-caption.json
shiveshnavin's picture
Add motivationa;
721d060
{
"transcript": "A surreal and intense scene of a man hand wrestling a gadha (donkey) in human form, the gadha depicted as a muscular humanoid with donkey ears, a furry face, and a powerful build; both locked in a fierce arm-wrestling match on a rough stone table, muscles straining, expressions full of determination; dramatic lighting casting deep shadows, with a rugged, ancient arena setting creating an epic and mythical atmosphere.",
"words": [
{
"case": "not-found-in-transcript",
"end": 0.01,
"phones": [
{
"duration": 0.01,
"phone": "ah_S"
}
],
"start": 0.0,
"word": "uh"
},
{
"alignedWord": "a",
"case": "success",
"end": 0.14,
"endOffset": 1,
"phones": [
{
"duration": 0.1,
"phone": "ah_S"
}
],
"start": 0.04,
"startOffset": 0,
"word": "A"
},
{
"alignedWord": "surreal",
"case": "success",
"end": 0.65,
"endOffset": 9,
"phones": [
{
"duration": 0.14,
"phone": "s_B"
},
{
"duration": 0.16,
"phone": "er_I"
},
{
"duration": 0.1,
"phone": "iy_I"
},
{
"duration": 0.11,
"phone": "l_E"
}
],
"start": 0.14,
"startOffset": 2,
"word": "surreal"
},
{
"alignedWord": "and",
"case": "success",
"end": 0.78,
"endOffset": 13,
"phones": [
{
"duration": 0.04,
"phone": "ae_B"
},
{
"duration": 0.06,
"phone": "n_I"
},
{
"duration": 0.03,
"phone": "d_E"
}
],
"start": 0.65,
"startOffset": 10,
"word": "and"
},
{
"alignedWord": "intense",
"case": "success",
"end": 1.23,
"endOffset": 21,
"phones": [
{
"duration": 0.06,
"phone": "ih_B"
},
{
"duration": 0.07,
"phone": "n_I"
},
{
"duration": 0.09,
"phone": "t_I"
},
{
"duration": 0.09,
"phone": "eh_I"
},
{
"duration": 0.1,
"phone": "n_I"
},
{
"duration": 0.04,
"phone": "s_E"
}
],
"start": 0.78,
"startOffset": 14,
"word": "intense"
},
{
"alignedWord": "scene",
"case": "success",
"end": 1.52,
"endOffset": 27,
"phones": [
{
"duration": 0.12,
"phone": "s_B"
},
{
"duration": 0.11,
"phone": "iy_I"
},
{
"duration": 0.05,
"phone": "n_E"
}
],
"start": 1.24,
"startOffset": 22,
"word": "scene"
},
{
"alignedWord": "of",
"case": "success",
"end": 1.69,
"endOffset": 30,
"phones": [
{
"duration": 0.07,
"phone": "ah_B"
},
{
"duration": 0.1,
"phone": "v_E"
}
],
"start": 1.52,
"startOffset": 28,
"word": "of"
},
{
"alignedWord": "a",
"case": "success",
"end": 1.74,
"endOffset": 32,
"phones": [
{
"duration": 0.05,
"phone": "ah_S"
}
],
"start": 1.69,
"startOffset": 31,
"word": "a"
},
{
"alignedWord": "man",
"case": "success",
"end": 2.08,
"endOffset": 36,
"phones": [
{
"duration": 0.11,
"phone": "m_B"
},
{
"duration": 0.14,
"phone": "ae_I"
},
{
"duration": 0.09,
"phone": "n_E"
}
],
"start": 1.74,
"startOffset": 33,
"word": "man"
},
{
"alignedWord": "hand",
"case": "success",
"end": 2.38,
"endOffset": 41,
"phones": [
{
"duration": 0.06,
"phone": "hh_B"
},
{
"duration": 0.11,
"phone": "ae_I"
},
{
"duration": 0.04,
"phone": "n_I"
},
{
"duration": 0.09,
"phone": "d_E"
}
],
"start": 2.08,
"startOffset": 37,
"word": "hand"
},
{
"alignedWord": "wrestling",
"case": "success",
"end": 2.82,
"endOffset": 51,
"phones": [
{
"duration": 0.06,
"phone": "r_B"
},
{
"duration": 0.07,
"phone": "eh_I"
},
{
"duration": 0.1,
"phone": "s_I"
},
{
"duration": 0.06,
"phone": "l_I"
},
{
"duration": 0.06,
"phone": "ih_I"
},
{
"duration": 0.09,
"phone": "ng_E"
}
],
"start": 2.38,
"startOffset": 42,
"word": "wrestling"
},
{
"case": "not-found-in-audio",
"endOffset": 53,
"startOffset": 52,
"word": "a"
},
{
"alignedWord": "<unk>",
"case": "success",
"end": 3.4000000000000004,
"endOffset": 59,
"phones": [
{
"duration": 0.43,
"phone": "oov_S"
}
],
"start": 2.97,
"startOffset": 54,
"word": "gadha"
},
{
"alignedWord": "donkey",
"case": "success",
"end": 4.38,
"endOffset": 67,
"phones": [
{
"duration": 0.13,
"phone": "d_B"
},
{
"duration": 0.07,
"phone": "aa_I"
},
{
"duration": 0.1,
"phone": "ng_I"
},
{
"duration": 0.12,
"phone": "k_I"
},
{
"duration": 0.3,
"phone": "iy_E"
}
],
"start": 3.66,
"startOffset": 61,
"word": "donkey"
},
{
"alignedWord": "in",
"case": "success",
"end": 4.66,
"endOffset": 71,
"phones": [
{
"duration": 0.1,
"phone": "ih_B"
},
{
"duration": 0.09,
"phone": "n_E"
}
],
"start": 4.47,
"startOffset": 69,
"word": "in"
},
{
"alignedWord": "human",
"case": "success",
"end": 5.03,
"endOffset": 77,
"phones": [
{
"duration": 0.04,
"phone": "hh_B"
},
{
"duration": 0.06,
"phone": "y_I"
},
{
"duration": 0.09,
"phone": "uw_I"
},
{
"duration": 0.01,
"phone": "m_I"
},
{
"duration": 0.08,
"phone": "ah_I"
},
{
"duration": 0.09,
"phone": "n_E"
}
],
"start": 4.66,
"startOffset": 72,
"word": "human"
},
{
"alignedWord": "form",
"case": "success",
"end": 5.48,
"endOffset": 82,
"phones": [
{
"duration": 0.09,
"phone": "f_B"
},
{
"duration": 0.16,
"phone": "ao_I"
},
{
"duration": 0.07,
"phone": "r_I"
},
{
"duration": 0.13,
"phone": "m_E"
}
],
"start": 5.03,
"startOffset": 78,
"word": "form"
},
{
"alignedWord": "the",
"case": "success",
"end": 5.88,
"endOffset": 87,
"phones": [
{
"duration": 0.08,
"phone": "dh_B"
},
{
"duration": 0.08,
"phone": "ah_E"
}
],
"start": 5.72,
"startOffset": 84,
"word": "the"
},
{
"alignedWord": "<unk>",
"case": "success",
"end": 6.16,
"endOffset": 93,
"phones": [
{
"duration": 0.28,
"phone": "oov_S"
}
],
"start": 5.88,
"startOffset": 88,
"word": "gadha"
},
{
"alignedWord": "depicted",
"case": "success",
"end": 6.64,
"endOffset": 102,
"phones": [
{
"duration": 0.06,
"phone": "d_B"
},
{
"duration": 0.04,
"phone": "ih_I"
},
{
"duration": 0.09,
"phone": "p_I"
},
{
"duration": 0.05,
"phone": "ih_I"
},
{
"duration": 0.07,
"phone": "k_I"
},
{
"duration": 0.05,
"phone": "t_I"
},
{
"duration": 0.05,
"phone": "ah_I"
},
{
"duration": 0.06,
"phone": "d_E"
}
],
"start": 6.17,
"startOffset": 94,
"word": "depicted"
},
{
"alignedWord": "as",
"case": "success",
"end": 6.79,
"endOffset": 105,
"phones": [
{
"duration": 0.08,
"phone": "ae_B"
},
{
"duration": 0.07,
"phone": "z_E"
}
],
"start": 6.64,
"startOffset": 103,
"word": "as"
},
{
"alignedWord": "a",
"case": "success",
"end": 6.83,
"endOffset": 107,
"phones": [
{
"duration": 0.04,
"phone": "ah_S"
}
],
"start": 6.79,
"startOffset": 106,
"word": "a"
},
{
"alignedWord": "muscular",
"case": "success",
"end": 7.3,
"endOffset": 116,
"phones": [
{
"duration": 0.1,
"phone": "m_B"
},
{
"duration": 0.09,
"phone": "ah_I"
},
{
"duration": 0.09,
"phone": "s_I"
},
{
"duration": 0.04,
"phone": "k_I"
},
{
"duration": 0.03,
"phone": "y_I"
},
{
"duration": 0.03,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "l_I"
},
{
"duration": 0.01,
"phone": "er_E"
}
],
"start": 6.83,
"startOffset": 108,
"word": "muscular"
},
{
"case": "not-found-in-transcript",
"end": 7.34,
"phones": [
{
"duration": 0.04,
"phone": "ah_S"
}
],
"start": 7.3,
"word": "uh"
},
{
"alignedWord": "<unk>",
"case": "success",
"end": 7.88,
"endOffset": 125,
"phones": [
{
"duration": 0.22,
"phone": "oov_S"
}
],
"start": 7.66,
"startOffset": 117,
"word": "humanoid"
},
{
"alignedWord": "with",
"case": "success",
"end": 8.04,
"endOffset": 130,
"phones": [
{
"duration": 0.06,
"phone": "w_B"
},
{
"duration": 0.05,
"phone": "ih_I"
},
{
"duration": 0.04,
"phone": "dh_E"
}
],
"start": 7.89,
"startOffset": 126,
"word": "with"
},
{
"alignedWord": "donkey",
"case": "success",
"end": 8.510000000000002,
"endOffset": 137,
"phones": [
{
"duration": 0.09,
"phone": "d_B"
},
{
"duration": 0.07,
"phone": "aa_I"
},
{
"duration": 0.09,
"phone": "ng_I"
},
{
"duration": 0.11,
"phone": "k_I"
},
{
"duration": 0.1,
"phone": "iy_E"
}
],
"start": 8.05,
"startOffset": 131,
"word": "donkey"
},
{
"alignedWord": "ears",
"case": "success",
"end": 8.92,
"endOffset": 142,
"phones": [
{
"duration": 0.17,
"phone": "iy_B"
},
{
"duration": 0.1,
"phone": "r_I"
},
{
"duration": 0.14,
"phone": "z_E"
}
],
"start": 8.51,
"startOffset": 138,
"word": "ears"
},
{
"alignedWord": "a",
"case": "success",
"end": 9.08,
"endOffset": 145,
"phones": [
{
"duration": 0.13,
"phone": "ah_S"
}
],
"start": 8.95,
"startOffset": 144,
"word": "a"
},
{
"alignedWord": "furry",
"case": "success",
"end": 9.41,
"endOffset": 151,
"phones": [
{
"duration": 0.13,
"phone": "f_B"
},
{
"duration": 0.11,
"phone": "er_I"
},
{
"duration": 0.09,
"phone": "iy_E"
}
],
"start": 9.08,
"startOffset": 146,
"word": "furry"
},
{
"alignedWord": "face",
"case": "success",
"end": 9.75,
"endOffset": 156,
"phones": [
{
"duration": 0.13,
"phone": "f_B"
},
{
"duration": 0.11,
"phone": "ey_I"
},
{
"duration": 0.1,
"phone": "s_E"
}
],
"start": 9.41,
"startOffset": 152,
"word": "face"
},
{
"alignedWord": "and",
"case": "success",
"end": 9.95,
"endOffset": 161,
"phones": [
{
"duration": 0.06,
"phone": "ah_B"
},
{
"duration": 0.06,
"phone": "n_I"
},
{
"duration": 0.05,
"phone": "d_E"
}
],
"start": 9.78,
"startOffset": 158,
"word": "and"
},
{
"alignedWord": "a",
"case": "success",
"end": 10.02,
"endOffset": 163,
"phones": [
{
"duration": 0.07,
"phone": "ah_S"
}
],
"start": 9.95,
"startOffset": 162,
"word": "a"
},
{
"alignedWord": "powerful",
"case": "success",
"end": 10.54,
"endOffset": 172,
"phones": [
{
"duration": 0.09,
"phone": "p_B"
},
{
"duration": 0.14,
"phone": "aw_I"
},
{
"duration": 0.08,
"phone": "er_I"
},
{
"duration": 0.07,
"phone": "f_I"
},
{
"duration": 0.04,
"phone": "ah_I"
},
{
"duration": 0.1,
"phone": "l_E"
}
],
"start": 10.02,
"startOffset": 164,
"word": "powerful"
},
{
"alignedWord": "build",
"case": "success",
"end": 10.92,
"endOffset": 178,
"phones": [
{
"duration": 0.07,
"phone": "b_B"
},
{
"duration": 0.1,
"phone": "ih_I"
},
{
"duration": 0.11,
"phone": "l_I"
},
{
"duration": 0.09,
"phone": "d_E"
}
],
"start": 10.55,
"startOffset": 173,
"word": "build"
},
{
"alignedWord": "both",
"case": "success",
"end": 11.409999999999998,
"endOffset": 184,
"phones": [
{
"duration": 0.11,
"phone": "b_B"
},
{
"duration": 0.1,
"phone": "ow_I"
},
{
"duration": 0.08,
"phone": "th_E"
}
],
"start": 11.12,
"startOffset": 180,
"word": "both"
},
{
"alignedWord": "locked",
"case": "success",
"end": 11.77,
"endOffset": 191,
"phones": [
{
"duration": 0.12,
"phone": "l_B"
},
{
"duration": 0.09,
"phone": "aa_I"
},
{
"duration": 0.08,
"phone": "k_I"
},
{
"duration": 0.06,
"phone": "t_E"
}
],
"start": 11.42,
"startOffset": 185,
"word": "locked"
},
{
"alignedWord": "in",
"case": "success",
"end": 11.879999999999999,
"endOffset": 194,
"phones": [
{
"duration": 0.04,
"phone": "ih_B"
},
{
"duration": 0.07,
"phone": "n_E"
}
],
"start": 11.77,
"startOffset": 192,
"word": "in"
},
{
"alignedWord": "a",
"case": "success",
"end": 11.940000000000001,
"endOffset": 196,
"phones": [
{
"duration": 0.06,
"phone": "ah_S"
}
],
"start": 11.88,
"startOffset": 195,
"word": "a"
},
{
"alignedWord": "fierce",
"case": "success",
"end": 12.35,
"endOffset": 203,
"phones": [
{
"duration": 0.13,
"phone": "f_B"
},
{
"duration": 0.1,
"phone": "ih_I"
},
{
"duration": 0.07,
"phone": "r_I"
},
{
"duration": 0.11,
"phone": "s_E"
}
],
"start": 11.94,
"startOffset": 197,
"word": "fierce"
},
{
"alignedWord": "arm",
"case": "success",
"end": 12.67,
"endOffset": 207,
"phones": [
{
"duration": 0.15,
"phone": "aa_B"
},
{
"duration": 0.07,
"phone": "r_I"
},
{
"duration": 0.09,
"phone": "m_E"
}
],
"start": 12.36,
"startOffset": 204,
"word": "arm"
},
{
"alignedWord": "wrestling",
"case": "success",
"end": 13.06,
"endOffset": 217,
"phones": [
{
"duration": 0.05,
"phone": "r_B"
},
{
"duration": 0.06,
"phone": "eh_I"
},
{
"duration": 0.09,
"phone": "s_I"
},
{
"duration": 0.05,
"phone": "l_I"
},
{
"duration": 0.05,
"phone": "ih_I"
},
{
"duration": 0.09,
"phone": "ng_E"
}
],
"start": 12.67,
"startOffset": 208,
"word": "wrestling"
},
{
"alignedWord": "match",
"case": "success",
"end": 13.309999,
"endOffset": 223,
"phones": [
{
"duration": 0.05,
"phone": "m_B"
},
{
"duration": 0.1,
"phone": "ae_I"
},
{
"duration": 0.1,
"phone": "ch_E"
}
],
"start": 13.059999,
"startOffset": 218,
"word": "match"
},
{
"alignedWord": "on",
"case": "success",
"end": 13.429998999999999,
"endOffset": 226,
"phones": [
{
"duration": 0.06,
"phone": "aa_B"
},
{
"duration": 0.06,
"phone": "n_E"
}
],
"start": 13.309999,
"startOffset": 224,
"word": "on"
},
{
"alignedWord": "a",
"case": "success",
"end": 13.509999,
"endOffset": 228,
"phones": [
{
"duration": 0.08,
"phone": "ah_S"
}
],
"start": 13.429999,
"startOffset": 227,
"word": "a"
},
{
"alignedWord": "rough",
"case": "success",
"end": 13.739999000000001,
"endOffset": 234,
"phones": [
{
"duration": 0.08,
"phone": "r_B"
},
{
"duration": 0.07,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "f_E"
}
],
"start": 13.509999,
"startOffset": 229,
"word": "rough"
},
{
"alignedWord": "stone",
"case": "success",
"end": 14.11,
"endOffset": 240,
"phones": [
{
"duration": 0.08,
"phone": "s_B"
},
{
"duration": 0.09,
"phone": "t_I"
},
{
"duration": 0.1,
"phone": "ow_I"
},
{
"duration": 0.1,
"phone": "n_E"
}
],
"start": 13.74,
"startOffset": 235,
"word": "stone"
},
{
"alignedWord": "table",
"case": "success",
"end": 14.579998999999999,
"endOffset": 246,
"phones": [
{
"duration": 0.08,
"phone": "t_B"
},
{
"duration": 0.12,
"phone": "ey_I"
},
{
"duration": 0.03,
"phone": "b_I"
},
{
"duration": 0.08,
"phone": "ah_I"
},
{
"duration": 0.13,
"phone": "l_E"
}
],
"start": 14.139999,
"startOffset": 241,
"word": "table"
},
{
"alignedWord": "muscles",
"case": "success",
"end": 15.309999999999999,
"endOffset": 255,
"phones": [
{
"duration": 0.13,
"phone": "m_B"
},
{
"duration": 0.07,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "s_I"
},
{
"duration": 0.05,
"phone": "ah_I"
},
{
"duration": 0.09,
"phone": "l_I"
},
{
"duration": 0.03,
"phone": "z_E"
}
],
"start": 14.86,
"startOffset": 248,
"word": "muscles"
},
{
"alignedWord": "straining",
"case": "success",
"end": 15.92,
"endOffset": 265,
"phones": [
{
"duration": 0.08,
"phone": "s_B"
},
{
"duration": 0.09,
"phone": "t_I"
},
{
"duration": 0.08,
"phone": "r_I"
},
{
"duration": 0.09,
"phone": "ey_I"
},
{
"duration": 0.04,
"phone": "n_I"
},
{
"duration": 0.08,
"phone": "ih_I"
},
{
"duration": 0.14,
"phone": "ng_E"
}
],
"start": 15.32,
"startOffset": 256,
"word": "straining"
},
{
"alignedWord": "expressions",
"case": "success",
"end": 16.66,
"endOffset": 278,
"phones": [
{
"duration": 0.09,
"phone": "ih_B"
},
{
"duration": 0.07,
"phone": "k_I"
},
{
"duration": 0.07,
"phone": "s_I"
},
{
"duration": 0.06,
"phone": "p_I"
},
{
"duration": 0.06,
"phone": "r_I"
},
{
"duration": 0.06,
"phone": "eh_I"
},
{
"duration": 0.09,
"phone": "sh_I"
},
{
"duration": 0.06,
"phone": "ah_I"
},
{
"duration": 0.07,
"phone": "n_I"
},
{
"duration": 0.07,
"phone": "z_E"
}
],
"start": 15.96,
"startOffset": 267,
"word": "expressions"
},
{
"alignedWord": "full",
"case": "success",
"end": 16.91,
"endOffset": 283,
"phones": [
{
"duration": 0.1,
"phone": "f_B"
},
{
"duration": 0.09,
"phone": "uh_I"
},
{
"duration": 0.06,
"phone": "l_E"
}
],
"start": 16.66,
"startOffset": 279,
"word": "full"
},
{
"alignedWord": "of",
"case": "success",
"end": 17.03,
"endOffset": 286,
"phones": [
{
"duration": 0.04,
"phone": "ah_B"
},
{
"duration": 0.08,
"phone": "v_E"
}
],
"start": 16.91,
"startOffset": 284,
"word": "of"
},
{
"alignedWord": "determination",
"case": "success",
"end": 17.909999,
"endOffset": 300,
"phones": [
{
"duration": 0.04,
"phone": "d_B"
},
{
"duration": 0.07,
"phone": "ih_I"
},
{
"duration": 0.09,
"phone": "t_I"
},
{
"duration": 0.1,
"phone": "er_I"
},
{
"duration": 0.03,
"phone": "m_I"
},
{
"duration": 0.07,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "n_I"
},
{
"duration": 0.1,
"phone": "ey_I"
},
{
"duration": 0.11,
"phone": "sh_I"
},
{
"duration": 0.06,
"phone": "ah_I"
},
{
"duration": 0.13,
"phone": "n_E"
}
],
"start": 17.029999,
"startOffset": 287,
"word": "determination"
},
{
"alignedWord": "dramatic",
"case": "success",
"end": 18.8,
"endOffset": 310,
"phones": [
{
"duration": 0.09,
"phone": "d_B"
},
{
"duration": 0.07,
"phone": "r_I"
},
{
"duration": 0.05,
"phone": "ah_I"
},
{
"duration": 0.06,
"phone": "m_I"
},
{
"duration": 0.1,
"phone": "ae_I"
},
{
"duration": 0.07,
"phone": "t_I"
},
{
"duration": 0.08,
"phone": "ih_I"
},
{
"duration": 0.07,
"phone": "k_E"
}
],
"start": 18.21,
"startOffset": 302,
"word": "dramatic"
},
{
"alignedWord": "lighting",
"case": "success",
"end": 19.29,
"endOffset": 319,
"phones": [
{
"duration": 0.09,
"phone": "l_B"
},
{
"duration": 0.11,
"phone": "ay_I"
},
{
"duration": 0.07,
"phone": "t_I"
},
{
"duration": 0.09,
"phone": "ih_I"
},
{
"duration": 0.13,
"phone": "ng_E"
}
],
"start": 18.8,
"startOffset": 311,
"word": "lighting"
},
{
"alignedWord": "casting",
"case": "success",
"end": 19.81,
"endOffset": 327,
"phones": [
{
"duration": 0.05,
"phone": "k_B"
},
{
"duration": 0.13,
"phone": "ae_I"
},
{
"duration": 0.09,
"phone": "s_I"
},
{
"duration": 0.06,
"phone": "t_I"
},
{
"duration": 0.06,
"phone": "ih_I"
},
{
"duration": 0.09,
"phone": "ng_E"
}
],
"start": 19.33,
"startOffset": 320,
"word": "casting"
},
{
"alignedWord": "deep",
"case": "success",
"end": 20.09,
"endOffset": 332,
"phones": [
{
"duration": 0.08,
"phone": "d_B"
},
{
"duration": 0.11,
"phone": "iy_I"
},
{
"duration": 0.09,
"phone": "p_E"
}
],
"start": 19.81,
"startOffset": 328,
"word": "deep"
},
{
"alignedWord": "shadows",
"case": "success",
"end": 20.66,
"endOffset": 340,
"phones": [
{
"duration": 0.13,
"phone": "sh_B"
},
{
"duration": 0.09,
"phone": "ae_I"
},
{
"duration": 0.07,
"phone": "d_I"
},
{
"duration": 0.11,
"phone": "ow_I"
},
{
"duration": 0.17,
"phone": "z_E"
}
],
"start": 20.09,
"startOffset": 333,
"word": "shadows"
},
{
"alignedWord": "with",
"case": "success",
"end": 21.14,
"endOffset": 346,
"phones": [
{
"duration": 0.09,
"phone": "w_B"
},
{
"duration": 0.06,
"phone": "ih_I"
},
{
"duration": 0.08,
"phone": "th_E"
}
],
"start": 20.91,
"startOffset": 342,
"word": "with"
},
{
"alignedWord": "a",
"case": "success",
"end": 21.240000000000002,
"endOffset": 348,
"phones": [
{
"duration": 0.1,
"phone": "ah_S"
}
],
"start": 21.14,
"startOffset": 347,
"word": "a"
},
{
"alignedWord": "rugged",
"case": "success",
"end": 21.610000000000003,
"endOffset": 355,
"phones": [
{
"duration": 0.11,
"phone": "r_B"
},
{
"duration": 0.05,
"phone": "ah_I"
},
{
"duration": 0.07,
"phone": "g_I"
},
{
"duration": 0.06,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "d_E"
}
],
"start": 21.240000000000002,
"startOffset": 349,
"word": "rugged"
},
{
"alignedWord": "ancient",
"case": "success",
"end": 22.09,
"endOffset": 364,
"phones": [
{
"duration": 0.16,
"phone": "ey_B"
},
{
"duration": 0.06,
"phone": "n_I"
},
{
"duration": 0.06,
"phone": "sh_I"
},
{
"duration": 0.06,
"phone": "ah_I"
},
{
"duration": 0.05,
"phone": "n_I"
},
{
"duration": 0.06,
"phone": "t_E"
}
],
"start": 21.64,
"startOffset": 357,
"word": "ancient"
},
{
"alignedWord": "arena",
"case": "success",
"end": 22.529999999999998,
"endOffset": 370,
"phones": [
{
"duration": 0.17,
"phone": "er_B"
},
{
"duration": 0.09,
"phone": "iy_I"
},
{
"duration": 0.07,
"phone": "n_I"
},
{
"duration": 0.07,
"phone": "ah_E"
}
],
"start": 22.13,
"startOffset": 365,
"word": "arena"
},
{
"alignedWord": "setting",
"case": "success",
"end": 23.01,
"endOffset": 378,
"phones": [
{
"duration": 0.11,
"phone": "s_B"
},
{
"duration": 0.12,
"phone": "eh_I"
},
{
"duration": 0.06,
"phone": "t_I"
},
{
"duration": 0.09,
"phone": "ih_I"
},
{
"duration": 0.1,
"phone": "ng_E"
}
],
"start": 22.53,
"startOffset": 371,
"word": "setting"
},
{
"alignedWord": "creating",
"case": "success",
"end": 23.499999999999996,
"endOffset": 387,
"phones": [
{
"duration": 0.08,
"phone": "k_B"
},
{
"duration": 0.07,
"phone": "r_I"
},
{
"duration": 0.08,
"phone": "iy_I"
},
{
"duration": 0.07,
"phone": "ey_I"
},
{
"duration": 0.06,
"phone": "t_I"
},
{
"duration": 0.07,
"phone": "ih_I"
},
{
"duration": 0.06,
"phone": "ng_E"
}
],
"start": 23.009999999999998,
"startOffset": 379,
"word": "creating"
},
{
"alignedWord": "an",
"case": "success",
"end": 23.67,
"endOffset": 390,
"phones": [
{
"duration": 0.05,
"phone": "ah_B"
},
{
"duration": 0.12,
"phone": "n_E"
}
],
"start": 23.5,
"startOffset": 388,
"word": "an"
},
{
"alignedWord": "epic",
"case": "success",
"end": 24.169999999999998,
"endOffset": 395,
"phones": [
{
"duration": 0.14,
"phone": "eh_B"
},
{
"duration": 0.08,
"phone": "p_I"
},
{
"duration": 0.09,
"phone": "ih_I"
},
{
"duration": 0.1,
"phone": "k_E"
}
],
"start": 23.759999999999998,
"startOffset": 391,
"word": "epic"
},
{
"alignedWord": "and",
"case": "success",
"end": 24.4,
"endOffset": 399,
"phones": [
{
"duration": 0.08,
"phone": "ae_B"
},
{
"duration": 0.13,
"phone": "n_I"
},
{
"duration": 0.01,
"phone": "d_E"
}
],
"start": 24.18,
"startOffset": 396,
"word": "and"
},
{
"alignedWord": "mythical",
"case": "success",
"end": 24.92,
"endOffset": 408,
"phones": [
{
"duration": 0.1,
"phone": "m_B"
},
{
"duration": 0.07,
"phone": "ih_I"
},
{
"duration": 0.08,
"phone": "th_I"
},
{
"duration": 0.07,
"phone": "ih_I"
},
{
"duration": 0.03,
"phone": "k_I"
},
{
"duration": 0.08,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "l_E"
}
],
"start": 24.41,
"startOffset": 400,
"word": "mythical"
},
{
"alignedWord": "atmosphere",
"case": "success",
"end": 25.650000000000002,
"endOffset": 419,
"phones": [
{
"duration": 0.11,
"phone": "ae_B"
},
{
"duration": 0.07,
"phone": "t_I"
},
{
"duration": 0.07,
"phone": "m_I"
},
{
"duration": 0.06,
"phone": "ah_I"
},
{
"duration": 0.06,
"phone": "s_I"
},
{
"duration": 0.09,
"phone": "f_I"
},
{
"duration": 0.1,
"phone": "ih_I"
},
{
"duration": 0.15,
"phone": "r_E"
}
],
"start": 24.94,
"startOffset": 409,
"word": "atmosphere"
}
]
}