reanimate/examples/voice_transcript.json
David Himmelstrup 7e1c7ea511 Voice control (#75)
Add voice control via Reanimate.Voice.
Include rtfd article.

Former-commit-id: f80bb58031f6dfbb83bc8f188c17013afcb2dfd9
2020-05-22 23:30:44 +08:00

753 lines
No EOL
14 KiB
JSON

{
"transcript": "This transcript is synced to\n\nmy voice automatically.\n\nThe beginning and end of each\n\nword is recorded precisely\n\nand can be used to trigger\n\nevents in the animation.\n",
"words": [
{
"alignedWord": "this",
"case": "success",
"end": 0.62,
"endOffset": 4,
"phones": [
{
"duration": 0.08,
"phone": "dh_B"
},
{
"duration": 0.09,
"phone": "ih_I"
},
{
"duration": 0.1,
"phone": "s_E"
}
],
"start": 0.35,
"startOffset": 0,
"word": "This"
},
{
"alignedWord": "transcript",
"case": "success",
"end": 1.21,
"endOffset": 15,
"phones": [
{
"duration": 0.06,
"phone": "t_B"
},
{
"duration": 0.06,
"phone": "r_I"
},
{
"duration": 0.06,
"phone": "ae_I"
},
{
"duration": 0.08,
"phone": "n_I"
},
{
"duration": 0.05,
"phone": "s_I"
},
{
"duration": 0.06,
"phone": "k_I"
},
{
"duration": 0.01,
"phone": "r_I"
},
{
"duration": 0.07,
"phone": "ih_I"
},
{
"duration": 0.07,
"phone": "p_I"
},
{
"duration": 0.04,
"phone": "t_E"
}
],
"start": 0.65,
"startOffset": 5,
"word": "transcript"
},
{
"alignedWord": "is",
"case": "success",
"end": 1.34,
"endOffset": 18,
"phones": [
{
"duration": 0.09,
"phone": "ih_B"
},
{
"duration": 0.01,
"phone": "z_E"
}
],
"start": 1.24,
"startOffset": 16,
"word": "is"
},
{
"alignedWord": "<unk>",
"case": "success",
"end": 1.6400000000000001,
"endOffset": 25,
"phones": [
{
"duration": 0.3,
"phone": "oov_S"
}
],
"start": 1.34,
"startOffset": 19,
"word": "synced"
},
{
"alignedWord": "to",
"case": "success",
"end": 1.81,
"endOffset": 28,
"phones": [
{
"duration": 0.09,
"phone": "t_B"
},
{
"duration": 0.05,
"phone": "uw_E"
}
],
"start": 1.67,
"startOffset": 26,
"word": "to"
},
{
"alignedWord": "my",
"case": "success",
"end": 1.9500000000000002,
"endOffset": 32,
"phones": [
{
"duration": 0.06,
"phone": "m_B"
},
{
"duration": 0.08,
"phone": "ay_E"
}
],
"start": 1.81,
"startOffset": 30,
"word": "my"
},
{
"alignedWord": "voice",
"case": "success",
"end": 2.3,
"endOffset": 38,
"phones": [
{
"duration": 0.09,
"phone": "v_B"
},
{
"duration": 0.17,
"phone": "oy_I"
},
{
"duration": 0.09,
"phone": "s_E"
}
],
"start": 1.95,
"startOffset": 33,
"word": "voice"
},
{
"alignedWord": "automatically",
"case": "success",
"end": 3.07,
"endOffset": 52,
"phones": [
{
"duration": 0.09,
"phone": "ao_B"
},
{
"duration": 0.07,
"phone": "t_I"
},
{
"duration": 0.05,
"phone": "ah_I"
},
{
"duration": 0.06,
"phone": "m_I"
},
{
"duration": 0.05,
"phone": "ae_I"
},
{
"duration": 0.06,
"phone": "t_I"
},
{
"duration": 0.05,
"phone": "ih_I"
},
{
"duration": 0.08,
"phone": "k_I"
},
{
"duration": 0.07,
"phone": "l_I"
},
{
"duration": 0.19,
"phone": "iy_E"
}
],
"start": 2.3,
"startOffset": 39,
"word": "automatically"
},
{
"alignedWord": "the",
"case": "success",
"end": 3.9,
"endOffset": 58,
"phones": [
{
"duration": 0.07,
"phone": "dh_B"
},
{
"duration": 0.04,
"phone": "ah_E"
}
],
"start": 3.79,
"startOffset": 55,
"word": "The"
},
{
"alignedWord": "beginning",
"case": "success",
"end": 4.43,
"endOffset": 68,
"phones": [
{
"duration": 0.05,
"phone": "b_B"
},
{
"duration": 0.06,
"phone": "ih_I"
},
{
"duration": 0.07,
"phone": "g_I"
},
{
"duration": 0.08,
"phone": "ih_I"
},
{
"duration": 0.03,
"phone": "n_I"
},
{
"duration": 0.1,
"phone": "ih_I"
},
{
"duration": 0.14,
"phone": "ng_E"
}
],
"start": 3.9,
"startOffset": 59,
"word": "beginning"
},
{
"alignedWord": "and",
"case": "success",
"end": 4.6499999999999995,
"endOffset": 72,
"phones": [
{
"duration": 0.08,
"phone": "ae_B"
},
{
"duration": 0.05,
"phone": "n_I"
},
{
"duration": 0.05,
"phone": "d_E"
}
],
"start": 4.47,
"startOffset": 69,
"word": "and"
},
{
"alignedWord": "end",
"case": "success",
"end": 5.069999999999999,
"endOffset": 76,
"phones": [
{
"duration": 0.19,
"phone": "eh_B"
},
{
"duration": 0.11,
"phone": "n_I"
},
{
"duration": 0.09,
"phone": "d_E"
}
],
"start": 4.68,
"startOffset": 73,
"word": "end"
},
{
"alignedWord": "of",
"case": "success",
"end": 5.22,
"endOffset": 79,
"phones": [
{
"duration": 0.07,
"phone": "ah_B"
},
{
"duration": 0.07,
"phone": "v_E"
}
],
"start": 5.08,
"startOffset": 77,
"word": "of"
},
{
"alignedWord": "each",
"case": "success",
"end": 5.529999999999999,
"endOffset": 84,
"phones": [
{
"duration": 0.15,
"phone": "iy_B"
},
{
"duration": 0.12,
"phone": "ch_E"
}
],
"start": 5.26,
"startOffset": 80,
"word": "each"
},
{
"alignedWord": "word",
"case": "success",
"end": 5.96,
"endOffset": 90,
"phones": [
{
"duration": 0.14,
"phone": "w_B"
},
{
"duration": 0.13,
"phone": "er_I"
},
{
"duration": 0.16,
"phone": "d_E"
}
],
"start": 5.53,
"startOffset": 86,
"word": "word"
},
{
"alignedWord": "is",
"case": "success",
"end": 6.24,
"endOffset": 93,
"phones": [
{
"duration": 0.09,
"phone": "ih_B"
},
{
"duration": 0.07,
"phone": "z_E"
}
],
"start": 6.08,
"startOffset": 91,
"word": "is"
},
{
"alignedWord": "recorded",
"case": "success",
"end": 6.69,
"endOffset": 102,
"phones": [
{
"duration": 0.04,
"phone": "r_B"
},
{
"duration": 0.06,
"phone": "ih_I"
},
{
"duration": 0.1,
"phone": "k_I"
},
{
"duration": 0.09,
"phone": "ao_I"
},
{
"duration": 0.01,
"phone": "r_I"
},
{
"duration": 0.05,
"phone": "d_I"
},
{
"duration": 0.06,
"phone": "ih_I"
},
{
"duration": 0.04,
"phone": "d_E"
}
],
"start": 6.24,
"startOffset": 94,
"word": "recorded"
},
{
"alignedWord": "precisely",
"case": "success",
"end": 7.44,
"endOffset": 112,
"phones": [
{
"duration": 0.02,
"phone": "p_B"
},
{
"duration": 0.02,
"phone": "r_I"
},
{
"duration": 0.04,
"phone": "iy_I"
},
{
"duration": 0.13,
"phone": "s_I"
},
{
"duration": 0.12,
"phone": "ay_I"
},
{
"duration": 0.11,
"phone": "s_I"
},
{
"duration": 0.09,
"phone": "l_I"
},
{
"duration": 0.22,
"phone": "iy_E"
}
],
"start": 6.69,
"startOffset": 103,
"word": "precisely"
},
{
"alignedWord": "and",
"case": "success",
"end": 7.9799999999999995,
"endOffset": 117,
"phones": [
{
"duration": 0.05,
"phone": "ae_B"
},
{
"duration": 0.02,
"phone": "n_I"
},
{
"duration": 0.06,
"phone": "d_E"
}
],
"start": 7.85,
"startOffset": 114,
"word": "and"
},
{
"alignedWord": "can",
"case": "success",
"end": 8.120000000000001,
"endOffset": 121,
"phones": [
{
"duration": 0.05,
"phone": "k_B"
},
{
"duration": 0.04,
"phone": "ae_I"
},
{
"duration": 0.05,
"phone": "n_E"
}
],
"start": 7.98,
"startOffset": 118,
"word": "can"
},
{
"alignedWord": "be",
"case": "success",
"end": 8.219999999999999,
"endOffset": 124,
"phones": [
{
"duration": 0.06,
"phone": "b_B"
},
{
"duration": 0.04,
"phone": "iy_E"
}
],
"start": 8.12,
"startOffset": 122,
"word": "be"
},
{
"alignedWord": "used",
"case": "success",
"end": 8.55,
"endOffset": 129,
"phones": [
{
"duration": 0.11,
"phone": "y_B"
},
{
"duration": 0.17,
"phone": "uw_I"
},
{
"duration": 0.04,
"phone": "z_I"
},
{
"duration": 0.01,
"phone": "d_E"
}
],
"start": 8.22,
"startOffset": 125,
"word": "used"
},
{
"alignedWord": "to",
"case": "success",
"end": 8.659999,
"endOffset": 132,
"phones": [
{
"duration": 0.05,
"phone": "t_B"
},
{
"duration": 0.05,
"phone": "ih_E"
}
],
"start": 8.559999,
"startOffset": 130,
"word": "to"
},
{
"alignedWord": "trigger",
"case": "success",
"end": 9.0,
"endOffset": 140,
"phones": [
{
"duration": 0.08,
"phone": "t_B"
},
{
"duration": 0.05,
"phone": "r_I"
},
{
"duration": 0.05,
"phone": "ih_I"
},
{
"duration": 0.09,
"phone": "g_I"
},
{
"duration": 0.07,
"phone": "er_E"
}
],
"start": 8.66,
"startOffset": 133,
"word": "trigger"
},
{
"alignedWord": "events",
"case": "success",
"end": 9.48,
"endOffset": 148,
"phones": [
{
"duration": 0.09,
"phone": "iy_B"
},
{
"duration": 0.08,
"phone": "v_I"
},
{
"duration": 0.07,
"phone": "eh_I"
},
{
"duration": 0.06,
"phone": "n_I"
},
{
"duration": 0.06,
"phone": "t_I"
},
{
"duration": 0.12,
"phone": "s_E"
}
],
"start": 9.0,
"startOffset": 142,
"word": "events"
},
{
"alignedWord": "in",
"case": "success",
"end": 9.64,
"endOffset": 151,
"phones": [
{
"duration": 0.07,
"phone": "ih_B"
},
{
"duration": 0.07,
"phone": "n_E"
}
],
"start": 9.5,
"startOffset": 149,
"word": "in"
},
{
"alignedWord": "the",
"case": "success",
"end": 9.729999,
"endOffset": 155,
"phones": [
{
"duration": 0.03,
"phone": "dh_B"
},
{
"duration": 0.06,
"phone": "ah_E"
}
],
"start": 9.639999,
"startOffset": 152,
"word": "the"
},
{
"alignedWord": "animation",
"case": "success",
"end": 10.290000000000001,
"endOffset": 165,
"phones": [
{
"duration": 0.02,
"phone": "ae_B"
},
{
"duration": 0.1,
"phone": "n_I"
},
{
"duration": 0.06,
"phone": "ah_I"
},
{
"duration": 0.08,
"phone": "m_I"
},
{
"duration": 0.07,
"phone": "ey_I"
},
{
"duration": 0.1,
"phone": "sh_I"
},
{
"duration": 0.07,
"phone": "ah_I"
},
{
"duration": 0.06,
"phone": "n_E"
}
],
"start": 9.73,
"startOffset": 156,
"word": "animation"
}
]
}