example/audio/en_prompt.json

[
  {
    "index": "vocal_5220_10280",
    "language": "English",
    "time": [
      5220,
      10280
    ],
    "duration": "0.24 0.36 0.30 0.78 0.24 0.56 0.19 0.53 0.36 0.20 0.32 0.57 0.19 0.22",
    "text": "<SP> Ooh Ooh <SP> I wish nothing nothing more more the best best <SP>",
    "phoneme": "<SP> en_UW1 en_UW1 <SP> en_AY1 en_W-IH1-SH en_N-AH1-TH-IH0-NG en_N-AH1-TH-IH0-NG en_M-AO1-R en_M-AO1-R en_DH-AH0 en_B-EH1-S-T en_B-EH1-S-T <SP>",
    "note_pitch": "0 63 65 0 65 67 68 62 62 64 67 67 65 0",
    "note_type": "1 2 3 1 2 2 2 3 2 3 2 2 3 1",
    "f0": "0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 345.2 343.1 341.6 339.8 337.8 331.9 319.5 312.1 310.8 312.6 315.1 316.1 315.3 314.6 315.3 317.9 322.0 329.6 337.5 344.7 347.5 347.2 344.3 339.5 338.2 341.7 342.8 342.2 340.7 343.0 342.9 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 347.0 345.3 348.7 350.2 350.9 350.3 344.7 340.3 338.3 338.0 342.8 347.4 348.3 346.7 343.4 339.5 340.5 345.2 350.4 357.7 367.3 376.6 385.9 392.6 393.6 389.9 384.7 381.8 382.0 383.0 380.6 373.5 367.9 377.0 385.4 391.4 393.8 395.6 396.1 397.2 399.8 406.0 413.5 416.1 416.0 414.4 413.5 412.9 415.5 418.9 417.5 408.8 389.2 373.9 0.0 0.0 0.0 288.5 286.0 284.2 285.6 288.9 291.3 293.5 294.5 295.2 297.8 299.5 301.0 303.0 305.9 306.8 306.0 304.4 301.8 301.0 300.8 301.8 310.2 309.8 308.2 305.9 303.6 301.5 299.3 298.5 300.0 302.1 303.5 303.6 302.2 299.7 297.5 296.3 296.4 296.8 298.6 302.6 311.8 322.0 333.8 349.0 368.8 393.3 407.1 410.7 407.0 402.3 401.2 401.7 403.9 405.7 403.5 396.8 387.4 378.6 377.8 381.4 384.0 384.7 383.5 382.5 380.8 377.3 378.4 383.5 390.0 392.7 390.5 387.6 385.3 382.7 381.0 382.8 383.9 382.2 379.6 379.3 380.2 383.1 386.0 386.5 385.4 384.3 383.7 384.4 386.2 388.2 388.5 385.0 378.6 360.4 333.7 328.2 332.4 340.2 348.9 339.6 334.9 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0"
  }
]