{
  "source": "https://github.com/CheyneyComputerScience/CREMA-D",
  "license": "https://opendatacommons.org/licenses/odbl/1-0/",
  "contentsLicense": "https://opendatacommons.org/licenses/dbcl/1-0/",
  "trainingIndexSha256": "e95ed487d9e44f094d968fbb17580a83870e2d41a94477d105254d38685ffdd5",
  "generatedAt": "2026-09-05T23:57:59.355529+00:00",
  "selection": "Eight non-neutral training recordings per source emotion, screened with the live Oruk Resonance model. This curated demo is not a benchmark or evaluation set.",
  "samples": [
    {
      "id": "1029_IEO_HAP_HI",
      "audioSrc": "/samples/emotional/1029_IEO_HAP_HI.wav",
      "audioSha256": "b325e376ae20d80ed81da700569c3d408d748a59404af12258104583e97aa90c",
      "trainingPcmSha256": "9758d7f9e914118d91b3032643f647d1099acd957465aed3a0a8489feb238808",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1029_IEO_HAP_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1029_IEO_HAP_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 2.06875,
      "waveform": [
        0.0074,
        0.0087,
        0.0092,
        0.0055,
        0.0094,
        0.0069,
        0.0054,
        0.0071,
        0.0098,
        0.0063,
        0.0066,
        0.0083,
        0.1334,
        0.3742,
        0.4816,
        0.4499,
        0.2352,
        0.1446,
        0.0952,
        0.0361,
        0.078,
        0.1951,
        0.2392,
        0.1704,
        0.1288,
        0.3144,
        1.0,
        0.57,
        0.5381,
        0.5284,
        0.2827,
        0.1898,
        0.2334,
        0.3011,
        0.2522,
        0.404,
        0.2497,
        0.1148,
        0.094,
        0.0384,
        0.0793,
        0.3111,
        0.4063,
        0.6215,
        0.7224,
        0.9416,
        0.6879,
        0.5296,
        0.7454,
        0.4522,
        0.3716,
        0.416,
        0.2589,
        0.1267,
        0.064,
        0.0229,
        0.0183,
        0.0314,
        0.0224,
        0.0137,
        0.009,
        0.0129,
        0.0117,
        0.0105,
        0.0065,
        0.0073,
        0.009,
        0.0098,
        0.0102,
        0.0082,
        0.0092,
        0.0093,
        0.0098,
        0.0106,
        0.0075,
        0.0071,
        0.0071,
        0.0086,
        0.0099,
        0.0071
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's 11 o'clock!",
        "duration": 2.06875,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.9688562154769897
          },
          {
            "label": "happy",
            "score": 0.9241418242454529
          }
        ],
        "styles": [
          {
            "label": "energetic",
            "score": 0.9967268705368042
          },
          {
            "label": "impatient",
            "score": 0.9473810195922852
          },
          {
            "label": "irritated",
            "score": 0.8933094143867493
          },
          {
            "label": "playful",
            "score": 0.7969253659248352
          }
        ]
      }
    },
    {
      "id": "1015_IEO_HAP_HI",
      "audioSrc": "/samples/emotional/1015_IEO_HAP_HI.wav",
      "audioSha256": "5e8f384e872d90c2b2fce2e6b5e90ec125243c9a9e5193cd869b167f90e3fdaa",
      "trainingPcmSha256": "6d6b4736197df6b73def8f12ee66d8f0584a8b8f9416019bc439c1b73834a59d",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1015_IEO_HAP_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1015_IEO_HAP_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 1.7684375,
      "waveform": [
        0.1081,
        0.1522,
        0.1586,
        0.1373,
        0.1082,
        0.1499,
        0.1451,
        0.1158,
        0.096,
        0.14,
        0.1634,
        0.3066,
        0.2819,
        0.2136,
        0.1717,
        0.2698,
        0.2507,
        0.1994,
        0.3637,
        0.5357,
        0.4458,
        0.4584,
        0.5869,
        0.6851,
        0.7657,
        0.4536,
        0.3949,
        0.8002,
        1.0,
        0.6845,
        0.6535,
        0.2249,
        0.2047,
        0.3548,
        0.251,
        0.2067,
        0.4454,
        0.7376,
        0.9793,
        0.8649,
        0.5844,
        0.6041,
        0.4101,
        0.2988,
        0.2479,
        0.1732,
        0.2123,
        0.2604,
        0.2172,
        0.1622,
        0.1814,
        0.1654,
        0.1491,
        0.155,
        0.1602,
        0.1598,
        0.1684,
        0.1771,
        0.2338,
        0.2017,
        0.1952,
        0.2061,
        0.1586,
        0.0899,
        0.1594,
        0.1526,
        0.1377,
        0.1346,
        0.1697,
        0.147,
        0.157,
        0.1822,
        0.1662,
        0.084,
        0.1608,
        0.1358,
        0.119,
        0.1115,
        0.158,
        0.1249
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's 11 o'clock.",
        "duration": 1.7684375,
        "emotions": [
          {
            "label": "happy",
            "score": 0.9184802770614624
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9683812260627747
          }
        ]
      }
    },
    {
      "id": "1080_DFA_HAP_XX",
      "audioSrc": "/samples/emotional/1080_DFA_HAP_XX.wav",
      "audioSha256": "d187c1041e5090d12aad24c42aaaeddad43e34fcaf719bfe79698a46e1c925d2",
      "trainingPcmSha256": "1b2e6c2db48446156b1edb296ad84755fbe23ccaea109f92a9d0175aa77d3e76",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1080_DFA_HAP_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1080_DFA_HAP_XX.wav",
      "transcript": "Don't forget a jacket",
      "duration": 1.968625,
      "waveform": [
        0.0414,
        0.0389,
        0.0326,
        0.0316,
        0.0472,
        0.0293,
        0.0255,
        0.033,
        0.0305,
        0.0315,
        0.0436,
        0.0453,
        0.0324,
        0.0511,
        0.036,
        0.0303,
        0.0378,
        0.0249,
        0.041,
        0.0783,
        0.2508,
        0.3413,
        0.642,
        0.4447,
        0.1981,
        0.0939,
        0.0618,
        0.053,
        0.1975,
        0.3194,
        0.202,
        0.1355,
        0.203,
        0.3661,
        1.0,
        0.5006,
        0.4903,
        0.3986,
        0.2989,
        0.1679,
        0.085,
        0.1749,
        0.1765,
        0.449,
        0.6968,
        0.5187,
        0.4827,
        0.6492,
        0.6096,
        0.305,
        0.1135,
        0.0705,
        0.1283,
        0.3616,
        0.459,
        0.2267,
        0.1141,
        0.077,
        0.0612,
        0.0472,
        0.0327,
        0.0202,
        0.0326,
        0.0369,
        0.0362,
        0.031,
        0.0434,
        0.0213,
        0.0306,
        0.0309,
        0.0276,
        0.0348,
        0.0393,
        0.0381,
        0.0413,
        0.0374,
        0.0393,
        0.0349,
        0.0332,
        0.0185
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Don't forget a jacket.",
        "duration": 1.968625,
        "emotions": [
          {
            "label": "happy",
            "score": 0.9940890073776245
          }
        ],
        "styles": [
          {
            "label": "warm",
            "score": 0.9955315589904785
          },
          {
            "label": "sincere",
            "score": 0.9780517220497131
          },
          {
            "label": "confident",
            "score": 0.8164063692092896
          }
        ]
      }
    },
    {
      "id": "1038_IOM_HAP_XX",
      "audioSrc": "/samples/emotional/1038_IOM_HAP_XX.wav",
      "audioSha256": "b9ddc44c3ccd3f466577769c6ee20b50c5543faf1dae1c09a348167103998f79",
      "trainingPcmSha256": "607891a528bb3935e264178150ac611cdf4c6e0038fd3f1a847c6322890a4aa9",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1038_IOM_HAP_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1038_IOM_HAP_XX.wav",
      "transcript": "I'm on my way to the meeting",
      "duration": 2.402375,
      "waveform": [
        0.0532,
        0.0377,
        0.0482,
        0.0438,
        0.042,
        0.0372,
        0.0408,
        0.0407,
        0.0368,
        0.0481,
        0.0447,
        0.048,
        0.0451,
        0.044,
        0.0465,
        0.0355,
        0.0413,
        0.0562,
        0.3899,
        0.3526,
        0.3229,
        0.4326,
        0.6254,
        0.8058,
        0.7838,
        0.3108,
        0.2484,
        0.4251,
        0.5531,
        0.7345,
        0.603,
        0.4376,
        0.7018,
        0.9569,
        1.0,
        0.3822,
        0.2444,
        0.1695,
        0.093,
        0.4427,
        0.3224,
        0.2484,
        0.3836,
        0.8117,
        0.4402,
        0.4552,
        0.4594,
        0.5505,
        0.496,
        0.2614,
        0.322,
        0.2584,
        0.2702,
        0.5715,
        0.7387,
        0.7014,
        0.5379,
        0.3116,
        0.3302,
        0.28,
        0.192,
        0.215,
        0.2489,
        0.1735,
        0.1802,
        0.133,
        0.0731,
        0.0515,
        0.0423,
        0.0338,
        0.0367,
        0.036,
        0.0533,
        0.0487,
        0.0517,
        0.0478,
        0.0396,
        0.0483,
        0.0421,
        0.0337
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I'm on my way to the meeting.",
        "duration": 2.402375,
        "emotions": [
          {
            "label": "happy",
            "score": 0.9518632292747498
          }
        ],
        "styles": [
          {
            "label": "passionate",
            "score": 0.9926542043685913
          },
          {
            "label": "formal",
            "score": 0.9924227595329285
          },
          {
            "label": "energetic",
            "score": 0.8887587189674377
          }
        ]
      }
    },
    {
      "id": "1056_IOM_HAP_XX",
      "audioSrc": "/samples/emotional/1056_IOM_HAP_XX.wav",
      "audioSha256": "9b7bf0bf9c181be7c2e132803c1d33a77a2a94827d7aabdbba7e36c8f71eacb2",
      "trainingPcmSha256": "3b8ca19058d272b84e9a33fbe68f4c4f66c030a12f4be6ee2756b6db1ed7c9ef",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1056_IOM_HAP_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1056_IOM_HAP_XX.wav",
      "transcript": "I'm on my way to the meeting",
      "duration": 1.8351875,
      "waveform": [
        0.078,
        0.0664,
        0.0836,
        0.0798,
        0.0527,
        0.0579,
        0.0593,
        0.0515,
        0.0639,
        0.0557,
        0.0614,
        0.0739,
        0.061,
        0.0727,
        0.0537,
        0.0679,
        0.0447,
        0.0564,
        0.0429,
        0.0603,
        0.2508,
        0.3981,
        0.448,
        0.5101,
        0.4217,
        0.5769,
        0.7436,
        0.8438,
        0.6895,
        0.5528,
        0.4254,
        0.6314,
        0.7972,
        0.6523,
        0.5814,
        0.4318,
        0.4853,
        0.913,
        1.0,
        0.8072,
        0.6293,
        0.4388,
        0.2868,
        0.2387,
        0.1663,
        0.2483,
        0.2253,
        0.2017,
        0.1217,
        0.3748,
        0.5118,
        0.4696,
        0.2778,
        0.3431,
        0.4863,
        0.46,
        0.4431,
        0.4258,
        0.3373,
        0.4046,
        0.3293,
        0.3038,
        0.2461,
        0.2482,
        0.1463,
        0.0933,
        0.1559,
        0.1141,
        0.1256,
        0.0702,
        0.0821,
        0.0591,
        0.0576,
        0.0558,
        0.0565,
        0.0533,
        0.0624,
        0.0685,
        0.0689,
        0.0786
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I'm on my way to the meeting.",
        "duration": 1.8351875,
        "emotions": [
          {
            "label": "happy",
            "score": 0.854884684085846
          }
        ],
        "styles": [
          {
            "label": "sincere",
            "score": 0.8233283758163452
          }
        ]
      }
    },
    {
      "id": "1005_TIE_HAP_XX",
      "audioSrc": "/samples/emotional/1005_TIE_HAP_XX.wav",
      "audioSha256": "f2d5e2e1cc51ec6a29a301953597b3dd7b01c6233aef68715832e53152d05071",
      "trainingPcmSha256": "426d93d05c566f2dea74acb5efcdb10ee03e5c5a6077e217b6200195c0241f1c",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1005_TIE_HAP_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1005_TIE_HAP_XX.wav",
      "transcript": "That is exactly what happened",
      "duration": 4.2041875,
      "waveform": [
        0.0157,
        0.0176,
        0.0146,
        0.0107,
        0.0141,
        0.0121,
        0.0168,
        0.0196,
        0.0166,
        0.2519,
        1.0,
        0.4168,
        0.4688,
        0.4221,
        0.1356,
        0.2641,
        0.6302,
        0.7637,
        0.3685,
        0.1917,
        0.1573,
        0.0831,
        0.3454,
        0.5266,
        0.4047,
        0.0966,
        0.0747,
        0.0906,
        0.1363,
        0.1764,
        0.7598,
        0.6128,
        0.4863,
        0.3977,
        0.2261,
        0.0415,
        0.0442,
        0.1836,
        0.3045,
        0.4124,
        0.4092,
        0.187,
        0.2213,
        0.4697,
        0.685,
        0.3636,
        0.1159,
        0.189,
        0.5252,
        0.6274,
        0.5193,
        0.2615,
        0.0669,
        0.0301,
        0.1131,
        0.146,
        0.0726,
        0.0536,
        0.0272,
        0.015,
        0.0146,
        0.0138,
        0.0121,
        0.0143,
        0.017,
        0.0126,
        0.0133,
        0.0131,
        0.02,
        0.0144,
        0.0154,
        0.0128,
        0.0163,
        0.016,
        0.0165,
        0.0133,
        0.0168,
        0.0179,
        0.011,
        0.0102
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "That is exactly what happened.",
        "duration": 4.2041875,
        "emotions": [
          {
            "label": "happy",
            "score": 0.8679338097572327
          }
        ],
        "styles": [
          {
            "label": "passionate",
            "score": 0.9674102663993835
          }
        ]
      }
    },
    {
      "id": "1010_IWW_HAP_XX",
      "audioSrc": "/samples/emotional/1010_IWW_HAP_XX.wav",
      "audioSha256": "9ddb5cafa84b6201c82cc7b4ffa9e3871179cf898d6e45644c6003fd13df4e17",
      "trainingPcmSha256": "2bd79799157613959c30a8e6e24bcec4feddedf31b7d5233c8152396f5caf02b",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1010_IWW_HAP_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1010_IWW_HAP_XX.wav",
      "transcript": "I wonder what this is about",
      "duration": 2.8695,
      "waveform": [
        0.0462,
        0.0427,
        0.0527,
        0.0526,
        0.0658,
        0.0668,
        0.0604,
        0.0506,
        0.0822,
        0.0824,
        0.0625,
        0.0696,
        0.0637,
        0.0547,
        0.0712,
        0.0576,
        0.0486,
        0.0352,
        0.0457,
        0.0593,
        0.0708,
        0.0949,
        0.0821,
        0.0614,
        0.0441,
        0.0394,
        0.0473,
        0.041,
        0.0543,
        0.0482,
        0.1754,
        0.4756,
        0.5063,
        0.4745,
        0.5058,
        0.7058,
        1.0,
        0.7174,
        0.719,
        0.3692,
        0.3569,
        0.5267,
        0.4066,
        0.3704,
        0.6483,
        0.5277,
        0.1942,
        0.1183,
        0.1237,
        0.4404,
        0.5219,
        0.4062,
        0.1713,
        0.1734,
        0.3844,
        0.36,
        0.2807,
        0.4159,
        0.4263,
        0.3507,
        0.1636,
        0.4559,
        0.5279,
        0.4888,
        0.464,
        0.548,
        0.3389,
        0.1892,
        0.1397,
        0.0942,
        0.08,
        0.0646,
        0.0568,
        0.0599,
        0.053,
        0.0574,
        0.0447,
        0.0567,
        0.0604,
        0.0525
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I wonder what this is about.",
        "duration": 2.8695,
        "emotions": [
          {
            "label": "surprised",
            "score": 0.9820137619972229
          },
          {
            "label": "happy",
            "score": 0.7969253659248352
          }
        ],
        "styles": [
          {
            "label": "skeptical",
            "score": 0.9994115829467773
          }
        ]
      }
    },
    {
      "id": "1009_ITS_HAP_XX",
      "audioSrc": "/samples/emotional/1009_ITS_HAP_XX.wav",
      "audioSha256": "20f33983315418b443e45858d9f7212fa5f4a96f3507f29aa891a5eaec03ecf6",
      "trainingPcmSha256": "7849e4c65a3682c32d5f8f9234cfb04898c139f63edb2ce9b1708d003d9b95aa",
      "trainingSplit": "train",
      "sourceEmotion": "happy",
      "sourceFile": "1009_ITS_HAP_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1009_ITS_HAP_XX.wav",
      "transcript": "I think I've seen this before",
      "duration": 2.56925,
      "waveform": [
        0.0397,
        0.0378,
        0.0398,
        0.0263,
        0.0216,
        0.0203,
        0.023,
        0.0339,
        0.06,
        0.1297,
        0.1699,
        0.0559,
        0.0631,
        0.037,
        0.223,
        0.2863,
        0.1838,
        0.1154,
        0.3312,
        0.6713,
        0.9402,
        0.3961,
        0.2784,
        0.1736,
        0.118,
        0.2713,
        0.3347,
        0.5319,
        0.5189,
        0.4411,
        0.4739,
        0.4086,
        0.2366,
        0.2119,
        0.1413,
        0.1501,
        0.2153,
        0.1377,
        0.0708,
        0.0557,
        0.2059,
        0.3752,
        1.0,
        0.464,
        0.6624,
        0.5428,
        0.2632,
        0.1751,
        0.2021,
        0.0929,
        0.0882,
        0.0433,
        0.0377,
        0.0281,
        0.0264,
        0.0323,
        0.0305,
        0.0411,
        0.033,
        0.0257,
        0.0292,
        0.0263,
        0.0295,
        0.0335,
        0.0348,
        0.0366,
        0.038,
        0.0277,
        0.0227,
        0.02,
        0.0227,
        0.0284,
        0.0247,
        0.0303,
        0.0274,
        0.0302,
        0.0441,
        0.0431,
        0.0411,
        0.0274
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I think I've seen this before.",
        "duration": 2.56925,
        "emotions": [
          {
            "label": "happy",
            "score": 0.9381240010261536
          },
          {
            "label": "hopeful",
            "score": 0.8757869601249695
          }
        ],
        "styles": [
          {
            "label": "confident",
            "score": 0.9489172697067261
          },
          {
            "label": "energetic",
            "score": 0.9059898257255554
          },
          {
            "label": "sincere",
            "score": 0.8918110132217407
          }
        ]
      }
    },
    {
      "id": "1076_IWW_SAD_XX",
      "audioSrc": "/samples/emotional/1076_IWW_SAD_XX.wav",
      "audioSha256": "2dc0791d9fb62b5fcb0aa12077e3fbc8386d64f93f51fe6bce382d9ebb5413e0",
      "trainingPcmSha256": "7030181d001632650f139059f5c4a6e780fec6807a5b3d1acfdd7b4fa1cdae96",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1076_IWW_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1076_IWW_SAD_XX.wav",
      "transcript": "I wonder what this is about",
      "duration": 2.1688125,
      "waveform": [
        0.2019,
        0.1319,
        0.1501,
        0.1234,
        0.1169,
        0.1007,
        0.1059,
        0.1196,
        0.127,
        0.1264,
        0.1245,
        0.0987,
        0.1445,
        0.105,
        0.1391,
        0.1493,
        0.1427,
        0.1827,
        0.1471,
        0.1593,
        0.1021,
        0.1134,
        0.1357,
        0.1153,
        0.1917,
        0.2903,
        0.3166,
        0.3149,
        0.2647,
        0.4659,
        0.5681,
        0.585,
        0.4334,
        0.5342,
        0.5581,
        0.6725,
        0.56,
        0.8601,
        0.7,
        0.389,
        0.1931,
        0.1618,
        0.4647,
        0.5533,
        0.4095,
        0.2884,
        0.2834,
        0.3046,
        0.432,
        0.2895,
        0.2624,
        0.4414,
        0.5726,
        0.4053,
        0.2407,
        0.3391,
        0.509,
        0.6404,
        1.0,
        0.8876,
        0.8218,
        0.7324,
        0.4952,
        0.3431,
        0.2306,
        0.1786,
        0.1266,
        0.1492,
        0.1141,
        0.1411,
        0.1523,
        0.1114,
        0.1282,
        0.1235,
        0.0933,
        0.0801,
        0.1333,
        0.1145,
        0.1296,
        0.1083
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I wonder what this is about.",
        "duration": 2.1688125,
        "emotions": [
          {
            "label": "sad",
            "score": 0.8840392827987671
          }
        ],
        "styles": [
          {
            "label": "impatient",
            "score": 0.9875683188438416
          },
          {
            "label": "irritated",
            "score": 0.929440438747406
          }
        ]
      }
    },
    {
      "id": "1006_IOM_SAD_XX",
      "audioSrc": "/samples/emotional/1006_IOM_SAD_XX.wav",
      "audioSha256": "e3224785a5979a16f2499d6be01b9a60edfb61db0cc7df5a9d429477da20c6be",
      "trainingPcmSha256": "68d9ac70ccdb38a0a65bcc7c12b94e7e76dbd7851aa4aa143033f317a6858472",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1006_IOM_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1006_IOM_SAD_XX.wav",
      "transcript": "I'm on my way to the meeting",
      "duration": 3.003,
      "waveform": [
        0.1655,
        0.1386,
        0.1425,
        0.1988,
        0.208,
        0.1322,
        0.1347,
        0.1746,
        0.2548,
        0.3014,
        0.2808,
        0.2532,
        0.1741,
        0.1724,
        0.1328,
        0.145,
        0.1735,
        0.4124,
        0.5861,
        0.5129,
        0.5032,
        0.3938,
        1.0,
        0.7623,
        0.5928,
        0.3959,
        0.2701,
        0.5822,
        0.4353,
        0.4107,
        0.454,
        0.438,
        0.2514,
        0.582,
        0.6467,
        0.6479,
        0.7947,
        0.7065,
        0.3199,
        0.4528,
        0.431,
        0.4413,
        0.6,
        0.4387,
        0.4703,
        0.6742,
        0.6036,
        0.5805,
        0.6017,
        0.3719,
        0.4218,
        0.3852,
        0.2509,
        0.2759,
        0.2281,
        0.1839,
        0.1367,
        0.0936,
        0.1334,
        0.1183,
        0.1297,
        0.1475,
        0.1231,
        0.2192,
        0.2123,
        0.1148,
        0.1561,
        0.1058,
        0.1503,
        0.1322,
        0.1752,
        0.1478,
        0.2427,
        0.2351,
        0.2029,
        0.2701,
        0.2437,
        0.1549,
        0.1939,
        0.1557
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I'm on my way to the meeting.",
        "duration": 3.003,
        "emotions": [
          {
            "label": "sad",
            "score": 0.7662936449050903
          }
        ],
        "styles": [
          {
            "label": "formal",
            "score": 0.9697853922843933
          },
          {
            "label": "impatient",
            "score": 0.9046505093574524
          },
          {
            "label": "confident",
            "score": 0.8489722013473511
          },
          {
            "label": "deadpan",
            "score": 0.7690802216529846
          }
        ]
      }
    },
    {
      "id": "1047_IOM_SAD_XX",
      "audioSrc": "/samples/emotional/1047_IOM_SAD_XX.wav",
      "audioSha256": "b9b2b42477539e622b77ec64d0ab3b2146ebac0a94f8afd6a5078015431b62cd",
      "trainingPcmSha256": "0930c1b274326257b20c353bf255b0e2be77b5e1ca8a9627ac007ed55baf09bd",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1047_IOM_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1047_IOM_SAD_XX.wav",
      "transcript": "I'm on my way to the meeting",
      "duration": 1.93525,
      "waveform": [
        0.1575,
        0.1304,
        0.1408,
        0.1492,
        0.1492,
        0.1422,
        0.1263,
        0.1311,
        0.1651,
        0.1528,
        0.1772,
        0.17,
        0.1657,
        0.1829,
        0.1674,
        0.1928,
        0.2467,
        0.2873,
        0.3158,
        0.4747,
        0.4361,
        0.4465,
        0.497,
        0.4835,
        0.4165,
        0.4182,
        0.5159,
        0.4408,
        0.5495,
        0.5416,
        0.5709,
        0.4267,
        0.4172,
        0.6534,
        1.0,
        0.9634,
        0.5055,
        0.2605,
        0.1836,
        0.3708,
        0.3511,
        0.1731,
        0.271,
        0.4074,
        0.272,
        0.3034,
        0.2802,
        0.2817,
        0.2681,
        0.3291,
        0.2731,
        0.2082,
        0.2464,
        0.3274,
        0.2048,
        0.2232,
        0.2231,
        0.2237,
        0.1916,
        0.1267,
        0.188,
        0.1125,
        0.1892,
        0.15,
        0.1985,
        0.1793,
        0.1595,
        0.1508,
        0.19,
        0.1123,
        0.1189,
        0.1488,
        0.1349,
        0.1655,
        0.137,
        0.154,
        0.1142,
        0.1324,
        0.1229,
        0.0948
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I'm on my way to the meeting.",
        "duration": 1.93525,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.8397339582443237
          },
          {
            "label": "sad",
            "score": 0.7759445905685425
          }
        ],
        "styles": [
          {
            "label": "tired",
            "score": 0.9697853922843933
          },
          {
            "label": "formal",
            "score": 0.9124361872673035
          },
          {
            "label": "casual",
            "score": 0.7799928784370422
          }
        ]
      }
    },
    {
      "id": "1056_DFA_SAD_XX",
      "audioSrc": "/samples/emotional/1056_DFA_SAD_XX.wav",
      "audioSha256": "6a2e4af41dff2b1ed1e922e9fe3862fab87026bab19da546235265d5131ccb5d",
      "trainingPcmSha256": "961411bfde77d337bcd3f7644e66679680b034a0976df30624926585c4127827",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1056_DFA_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1056_DFA_SAD_XX.wav",
      "transcript": "Don't forget a jacket",
      "duration": 1.901875,
      "waveform": [
        0.1557,
        0.1801,
        0.1715,
        0.2038,
        0.123,
        0.1419,
        0.2854,
        0.1975,
        0.1949,
        0.1392,
        0.1525,
        0.1864,
        0.2356,
        0.1934,
        0.2046,
        0.1208,
        0.2384,
        0.2391,
        0.2012,
        0.2123,
        0.1597,
        0.1902,
        0.1831,
        0.2817,
        0.5901,
        0.7517,
        0.6919,
        0.6934,
        0.8106,
        0.7398,
        0.4938,
        0.3145,
        0.2041,
        0.2138,
        0.3461,
        0.5872,
        0.4112,
        0.333,
        0.2081,
        0.2704,
        0.8181,
        0.6709,
        0.7048,
        0.4317,
        0.765,
        1.0,
        0.9093,
        0.8796,
        0.5573,
        0.3779,
        0.2409,
        0.4509,
        0.7696,
        0.6723,
        0.7593,
        0.9215,
        0.6832,
        0.6269,
        0.6734,
        0.8078,
        0.8286,
        0.4205,
        0.3324,
        0.2625,
        0.1659,
        0.1858,
        0.4283,
        0.4121,
        0.3365,
        0.1873,
        0.2994,
        0.2038,
        0.1521,
        0.2029,
        0.1691,
        0.1545,
        0.1726,
        0.166,
        0.112,
        0.1047
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Don't forget a jacket.",
        "duration": 1.901875,
        "emotions": [
          {
            "label": "sad",
            "score": 0.8459424376487732
          }
        ],
        "styles": [
          {
            "label": "warm",
            "score": 0.9273632764816284
          },
          {
            "label": "irritated",
            "score": 0.8365545868873596
          }
        ]
      }
    },
    {
      "id": "1015_MTI_SAD_XX",
      "audioSrc": "/samples/emotional/1015_MTI_SAD_XX.wav",
      "audioSha256": "7af637f2ef9db93974ff9c8db92c3b5885d0a68d22e2fc6f55aeb2dc1866e39a",
      "trainingPcmSha256": "3926b02f1448631b032e159373ebd5fbbda7d69e36b9a354d878c2490c323868",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1015_MTI_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1015_MTI_SAD_XX.wav",
      "transcript": "Maybe tomorrow it will be cold",
      "duration": 2.06875,
      "waveform": [
        0.106,
        0.0833,
        0.1011,
        0.1204,
        0.1304,
        0.1198,
        0.1447,
        0.1589,
        0.121,
        0.121,
        0.2379,
        0.2796,
        0.3493,
        0.3771,
        0.2465,
        0.2104,
        0.3682,
        0.4299,
        0.177,
        0.2361,
        0.1511,
        0.1447,
        0.5548,
        0.8487,
        0.7955,
        1.0,
        0.7994,
        0.7326,
        0.8566,
        0.8561,
        0.7666,
        0.743,
        0.7023,
        0.5226,
        0.5176,
        0.472,
        0.6055,
        0.7685,
        0.2714,
        0.2516,
        0.163,
        0.2094,
        0.2093,
        0.1574,
        0.1569,
        0.2599,
        0.329,
        0.2865,
        0.1514,
        0.1327,
        0.3931,
        0.2647,
        0.1669,
        0.2983,
        0.4218,
        0.7474,
        0.4246,
        0.3593,
        0.2811,
        0.2331,
        0.2394,
        0.1984,
        0.1936,
        0.1226,
        0.131,
        0.1197,
        0.1221,
        0.1002,
        0.1492,
        0.1104,
        0.1018,
        0.1858,
        0.1045,
        0.104,
        0.0911,
        0.1179,
        0.1194,
        0.0911,
        0.1079,
        0.1234
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Maybe tomorrow that will be cold.",
        "duration": 2.06875,
        "emotions": [
          {
            "label": "sad",
            "score": 0.9263036847114563
          },
          {
            "label": "frustrated",
            "score": 0.9161096215248108
          }
        ],
        "styles": [
          {
            "label": "tired",
            "score": 0.8840392827987671
          },
          {
            "label": "irritated",
            "score": 0.879974365234375
          }
        ]
      }
    },
    {
      "id": "1078_TSI_SAD_XX",
      "audioSrc": "/samples/emotional/1078_TSI_SAD_XX.wav",
      "audioSha256": "6fd8464279fc2a46efaf937e6ffb05d0d8d75d5af9ed067a421d68b40f493142",
      "trainingPcmSha256": "51a43c78ab079d0753553a6edcc3050c278097d937a9b4319d5c0f0472e01564",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1078_TSI_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1078_TSI_SAD_XX.wav",
      "transcript": "The surface is slick",
      "duration": 2.5025,
      "waveform": [
        0.0635,
        0.0497,
        0.0455,
        0.0644,
        0.0662,
        0.0748,
        0.0848,
        0.0766,
        0.0773,
        0.0964,
        0.0709,
        0.0734,
        0.0644,
        0.1265,
        0.111,
        0.0667,
        0.0798,
        0.1073,
        0.1111,
        0.1374,
        0.1254,
        0.1146,
        0.1083,
        0.0954,
        0.0979,
        0.0989,
        0.1709,
        0.8759,
        0.6714,
        1.0,
        0.5692,
        0.2655,
        0.1649,
        0.1202,
        0.084,
        0.2924,
        0.2263,
        0.2464,
        0.1497,
        0.116,
        0.1006,
        0.182,
        0.3271,
        0.3862,
        0.1558,
        0.1193,
        0.1243,
        0.1203,
        0.1062,
        0.0861,
        0.0698,
        0.1459,
        0.17,
        0.2041,
        0.2034,
        0.3341,
        0.4151,
        0.2326,
        0.0576,
        0.0748,
        0.0611,
        0.0431,
        0.0751,
        0.0556,
        0.063,
        0.0752,
        0.0619,
        0.0574,
        0.0688,
        0.0639,
        0.0725,
        0.0717,
        0.0607,
        0.0592,
        0.048,
        0.0799,
        0.0985,
        0.0529,
        0.0582,
        0.0513
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The surface is slick.",
        "duration": 2.5025,
        "emotions": [
          {
            "label": "sad",
            "score": 0.7606506943702698
          }
        ],
        "styles": [
          {
            "label": "casual",
            "score": 0.9124361872673035
          }
        ]
      }
    },
    {
      "id": "1038_TAI_SAD_XX",
      "audioSrc": "/samples/emotional/1038_TAI_SAD_XX.wav",
      "audioSha256": "abb567c790ea7d5eca439025153642eea1719ac45080665a63a1c9efb791992d",
      "trainingPcmSha256": "895b95a647ad36b1b9c05073a09757e17bb02b55e16e9669c94d4dff5d5d4d5b",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1038_TAI_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1038_TAI_SAD_XX.wav",
      "transcript": "The airplane is almost full",
      "duration": 2.93625,
      "waveform": [
        0.091,
        0.0834,
        0.0869,
        0.0781,
        0.0786,
        0.0763,
        0.0815,
        0.0814,
        0.07,
        0.0697,
        0.0617,
        0.0626,
        0.0764,
        0.0783,
        0.0775,
        0.0787,
        0.0919,
        0.079,
        0.0855,
        0.0776,
        0.0919,
        0.1869,
        0.3434,
        0.3661,
        0.3484,
        0.3655,
        0.4486,
        0.3922,
        0.3204,
        0.1818,
        0.0743,
        0.0991,
        0.0975,
        0.2481,
        0.373,
        0.4167,
        0.3016,
        0.3826,
        0.4178,
        0.2404,
        0.1899,
        0.3743,
        0.5155,
        0.4934,
        0.5769,
        0.4733,
        0.4423,
        0.584,
        0.705,
        0.4731,
        0.2604,
        0.1958,
        0.1641,
        0.1378,
        0.1288,
        0.09,
        0.0956,
        0.1083,
        0.0637,
        0.2375,
        0.5031,
        0.5602,
        0.4926,
        1.0,
        0.8435,
        0.6213,
        0.4577,
        0.3797,
        0.241,
        0.2259,
        0.1655,
        0.1182,
        0.0762,
        0.0657,
        0.0863,
        0.068,
        0.083,
        0.1032,
        0.0757,
        0.0765
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The airplane is almost full.",
        "duration": 2.93625,
        "emotions": [
          {
            "label": "worried",
            "score": 0.9919379353523254
          },
          {
            "label": "sad",
            "score": 0.9458011984825134
          },
          {
            "label": "disappointed",
            "score": 0.9149009585380554
          }
        ],
        "styles": [
          {
            "label": "tired",
            "score": 0.9817357659339905
          }
        ]
      }
    },
    {
      "id": "1084_ITS_SAD_XX",
      "audioSrc": "/samples/emotional/1084_ITS_SAD_XX.wav",
      "audioSha256": "0766407ac6d9ae13b4459f4e0accb3aa5ee90677b5a16f18496f6574791184d7",
      "trainingPcmSha256": "b91a907f31e21cb6e10f9d24c22672b0c2a4d431339afea2e83239fb75e4ab9f",
      "trainingSplit": "train",
      "sourceEmotion": "sad",
      "sourceFile": "1084_ITS_SAD_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1084_ITS_SAD_XX.wav",
      "transcript": "I think I've seen this before",
      "duration": 2.1688125,
      "waveform": [
        0.1252,
        0.1832,
        0.1795,
        0.1838,
        0.1479,
        0.1655,
        0.1554,
        0.1387,
        0.1415,
        0.1322,
        0.1206,
        0.1882,
        0.4949,
        0.723,
        0.7952,
        0.7542,
        0.4014,
        0.2103,
        0.2749,
        0.9784,
        0.9829,
        1.0,
        0.4582,
        0.3884,
        0.3424,
        0.6543,
        0.6283,
        0.6288,
        0.2648,
        0.1966,
        0.196,
        0.306,
        0.2661,
        0.3022,
        0.3179,
        0.7265,
        0.9203,
        0.8721,
        0.8666,
        0.8227,
        0.6902,
        0.6406,
        0.6511,
        0.5538,
        0.3632,
        0.3626,
        0.3402,
        0.3033,
        0.2281,
        0.2136,
        0.1332,
        0.155,
        0.3194,
        0.3182,
        0.2396,
        0.1347,
        0.1482,
        0.123,
        0.1297,
        0.2119,
        0.2146,
        0.2603,
        0.2609,
        0.2661,
        0.2506,
        0.2331,
        0.2212,
        0.1709,
        0.1811,
        0.1875,
        0.1875,
        0.1322,
        0.1512,
        0.1705,
        0.2164,
        0.1385,
        0.1296,
        0.1072,
        0.1588,
        0.1158
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I think I've seen this before.",
        "duration": 2.1688125,
        "emotions": [
          {
            "label": "sad",
            "score": 0.9916841983795166
          }
        ],
        "styles": [
          {
            "label": "tired",
            "score": 0.9532750844955444
          },
          {
            "label": "deadpan",
            "score": 0.9489172697067261
          },
          {
            "label": "casual",
            "score": 0.7943849563598633
          }
        ]
      }
    },
    {
      "id": "1047_IEO_ANG_HI",
      "audioSrc": "/samples/emotional/1047_IEO_ANG_HI.wav",
      "audioSha256": "855b0a63c18e31507a3b98e8be6d31af69a5a4c4fcb069aee2b1d3fef277f422",
      "trainingPcmSha256": "f81189d86cb1bc398e2c380a192e1c71a695542817669534dba50d97a75ce987",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1047_IEO_ANG_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1047_IEO_ANG_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 2.535875,
      "waveform": [
        0.0105,
        0.01,
        0.0095,
        0.0099,
        0.0079,
        0.0076,
        0.0077,
        0.0092,
        0.0082,
        0.0127,
        0.0118,
        0.0075,
        0.0093,
        0.0098,
        0.0096,
        0.1661,
        0.2855,
        0.2018,
        0.089,
        0.0368,
        0.036,
        0.0279,
        0.0978,
        0.3031,
        0.3784,
        0.1891,
        0.2029,
        0.2158,
        0.1717,
        0.5524,
        0.7108,
        0.6466,
        0.6775,
        0.2976,
        0.1429,
        0.3732,
        0.4747,
        0.281,
        0.2105,
        0.1424,
        0.1962,
        0.2313,
        0.0991,
        0.0478,
        0.044,
        0.029,
        0.0697,
        0.1797,
        0.658,
        0.8657,
        1.0,
        0.6273,
        0.587,
        0.2298,
        0.1172,
        0.045,
        0.0193,
        0.025,
        0.0513,
        0.0405,
        0.0204,
        0.0156,
        0.0105,
        0.0129,
        0.0118,
        0.01,
        0.0106,
        0.0106,
        0.0113,
        0.0076,
        0.0075,
        0.0086,
        0.0101,
        0.0078,
        0.0089,
        0.0098,
        0.0105,
        0.0119,
        0.0099,
        0.0065
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's eleven o'clock!",
        "duration": 2.535875,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.9966233968734741
          },
          {
            "label": "angry",
            "score": 0.9840936064720154
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9899863600730896
          }
        ]
      }
    },
    {
      "id": "1006_IEO_ANG_HI",
      "audioSrc": "/samples/emotional/1006_IEO_ANG_HI.wav",
      "audioSha256": "6cb4132714521cf449dc20ffe25ce098ca7ce716b5d25062cacc245e8a7c6dc8",
      "trainingPcmSha256": "b19c3fdeaa96425427dfe1d53df7ba0bbf92937621ba37b6287c687eeb6a6062",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1006_IEO_ANG_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1006_IEO_ANG_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 2.56925,
      "waveform": [
        0.013,
        0.0089,
        0.0147,
        0.0164,
        0.0135,
        0.0219,
        0.0137,
        0.0193,
        0.0208,
        0.0162,
        0.013,
        0.0091,
        0.1558,
        0.3129,
        0.3451,
        0.2068,
        0.0895,
        0.0614,
        0.2075,
        0.7025,
        1.0,
        0.5066,
        0.3837,
        0.2945,
        0.2899,
        0.3444,
        0.4177,
        0.5778,
        0.5231,
        0.4601,
        0.2273,
        0.3195,
        0.1743,
        0.2657,
        0.3937,
        0.2447,
        0.0944,
        0.0502,
        0.0407,
        0.031,
        0.0167,
        0.023,
        0.0757,
        0.1522,
        0.2508,
        0.3742,
        0.4597,
        0.4829,
        0.3825,
        0.5021,
        0.212,
        0.2128,
        0.0814,
        0.0375,
        0.0206,
        0.014,
        0.0235,
        0.0201,
        0.0107,
        0.0113,
        0.0134,
        0.0115,
        0.0107,
        0.0135,
        0.0182,
        0.0184,
        0.0134,
        0.0128,
        0.0163,
        0.0144,
        0.0124,
        0.0124,
        0.0137,
        0.0087,
        0.0111,
        0.0156,
        0.0225,
        0.02,
        0.0182,
        0.0056
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's eleven o'clock.",
        "duration": 2.56925,
        "emotions": [
          {
            "label": "disappointed",
            "score": 0.9678993225097656
          },
          {
            "label": "frustrated",
            "score": 0.9621075391769409
          },
          {
            "label": "angry",
            "score": 0.9553191661834717
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.961533784866333
          }
        ]
      }
    },
    {
      "id": "1009_TSI_ANG_XX",
      "audioSrc": "/samples/emotional/1009_TSI_ANG_XX.wav",
      "audioSha256": "59184cb02a9e1513cc959d0e3d6c0fa090c6866d4a396ceda5696fa58ff1484a",
      "trainingPcmSha256": "f2a04c2180891f3bd07a74d562cbe8f33bb20eb4478de30664fdfa0d380bc878",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1009_TSI_ANG_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1009_TSI_ANG_XX.wav",
      "transcript": "The surface is slick",
      "duration": 2.3356875,
      "waveform": [
        0.0107,
        0.0207,
        0.2017,
        1.0,
        0.6759,
        0.2292,
        0.1653,
        0.0821,
        0.0598,
        0.0609,
        0.0584,
        0.2622,
        0.3727,
        0.4657,
        0.658,
        0.689,
        0.2178,
        0.1687,
        0.0789,
        0.0412,
        0.1327,
        0.2544,
        0.3006,
        0.1535,
        0.1231,
        0.0988,
        0.0614,
        0.0424,
        0.0272,
        0.0128,
        0.0337,
        0.102,
        0.1035,
        0.1005,
        0.1389,
        0.1311,
        0.0655,
        0.0459,
        0.0477,
        0.0546,
        0.0585,
        0.0384,
        0.0344,
        0.09,
        0.1939,
        0.5063,
        0.6203,
        0.6705,
        0.4428,
        0.167,
        0.0946,
        0.0391,
        0.0183,
        0.0244,
        0.0339,
        0.0189,
        0.0101,
        0.0102,
        0.0087,
        0.0099,
        0.0099,
        0.0083,
        0.0106,
        0.0076,
        0.0076,
        0.0075,
        0.0069,
        0.0093,
        0.0075,
        0.0099,
        0.0079,
        0.0076,
        0.008,
        0.0101,
        0.0102,
        0.0116,
        0.0108,
        0.0103,
        0.0077,
        0.0055
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The surface is slick!",
        "duration": 2.3356875,
        "emotions": [
          {
            "label": "angry",
            "score": 0.9796676635742188
          },
          {
            "label": "frustrated",
            "score": 0.8933094143867493
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9230391979217529
          },
          {
            "label": "energetic",
            "score": 0.851952850818634
          }
        ]
      }
    },
    {
      "id": "1002_DFA_ANG_XX",
      "audioSrc": "/samples/emotional/1002_DFA_ANG_XX.wav",
      "audioSha256": "31eda0c90ebd72b7f311ab3b980258c6d094e08be96da3d15fbd6a7e19ff91d8",
      "trainingPcmSha256": "90dfe841eaef476cdad34e68cbd55a58766e039d5a62746e6d79ff1fac1f3724",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1002_DFA_ANG_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1002_DFA_ANG_XX.wav",
      "transcript": "Don't forget a jacket",
      "duration": 2.56925,
      "waveform": [
        0.0131,
        0.0099,
        0.011,
        0.0104,
        0.0083,
        0.0141,
        0.0125,
        0.0121,
        0.0144,
        0.0125,
        0.0136,
        0.0142,
        0.0107,
        0.0758,
        0.2399,
        0.4296,
        0.4046,
        0.1758,
        0.0731,
        0.1019,
        0.5772,
        0.6441,
        0.2983,
        0.4918,
        0.6172,
        0.5741,
        0.5916,
        0.5228,
        0.7432,
        0.3624,
        0.1256,
        0.0705,
        0.0432,
        0.094,
        0.3173,
        0.4911,
        1.0,
        0.5558,
        0.638,
        0.3431,
        0.1095,
        0.0425,
        0.1192,
        0.254,
        0.2668,
        0.7558,
        0.6345,
        0.246,
        0.052,
        0.033,
        0.0516,
        0.0775,
        0.0673,
        0.0385,
        0.0176,
        0.0087,
        0.0063,
        0.007,
        0.0056,
        0.0058,
        0.0109,
        0.0085,
        0.0101,
        0.0099,
        0.0083,
        0.0096,
        0.0084,
        0.0067,
        0.0125,
        0.0131,
        0.0084,
        0.0152,
        0.0124,
        0.0137,
        0.0116,
        0.0098,
        0.0129,
        0.0098,
        0.0094,
        0.0082
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Don't forget a jacket!",
        "duration": 2.56925,
        "emotions": [
          {
            "label": "worried",
            "score": 0.9693241715431213
          },
          {
            "label": "angry",
            "score": 0.8606036305427551
          }
        ],
        "styles": [
          {
            "label": "passionate",
            "score": 0.869714617729187
          }
        ]
      }
    },
    {
      "id": "1010_TAI_ANG_XX",
      "audioSrc": "/samples/emotional/1010_TAI_ANG_XX.wav",
      "audioSha256": "3ebcc12c417e95fe6529143f97d07ca8d54dfbf1ca6b9499a54c760f64ef6d20",
      "trainingPcmSha256": "8221cc7156984a628546a0ea2945b007434a5fd2c95e0d186ea80c805ba4fbc4",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1010_TAI_ANG_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1010_TAI_ANG_XX.wav",
      "transcript": "The airplane is almost full",
      "duration": 2.56925,
      "waveform": [
        0.0326,
        0.0225,
        0.0165,
        0.0241,
        0.0245,
        0.0183,
        0.0203,
        0.0229,
        0.0265,
        0.0332,
        0.031,
        0.0206,
        0.2016,
        0.4789,
        0.3773,
        0.2503,
        0.2303,
        0.1068,
        0.451,
        0.8275,
        0.5483,
        0.7733,
        0.4521,
        0.1766,
        0.0855,
        0.052,
        0.1653,
        0.7199,
        0.4019,
        0.2306,
        0.2496,
        0.1554,
        0.2489,
        0.3138,
        0.2253,
        0.1275,
        0.0837,
        0.051,
        0.1725,
        0.8882,
        0.7255,
        1.0,
        0.4478,
        0.4328,
        0.3746,
        0.5398,
        0.6312,
        0.258,
        0.1825,
        0.0934,
        0.0814,
        0.0727,
        0.0402,
        0.0296,
        0.0247,
        0.0191,
        0.059,
        0.288,
        0.2621,
        0.4619,
        0.4258,
        0.3693,
        0.2284,
        0.0849,
        0.0577,
        0.0323,
        0.0242,
        0.0173,
        0.017,
        0.0186,
        0.0152,
        0.0175,
        0.0261,
        0.0245,
        0.022,
        0.0223,
        0.0249,
        0.0165,
        0.0246,
        0.0087
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The airplane is almost full.",
        "duration": 2.56925,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.9585376977920532
          },
          {
            "label": "angry",
            "score": 0.8529354333877563
          }
        ],
        "styles": [
          {
            "label": "impatient",
            "score": 0.9777138829231262
          }
        ]
      }
    },
    {
      "id": "1083_IWL_ANG_XX",
      "audioSrc": "/samples/emotional/1083_IWL_ANG_XX.wav",
      "audioSha256": "118878fe514f2901f39ac9d08becf96a0f57f1ff705341ba8e7e64b9dff479cc",
      "trainingPcmSha256": "c8184e372d83ad654afb017bd2fd8f082b21ea534f1e3609fe0d1bb663655386",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1083_IWL_ANG_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1083_IWL_ANG_XX.wav",
      "transcript": "I would like a new alarm clock",
      "duration": 3.7036875,
      "waveform": [
        0.0392,
        0.0316,
        0.0324,
        0.0282,
        0.0334,
        0.0383,
        0.0383,
        0.3538,
        0.3714,
        0.472,
        0.2726,
        0.1991,
        0.2713,
        0.1058,
        0.1442,
        0.3111,
        0.3696,
        0.4124,
        0.4618,
        0.5789,
        0.6187,
        0.4629,
        0.3618,
        0.1145,
        0.0628,
        0.0503,
        0.0327,
        0.0292,
        0.0311,
        0.0365,
        0.0223,
        0.027,
        0.0398,
        0.176,
        0.35,
        0.321,
        0.3701,
        0.4542,
        0.4265,
        0.436,
        0.4854,
        0.4505,
        0.3457,
        0.1533,
        0.3204,
        0.1553,
        0.0501,
        0.3065,
        0.4695,
        0.4585,
        0.3583,
        0.2453,
        0.503,
        0.6906,
        0.81,
        1.0,
        0.8874,
        0.7269,
        0.3713,
        0.1421,
        0.0962,
        0.0594,
        0.2012,
        0.2449,
        0.3128,
        0.2231,
        0.0911,
        0.0426,
        0.0421,
        0.0677,
        0.0459,
        0.0349,
        0.0329,
        0.0405,
        0.034,
        0.0387,
        0.04,
        0.0261,
        0.0323,
        0.0221
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I would like a new alarm clock.",
        "duration": 3.7036875,
        "emotions": [
          {
            "label": "angry",
            "score": 0.997368335723877
          },
          {
            "label": "frustrated",
            "score": 0.9921841025352478
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9995694756507874
          },
          {
            "label": "impatient",
            "score": 0.9955315589904785
          }
        ]
      }
    },
    {
      "id": "1074_TAI_ANG_XX",
      "audioSrc": "/samples/emotional/1074_TAI_ANG_XX.wav",
      "audioSha256": "1962f6ea7845abefae75bcaa79c14128113803fac8dd2300b17720872e64be8f",
      "trainingPcmSha256": "07f56b9e1400b27aaf363d8647c7be8a969ad6e1db47479e27279a5bcc9f4226",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1074_TAI_ANG_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1074_TAI_ANG_XX.wav",
      "transcript": "The airplane is almost full",
      "duration": 2.93625,
      "waveform": [
        0.0118,
        0.0124,
        0.012,
        0.0096,
        0.0107,
        0.0118,
        0.0122,
        0.0109,
        0.0108,
        0.0227,
        0.1416,
        0.3738,
        0.3959,
        0.1619,
        0.0963,
        0.3105,
        0.3844,
        0.5635,
        0.5546,
        0.5969,
        0.4912,
        0.1865,
        0.1152,
        0.2234,
        0.2618,
        0.2788,
        0.2166,
        0.1988,
        0.323,
        0.3,
        0.3396,
        0.2224,
        0.1661,
        0.0939,
        0.0464,
        0.0266,
        0.0426,
        0.2665,
        0.4936,
        0.6625,
        0.8328,
        0.4225,
        0.3101,
        0.5278,
        1.0,
        0.7669,
        0.4006,
        0.1552,
        0.0761,
        0.0326,
        0.0191,
        0.021,
        0.0127,
        0.0154,
        0.1714,
        0.4882,
        0.5189,
        0.7714,
        0.7872,
        0.7666,
        0.5202,
        0.2564,
        0.1638,
        0.1104,
        0.0732,
        0.0506,
        0.032,
        0.0205,
        0.0151,
        0.0094,
        0.0147,
        0.0108,
        0.0118,
        0.0128,
        0.012,
        0.0095,
        0.012,
        0.0098,
        0.0099,
        0.0123
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The airplane is almost full",
        "duration": 2.93625,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.9664104580879211
          },
          {
            "label": "angry",
            "score": 0.9334307909011841
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9449946880340576
          },
          {
            "label": "impatient",
            "score": 0.8333246111869812
          }
        ]
      }
    },
    {
      "id": "1015_TIE_ANG_XX",
      "audioSrc": "/samples/emotional/1015_TIE_ANG_XX.wav",
      "audioSha256": "bbf8312239a8ba6d048006ece2a86e28cca5087264b59b3b00dd49e97e9972eb",
      "trainingPcmSha256": "e1dd7698bfb6364c0bb38fc0fb9d64cac2005fcab053837ab2843ac559cb31b6",
      "trainingSplit": "train",
      "sourceEmotion": "angry",
      "sourceFile": "1015_TIE_ANG_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1015_TIE_ANG_XX.wav",
      "transcript": "That is exactly what happened",
      "duration": 3.036375,
      "waveform": [
        0.0313,
        0.0258,
        0.0355,
        0.0272,
        0.0328,
        0.0379,
        0.0383,
        0.0412,
        0.034,
        0.0276,
        0.0294,
        0.0264,
        0.0305,
        0.0325,
        0.0373,
        0.0285,
        0.047,
        0.058,
        0.0825,
        0.0805,
        0.0688,
        0.0923,
        0.0572,
        0.0474,
        0.0811,
        0.0711,
        0.0445,
        0.055,
        0.1143,
        0.1954,
        0.2298,
        0.9566,
        1.0,
        0.6796,
        0.3168,
        0.1058,
        0.0621,
        0.0553,
        0.0815,
        0.1563,
        0.2025,
        0.1715,
        0.0815,
        0.0464,
        0.0511,
        0.0757,
        0.0644,
        0.0562,
        0.0502,
        0.0861,
        0.3307,
        0.4027,
        0.1755,
        0.0668,
        0.036,
        0.0539,
        0.0625,
        0.0415,
        0.0426,
        0.036,
        0.0338,
        0.0244,
        0.0358,
        0.0428,
        0.0434,
        0.0316,
        0.0429,
        0.0405,
        0.0317,
        0.0355,
        0.0451,
        0.0462,
        0.0578,
        0.0384,
        0.0399,
        0.0329,
        0.0337,
        0.0298,
        0.0282,
        0.0234
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "That is exactly what happened.",
        "duration": 3.036375,
        "emotions": [
          {
            "label": "angry",
            "score": 0.9724147915840149
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9928786158561707
          }
        ]
      }
    },
    {
      "id": "1047_IEO_FEA_HI",
      "audioSrc": "/samples/emotional/1047_IEO_FEA_HI.wav",
      "audioSha256": "ac1a0ab5f0cec0681e64014479e9f75b88358b05d46c31818d87837b762c89f8",
      "trainingPcmSha256": "943ece90b82602a394efa8ee7114f0460ec1d96b29942c7d077b74e13a2d20bf",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1047_IEO_FEA_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1047_IEO_FEA_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 1.7016875,
      "waveform": [
        0.0142,
        0.0125,
        0.0099,
        0.0093,
        0.0105,
        0.0115,
        0.0109,
        0.0097,
        0.0095,
        0.0115,
        0.0102,
        0.1566,
        0.2207,
        0.1092,
        0.0811,
        0.0518,
        0.1235,
        0.5028,
        0.4134,
        0.4912,
        0.3364,
        0.308,
        0.5701,
        0.7043,
        1.0,
        0.9291,
        0.5951,
        0.3163,
        0.3228,
        0.2427,
        0.2357,
        0.4344,
        0.4295,
        0.167,
        0.106,
        0.0625,
        0.0497,
        0.1093,
        0.2254,
        0.4889,
        0.6173,
        0.582,
        0.8037,
        0.8586,
        0.5219,
        0.6153,
        0.7117,
        0.3565,
        0.1968,
        0.0972,
        0.0473,
        0.0512,
        0.0597,
        0.0393,
        0.025,
        0.0165,
        0.013,
        0.0153,
        0.0169,
        0.008,
        0.0102,
        0.0158,
        0.0154,
        0.0118,
        0.0119,
        0.0136,
        0.0161,
        0.0141,
        0.0121,
        0.0132,
        0.0098,
        0.011,
        0.0098,
        0.0108,
        0.0107,
        0.0083,
        0.015,
        0.0095,
        0.0125,
        0.0078
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's eleven o'clock!",
        "duration": 1.7016875,
        "emotions": [
          {
            "label": "scared",
            "score": 0.9532750844955444
          }
        ],
        "styles": [
          {
            "label": "impatient",
            "score": 0.9559813141822815
          },
          {
            "label": "energetic",
            "score": 0.9241418242454529
          },
          {
            "label": "irritated",
            "score": 0.8187368512153625
          }
        ]
      }
    },
    {
      "id": "1059_DFA_FEA_XX",
      "audioSrc": "/samples/emotional/1059_DFA_FEA_XX.wav",
      "audioSha256": "1ad3af9ecb106a437aca9adb541ec5e12a2689be24c58d6ee82a00f9b89f9ecc",
      "trainingPcmSha256": "20e73cf630fb42d28e7ef323bb3deb613be43e96307f54e9d0d58960800a6677",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1059_DFA_FEA_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1059_DFA_FEA_XX.wav",
      "transcript": "Don't forget a jacket",
      "duration": 2.06875,
      "waveform": [
        0.0079,
        0.0066,
        0.009,
        0.0085,
        0.0085,
        0.0055,
        0.0057,
        0.0072,
        0.006,
        0.009,
        0.0084,
        0.0066,
        0.0078,
        0.0087,
        0.0107,
        0.0079,
        0.008,
        0.0092,
        0.0068,
        0.0106,
        0.0088,
        0.0084,
        0.0074,
        0.0072,
        0.009,
        0.0357,
        0.4596,
        1.0,
        0.5196,
        0.6003,
        0.3566,
        0.2442,
        0.1374,
        0.0923,
        0.2303,
        0.4676,
        0.4959,
        0.2351,
        0.2011,
        0.1266,
        0.2587,
        0.34,
        0.2925,
        0.4775,
        0.5702,
        0.4301,
        0.2463,
        0.0855,
        0.1292,
        0.1207,
        0.3967,
        0.6256,
        0.6431,
        0.5864,
        0.627,
        0.7337,
        0.4647,
        0.2286,
        0.1106,
        0.044,
        0.0367,
        0.1239,
        0.1686,
        0.1884,
        0.1111,
        0.0504,
        0.038,
        0.0243,
        0.016,
        0.0098,
        0.0092,
        0.0088,
        0.0065,
        0.0077,
        0.0064,
        0.0118,
        0.0065,
        0.0073,
        0.0073,
        0.0044
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Don't forget a jacket",
        "duration": 2.06875,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.9674102663993835
          },
          {
            "label": "scared",
            "score": 0.949669361114502
          },
          {
            "label": "worried",
            "score": 0.8587185740470886
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9736446738243103
          },
          {
            "label": "impatient",
            "score": 0.9603611826896667
          }
        ]
      }
    },
    {
      "id": "1056_TIE_FEA_XX",
      "audioSrc": "/samples/emotional/1056_TIE_FEA_XX.wav",
      "audioSha256": "6a3fb8242f5e7158d96e49ad96fc6b8488a396e9b443690a938950a305c806f1",
      "trainingPcmSha256": "a74c0fe38181628edb0e80375cc35b2029377938563f6a21d5ea4c90e62adfd7",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1056_TIE_FEA_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1056_TIE_FEA_XX.wav",
      "transcript": "That is exactly what happened",
      "duration": 3.1698125,
      "waveform": [
        0.0751,
        0.0769,
        0.051,
        0.0649,
        0.0513,
        0.0455,
        0.0639,
        0.0643,
        0.0667,
        0.0644,
        0.0577,
        0.0532,
        0.0596,
        0.068,
        0.0485,
        0.0994,
        0.6226,
        0.6093,
        0.543,
        0.6034,
        0.6498,
        0.4528,
        0.4214,
        0.8261,
        0.5557,
        0.2946,
        0.2718,
        0.1588,
        0.1996,
        0.1614,
        0.2477,
        0.9428,
        0.6077,
        0.544,
        0.3008,
        0.1052,
        0.1585,
        0.2939,
        0.5773,
        0.347,
        0.3253,
        0.1824,
        0.482,
        1.0,
        0.7163,
        0.5241,
        0.2664,
        0.137,
        0.1512,
        0.4648,
        0.6656,
        0.9376,
        0.506,
        0.1455,
        0.1316,
        0.4098,
        0.3914,
        0.2049,
        0.1268,
        0.111,
        0.0635,
        0.0643,
        0.0729,
        0.0612,
        0.0617,
        0.0684,
        0.1026,
        0.0543,
        0.0468,
        0.0596,
        0.0555,
        0.0539,
        0.0411,
        0.084,
        0.0678,
        0.0681,
        0.0552,
        0.0555,
        0.0569,
        0.059
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "That is exactly what happened.",
        "duration": 3.1698125,
        "emotions": [
          {
            "label": "frustrated",
            "score": 0.9664104580879211
          },
          {
            "label": "scared",
            "score": 0.8529354333877563
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9899863600730896
          }
        ]
      }
    },
    {
      "id": "1080_ITH_FEA_XX",
      "audioSrc": "/samples/emotional/1080_ITH_FEA_XX.wav",
      "audioSha256": "5d8bca476779a6ea675efff78686bf42c4b57c80857b504b1ad07a9987a22abb",
      "trainingPcmSha256": "3c509f4d2d883daf17680eb4ee5ef38f908cdf81a2ef179a104e6170f08e0fc3",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1080_ITH_FEA_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1080_ITH_FEA_XX.wav",
      "transcript": "I think I have a doctor's appointment",
      "duration": 3.536875,
      "waveform": [
        0.0974,
        0.1394,
        0.1503,
        0.135,
        0.1636,
        0.1093,
        0.1317,
        0.146,
        0.14,
        0.1589,
        0.14,
        0.1586,
        0.1664,
        0.1534,
        0.1549,
        0.1223,
        0.1455,
        0.1492,
        0.1596,
        0.1144,
        0.11,
        0.1399,
        0.1374,
        0.1522,
        0.1948,
        0.2672,
        0.164,
        0.1497,
        0.1606,
        0.6043,
        0.8732,
        0.4016,
        0.3365,
        0.5633,
        0.2978,
        0.3998,
        0.6314,
        0.4038,
        0.6896,
        0.3573,
        0.2085,
        0.1508,
        0.1452,
        0.1127,
        0.1251,
        0.349,
        0.7611,
        0.7212,
        1.0,
        0.7102,
        0.346,
        0.274,
        0.5163,
        0.5202,
        0.4381,
        0.3995,
        0.4584,
        0.2721,
        0.238,
        0.19,
        0.6499,
        0.4566,
        0.2957,
        0.1892,
        0.2869,
        0.2742,
        0.1801,
        0.1956,
        0.148,
        0.1879,
        0.1688,
        0.1743,
        0.2014,
        0.121,
        0.135,
        0.1633,
        0.1478,
        0.1511,
        0.1127,
        0.1228
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I think I have a doctor's appointment.",
        "duration": 3.536875,
        "emotions": [
          {
            "label": "worried",
            "score": 0.9736446738243103
          },
          {
            "label": "scared",
            "score": 0.970687747001648
          }
        ],
        "styles": [
          {
            "label": "formal",
            "score": 0.8529354333877563
          }
        ]
      }
    },
    {
      "id": "1072_ITH_FEA_XX",
      "audioSrc": "/samples/emotional/1072_ITH_FEA_XX.wav",
      "audioSha256": "90279397554f9c1873a907a1aa475e74ffde36a3519e11e83eb8b1e313cd7b21",
      "trainingPcmSha256": "f704ff82a36154d18c1fb771587fec47d7375d9213968bfa81524621df5341f2",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1072_ITH_FEA_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1072_ITH_FEA_XX.wav",
      "transcript": "I think I have a doctor's appointment",
      "duration": 2.6693125,
      "waveform": [
        0.0359,
        0.0391,
        0.0408,
        0.0369,
        0.0413,
        0.0392,
        0.0278,
        0.0334,
        0.0439,
        0.0353,
        0.0428,
        0.0347,
        0.0384,
        0.0302,
        0.0311,
        0.0429,
        0.0346,
        0.0363,
        0.0341,
        0.0323,
        0.0253,
        0.0355,
        0.0429,
        0.0349,
        0.0403,
        0.0416,
        0.06,
        0.3918,
        0.5436,
        0.194,
        0.388,
        0.3855,
        0.3128,
        0.169,
        0.2222,
        0.1934,
        0.4143,
        0.524,
        0.4476,
        0.7181,
        0.4954,
        0.1648,
        0.5632,
        0.8091,
        0.778,
        0.6257,
        0.4041,
        0.1395,
        0.9319,
        1.0,
        0.5637,
        0.2637,
        0.842,
        0.6676,
        0.188,
        0.1201,
        0.4252,
        0.874,
        0.6602,
        0.2609,
        0.2085,
        0.1684,
        0.2597,
        0.2642,
        0.105,
        0.0644,
        0.0505,
        0.0413,
        0.0417,
        0.026,
        0.0349,
        0.0281,
        0.0316,
        0.0408,
        0.0412,
        0.0378,
        0.0536,
        0.0297,
        0.045,
        0.0332
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I think I have a doctor's appointment.",
        "duration": 2.6693125,
        "emotions": [
          {
            "label": "worried",
            "score": 0.9489172697067261
          },
          {
            "label": "scared",
            "score": 0.9441768527030945
          },
          {
            "label": "excited",
            "score": 0.8749346137046814
          }
        ],
        "styles": [
          {
            "label": "energetic",
            "score": 0.9678993225097656
          }
        ]
      }
    },
    {
      "id": "1005_TAI_FEA_XX",
      "audioSrc": "/samples/emotional/1005_TAI_FEA_XX.wav",
      "audioSha256": "29049ed53c94105806fbdca0a1fcaf8376582fbda8d059a00014bc7c0239a62a",
      "trainingPcmSha256": "5e78d2b40af4465122bc14db40a2ac837e9aa97a586beeb6b9fd2c0f410125a1",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1005_TAI_FEA_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1005_TAI_FEA_XX.wav",
      "transcript": "The airplane is almost full",
      "duration": 2.535875,
      "waveform": [
        0.03,
        0.0391,
        0.0208,
        0.025,
        0.0204,
        0.0213,
        0.0178,
        0.1248,
        0.3843,
        0.3162,
        0.3771,
        0.5183,
        0.8509,
        1.0,
        0.6364,
        0.2143,
        0.129,
        0.1964,
        0.3539,
        0.6146,
        0.7119,
        0.59,
        0.5978,
        0.4547,
        0.6065,
        0.4183,
        0.2686,
        0.2525,
        0.3217,
        0.5425,
        0.6319,
        0.4567,
        0.3903,
        0.3482,
        0.5232,
        0.7992,
        0.714,
        0.4672,
        0.3041,
        0.2028,
        0.1491,
        0.0867,
        0.0666,
        0.0721,
        0.1666,
        0.5995,
        0.7633,
        0.7085,
        0.6343,
        0.435,
        0.3105,
        0.406,
        0.1733,
        0.1413,
        0.1065,
        0.0519,
        0.0311,
        0.0343,
        0.0339,
        0.0241,
        0.0193,
        0.0225,
        0.0307,
        0.0295,
        0.0371,
        0.0208,
        0.0178,
        0.0206,
        0.0206,
        0.0164,
        0.0239,
        0.0181,
        0.0195,
        0.0221,
        0.0329,
        0.0245,
        0.025,
        0.0212,
        0.0245,
        0.0168
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The airplane is almost full.",
        "duration": 2.535875,
        "emotions": [
          {
            "label": "worried",
            "score": 0.9566342234611511
          },
          {
            "label": "excited",
            "score": 0.9324532747268677
          },
          {
            "label": "scared",
            "score": 0.917302668094635
          }
        ],
        "styles": [
          {
            "label": "energetic",
            "score": 0.9559813141822815
          }
        ]
      }
    },
    {
      "id": "1041_MTI_FEA_XX",
      "audioSrc": "/samples/emotional/1041_MTI_FEA_XX.wav",
      "audioSha256": "d3b1ab3bac396e28c5a955f197b900555332aa956fa3082aac559c1f07337ee7",
      "trainingPcmSha256": "515a5ae1be5b2f01c53be6c68ba127315459e2827d686179ddb5fdef7487e599",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1041_MTI_FEA_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1041_MTI_FEA_XX.wav",
      "transcript": "Maybe tomorrow it will be cold",
      "duration": 2.369,
      "waveform": [
        0.2081,
        0.223,
        0.2271,
        0.3086,
        0.3029,
        0.2517,
        0.1947,
        0.2684,
        0.2042,
        0.2259,
        0.2316,
        0.1866,
        0.3028,
        0.2585,
        0.6044,
        0.6786,
        0.7791,
        0.5561,
        0.4738,
        0.5549,
        0.4188,
        0.3607,
        0.4201,
        0.5351,
        0.4609,
        0.5141,
        0.6016,
        0.5882,
        0.5713,
        0.752,
        0.782,
        0.6609,
        0.7169,
        0.7191,
        0.546,
        0.6073,
        0.5398,
        0.3334,
        0.398,
        0.5194,
        0.4972,
        0.4677,
        0.3283,
        0.4282,
        0.4389,
        0.2707,
        0.2879,
        0.285,
        0.3385,
        0.3887,
        0.362,
        0.6037,
        0.8465,
        0.8711,
        1.0,
        0.8083,
        0.8688,
        0.51,
        0.5125,
        0.3017,
        0.3188,
        0.3968,
        0.2362,
        0.1634,
        0.2385,
        0.2607,
        0.24,
        0.2519,
        0.2209,
        0.3173,
        0.244,
        0.3041,
        0.3451,
        0.2921,
        0.215,
        0.2334,
        0.2023,
        0.1832,
        0.3093,
        0.2521
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Maybe tomorrow it will be cold.",
        "duration": 2.369,
        "emotions": [
          {
            "label": "scared",
            "score": 0.9890130758285522
          },
          {
            "label": "worried",
            "score": 0.9886682629585266
          }
        ],
        "styles": [
          {
            "label": "skeptical",
            "score": 0.9343951344490051
          }
        ]
      }
    },
    {
      "id": "1005_IEO_DIS_HI",
      "audioSrc": "/samples/emotional/1005_IEO_DIS_HI.wav",
      "audioSha256": "13f5389c8552a38c6db539125d656f55be5375c18b192c45355b944cf9d61dc1",
      "trainingPcmSha256": "fb8b0d748e5eea277628c22e915883420009c171c86d4758409fbc7ad9b0a10b",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1005_IEO_DIS_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1005_IEO_DIS_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 2.8028125,
      "waveform": [
        0.0318,
        0.0335,
        0.037,
        0.0304,
        0.0429,
        0.0363,
        0.0442,
        0.0314,
        0.0305,
        0.1249,
        0.3438,
        0.6872,
        1.0,
        0.7068,
        0.3412,
        0.2198,
        0.1255,
        0.1088,
        0.1581,
        0.323,
        0.6647,
        0.5605,
        0.3529,
        0.1658,
        0.1416,
        0.1306,
        0.4021,
        0.4837,
        0.9347,
        0.59,
        0.3271,
        0.2152,
        0.2724,
        0.3457,
        0.3728,
        0.1865,
        0.1918,
        0.2401,
        0.3519,
        0.1834,
        0.1052,
        0.0699,
        0.0778,
        0.158,
        0.0871,
        0.0541,
        0.0971,
        0.2064,
        0.4166,
        0.5876,
        0.5104,
        0.4914,
        0.5101,
        0.5463,
        0.5791,
        0.3018,
        0.2155,
        0.1428,
        0.087,
        0.0441,
        0.0403,
        0.034,
        0.0367,
        0.0343,
        0.0619,
        0.058,
        0.0547,
        0.0527,
        0.0502,
        0.0468,
        0.0334,
        0.0389,
        0.0303,
        0.0362,
        0.0363,
        0.0317,
        0.0331,
        0.0305,
        0.038,
        0.0291
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's eleven o'clock.",
        "duration": 2.8028125,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.9362850189208984
          },
          {
            "label": "angry",
            "score": 0.9046505093574524
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9637799859046936
          }
        ]
      }
    },
    {
      "id": "1038_IEO_DIS_HI",
      "audioSrc": "/samples/emotional/1038_IEO_DIS_HI.wav",
      "audioSha256": "644d4536032bb9837424ef0ef9e9d50c1658acc39b8050d4faf10d143bb2917f",
      "trainingPcmSha256": "0e1a943532e7439aaf363594cdcb96681143ee3f178debdf678c2087ef79e81c",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1038_IEO_DIS_HI.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1038_IEO_DIS_HI.wav",
      "transcript": "It's eleven o'clock",
      "duration": 2.8028125,
      "waveform": [
        0.0249,
        0.0219,
        0.0322,
        0.0306,
        0.0315,
        0.0249,
        0.0213,
        0.0283,
        0.0243,
        0.0289,
        0.0369,
        0.0252,
        0.0395,
        0.0351,
        0.021,
        0.0319,
        0.0299,
        0.0289,
        0.1482,
        0.4368,
        0.3157,
        0.2375,
        0.0983,
        0.073,
        0.1953,
        0.4538,
        0.3243,
        0.3159,
        0.3285,
        0.3663,
        0.4162,
        0.6787,
        0.7755,
        0.9408,
        0.6078,
        0.2222,
        0.3433,
        0.5218,
        0.3814,
        0.1738,
        0.1065,
        0.1882,
        0.4193,
        0.2578,
        0.093,
        0.0599,
        0.0761,
        0.117,
        0.1061,
        0.2188,
        0.4059,
        0.6939,
        1.0,
        0.8394,
        0.8007,
        0.8677,
        0.7738,
        0.495,
        0.5255,
        0.6955,
        0.4053,
        0.2902,
        0.0869,
        0.0416,
        0.0424,
        0.0446,
        0.0431,
        0.0331,
        0.0273,
        0.0279,
        0.03,
        0.0321,
        0.026,
        0.0288,
        0.0283,
        0.0284,
        0.0314,
        0.0245,
        0.022,
        0.0371
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's eleven o'clock",
        "duration": 2.8028125,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.9511421918869019
          },
          {
            "label": "angry",
            "score": 0.8469578623771667
          }
        ],
        "styles": [
          {
            "label": "tired",
            "score": 0.9933071732521057
          }
        ]
      }
    },
    {
      "id": "1083_IOM_DIS_XX",
      "audioSrc": "/samples/emotional/1083_IOM_DIS_XX.wav",
      "audioSha256": "9b4ffda00dbb4915a0f90b49aa98443a1fc0aae9da9304d3f5e83ca71c6b3936",
      "trainingPcmSha256": "8a7ea9c8f6e1d18722403d4cb1e83211348e25dedcce449f3ae0ee02cb6eb5a6",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1083_IOM_DIS_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1083_IOM_DIS_XX.wav",
      "transcript": "I'm on my way to the meeting",
      "duration": 2.469125,
      "waveform": [
        0.1388,
        0.1751,
        0.1051,
        0.1353,
        0.1374,
        0.172,
        0.1245,
        0.0885,
        0.1158,
        0.1103,
        0.1397,
        0.1782,
        0.1582,
        0.092,
        0.2516,
        0.6042,
        0.8015,
        0.6775,
        0.5027,
        0.4444,
        0.5186,
        0.6272,
        0.7271,
        1.0,
        0.8885,
        0.7583,
        0.6762,
        0.576,
        0.8011,
        0.6337,
        0.3402,
        0.526,
        0.4817,
        0.4208,
        0.5699,
        0.3344,
        0.1845,
        0.2623,
        0.212,
        0.2243,
        0.2876,
        0.3585,
        0.4002,
        0.304,
        0.2758,
        0.3774,
        0.2624,
        0.3426,
        0.3084,
        0.4622,
        0.563,
        0.3066,
        0.4027,
        0.5655,
        0.3669,
        0.352,
        0.1462,
        0.1756,
        0.1438,
        0.197,
        0.1002,
        0.1004,
        0.0997,
        0.1537,
        0.1803,
        0.187,
        0.1086,
        0.1728,
        0.1318,
        0.1507,
        0.1394,
        0.1237,
        0.1879,
        0.1443,
        0.158,
        0.1391,
        0.1522,
        0.1163,
        0.1492,
        0.0968
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I'm on my way to the meeting.",
        "duration": 2.469125,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.8354835510253906
          },
          {
            "label": "scared",
            "score": 0.8068526387214661
          }
        ],
        "styles": [
          {
            "label": "deadpan",
            "score": 0.8856314420700073
          },
          {
            "label": "irritated",
            "score": 0.8749346137046814
          },
          {
            "label": "casual",
            "score": 0.8365545868873596
          }
        ]
      }
    },
    {
      "id": "1020_TAI_DIS_XX",
      "audioSrc": "/samples/emotional/1020_TAI_DIS_XX.wav",
      "audioSha256": "8932724c16d79b55f941269be56835cd894963f4c0a3ff9ea2367fd9a324f010",
      "trainingPcmSha256": "3afb554777bc3192d100fc161cd1936d445f920f007a360a2a27139e0781e769",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1020_TAI_DIS_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1020_TAI_DIS_XX.wav",
      "transcript": "The airplane is almost full",
      "duration": 3.2031875,
      "waveform": [
        0.0997,
        0.0914,
        0.1616,
        0.1197,
        0.164,
        0.2807,
        0.2635,
        0.2195,
        0.1297,
        0.4141,
        0.7334,
        0.9232,
        1.0,
        0.3486,
        0.1402,
        0.1208,
        0.1077,
        0.1238,
        0.2559,
        0.3459,
        0.4928,
        0.3864,
        0.2763,
        0.2499,
        0.3728,
        0.2855,
        0.2448,
        0.1739,
        0.1803,
        0.2297,
        0.1503,
        0.1125,
        0.1134,
        0.0949,
        0.2475,
        0.307,
        0.2207,
        0.2878,
        0.3404,
        0.2926,
        0.1888,
        0.2001,
        0.1689,
        0.1283,
        0.134,
        0.0936,
        0.1396,
        0.0972,
        0.1095,
        0.0861,
        0.0761,
        0.0952,
        0.0779,
        0.1001,
        0.132,
        0.3047,
        0.2374,
        0.3158,
        0.6506,
        0.5919,
        0.4145,
        0.225,
        0.2005,
        0.1582,
        0.1174,
        0.1179,
        0.1104,
        0.0883,
        0.1113,
        0.0815,
        0.0994,
        0.0945,
        0.0893,
        0.096,
        0.0733,
        0.0852,
        0.0687,
        0.0808,
        0.0985,
        0.0683
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The airplane is almost full.",
        "duration": 3.2031875,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.9669140577316284
          },
          {
            "label": "worried",
            "score": 0.9284088015556335
          }
        ],
        "styles": [
          {
            "label": "casual",
            "score": 0.730289876461029
          }
        ]
      }
    },
    {
      "id": "1029_IOM_DIS_XX",
      "audioSrc": "/samples/emotional/1029_IOM_DIS_XX.wav",
      "audioSha256": "9d4711226b5e24b6408878efd865338512e6a19d6162009b0d5bba8c66bc3224",
      "trainingPcmSha256": "6c8c5ca452239b43dc578329b139cf24518cfeef65a567bd640265c7a6f2a5ad",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1029_IOM_DIS_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1029_IOM_DIS_XX.wav",
      "transcript": "I'm on my way to the meeting",
      "duration": 2.2755625,
      "waveform": [
        0.0002,
        0.0774,
        0.0708,
        0.0726,
        0.0792,
        0.0946,
        0.0965,
        0.0812,
        0.1032,
        0.0888,
        0.0826,
        0.0841,
        0.0703,
        0.0834,
        0.0773,
        0.062,
        0.0924,
        0.1075,
        0.094,
        0.0845,
        0.0935,
        0.1023,
        0.0803,
        0.2062,
        0.3172,
        0.3416,
        0.2734,
        0.2541,
        0.3435,
        0.3249,
        0.4759,
        0.6657,
        0.4169,
        0.4969,
        0.8273,
        0.815,
        0.3779,
        0.4386,
        0.301,
        0.2351,
        0.3782,
        0.4211,
        0.6164,
        0.7761,
        0.7944,
        0.4974,
        0.5688,
        0.3361,
        0.1758,
        0.1901,
        0.1404,
        0.1346,
        0.1093,
        0.1606,
        0.1523,
        0.18,
        0.2226,
        0.2862,
        0.3508,
        0.3964,
        0.8189,
        1.0,
        0.7156,
        0.6151,
        0.5549,
        0.589,
        0.386,
        0.3761,
        0.2207,
        0.1434,
        0.1109,
        0.1197,
        0.0972,
        0.0812,
        0.071,
        0.0731,
        0.097,
        0.0982,
        0.0921,
        0.1032
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "I'm on my way to the meeting.",
        "duration": 2.2755625,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.9362850189208984
          },
          {
            "label": "frustrated",
            "score": 0.9314625263214111
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.9919379353523254
          },
          {
            "label": "impatient",
            "score": 0.9763104915618896
          },
          {
            "label": "distracted",
            "score": 0.8164063692092896
          }
        ]
      }
    },
    {
      "id": "1016_TSI_DIS_XX",
      "audioSrc": "/samples/emotional/1016_TSI_DIS_XX.wav",
      "audioSha256": "455a1d2127de402ec6ed78abcd603b9fed0e5448e9486ca8c556310275bcc90e",
      "trainingPcmSha256": "de437dfbaea3abf3fc66a5d747976940d15ceba09f60af252b791df557e0d98f",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1016_TSI_DIS_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1016_TSI_DIS_XX.wav",
      "transcript": "The surface is slick",
      "duration": 2.8028125,
      "waveform": [
        0.0137,
        0.0161,
        0.0157,
        0.0177,
        0.0177,
        0.0139,
        0.0232,
        0.0183,
        0.0172,
        0.0154,
        0.0142,
        0.0246,
        0.0199,
        0.05,
        0.1112,
        0.1123,
        0.0786,
        0.1038,
        0.1201,
        0.2491,
        0.5153,
        0.6853,
        1.0,
        0.6008,
        0.2493,
        0.077,
        0.057,
        0.0988,
        0.1435,
        0.095,
        0.1026,
        0.1306,
        0.1699,
        0.1053,
        0.048,
        0.0424,
        0.1122,
        0.1825,
        0.1831,
        0.2027,
        0.2375,
        0.2649,
        0.2323,
        0.2391,
        0.2511,
        0.2357,
        0.1081,
        0.0333,
        0.0225,
        0.0232,
        0.0228,
        0.0237,
        0.0241,
        0.0686,
        0.1361,
        0.1462,
        0.1387,
        0.0545,
        0.0227,
        0.0185,
        0.0669,
        0.0567,
        0.0309,
        0.0134,
        0.0132,
        0.0176,
        0.0185,
        0.0203,
        0.0145,
        0.0131,
        0.0196,
        0.0213,
        0.0216,
        0.0148,
        0.0182,
        0.0132,
        0.0146,
        0.016,
        0.017,
        0.013
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "The surface is slick.",
        "duration": 2.8028125,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.9149009585380554
          },
          {
            "label": "frustrated",
            "score": 0.8740772008895874
          }
        ],
        "styles": [
          {
            "label": "sarcastic",
            "score": 0.9273632764816284
          },
          {
            "label": "casual",
            "score": 0.8418256044387817
          },
          {
            "label": "deadpan",
            "score": 0.7759445905685425
          }
        ]
      }
    },
    {
      "id": "1074_WSI_DIS_XX",
      "audioSrc": "/samples/emotional/1074_WSI_DIS_XX.wav",
      "audioSha256": "1d3620d3e97c8af3fc94e6d076b1e68576816f3bbb76f37c1b2698ed2372101e",
      "trainingPcmSha256": "32cb69d3b620be203c6a72f7f8bcd14784dde3ce430d6e117a3620be35b0d8ef",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1074_WSI_DIS_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1074_WSI_DIS_XX.wav",
      "transcript": "We'll stop in a couple of minutes",
      "duration": 3.103125,
      "waveform": [
        0.0145,
        0.0135,
        0.0128,
        0.0149,
        0.0135,
        0.0119,
        0.0154,
        0.0129,
        0.0146,
        0.0131,
        0.0124,
        0.0145,
        0.0098,
        0.0137,
        0.0151,
        0.0161,
        0.0103,
        0.0118,
        0.0141,
        0.0125,
        0.0133,
        0.0105,
        0.0131,
        0.0137,
        0.0175,
        0.0765,
        0.1029,
        0.2197,
        0.4853,
        0.4128,
        0.1487,
        0.091,
        0.0454,
        0.0243,
        0.4894,
        1.0,
        0.9167,
        0.961,
        0.962,
        0.2812,
        0.0814,
        0.4128,
        0.3918,
        0.2663,
        0.3517,
        0.2495,
        0.1064,
        0.0674,
        0.0879,
        0.6309,
        0.2657,
        0.0929,
        0.1019,
        0.3861,
        0.177,
        0.1725,
        0.2224,
        0.1094,
        0.0722,
        0.0738,
        0.1072,
        0.223,
        0.2427,
        0.2992,
        0.1768,
        0.194,
        0.1735,
        0.0952,
        0.0447,
        0.0242,
        0.0246,
        0.0247,
        0.017,
        0.0146,
        0.0142,
        0.0128,
        0.0135,
        0.0133,
        0.0136,
        0.0101
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "We'll stop in a couple of minutes.",
        "duration": 3.103125,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.8791467547416687
          },
          {
            "label": "frustrated",
            "score": 0.8499711751937866
          }
        ],
        "styles": [
          {
            "label": "irritated",
            "score": 0.8233283758163452
          }
        ]
      }
    },
    {
      "id": "1072_DFA_DIS_XX",
      "audioSrc": "/samples/emotional/1072_DFA_DIS_XX.wav",
      "audioSha256": "ba1ebcd08ad4d50d33c8ef6d9008e793c968dc131369d84cfafdc67f20f572df",
      "trainingPcmSha256": "c579580fa36ec0f54d3267fd520d3901551269d9b069248aa37e54628490782e",
      "trainingSplit": "train",
      "sourceEmotion": "disgusted",
      "sourceFile": "1072_DFA_DIS_XX.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1072_DFA_DIS_XX.wav",
      "transcript": "Don't forget a jacket",
      "duration": 2.8361875,
      "waveform": [
        0.0696,
        0.0658,
        0.0797,
        0.0537,
        0.055,
        0.0765,
        0.0559,
        0.0638,
        0.0795,
        0.0649,
        0.0621,
        0.0777,
        0.0711,
        0.0888,
        0.078,
        0.0475,
        0.0662,
        0.0647,
        0.0531,
        0.0632,
        0.0683,
        0.0606,
        0.0518,
        0.0729,
        0.0563,
        0.239,
        0.5906,
        0.4833,
        0.4651,
        0.2415,
        0.283,
        0.755,
        0.4444,
        0.248,
        0.5677,
        1.0,
        0.817,
        0.4532,
        0.2631,
        0.1658,
        0.0946,
        0.0596,
        0.1522,
        0.2596,
        0.1513,
        0.0751,
        0.1122,
        0.1383,
        0.1375,
        0.4185,
        0.4338,
        0.2284,
        0.1881,
        0.172,
        0.0963,
        0.1092,
        0.1549,
        0.1583,
        0.1463,
        0.1253,
        0.0765,
        0.0684,
        0.0558,
        0.1033,
        0.081,
        0.0666,
        0.0679,
        0.0748,
        0.0632,
        0.0708,
        0.0664,
        0.0496,
        0.0553,
        0.0524,
        0.0718,
        0.0737,
        0.0715,
        0.0504,
        0.0712,
        0.059
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "Don't forget a jacket.",
        "duration": 2.8361875,
        "emotions": [
          {
            "label": "disgusted",
            "score": 0.9648551344871521
          }
        ],
        "styles": [
          {
            "label": "warm",
            "score": 0.9019206762313843
          },
          {
            "label": "sarcastic",
            "score": 0.8918110132217407
          },
          {
            "label": "confident",
            "score": 0.740174412727356
          }
        ]
      }
    },
    {
      "id": "1013_IEO_FEA_MD",
      "audioSrc": "/samples/emotional/1013_IEO_FEA_MD.wav",
      "audioSha256": "eb97a230f35889abc9af4af3f490156f4b42d7e084f12c04cf0f874b256fdef9",
      "trainingPcmSha256": "fa2623c663a2aa9dd85e8465531129af70d041226728c0ba8e5a63d4301051ab",
      "trainingSplit": "train",
      "sourceEmotion": "scared",
      "sourceFile": "1013_IEO_FEA_MD.wav",
      "sourceUrl": "https://github.com/CheyneyComputerScience/CREMA-D/blob/master/AudioWAV/1013_IEO_FEA_MD.wav",
      "transcript": "It's eleven o'clock",
      "duration": 2.1688125,
      "waveform": [
        0.2419,
        0.1953,
        0.2907,
        0.1996,
        0.2574,
        0.2133,
        0.1802,
        0.2223,
        0.2724,
        0.2113,
        0.2018,
        0.206,
        0.2222,
        0.2549,
        0.236,
        0.2568,
        0.255,
        0.2705,
        0.263,
        0.2221,
        0.2097,
        0.177,
        0.2593,
        0.2428,
        0.2356,
        0.4354,
        0.7106,
        1.0,
        0.7586,
        0.7231,
        0.6069,
        0.4843,
        0.7469,
        0.5181,
        0.2838,
        0.4648,
        0.4437,
        0.2649,
        0.2306,
        0.2754,
        0.2927,
        0.5247,
        0.4819,
        0.7076,
        0.5482,
        0.3781,
        0.2743,
        0.3048,
        0.2499,
        0.2501,
        0.3068,
        0.3265,
        0.262,
        0.2684,
        0.2478,
        0.217,
        0.2117,
        0.2396,
        0.2637,
        0.2206,
        0.291,
        0.2103,
        0.2146,
        0.3028,
        0.307,
        0.4232,
        0.3442,
        0.2875,
        0.2061,
        0.2044,
        0.243,
        0.226,
        0.1813,
        0.2147,
        0.2891,
        0.1776,
        0.2336,
        0.206,
        0.3164,
        0.2999
      ],
      "result": {
        "object": "speech.result",
        "task": "analysis",
        "model": "oruk-resonance",
        "text": "It's eleven o'clock.",
        "duration": 2.1688125,
        "emotions": [
          {
            "label": "scared",
            "score": 0.9465966820716858
          },
          {
            "label": "worried",
            "score": 0.8933094143867493
          },
          {
            "label": "frustrated",
            "score": 0.8386797308921814
          }
        ],
        "styles": [
          {
            "label": "casual",
            "score": 0.8902942538261414
          },
          {
            "label": "tired",
            "score": 0.873214840888977
          },
          {
            "label": "impatient",
            "score": 0.873214840888977
          }
        ]
      }
    }
  ]
}