{
  "model": "tiny.en",
  "device": "cpu",
  "compute_type": "int8",
  "word_timestamps": true,
  "model_load_seconds": 19.622,
  "inference_seconds": 0.425,
  "duration": 9.472125,
  "language": "en",
  "segments": [
    {
      "id": 1,
      "seek": 0,
      "start": 0.0,
      "end": 1.98,
      "text": " This is a local tutorial test.",
      "tokens": [
        50363,
        770,
        318,
        257,
        1957,
        11808,
        1332,
        13,
        50473
      ],
      "avg_logprob": -0.22426387236306541,
      "compression_ratio": 1.236842105263158,
      "no_speech_prob": 0.04013679176568985,
      "words": [
        {
          "start": 0.0,
          "end": 0.24,
          "word": " This",
          "probability": 0.7451871633529663
        },
        {
          "start": 0.24,
          "end": 0.46,
          "word": " is",
          "probability": 0.9975110292434692
        },
        {
          "start": 0.46,
          "end": 0.64,
          "word": " a",
          "probability": 0.980759859085083
        },
        {
          "start": 0.64,
          "end": 0.86,
          "word": " local",
          "probability": 0.9516679048538208
        },
        {
          "start": 0.86,
          "end": 1.34,
          "word": " tutorial",
          "probability": 0.9405432343482971
        },
        {
          "start": 1.34,
          "end": 1.98,
          "word": " test.",
          "probability": 0.9905322790145874
        }
      ],
      "temperature": 0.0
    },
    {
      "id": 2,
      "seek": 0,
      "start": 2.3,
      "end": 6.78,
      "text": " We render a short video, check its frame rate, and export word timestamps.",
      "tokens": [
        50473,
        775,
        8543,
        257,
        1790,
        2008,
        11,
        2198,
        663,
        5739,
        2494,
        11,
        290,
        10784,
        1573,
        4628,
        395,
        9430,
        13,
        50721
      ],
      "avg_logprob": -0.22426387236306541,
      "compression_ratio": 1.236842105263158,
      "no_speech_prob": 0.04013679176568985,
      "words": [
        {
          "start": 2.3,
          "end": 2.38,
          "word": " We",
          "probability": 0.9768357276916504
        },
        {
          "start": 2.38,
          "end": 2.64,
          "word": " render",
          "probability": 0.9980752468109131
        },
        {
          "start": 2.64,
          "end": 2.9,
          "word": " a",
          "probability": 0.9984985589981079
        },
        {
          "start": 2.9,
          "end": 3.12,
          "word": " short",
          "probability": 0.993059515953064
        },
        {
          "start": 3.12,
          "end": 3.58,
          "word": " video,",
          "probability": 0.9993990659713745
        },
        {
          "start": 3.88,
          "end": 4.08,
          "word": " check",
          "probability": 0.8464763760566711
        },
        {
          "start": 4.08,
          "end": 4.3,
          "word": " its",
          "probability": 0.9343180060386658
        },
        {
          "start": 4.3,
          "end": 4.62,
          "word": " frame",
          "probability": 0.9297915101051331
        },
        {
          "start": 4.62,
          "end": 4.92,
          "word": " rate,",
          "probability": 0.990594744682312
        },
        {
          "start": 5.22,
          "end": 5.46,
          "word": " and",
          "probability": 0.997119665145874
        },
        {
          "start": 5.46,
          "end": 5.7,
          "word": " export",
          "probability": 0.9806035161018372
        },
        {
          "start": 5.7,
          "end": 6.1,
          "word": " word",
          "probability": 0.9348233342170715
        },
        {
          "start": 6.1,
          "end": 6.78,
          "word": " timestamps.",
          "probability": 0.9479482372601827
        }
      ],
      "temperature": 0.0
    },
    {
      "id": 3,
      "seek": 0,
      "start": 7.16,
      "end": 9.0,
      "text": " The original audio stays unchanged.",
      "tokens": [
        50721,
        383,
        2656,
        6597,
        14768,
        21588,
        13,
        50825
      ],
      "avg_logprob": -0.22426387236306541,
      "compression_ratio": 1.236842105263158,
      "no_speech_prob": 0.04013679176568985,
      "words": [
        {
          "start": 7.16,
          "end": 7.36,
          "word": " The",
          "probability": 0.9816280007362366
        },
        {
          "start": 7.36,
          "end": 7.82,
          "word": " original",
          "probability": 0.9764364957809448
        },
        {
          "start": 7.82,
          "end": 8.28,
          "word": " audio",
          "probability": 0.9681890606880188
        },
        {
          "start": 8.28,
          "end": 8.6,
          "word": " stays",
          "probability": 0.995949387550354
        },
        {
          "start": 8.6,
          "end": 9.0,
          "word": " unchanged.",
          "probability": 0.9974799752235413
        }
      ],
      "temperature": 0.0
    }
  ]
}