verbose_json 输出。{
"text": "string",
"duration": 0,
"language": "string",
"segments": [
{
"id": 0,
"start": 0,
"end": 0,
"text": "string",
"tokens": [
0
],
"avg_logprob": 0,
"no_speech_prob": 0
}
],
"timestamp_granularities": [
"segment"
]
}