比如 [ {"start":0.0,"end":3.1,"caption":"dog barking"}, {"start":2.8,"end":7.0,"caption":"woman speaking"}, {"start":6.9,"end":12.0,"caption":"car engine starts"} ] 这样的，自动切割音频并分段caption
比如
[
{"start":0.0,"end":3.1,"caption":"dog barking"},
{"start":2.8,"end":7.0,"caption":"woman speaking"},
{"start":6.9,"end":12.0,"caption":"car engine starts"}
]
这样的，自动切割音频并分段caption