Is there a way to return the word timestamp of a sentence?

[CuiRobert]

Is there a way to return the word timestamp of a sentence?

example: input sentence: "Hello readers,welcome!" output: [{ "word": "Hello", "start_time": 0.02, "end_time": 0.36, }, { "word": "readers", "start_time": 0.36, "end_time": 0.855, }, { "word": "，", "start_time": 0.855, "end_time": 1.155, "type": "mark" }, { "word": "welcome", "start_time": 1.155, "end_time": 1.665, }, { "word": "!", "start_time": 1.665, "end_time": 1.955, } ]

[2721031254a]

raise the same question

[ruifengma]

Same question, the speaker diarization relies on timestamps, so it could not be used in speaker recognition case

[pengzhendong]

One could obtain the timestamps, however, it is not entirely accurate.