Timestamp output for Words

[dazzafact]

How its possible to get the Timestamp of each spoken Word, like Google Speech-to-Text do, what i have to change in my Code?
I only get Sentences like:

[04:19.000 --> 04:20.000]  What's the most memorable thing that you've ever worn?
[04:20.000 --> 04:22.000]  Met Gala Award, Taxitio from Gucci with a diamond and
[04:22.000 --> 04:24.000]  crossed it's sort of a cobra on the back.

But need

[04:19.000 --> 04:19.200] What's
[04:19.250 --> 04:19.300] the
[04:19.320 --> 04:19.400] most
[04:19.550 --> 04:19.660] memorable
[04:19.700 --> 04:19.800] thing

import whisper

model = whisper.load_model("medium")
result = whisper.transcribe(model,"audio.mp3", language="wn", verbose=True)
print(result)

[dazzafact]

Ok, found something

https://github.com/jianfch/stable-ts

[KrahmalK]

And whisper-timestamped