# How to get ASR timestamps of expert commentary text tokens?

**URL:** <https://discuss.ego4d-data.org/t/how-to-get-asr-timestamps-of-expert-commentary-text-tokens/568>\
**Category:** Uncategorized\
**Created:** [April 3, 2024, 4:35pm UTC](https://discuss.ego4d-data.org/t/how-to-get-asr-timestamps-of-expert-commentary-text-tokens/568 "2024-04-03T16:35:28Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![joyachen](https://avatars.discourse-cdn.com/v4/letter/j/8c91f0/32.png) [@joyachen](https://discuss.ego4d-data.org/u/joyachen)\
**Post date:** [April 3, 2024, 4:35pm UTC](https://discuss.ego4d-data.org/t/how-to-get-asr-timestamps-of-expert-commentary-text-tokens/568/1 "2024-04-03T16:35:28Z")

</div>

Thank you for the amazing data! If I want to know the specific time of each ASR recognized text tokens in expert commentary, e.g. 0.webm → whisper → text tokens → the timestamp of each text token, what should I do?

---

<div class="post-metadata">

**Author:** ![miguelmartin](https://avatars.discourse-cdn.com/v4/letter/m/f19dbf/32.png) [@miguelmartin](https://discuss.ego4d-data.org/u/miguelmartin)\
**Post date:** [April 6, 2024, 10:33pm UTC](https://discuss.ego4d-data.org/t/how-to-get-asr-timestamps-of-expert-commentary-text-tokens/568/2 "2024-04-06T22:33:48Z")

</div>

You can see how I transcribed the expert commentary audio files here: [Ego4d/ego4d/internal/expert\_commentary/transcribe.py at main · facebookresearch/Ego4d · GitHub](https://github.com/facebookresearch/Ego4d/blob/main/ego4d/internal/expert_commentary/transcribe.py#L22-L40)

You can re-process the audio files with whisper, as it does support word-level timestamps (refer to [Ego4d/ego4d/egoexo/scripts/extract\_audio\_transcribe.py at main · facebookresearch/Ego4d · GitHub](https://github.com/facebookresearch/Ego4d/blob/main/ego4d/egoexo/scripts/extract_audio_transcribe.py#L46) for details)

I can do this on my end, but this wont be available for awhile.