Share
Explore

icon picker
Speaker Diarization

Implement and Benchmark technologies to Identify different Speakers in a audio recording.

Research on what is the state of the art and compare results of top 5 libraries or open source projects.
Some libs improve results significantly if they are provided with speaker count.
Create an API interface on lambda

/speakersaudio url - speaker_count (optional ) callback -

Result Interface

result : { speaker_ids : [id1, id2, .. ], timestamps : [ { start: <>, end: <>, speaker_id: <>} .... ] }

Reading Sources:
⁠
https://huggingface.co/spaces/vumichien/whisper-speaker-diarization
⁠
⁠

Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.