HHousen/speaker-change-detection

Speaker change detection using SincNet and an LSTM/Transformer

40
/ 100
Emerging

This tool helps analyze audio recordings of conversations, meetings, or interviews. You provide an audio file, and it tells you precisely when a new person starts speaking. This is ideal for researchers, analysts, or anyone who needs to identify speaker turns without knowing who the speakers are.

No commits in the last 6 months.

Use this if you need to quickly find all the points in an audio recording where one speaker stops and another begins, without caring about the identity of the speakers.

Not ideal if you need to know *who* is speaking at any given time, or if you need to track individual speakers throughout an entire conversation (speaker diarization).

audio-analysis meeting-transcription conversation-analysis interview-analysis speech-processing
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

57

Forks

8

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

May 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HHousen/speaker-change-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.