OpenBMB / OpenBMB/MiniCPM-o-Demo

Full-duplex mode cannot be interrupted in the demo deployment

Open
#5 7 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
386
Forks
81
Avg merge
1h 59m
Merged PRs (30d)
3

Description

Hi! Thanks for the awesome project.

I deployed the author’s demo and noticed an issue with full-duplex mode: it cannot be interrupted once it starts (barge-in doesn’t work). In my tests, user speech during the assistant’s output is ignored, and the current response continues until completion.

One more detail: I’m using a microphone. The input level / waveform keeps moving, which indicates the app is continuously capturing audio, but the interruption still doesn’t happen.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the issue in the demo's full-duplex mode with a microphone while the assistant is speaking. Trace the microphone input, assistant output, and interruption behavior; it is done when speech reliably stops the current response and allows the user's turn to continue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
audio-video-rtc
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.