Long Chen

What's the different to the "segment anything + inpainting" pipeline?

3

Thanks for sharing this cool demo. It looks similar to the pipeline of masking out the foreground and then inpainting the background, optionally with some IP adaptor-like background control. Since...

1. add support for python3 2. add requirements.txt, install motmetrics from pip

fix: fix speech_buffer missing data in VADStream

5

Originally `speech_buffer` got only a subset of the audio data for each audio frame from mic bc of ```python to_copy_buffer = min(self._model.window_size_samples, available_space) ``` This makes the subsequent non-stream STT...

fix: fallback when cpu.max not found

1

Fix https://github.com/livekit/agents/issues/1000

feat: expose user_speech_committed and agent_speech_committed for multimodal agents

5

- Expose the `user_speech_committed`, `agent_speech_committed`, and `agent_speech_interrupted` for multimodal agents - Emit `user_started_speaking` and `user_stopped_speaking` for multimodal agents - Fixed a bug that `handle._tr_fwd` of multimodal agents cannot be closed...

"/sys/fs/cgroup/cpu.max" not found

2

For some reason there is no "/sys/fs/cgroup/cpu.max" on my linux system. ``` $ ls /sys/fs/cgroup/cpu* /sys/fs/cgroup/cpu.pressure /sys/fs/cgroup/cpuset.mems.effective /sys/fs/cgroup/cpu.stat.local /sys/fs/cgroup/cpuset.cpus.effective /sys/fs/cgroup/cpu.stat ``` Should we add a fallback when this file is...

[draft] feat: sync chat_ctx for multimodal agents from and to the realtime session

2

- write transcripts to chat context - update realtime session based on input chat_ctx - add `sync_chat_ctx` to sync the local chat context to OAI realtime session