wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update CHANGELOG

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-11-06 13:16:58 -08:00
parent a9e565f355
commit 5353d13151
1 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
CHANGELOG.md
View File

@@ -9,15 +9,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Added ### Added
- There's now an input queue for each frame processor. When you call - There's now an input queue in each frame processor. When you call
`FrameProcessor.push_frame()` this will internally call `FrameProcessor.push_frame()` this will internally call
`FrameProcessor.queue_frame()` on the next processor (upstream or `FrameProcessor.queue_frame()` on the next processor (upstream or downstream)
downstream). Then, the queue frames will get processed. With this input queue and the frame will be internally queued (except system frames). Then, the
it is now possible for FrameProcessors to block processing more frames via a queued frames will get processed. With this input queue it is also possible
list of blocking frames. For example, some TTS services now block processing for FrameProcessors to block processing more frames via a list of blocking
more frames if they see a `TTSSpeakFrame` or a `LLMFullResponseEndFrame` until frames. For example, some TTS services now block processing more frames if
the bot has stopped speaking. This makes sure we don't mix audio from they see a `TTSSpeakFrame` or a `LLMFullResponseEndFrame` until the bot has
different sentences. The way to resume processing frames is by calling stopped speaking. This makes sure we don't mix audio from different
sentences. The way to resume processing frames is by calling
`FrameProcessor.resume_processing_frames()`. `FrameProcessor.resume_processing_frames()`.
- Added audio filter `NoisereduceFilter`. - Added audio filter `NoisereduceFilter`.