adding metric generation without deepgram VAD

This commit is contained in:
Vaibhav159
2025-01-16 21:23:56 +05:30
parent b8ffd7b16b
commit 7ee6e7193d
2 changed files with 13 additions and 4 deletions

View File

@@ -74,6 +74,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
`UserStoppedSpeakingFrame`. This helps in faster transcriptions and clearing
the `Deepgram` audio buffer.
- Changed `DeepgramSTTService` to generate metrics using pipeline VAD.
### Fixed
- Fixed an issue where websocket based TTS services could incorrectly terminate