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

Merge pull request #1263 from Vaibhav159/vl_fix_deepgram_sample_rate_mismatch

Browse Source 
fixing deepgram mismatch
This commit is contained in:
Aleix Conchillo Flaqué
2025-02-20 22:39:06 -08:00
committed by GitHub
parent 7e5e167a4b 9c5fe5c85e
commit 91fcaebe25
2 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.md
View File

@@ -50,6 +50,10 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
- Fixed a `STTMuteFilter` issue that would not mute user audio frames causing - Fixed a `STTMuteFilter` issue that would not mute user audio frames causing
transcriptions to be generated by the STT service. transcriptions to be generated by the STT service.
- Fixes an issue in `DeepgramSTTService` where `sample_rate` passed to the
`LiveOptions` was not being used, causing the service to use the default
sample rate of pipeline.
### Other ### Other
- Added Gemini support to `examples/phone-chatbot`. - Added Gemini support to `examples/phone-chatbot`.

1
src/pipecat/services/deepgram.py
View File

@@ -124,6 +124,7 @@ class DeepgramSTTService(STTService):
addons: Optional[Dict] = None, addons: Optional[Dict] = None,
**kwargs, **kwargs,
): ):
sample_rate = sample_rate or (live_options.sample_rate if live_options else None)
super().__init__(sample_rate=sample_rate, **kwargs) super().__init__(sample_rate=sample_rate, **kwargs)
default_options = LiveOptions( default_options = LiveOptions(