-
Notifications
You must be signed in to change notification settings - Fork 475
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug]: Poor audio quality when using Google Synthesizer #628
Comments
Pull Request provided to address found issue: #629 |
Hii @jstahlbaum-fibernetics ! Are the changes which you made running on your local? Also please do run the tests using |
* [Bug-628] correct coding errors in the google synthesiser * create_speech --> create_speech_uncached --------- Co-authored-by: Ajay Raj <[email protected]>
* [Bug #628] correct coding errors in the google synthesiser (#629) * [Bug-628] correct coding errors in the google synthesiser * create_speech --> create_speech_uncached --------- Co-authored-by: Ajay Raj <[email protected]> * [DOW-119] creates AudioPipeline abstraction (#625) * make terminate async * creates audio pipeline abstraction * fix streaming conversation api * make terminate() invocations in tests async * removes the vector_db.tear_down() call in streaming conversation --------- Co-authored-by: jstahlbaum-fibernetics <[email protected]>
* [Bug-628] correct coding errors in the google synthesiser * create_speech --> create_speech_uncached --------- Co-authored-by: Ajay Raj <[email protected]>
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. |
This issue has been automatically closed due to inactivity. Thank you for your contributions. |
Brief Description
I noticed some issues with the GoogleSynthesizer class during development. It seams to importing the old version of the library causing a compile error. The sample rate seems fixed when it could use the config. There is garbage data because the class is not stripping the wav header off the response from google. Not sure if it was intentional but that synthesizer was also removed from the default factor during the transition between version 111 and 113
LLM
None
Transcription Services
None
Synthesis Services
Google Cloud
Telephony Services
None
Conversation Type and Platform
No response
Steps to Reproduce
-Create a custom Synthiziser and override the create_synthesizer
Expected Behavior
Since this class was previously included, i think it should continue to be functional
Screenshots
No response
The text was updated successfully, but these errors were encountered: