-
Notifications
You must be signed in to change notification settings - Fork 18
feat: specify language for AudioToText #266
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
Conversation
5e025d7 to
f43c9c3
Compare
f43c9c3 to
e8fc6a2
Compare
Signed-off-by: Lukas Schaefer <[email protected]>
e8fc6a2 to
e5fb43c
Compare
kyteinsky
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🚀
julien-nc
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sorry I'm a bit late to the party.
There's something missing. I should have been more explicit in the issue.
It would be nice to let the user choose a language in which they will talk in the audio chat feature. I think another (yeah one more) field in the user settings would be good.
Something like "Audio chat language" with a hint like "If you set this, it can improve the transcription of what you say when using the audio chat".
This field value would be stored as a user config value (in oc_preferences with IConfig) and used by the AudioToAudioChatProvider when calling openAiAPIService->transcribeFile.
Signed-off-by: Lukas Schaefer <[email protected]>
df7593e to
374344a
Compare
|
Updated the pr to now be able to set a default in the user settings for the language that is used. Still supports the other way of selecting the language for a specific transcribe audio task. |
julien-nc
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Work perfectly.
Optional tit picking (for later maybe): The default input value for language in AudioToTextProvider could be set to the one chosen in the personal settings of the user. In the end it does not matter so much because default is the selected value and it will result in selecting the correct value when processing the task.
|
ah, noticed after merging there was a comment. Maybe the adjustment can be included in a new PR if required @lukasdotcom ? |
Resolves: #264

I tested it with french on english audio and it did use french quotation marks
<<instead of the english ones".