Skip to content

Adding support for transcriptions ( and OpenAI Whisper model) #300

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.

Sign up for GitHub

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

Jump to bottom
Closed
wants to merge 1 commit into from
Closed

Adding support for transcriptions ( and OpenAI Whisper model) #300

wants to merge 1 commit into from

Conversation

michaellavelle
Copy link
Contributor

No description provided.

michaellavelle
michaellavelle commented Feb 6, 2024
View reviewed changes
.../spring-ai-openai/src/main/java/org/springframework/ai/openai/OpenAiTranscriptionClient.java Outdated

Transcript transcript = new Transcript(transcription.text());

RateLimit rateLimits = OpenAiResponseHeaderExtractor.extractAiResponseHeaders(transcriptionEntity);
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm re-using these RateLimit and Usage classes from the chat packages here, but given that these are now used outside of chat, should they be moved into a more generic package ?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am not yet sure, we need to review this in the 0.9.0 timeline. I suspect there are cross cutting concerns. Now we are wrapping up the other direction, input options, to support a tiered structure of portable and model specific options. The same analysis and likely same approach needs to apply for the metadata info coming out of the response.

@michaellavelle michaellavelle mentioned this pull request Feb 6, 2024
Closed
@michaellavelle
Copy link
Contributor Author

Please see #149

@markpollack
Copy link
Member

Thanks for the contribution, this looks like a very strong PR on first glance!

@hemeda3
Copy link
Contributor

hemeda3 commented Feb 12, 2024

Thank you.
Your PR inspired me to do the Text To Audio (Speech API).

Added support for OpenAI Text to Audio (Speech API )
#317

@markpollack markpollack added this to the 0.9.0 milestone Feb 12, 2024
@markpollack markpollack modified the milestones: 0.9.0, 0.8.1 Feb 29, 2024
@markpollack markpollack requested a review from tzolov February 29, 2024 15:54
@tzolov tzolov added enhancement New feature or request model client labels Mar 1, 2024
@tzolov tzolov self-assigned this Mar 1, 2024
@tzolov
Copy link
Contributor

tzolov commented Mar 5, 2024

Thank you @michaellavelle
I've replaced the lower-level client and removed the code from the spring-ai-core. We will need at least few audio and transcription client implementations before we can generalise.
Reworked, rebased, squashed and merged at 7d04167

@tzolov tzolov closed this Mar 5, 2024
@tzolov tzolov mentioned this pull request Mar 6, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@markpollack markpollack markpollack left review comments

@tzolov tzolov Awaiting requested review from tzolov

Assignees

@tzolov tzolov

Labels
enhancement New feature or request model client
Projects
None yet
Milestone
0.8.1
Development

Successfully merging this pull request may close these issues.
4 participants
@michaellavelle @markpollack @hemeda3 @tzolov