feature: Add common TranscriptionModel interface for audio transcription #1484
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Created TranscriptionModel interface that extends Model<AudioTranscriptionPrompt, AudioTranscriptionResponse> - Implemented `call(AudioTranscriptionPrompt)` method for better compatibility between OpenAI and Azure OpenAI transcription models - Added default convenience methods for handling Resource and AudioTranscriptionOptions to return transcription as a String
habuma
reviewed
Oct 7, 2024
|
Meanwhile, as an enrichment to transcription take a look at #1278 |
| @@ -0,0 +1,22 @@ | |||
| package org.springframework.ai.model; | |||
There was a problem hiding this comment.
Should this interface be in the package org.springframework.ai.model.audio.transcription?
There was a problem hiding this comment.
yes, it should.
Model interfaces should be placed in packages that reflect their functional domain:
-
For single-level domains:
org.springframework.ai.<domain> -
For hierarchical domains:
org.springframework.ai.<category>.<subdomain>
| Model Interface | Package Location |
|---|---|
EmbeddingModel |
org.springframework.ai.embedding |
ModerationModel |
org.springframework.ai.moderation |
TextToSpeechModel |
org.springframework.ai.audio.tts |
|
Tests should be added too. |
|
Is there another transcription model we can use to verify the abstraction? |
|
I've added the additional tests to check the default methods etc. Merged in 4cf2377 Thanks @mudabirhussain and others. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
call(AudioTranscriptionPrompt)method for better compatibility between OpenAI and Azure OpenAI transcription modelsResolution of this opened issue: #1478