feat: extend OpenAI adapter for self-hosted Whisper endpoints#443
Open
abn wants to merge 1 commit intorishikanthc:mainfrom
Open
feat: extend OpenAI adapter for self-hosted Whisper endpoints#443abn wants to merge 1 commit intorishikanthc:mainfrom
abn wants to merge 1 commit intorishikanthc:mainfrom
Conversation
The OpenAI transcription profile now works with any OpenAI-compatible Whisper server (faster-whisper, whisper.cpp, etc.), not just api.openai.com. Users can set a custom base URL per job in the config dialog. When a custom URL is provided: - The model field becomes a free-text input so any server-specific model name can be used - API key validation is hidden (most self-hosted servers don't require auth) - A configurable timeout is exposed, defaulting to 30 minutes to accommodate slower hardware - Speaker diarization can be enabled, handled as a post-processing step the same way it works for local models The official OpenAI endpoint behaviour is unchanged, including the special response format handling for gpt-4o audio models.
Author
|
@rishikanthc would this be something of interest to the project? |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The OpenAI transcription profile now works with any OpenAI-compatible Whisper server (faster-whisper, whisper.cpp, etc.), not just api.openai.com.
Users can set a custom base URL per job in the config dialog. When a custom URL is provided:
The official OpenAI endpoint behaviour is unchanged, including the special response format handling for gpt-4o audio models.
Closes: #439