-
Notifications
You must be signed in to change notification settings - Fork 30
Create enhanced AudioToTextEnhancedProvider that also reformats text from transcription and ReformatParagraphs provider #363
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
Merged
Merged
Changes from all commits
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
15abc4b
Resolve feedback
lukasdotcom 7f4ab39
Create enhanced AudioToTextEnhancedProvider that also reformats text …
lukasdotcom 0cc77cb
Switch away from extend and to dependency injection
lukasdotcom 910c47b
Don't use AudioToTextProvider functions for output types
lukasdotcom 693e6e8
Disclaimer about runtime
lukasdotcom File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,109 @@ | ||
| <?php | ||
|
|
||
| declare(strict_types=1); | ||
|
|
||
| /** | ||
| * SPDX-FileCopyrightText: 2026 Nextcloud GmbH and Nextcloud contributors | ||
| * SPDX-License-Identifier: AGPL-3.0-or-later | ||
| */ | ||
|
|
||
| namespace OCA\OpenAi\TaskProcessing; | ||
|
|
||
| use OCA\OpenAi\AppInfo\Application; | ||
| use OCA\OpenAi\Service\OpenAiAPIService; | ||
| use OCP\TaskProcessing\IManager; | ||
| use OCP\TaskProcessing\ISynchronousProvider; | ||
| use OCP\TaskProcessing\Task; | ||
| use OCP\TaskProcessing\TaskTypes\AudioToText; | ||
| use Psr\Log\LoggerInterface; | ||
| use Throwable; | ||
|
|
||
| class AudioToTextEnhancedProvider implements ISynchronousProvider { | ||
|
|
||
| public function __construct( | ||
| private AudioToTextProvider $audioToTextProvider, | ||
| private OpenAiAPIService $openAiAPIService, | ||
| private IManager $taskProcessingManager, | ||
| private LoggerInterface $logger, | ||
| ) { | ||
| } | ||
|
|
||
| public function getId(): string { | ||
| return $this->audioToTextProvider->getId() . '-enhanced'; | ||
| } | ||
|
|
||
| public function getName(): string { | ||
| return $this->audioToTextProvider->getName() . ' (with paragraph reformatting)'; | ||
| } | ||
|
|
||
| public function getTaskTypeId(): string { | ||
| return AudioToText::ID; | ||
| } | ||
|
|
||
| public function getExpectedRuntime(): int { | ||
| // The audio to text provider may not be openai and this assumes it is | ||
| return $this->audioToTextProvider->getExpectedRuntime() + $this->openAiAPIService->getExpTextProcessingTime(); | ||
| } | ||
|
|
||
| public function getInputShapeEnumValues(): array { | ||
| return $this->audioToTextProvider->getInputShapeEnumValues(); | ||
| } | ||
|
|
||
| public function getInputShapeDefaults(): array { | ||
| return $this->audioToTextProvider->getInputShapeDefaults(); | ||
| } | ||
|
|
||
| public function getOptionalInputShape(): array { | ||
| return $this->audioToTextProvider->getOptionalInputShape(); | ||
| } | ||
|
|
||
| public function getOptionalInputShapeEnumValues(): array { | ||
| return $this->audioToTextProvider->getOptionalInputShapeEnumValues(); | ||
| } | ||
|
|
||
| public function getOptionalInputShapeDefaults(): array { | ||
| return $this->audioToTextProvider->getOptionalInputShapeDefaults(); | ||
| } | ||
|
|
||
| public function getOutputShapeEnumValues(): array { | ||
| return []; | ||
| } | ||
|
|
||
| public function getOptionalOutputShape(): array { | ||
| return []; | ||
| } | ||
|
|
||
| public function getOptionalOutputShapeEnumValues(): array { | ||
| return []; | ||
| } | ||
|
|
||
| public function process(?string $userId, array $input, callable $reportProgress): array { | ||
| $transcription = $this->audioToTextProvider->process($userId, $input, $reportProgress)['output']; | ||
|
|
||
| // Skip reformatting if the transcription is empty | ||
| if (trim($transcription) === '') { | ||
| return ['output' => $transcription]; | ||
| } | ||
|
|
||
| $reformatTask = new Task( | ||
| \OCP\TaskProcessing\TaskTypes\TextToTextReformatParagraphs::ID, | ||
| ['input' => $transcription], | ||
| Application::APP_ID, | ||
| $userId, | ||
| 'audio2text_enhanced', | ||
| ); | ||
|
lukasdotcom marked this conversation as resolved.
|
||
|
|
||
| try { | ||
| $finished = $this->taskProcessingManager->runTask($reformatTask); | ||
| $output = $finished->getOutput(); | ||
| if (is_array($output) && isset($output['output']) && is_string($output['output']) && $output['output'] !== '') { | ||
| return ['output' => $output['output']]; | ||
| } | ||
| $this->logger->warning('ReformatParagraphs follow-up task returned no usable output, falling back to raw transcription'); | ||
|
lukasdotcom marked this conversation as resolved.
|
||
| } catch (Throwable $e) { | ||
| $this->logger->warning('ReformatParagraphs follow-up task failed, falling back to raw transcription: ' . $e->getMessage(), ['exception' => $e]); | ||
| } | ||
|
|
||
| return ['output' => $transcription]; | ||
| } | ||
| } | ||
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.