Integrate OpenAI Whisper API Support for Enhanced Transcription Options #137 #142
Conversation
This file contains 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
Implement a new audio transcription option using OpenAI's Whisper API alongside the existing AWS transcription service. This change: - Add BaseTranscriber class to share common functionality - Create OpenAITranscriber class for Whisper API integration - Refactor AudioTranscriber to support multiple transcription services - Add configuration options to switch between AWS and OpenAI services - Move AWS service initialization to transcriber class - Add OPENAI_API_KEY and TRANSCRIPTION_SERVICE config variables The service can now be configured via environment variables to use either AWS Transcribe or OpenAI Whisper for audio transcription.
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Outdated suggestions cannot be applied.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.
Pull Request Description
Title: Support for Additional Whisper Services with OpenAI Whisper API Integration
Overview:
This pull request addresses issue #137, which requests the integration of additional transcription services into the Telegram bot currently utilizing AWS Whisper. Specifically, this update includes support for the OpenAI Whisper API, enhancing versatility and providing users with flexible transcription options.
Key Changes:
Integration of OpenAI Whisper API:
OpenAITranscriberto handle interactions with the OpenAI API for voice message transcription.BaseTranscriberthat encapsulates shared functionality for different transcription services.AWSTranscriber, promoting cleaner and modular code.Configuration Adjustments:
config.pyfile to allow for seamless configuration of the chosen transcription service:OPENAI_API_KEY: Added for authenticating requests to the OpenAI API.TRANSCRIPTION_SERVICE: Introduced a new setting, allowing the user to specify their preferred transcription service (default set to 'aws').Updates to Bot Handlers:
bot_handlers.pyto facilitate a dynamic initialization of theAudioTranscriberclass based on the specified configuration, enabling clear separation of concern and functionality.New Features:
TRANSCRIPTION_SERVICEenvironment variable. When selecting OpenAI, users must ensure to provide theirOPENAI_API_KEYfor successful integration.Testing:
All new features have been rigorously tested, ensuring compatibility and performance expectations meet the needs outlined in the original issue description.
Conclusion:
This implementation provides a step forward in supporting diverse transcription services, ultimately leading to improved user experiences and operational efficiency. We welcome any feedback or questions regarding this enhancement.
Related Links:
Thank you for considering this pull request!