Add Support for OpenAI Whisper API as Additional Transcription Backend #153
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 flexible transcription service system that allows users to choose between AWS Transcribe and OpenAI Whisper API. Changes include: - Add BaseTranscriber abstract class for transcription service interface - Implement OpenAITranscriber class for Whisper API integration - Update configuration to support service selection via TRANSCRIPTION_SERVICE - Add new environment variables for OpenAI API key - Update README with new configuration options and documentation links - Add openai package dependency to pyproject.toml This change allows users to select their preferred transcription service while maintaining the existing AWS Transcribe functionality as default.
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Outdated suggestions cannot be applied.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: Support for OpenAI Whisper API Integration
Summary
This pull request addresses Issue #137 by integrating the OpenAI Whisper API into our Telegram bot for audio transcription. This enhancement aims to provide users with more flexibility in choosing their transcription services based on performance, cost, and individual needs.
Key Changes
The following modifications have been made to incorporate the OpenAI Whisper API:
New Transcription Service:
OpenAITranscriberclass has been implemented. This class works in conjunction with the existingAWSTranscriberclass, enabling the bot to support transcriptions through OpenAI's Whisper API.Configuration Updates:
config.py) has been updated to include:OPENAI_API_KEY: Required for accessing the OpenAI Whisper API.TRANSCRIPTION_SERVICE: A new setting that allows users to switch between AWS and OpenAI transcription services.Bot Handlers Update:
bot_handlers.pyfile to support the selection of the transcription service specified in the configuration, ensuring that the appropriate transcriber is utilized based on user settings.Dependency Management:
pyproject.tomlfile, ensuring that users can install the necessary libraries for the OpenAI API integration.Documentation:
READMEfile has been updated to include details on configuring the bot for either AWS or OpenAI transcription services. This includes a detailed guide on setting up API keys and the prerequisites for both services.Usage
Users can now easily switch between the AWS Transcribe and OpenAI Whisper API services by:
TRANSCRIPTION_SERVICEenvironment variable to either "aws" or "openai".Conclusion
This integration enhances the bot's transcription capabilities, offering users a choice that can better adapt to their specific needs. Please review the changes and let me know if you have any questions or require further modifications.
Thank you for your consideration!