- Introduce `AudioTranscriptionsFile` method in the OpenAI package to transcribe audio directly from a file path, improving memory efficiency.
- Implement new test cases for `AudioTranscriptionsFile`, including scenarios for language options and error handling for non-existent files.
- Update the process package to support the new transcription method, ensuring compatibility with existing functionality.
- Enhance test coverage for audio transcription processes, validating expected outputs and error conditions.
- Replace deprecated model "text-davinci-003" with "gpt-3_5-turbo-instruct"
- Comment out deprecated Edits method in tests and implementation
- Enhance HTTP request headers with explicit Content-Type
- Add fallback for model configuration when not explicitly set
- Improve header handling for Azure and standard OpenAI authentication
