speech to text support

[pelikhan]

Transcribe/translate audio with timestamps.

• openai whisper
• HF transformers

[github-actions]

The request seems clear, but there are a few details that could be useful for more accurate feedback:

1. Use Case: Are you looking for speech-to-text functionality only, translation functionality only, or both?
2. Output Requirements: What format do you require the output to be in? For example, should the timestamps include milliseconds, and should they be represented as JSON arrays?
3. Error Handling: How would you like to handle errors, such as network issues or audio quality problems?
4. Integration: Do you need this functionality integrated into an existing project, or is it a standalone tool you're envisioning?

Additional information will help in providing more tailored feedback.

AI-generated content by issue-reviewer may be incorrect

[pelikhan]

#995