Refactor speech_to_text.py to implement a singleton ASR pipeline, enhance error handling, and introduce SpeechToTextTool for better integration. Update spreadsheet_tool.py to support querying and improve parsing functionality, including CSV support. Enhance video_processing_tool.py with new tasks for metadata extraction and frame extraction, while improving object detection capabilities and initialization checks.

refactor: update tool classes to inherit from Tool base class for consistency and improved structure

add smolagents docstrings

feat: implement SpreadsheetTool for parsing and querying Excel files with detailed summaries