FunASR: FunASR is a fundamental end-to-end speech recognition toolkit. It offers industrial-grade speech recognition, being 170x faster than Whisper, supporting over 50 languages, and integrating features like speaker diarization, emotion detection, and streaming.; optuna-mcp: Optuna MCP Server exposes the Optuna hyperparameter optimization framework as a Model Context Protocol server. It lets LLMs and AI assistants run and manage optimization studies directly through a chat interface, create and analyze Optuna trials, and optimize parameters for any workflow. Compatible with Claude Desktop, Cursor, and other MCP clients via uv or Docker.
Meeting transcription with speaker labels, timestamps, and punctuation
Automated hyperparameter tuning for ML models driven by an LLM