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.; mcp-raganything: A multi-modal RAG service that exposes a REST API and MCP server for document indexing and knowledge-base querying. It uses RAGAnything/LightRAG for indexing and retrieval, MinIO for object storage, and PostgreSQL for the knowledge graph. Each project is isolated by its own working directory.
Meeting transcription with speaker labels, timestamps, and punctuation
Index and query documents for knowledge base Q&A