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.; codeindex: codeindex is a dependency analyzer that builds a blast-radius impact score for every file in your repo — showing which files will break if a given file changes. It also generates a symbol index mapping every function and class to its exact file and line number, so AI tools can locate any symbol in one lookup without scanning the whole codebase. Supports 12+ languages, zero required dependencies (pure Python stdlib), and five consumption modes including CLI, MCP server, and CLAUDE.md injection.
Meeting transcription with speaker labels, timestamps, and punctuation
Assessing refactoring risk before touching a high-impact file