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.; Kompl: Kompl is a knowledge compiler that ingests scattered sources like links, files, and bookmarks, and automatically compiles them into an interlinked wiki. It uses Gemini LLM and NLP to generate entity pages, concept pages, and cross-references. It runs locally via Docker, ensuring privacy and control over data.
Meeting transcription with speaker labels, timestamps, and punctuation
Personal knowledge management from bookmarks, PDFs, and links