Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Enables phrase-aware wrapping of Korean headlines into up to three lines at a specified approximate display width, using punctuation and Korean connective endings to avoid awkward word splits. Runs locally as a deterministic, read-only tool that preserves the original wording and returns both line arrays and text.