BaseRT .base build of openai/whisper-large-v3-turbo, OpenAI's 809M-parameter Whisper speech-recognition model (turbo: 4-layer decoder distillation of large-v3, 128 mel bins), for fast local transcription on Apple Silicon.

F16 and Q8 are transcription-quality equivalent (Q8 passes the same word-error parity gates against reference openai-whisper). Q4 is the smallest and remains accurate; on some smaller variants it can occasionally repeat a word in timestamped beam decoding.

POST /v1/audio/transcriptions (multipart or JSON) returns json, text, srt, vtt, or verbose_json (with per-segment avg_logprob / no_speech_prob / compression_ratio / temperature and the detected language), with optional SSE streaming and POST /v1/audio/translations. Supported request fields: language (or "auto" to detect), prompt (initial prompt / vocabulary bias), task (transcribe/translate). Or transcribe directly from the CLI:

Multilingual: pass language (e.g. --lang de), or auto to detect, across the 100 supported languages. Note: turbo was distilled without translation training, so task=translate is rejected.

Released under the apache-2.0 license, inherited from the base model.