whisper-large-v2

BaseRT .base build of openai/whisper-large-v2, OpenAI's 1.55B-parameter Whisper speech-recognition model, for fast local transcription on Apple Silicon.

Files

File	Precision	Size
whisper-large-v2-F16.base	float16	3.10 GB
whisper-large-v2-Q8.base	8-bit linears, f16 embeddings/conv/norms	1.68 GB
whisper-large-v2-Q4.base	4-bit linears, f16 embeddings/conv/norms	987 MB

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.

Usage

curl -LsSf https://basecompute.co/install.sh | sh
basert serve --model whisper-large-v2-F16.base

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:

basert-transcribe whisper-large-v2-F16.base audio.wav --lang auto

Multilingual: pass language (e.g. --lang de), or auto to detect, across the 99 supported languages. task=translate produces English from any source language (also via POST /v1/audio/translations).

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