Views
No views yet
.base build of
openai/whisper-large,
OpenAI's 1.55B-parameter Whisper speech-recognition model,
for fast local transcription on Apple Silicon.| File | Precision | Size |
|---|---|---|
whisper-large-F16.base | float16 | 3.10 GB |
whisper-large-Q8.base | 8-bit linears, f16 embeddings/conv/norms | 1.68 GB |
whisper-large-Q4.base | 4-bit linears, f16 embeddings/conv/norms | 987 MB |
1curl -LsSf https://basecompute.co/install.sh | sh
2basert serve --model whisper-large-F16.basePOST /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-F16.base audio.wav --lang autolanguage (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).