Fast multilingual Whisper built from pruned large-v3
Whisper Large v3 Turbo is OpenAI's faster variant of Whisper large-v3: it keeps the same
Whisper architecture and multilingual speech-recognition/translation interface, but reduces
the decoder depth from 32 layers to 4. The upstream card describes the result as much faster
with only a minor quality trade-off, while retaining Whisper's broad zero-shot behavior from
training on more than five million hours of labeled audio. This OpenASR repo repackages the
original openai/whisper-large-v3-turbo weights as .oasr packs that run natively in the
OpenASR runtime with no Python at inference time. For most users the q8_0 build is the
recommended default; q4_k is for tighter memory budgets and fp16 is for verification or
maximum fidelity.
.oasr packs run with no Python at inference, engineered for peak performance on CPU & GPUThese are CLI / local-server examples. The desktop app runs this model without typing a command — see the desktop install path above.
$ openasr pull whisper-large-v3-turbo:q8 ↓ whisper-large-v3-turbo.oasr 888.2 MB ✓ verified sha256 $ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/whisper-large-v3-turbo/q8_0/whisper-large-v3-turbo-q8_0.oasr ✓ local transcript · 0 bytes sent
$ openasr serve --backend native --model-pack ~/.openasr/models/whisper-large-v3-turbo/q8_0/whisper-large-v3-turbo-q8_0.oasr --addr 127.0.0.1:8080 ▶ http://127.0.0.1:8080 · model=whisper-large-v3-turbo · 0 bytes will leave this host
from openai import OpenAI client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local") audio = open("meeting.wav", "rb") text = client.audio.transcriptions.create(model="whisper-large-v3-turbo", file=audio)