The smallest English-only Whisper, fastest for English speech
Whisper Tiny.en is OpenAI's 39M-parameter English-only Whisper checkpoint. It uses the standard
Whisper encoder-decoder architecture for automatic speech recognition, trained with large-scale
weak supervision on 680k hours of labelled speech. As an English-specialized model it tends to
outperform the same-size multilingual Whisper on English audio, at the lowest footprint and
fastest inference in the family. This OpenASR repo repackages the original openai/whisper-tiny.en
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 the tightest memory
budgets and fp16 is for verification or maximum fidelity.
.oasr packs run with no Python at inference, engineered for CPU and Apple SiliconThese are CLI / local-server examples. The desktop app runs this model without typing a command — see the desktop install path above.
$ openasr pull whisper-tiny.en:q8 ↓ whisper-tiny.en.oasr 60.3 MB ✓ verified sha256 $ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/whisper-tiny.en/q8_0/whisper-tiny.en-q8_0.oasr ✓ local transcript · 0 bytes sent
$ openasr serve --backend native --model-pack ~/.openasr/models/whisper-tiny.en/q8_0/whisper-tiny.en-q8_0.oasr --addr 127.0.0.1:8080 ▶ http://127.0.0.1:8080 · model=whisper-tiny.en · 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-tiny.en", file=audio)