Balanced English-only Whisper for accurate local transcription
Whisper Small.en is OpenAI's 244M-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, making it a strong default for
English-only workloads that want accuracy without a large footprint. This OpenASR repo
repackages the original openai/whisper-small.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 tighter 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-small.en:q8 ↓ whisper-small.en.oasr 288.8 MB ✓ verified sha256 $ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/whisper-small.en/q8_0/whisper-small.en-q8_0.oasr ✓ local transcript · 0 bytes sent
$ openasr serve --backend native --model-pack ~/.openasr/models/whisper-small.en/q8_0/whisper-small.en-q8_0.oasr --addr 127.0.0.1:8080 ▶ http://127.0.0.1:8080 · model=whisper-small.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-small.en", file=audio)