Whisper Base

Compact multilingual Whisper, a step up from tiny

MultilingualApache-2.0
Desktop app Open the Models screen and click install.
CLI
$ openasr pull whisper-base:q8
Download .oasr

Overview

Whisper Base is OpenAI's 74M-parameter multilingual Whisper checkpoint. It uses the standard Whisper encoder-decoder architecture for automatic speech recognition and speech translation, trained with large-scale weak supervision on 680k hours of labelled speech. Base offers a meaningful accuracy gain over tiny while staying small and fast enough for low-resource devices. This OpenASR repo repackages the original openai/whisper-base 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.

Highlights

  • 🎧 Multilingual ASR — transcribes many languages and can translate speech to English
  • 🪶 74M parameters — a small footprint with noticeably better accuracy than tiny
  • 🌐 Weak-supervision scale — trained with Whisper's 680k-hour labelled speech corpus
  • 🦀 Native in OpenASR.oasr packs run with no Python at inference, engineered for CPU and Apple Silicon

Tags

Pull stringSizeQuantJFK ΔWER
whisper-base:fp16 142.2 MB fp16 0%
whisper-base:q8default 102.8 MB q8_0 0%
whisper-base:q4 81.8 MB q4_k 0%

Usage

These are CLI / local-server examples. The desktop app runs this model without typing a command — see the desktop install path above.

bash · transcribe a file
$ openasr pull whisper-base:q8
↓ whisper-base.oasr  102.8 MB  ✓ verified sha256
$ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/whisper-base/q8_0/whisper-base-q8_0.oasr
✓ local transcript · 0 bytes sent
bash · serve a local API
$ openasr serve --backend native --model-pack ~/.openasr/models/whisper-base/q8_0/whisper-base-q8_0.oasr --addr 127.0.0.1:8080
▶ http://127.0.0.1:8080 · model=whisper-base · 0 bytes will leave this host
python · client.py
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-base", file=audio)

Other models