Live transcription · Multilingual

Whisper Medium

High-accuracy multilingual Whisper at 769M parameters

Multilingual · 2.2× · 833.8 MB

Install in OpenASR Desktop

Opens the desktop app and downloads this model for you.

Don't have the app yet? Download OpenASR Desktop

On-deviceOn this computer
interview.m4a12:04

let's line up this week's release plan,

the beta build can ship on Friday,

then loop in design and QA,

Why it fits

Whisper Medium is OpenAI's 769M-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. Medium delivers much of the large model's accuracy at a smaller footprint, a strong choice when quality matters but the largest checkpoint is too heavy. This OpenASR repo repackages the original openai/whisper-medium 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.

What you can do with it

  • 🎧 Multilingual ASR — transcribes many languages and can translate speech to English
  • 🎯 769M parameters — near-large accuracy with a more manageable footprint
  • 🌐 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

Other models

Developer details CLI commands, file hashes, and per-quant downloads — for scripting and verification.

Downloads by quantization

Pull stringSizeQuant
whisper-medium:fp16 1.4 GB fp16
open .oasr
whisper-medium:q8default 833.8 MB q8_0
open .oasr
whisper-medium:q4 641.8 MB q4_k
open .oasr

Model facts

Size833.8 MB
Speed2.2× real-time
LanguageMultilingual
Familywhisper
Vendoropenai
Released2022-09-21
Peak memory2 GB
Quantizationq8_0
LicenseApache-2.0
Revisiond77e227b9e238851db9288badfeec1068423f348
sha2565e663d322bcaa5743c3e4b3dac680f0b6c79f87edb9d7f1b9147a09329278c37

Usage

These are CLI / local-server examples. The desktop app runs this model without typing a command — use Install above.

bash · transcribe a file
$ openasr pull whisper-medium:q8
↓ whisper-medium.oasr  833.8 MB  ✓ verified sha256
$ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/whisper-medium/q8_0/whisper-medium-q8_0.oasr
✓ local transcript · 0 bytes sent
bash · serve a local API
$ openasr serve --backend native --model-pack ~/.openasr/models/whisper-medium/q8_0/whisper-medium-q8_0.oasr --addr 127.0.0.1:8080
▶ http://127.0.0.1:8080 · model=whisper-medium · 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-medium", file=audio)