alt.freeweights.speech / whisper-large-v3-turbo-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.speechSubject:

whisper-large-v3-turbo-4bit

Date: 2026-11-15Commit: 0f058d3Signed: 2DC28CC7B26A283B ✓

Automatic speech recognition model with 807M parameters. Safetensors weights, 464 MB in all. Published by mlx-community under Apache-2.0.

807M params464MBwhisper-large-v3-turbo-4bitsafetensorspermissive
FactsParams807MSize464 MBFormatssafetensorsTaskautomatic speech recognitionLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/whisper-large-v3-turbo-4bit
# manifest sha256 8188e66382d5… · 464 MB · 5 files
$ fw verify ./whisper-large-v3-turbo-4bit mlx-community/whisper-large-v3-turbo-4bit
From sourceHosted (signed)mlx-community/whisper-large-v3-turbo-4bitLast check: 2026-11-15 02:41 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of whisper-large-v3-turbo.

Works with

Overview

Size
464 MB
Weights
463 MB (safetensors)
Parameters
807M
Formats
safetensors
Task
automatic speech recognition
License
Apache-2.0 (permissive)
Files
5, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.speech
Lineage

Original release from the publisher.

Base model: openai/whisper-large-v3-turbo

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 02:41 UTCpassed

Model card

From the publisher at commit 0f058d3. Shown as plain text with links; images open at the publisher.

mlx-community/whisper-large-v3-turbo-4bit#

This model was converted to MLX format from openai/whisper-large-v3-turbo using mlx-audio-plus version 0.1.4.

Use with mlx-audio-plus#

pip install -U mlx-audio-plus
Command line#
mlx_audio.stt --model mlx-community/whisper-large-v3-turbo-4bit --audio audio.mp3
Python#
from mlx_audio.stt import transcribe

result = transcribe(
    audio="audio.mp3",
    model="mlx-community/whisper-large-v3-turbo-4bit",
)
print(result["text"])

Files

5 files · 464 MBWeights 463 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 5 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md849 B585cbed556243f48a6e9bfbdc3c0984a8bd0b3e6eca8a09ef69dd48a5e27cb58
config.json341 B538e24557b8f9bc504700add5e7bbe32087c2353001ff563e64772ad4398671a
model.safetensors463 MBe2d6146b49644c13ed7467060d3c43c402bbdfca1f01f1c21f6fbeda23b6567e
multilingual.tiktoken817 KBb34b360dbb493e781e479794586d661700670d65564001f23024971d1f2fa126
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0f058d3817 pinned now2026-11-15 02:41 UTC5 files · 464 MB

Use it

$ fw get mlx-community/whisper-large-v3-turbo-4bit
# manifest sha256 8188e66382d5… · 464 MB · 5 files
$ fw verify ./whisper-large-v3-turbo-4bit mlx-community/whisper-large-v3-turbo-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/whisper-large-v3-turbo-4bit.json --dir ./whisper-large-v3-turbo-4bit $ python3 fw.py verify ./whisper-large-v3-turbo-4bit ./mlx-community__whisper-large-v3-turbo-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/whisper-large-v3-turbo-4bit --revision 0f058d38170d183f9fdee07908f5b515d91793a8 --local-dir ./whisper-large-v3-turbo-4bit
transformersSpeech recognition with the transformers pipeline.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import pipeline asr = pipeline("automatic-speech-recognition", model="mlx-community/whisper-large-v3-turbo-4bit", revision="0f058d38170d183f9fdee07908f5b515d91793a8") print(asr("audio.wav")["text"])

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
585cbed556243f48a6e9bfbdc3c0984a8bd0b3e6eca8a09ef69dd48a5e27cb58
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.speechSubject: whisper-large-v3-turbo-4bitDate: 2026-11-15Commit: 0f058d3Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/whisper-large-v3-turbo-4bit
Pinned commit
0f058d38170d183f9fdee07908f5b515d91793a8
Manifest
whisper-large-v3-turbo-4bit.json · .minisig
Manifest sha256
8188e66382d5855d01411b74ca76fca20dc3140edbfaa5182a0753d3bb9aaf0e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:41 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/whisper-large-v3-turbo-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/whisper-large-v3-turbo-4bit.json.minisig $ minisign -Vm whisper-large-v3-turbo-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

openai/whisper-large-v3-turbo · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/whisper-large-v3-turbo-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. whisper-large-v3-turbo-4bit.json. Provenance. Takedown history: none.
From: MIT <huggingface.co/MIT>Subject: ast-finetuned-audioset-10-10-0.4593
From: onnx-community <huggingface.co/onnx-community>Subject: ast-finetuned-audioset-10-10-0.4593-ONNX
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Preview-0.6b
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Realistic-Air
From: facebook <huggingface.co/facebook>Subject: audiobox-aesthetics
From: mlx-community <huggingface.co/mlx-community>Subject: chatterbox-4bit