alt.freeweights.speech / whisper-large-v3
From: openai <huggingface.co/openai>Newsgroups: alt.freeweights.speechSubject:

whisper-large-v3

Date: 2026-11-14Commit: 06f233fSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model with 1.5B parameters. Safetensors weights, 24.7 GB in all. Published by openai under Apache-2.0.

1.5B params24.7GBwhisper-large-v3safetensorspermissive
FactsParams1.5BSize24.7 GBFormatssafetensorsTaskautomatic speech recognitionLicenseApache-2.0From sourcepermissive
$ fw get openai/whisper-large-v3
# manifest sha256 8a5be8c42ab7… · 24.7 GB · 21 files
$ fw verify ./whisper-large-v3 openai/whisper-large-v3
From sourceopenai/whisper-large-v3Last check: 2026-11-14 06:36 UTC
Runs withwhisper.cpp

Overview

Size
24.7 GB
Weights
9.26 GB (safetensors)
Parameters
1.5B
Formats
safetensors
Task
automatic speech recognition
License
Apache-2.0 (permissive)
Files
21, each with a sha256
Publisher
openai
Added
2026-11-14
Section
alt.freeweights.speech
Lineage

Original release from the publisher.

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.co2026-11-14 06:36 UTCpassed

Files

21 files · 24.7 GBWeights 9.26 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 21 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md21.8 KBb05416eb578e9fc65ce137f3401bafdf3bc2feac7448e7dd180dcd367b8cfb52
added_tokens.json34.6 KB3c51f66c4c21f9e126970078f11ae77a78c74aee8df606ee9daba86e467108e0
config.json1.27 KBad0e8d1e46f4d01f7861a21509e5d0f977d6cc1f367a370603c92541d819807b
flax_model.msgpack6.17 GBe9c7b745947df8856bb809974ac7f9ef2704f7834ab1760fc925f38f8f5517f5
generation_config.json3.90 KBfbdfa70135de9b1d31553393f14e80aaeb1936ea36576b2ba864055943c09d23
merges.txt494 KB2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6
model.fp32-00001-of-00002.safetensors4.99 GB08e0005225b3dbaf55dd13ac62926cc7e02c1025d66fa375e6fb305ff79cd4f9
model.fp32-00002-of-00002.safetensors1.18 GB630ca774672856d2e0e39a702e590f635a1cfc5726a64b6578ab46dd367369a9
model.safetensors3.09 GBa8e94b85976e5864ba3e9525c7e6c83b2a1eca42d4b797a0c7c24d778e40fd95
model.safetensors.index.fp32.json118 KBbccecde4044933c7f3cbea731a5a4eb1e2dcbef1b9bc5f603d510b8361c45835
normalizer.json52.7 KBbf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
preprocessor_config.json340 B7ccc62c6f2765af1f3b46c00c9b5894426835a05021c8b9c01eecb6dfb542711
pytorch_model.bin3.09 GB8f3dd0108a56caf505b47740a385a6f61be03e670f4fc34e21e3d2bc98d7b6d1
pytorch_model.bin.index.fp32.json118 KB321c26ca640af6ad1f00a0cb3a53cb47265a41e66399ae713d7dbbf0cd923b69
pytorch_model.fp32-00001-of-00002.bin4.99 GBfed9e023b3519cba5b7279bdfbfd81aacfeb001f04bbe0cd9b8d1995a900b0d8
pytorch_model.fp32-00002-of-00002.bin1.18 GBaadd3bdfecf9bc81e6ef6acf3c1ccaf3124c82eb06a94190064a28fdee096d64
special_tokens_map.json2.07 KB1c70773c078cb2ca96e0fcff113102f1d3e2b1504272c3bb63b035d4a6700d87
tokenizer.json2.48 MB6d8cbd7cd0d8d5815e478dac67b85a26bbe77c1f5e0c6d76d1ce2abc0e5f21ca
tokenizer_config.json283 KB844b642c73a91359722f47b35705f7174686df33d252695d8572cf9ac03a6389
vocab.json1.04 MBe2aa043ef015641d363d8288e7c241c85e36a5c761fb303598e0710233344387

Use it

$ fw get openai/whisper-large-v3
# manifest sha256 8a5be8c42ab7… · 24.7 GB · 21 files
$ fw verify ./whisper-large-v3 openai/whisper-large-v3
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/openai/whisper-large-v3.json --dir ./whisper-large-v3 $ python3 fw.py verify ./whisper-large-v3 ./openai__whisper-large-v3.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download openai/whisper-large-v3 --revision 06f233fe06e710322aca913c1bc4249a0d71fce1 --local-dir ./whisper-large-v3
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="openai/whisper-large-v3", revision="06f233fe06e710322aca913c1bc4249a0d71fce1") print(asr("audio.wav")["text"])
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Text in
README.md
Text sha256
b05416eb578e9fc65ce137f3401bafdf3bc2feac7448e7dd180dcd367b8cfb52
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: openai <huggingface.co/openai>Newsgroups: alt.freeweights.speechSubject: whisper-large-v3Date: 2026-11-14Commit: 06f233fSigned: 2DC28CC7B26A283B ✓
Upstream
openai/whisper-large-v3
Pinned commit
06f233fe06e710322aca913c1bc4249a0d71fce1
Manifest
whisper-large-v3.json · .minisig
Manifest sha256
8a5be8c42ab75efd9752c4c9f93161d4baf952db0401afe16713ffe338518699
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:36 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/openai/whisper-large-v3.json $ curl -O https://freeweights.allternit.com/manifests/openai/whisper-large-v3.json.minisig $ minisign -Vm whisper-large-v3.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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download openai/whisper-large-v3
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. whisper-large-v3.json. Provenance. Takedown history: none.
From: fishaudio <huggingface.co/fishaudio>Subject: s2-pro
From: ResembleAI <huggingface.co/ResembleAI>Subject: chatterbox
From: onnx-community <huggingface.co/onnx-community>Subject: Kokoro-82M-v1.0-ONNX
From: openai <huggingface.co/openai>Subject: whisper-large-v3-turbo