alt.freeweights.speech / whisper-large-v3-turbo_timestamped

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.speechSubject:

whisper-large-v3-turbo_timestamped

Date: 2026-11-14Commit: b3f77bfSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model. Onnx weights, 10.2 GB in all. Published by onnx-community under MIT.

speech

10.2GBwhisper-large-v3-turbo_timestampedonnxpermissive

FactsParamsnot statedSize10.2 GBFormatsonnxTaskautomatic speech recognitionLicenseMITFrom sourcepermissive

$ fw get onnx-community/whisper-large-v3-turbo_timestamped
# manifest sha256 d252f70490ad… · 10.2 GB · 30 files
$ fw verify ./whisper-large-v3-turbo_timestamped onnx-community/whisper-large-v3-turbo_timestamped

From sourceHosted (signed)onnx-community/whisper-large-v3-turbo_timestampedLast check: 2026-11-14 21:31 UTC

Run at home Get help

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

Quantized of whisper-large-v3-turbo.

Works with

Run18 Convert3 Scan1

Runs with

Ranked by fit to this model (onnx), then by GitHub stars.

whisper.cpp

Whisper Ultralytics faster-whisper WhisperX FunASR NeMo Speech Pipecat LiveKit Agents

Speech-to-Speech SpeechBrain Moshi

Show all 18

OpenVINO pyannote.audio RealtimeSTT ESPnet WhisperKit WhisperLive

Convert with

ONNX

Optimum

Olive

Scan with

ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 10.2 GB
Weights: 194 MB (smallest of 16 ONNX variants)
Parameters: not stated
Formats: onnx
Task: automatic speech recognition
License: MIT (permissive)
Files: 30, each with a sha256
Publisher: onnx-community
Added: 2026-11-14
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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-14 21:31 UTC	passed

Model card

From the publisher at commit b3f77bf. Shown as plain text with links; images open at the publisher.

https://huggingface.co/openai/whisper-large-v3-turbo with ONNX weights to be compatible with Transformers.js.

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Files

30 files · 10.2 GBWeights 194 MB (smallest of 16 ONNX variants). Sizes and sha256 from the signed manifest.

Show all 30 files with their sha256

File	Size	sha256
.gitattributes	1.58 KB	78010516a7b5c497fa33a3c641e2577f53187e3f7dc7031a0d8ce85a7da742e1
README.md	551 B	19af35fc51ff4eab95ea53a4955af5c2b13f720b802be3191b79fd6f053e4ce7
added_tokens.json	34.6 KB	3c51f66c4c21f9e126970078f11ae77a78c74aee8df606ee9daba86e467108e0
config.json	1.33 KB	32c02d1dfb9a93ff236cdcf0f741f8f3a4cedb437c407a361a022451ac009131
generation_config.json	3.80 KB	8568ddf83476167b4607014956b87142763fa6923e71259a606734beb39bdfc8
merges.txt	494 KB	2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6
normalizer.json	52.7 KB	bf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
onnx/decoder_model_merged.onnx	688 MB	a266a7ea5896e41846751a8e94f7b4993e0c24856789b99bcf534a86660366ea
onnx/decoder_model_merged_bnb4.onnx	328 MB	d36f14efa497e3776df98e28b64341d9f866ef95ee4ce8eeda27c8507ff820dd
onnx/decoder_model_merged_fp16.onnx	344 MB	4ed6335ca4c12afe33390a228615c7ca50449f953dddb2d41eb12e875504c621
onnx/decoder_model_merged_int8.onnx	440 MB	b4ab1c92a9bcf8c8fdc49deacb57ac51b707d5248bc7868af42371b896c3ae52
onnx/decoder_model_merged_q4.onnx	334 MB	6bf129462f6bc8722726291e3fdbd8bc07000f66336b4ef1387d5d8d636f4186
onnx/decoder_model_merged_q4f16.onnx	194 MB	617e5b4f91ca190c43fa4d3bd2e671cfbee19c9a6ac4890f0a4bbaf658f00cf4
onnx/decoder_model_merged_quantized.onnx	440 MB	b4ab1c92a9bcf8c8fdc49deacb57ac51b707d5248bc7868af42371b896c3ae52
onnx/decoder_model_merged_uint8.onnx	440 MB	7d344422559036cc35d1ee47e863f8a226c3bd68720a2ad67246f6ce574bda51
onnx/encoder_model.onnx	500 KB	5f17ad18cf466d382b1544f94c9c22d28360302461dda74a2d64d2f37bdcc60f
onnx/encoder_model.onnx_data	2.55 GB	c87f74d17ea85478cd563a614215868eff35a8a7ec4ff692d1edd49413f56f86
onnx/encoder_model_bnb4.onnx	386 MB	de90e2a07ec80d543c6a3d688e7c6cf8646f6384fb9bc94d34c2198beb33e37f
onnx/encoder_model_fp16.onnx	1.27 GB	45ff31e8776048fe802d293375060f3b801763c33393066a7e997c77604b5d10
onnx/encoder_model_int8.onnx	645 MB	3cb43fe7c779110a2f33635fbe24d0db175720834215cb1e4dcc51d4786af156
onnx/encoder_model_q4.onnx	425 MB	41ad35ee01012d68837d142d74de34d3bb32dc040a61817de470011219b1b1eb
onnx/encoder_model_q4f16.onnx	370 MB	65261f977474ce30e46ed2c2b885e8ef68ef917941f78af48b098b86fad1adaa
onnx/encoder_model_quantized.onnx	645 MB	a5bece0f99f86b5fed85e59b6b23299500639b283a0a6e00098e6583ed1baeb8
onnx/encoder_model_uint8.onnx	645 MB	a5bece0f99f86b5fed85e59b6b23299500639b283a0a6e00098e6583ed1baeb8
preprocessor_config.json	340 B	7ccc62c6f2765af1f3b46c00c9b5894426835a05021c8b9c01eecb6dfb542711
quantize_config.json	285 B	8da6e4e50ef7c210ba66a98a4256e6d60e38cef8a9a9c74d327251aaf4e78767
special_tokens_map.json	2.19 KB	baea4ea09372eb4fca86b4e4346139fd73cb807d5087e9de0948e971739c3e74
tokenizer.json	2.48 MB	b3c8202bbf06d8ee4232c5984baa563784ac4737e2e7fdc42fa180200d3cfcdb
tokenizer_config.json	283 KB	844b642c73a91359722f47b35705f7174686df33d252695d8572cf9ac03a6389
vocab.json	1.04 MB	e2aa043ef015641d363d8288e7c241c85e36a5c761fb303598e0710233344387

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
b3f77bf9a8 pinned now	2026-11-14 21:31 UTC	30 files · 10.2 GB

Use it

$ fw get onnx-community/whisper-large-v3-turbo_timestamped
# manifest sha256 d252f70490ad… · 10.2 GB · 30 files
$ fw verify ./whisper-large-v3-turbo_timestamped onnx-community/whisper-large-v3-turbo_timestamped

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/whisper-large-v3-turbo_timestamped.json --dir ./whisper-large-v3-turbo_timestamped
$ python3 fw.py verify ./whisper-large-v3-turbo_timestamped ./onnx-community__whisper-large-v3-turbo_timestamped.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/whisper-large-v3-turbo_timestamped --revision b3f77bf9a8c4d5ea3415827033d1ffea7955fd9a --local-dir ./whisper-large-v3-turbo_timestamped

Run at home

License

Name: MIT License
Id: MIT
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: Inherited from the base model openai/whisper-large-v3-turbo: the strictest license along the lineage applies. 2026-11-14
Text in: README.md
Text sha256: 19af35fc51ff4eab95ea53a4955af5c2b13f720b802be3191b79fd6f053e4ce7
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:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.speechSubject: whisper-large-v3-turbo_timestampedDate: 2026-11-14Commit: b3f77bfSigned: 2DC28CC7B26A283B ✓

Upstream: onnx-community/whisper-large-v3-turbo_timestamped
Pinned commit: b3f77bf9a8c4d5ea3415827033d1ffea7955fd9a
Manifest: whisper-large-v3-turbo_timestamped.json · .minisig
Manifest sha256: d252f70490ad20dea8559594345ebe230feed9c9c54c495c0f8b3597edcd86c8
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-14 21:31 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/whisper-large-v3-turbo_timestamped.json
$ curl -O https://freeweights.allternit.com/manifests/onnx-community/whisper-large-v3-turbo_timestamped.json.minisig
$ minisign -Vm whisper-large-v3-turbo_timestamped.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 quantization of it

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

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/whisper-large-v3-turbo_timestamped

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_timestamped.json. Provenance. Takedown history: none.

Source

huggingface.co/onnx-community/whisper-large-v3-turbo_timestamped

Related models

All of alt.freeweights.speech →

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