CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.speech / ast-finetuned-audioset-10-10-0.4593
From: MIT <huggingface.co/MIT>Newsgroups: alt.freeweights.speechSubject:

ast-finetuned-audioset-10-10-0.4593

Date: 2026-11-15Commit: f826b80Signed: 2DC28CC7B26A283B ✓

Audio classification model with 87M parameters. Safetensors weights, 693 MB in all. Published by MIT under BSD-3-Clause.

87M params693MBast-finetuned-audioset-10-10-0.4593safetensorspermissive
FactsParams87MSize693 MBFormatssafetensorsTaskaudio classificationLicenseBSD-3-ClauseFrom sourcepermissive
$ fw get MIT/ast-finetuned-audioset-10-10-0.4593
# manifest sha256 ccd436e77155… · 693 MB · 6 files
$ fw verify ./ast-finetuned-audioset-10-10-0.4593 MIT/ast-finetuned-audioset-10-10-0.4593
From sourceHosted (signed)MIT/ast-finetuned-audioset-10-10-0.4593Last check: 2026-11-15 02:25 UTC
Run at homeGet help

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

Works with

Run8Fine-tune7Convert8Scan2

Runs with

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

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
693 MB
Weights
346 MB (safetensors)
Parameters
87M
Formats
safetensors
Task
audio classification
License
BSD-3-Clause (permissive)
Files
6, each with a sha256
Publisher
MIT
Added
2026-11-15
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.co2026-11-15 02:25 UTCpassed

Model card

From the publisher at commit f826b80. Shown as plain text with links; images open at the publisher.

Audio Spectrogram Transformer (fine-tuned on AudioSet)#

Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository.

Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description#

The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.

Usage#

You can use the raw model for classifying audio into one of the AudioSet classes. See the documentation for more info.

Files

6 files · 693 MBWeights 346 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes1.48 KBdb7c0371f46f0840b8f25794c1e3321c9b5820a8cb6ba9694a46fc64b8fae5a6
README.md1.17 KBdbc8ce1fc5abd1635d073640d8cb032901bfe264a5e06507f363f10a6112cfc8
config.json26.8 KBa93d525511d77e8ecc933d09674b85099815bbbb417c228a4edd655e252fb9ff
model.safetensors346 MBae0c1e2ad4e1381d851fa9bf298ba13ebc9c5a914cdee2dbe427a6583869924d
preprocessor_config.json297 B8d04ba5a9c6fca5d39d0de2b1fd05ecf79deb589fbba279728bbebac39934231
pytorch_model.bin346 MB9ca280ba0276a0d2243f7dd561c72b10cc7c3955a2b1f12e42e93983f24b8ca4
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f826b80d28 pinned now2026-11-15 02:25 UTC6 files · 693 MB

Use it

$ fw get MIT/ast-finetuned-audioset-10-10-0.4593
# manifest sha256 ccd436e77155… · 693 MB · 6 files
$ fw verify ./ast-finetuned-audioset-10-10-0.4593 MIT/ast-finetuned-audioset-10-10-0.4593
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/MIT/ast-finetuned-audioset-10-10-0.4593.json --dir ./ast-finetuned-audioset-10-10-0.4593 $ python3 fw.py verify ./ast-finetuned-audioset-10-10-0.4593 ./MIT__ast-finetuned-audioset-10-10-0.4593.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download MIT/ast-finetuned-audioset-10-10-0.4593 --revision f826b80d28226b62986cc218e5cec390b1096902 --local-dir ./ast-finetuned-audioset-10-10-0.4593
Run at home

License

Name
BSD 3-Clause License
Id
BSD-3-Clause
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
dbc8ce1fc5abd1635d073640d8cb032901bfe264a5e06507f363f10a6112cfc8
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: MIT <huggingface.co/MIT>Newsgroups: alt.freeweights.speechSubject: ast-finetuned-audioset-10-10-0.4593Date: 2026-11-15Commit: f826b80Signed: 2DC28CC7B26A283B ✓
Upstream
MIT/ast-finetuned-audioset-10-10-0.4593
Pinned commit
f826b80d28226b62986cc218e5cec390b1096902
Manifest
ast-finetuned-audioset-10-10-0.4593.json · .minisig
Manifest sha256
ccd436e771552faf9cba55ded34f54602f30180f07acc5dd60b0395a2b8f00a5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:25 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/MIT/ast-finetuned-audioset-10-10-0.4593.json $ curl -O https://freeweights.allternit.com/manifests/MIT/ast-finetuned-audioset-10-10-0.4593.json.minisig $ minisign -Vm ast-finetuned-audioset-10-10-0.4593.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

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download MIT/ast-finetuned-audioset-10-10-0.4593
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. ast-finetuned-audioset-10-10-0.4593.json. Provenance. Takedown history: none.
Source
huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593

Variants

1 quantized or adapter build of ast-finetuned-audioset-10-10-0.4593. Each has its own license check and page.

SubjectSizeParamsLicenseDate
ast-finetuned-audioset-10-10-0.4593-ONNXHosted (signed) From: onnx-community in alt.freeweights.speech958 MB—Permissive2026-11-15

Related models

All of alt.freeweights.speech →
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
From: mlx-community <huggingface.co/mlx-community>Subject: chatterbox-8bit