CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.speech / VibeVoice-ASR
From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.speechSubject:

VibeVoice-ASR

Date: 2026-11-14Commit: d0c9efdSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model with 8.7B parameters. Safetensors weights, 17.3 GB in all. Published by microsoft under MIT.

8.7B params17.3GBVibeVoice-ASRsafetensorspermissive
FactsParams8.7BSize17.3 GBFormatssafetensorsTaskautomatic speech recognitionLicenseMITFrom sourcepermissive
$ fw get microsoft/VibeVoice-ASR
# manifest sha256 0fc7fc2599ed… · 17.3 GB · 17 files
$ fw verify ./VibeVoice-ASR microsoft/VibeVoice-ASR
From sourceHosted (signed)microsoft/VibeVoice-ASRLast check: 2026-11-14 21:23 UTC
Run at homeGet help

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

Works with

Run23Fine-tune7Convert8Scan2
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
17.3 GB
Weights
17.3 GB (safetensors)
Parameters
8.7B
Formats
safetensors
Task
automatic speech recognition
License
MIT (permissive)
Files
17, each with a sha256
Publisher
microsoft
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 21:23 UTCpassed

Model card

From the publisher at commit d0c9efd. Shown as plain text with links; images open at the publisher.

VibeVoice-ASR#

GitHub Live Playground Technical Report

VibeVoice-ASR is a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords and over 50 languages.

➡️ Code: microsoft/VibeVoice

➡️ Demo: VibeVoice-ASR-Demo

➡️ Report: VibeVoice-ASR Technical Report

➡️ Finetuning: Finetuning

➡️ vLLM: vLLM-VibeVoice-ASR

Image: VibeVoice-ASR Architecture

🔥 Key Features#

  • 🕒 60-minute Single-Pass Processing: Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to 60 minutes of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour.
  • 👤 Customized Hotwords: Users can provide customized hotwords (e.g., specific names, technical terms, or background info) to guide the recognition process, significantly improving accuracy on domain-specific content.
  • 📝 Rich Transcription (Who, When, What): The model jointly performs ASR, diarization, and timestamping, producing a structured output that indicates who said what and when.
  • 🌍 Multilingual & Code-Switching Support: It supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. Language distribution can be found here.

Evaluation#

Image: DER Image: cpWER Image: tcpWER

Installation and Usage#

Please refer to GitHub README.

Language Distribution#

Image: Language Distribution

License#

This project is licensed under the MIT License.

Contact#

This project was conducted by members of Microsoft Research. We welcome feedback and collaboration from our audience. If you have suggestions, questions, or observe unexpected/offensive behavior in our technology, please contact us at VibeVoice@microsoft.com. If the team receives reports of undesired behavior or identifies issues independently, we will update this repository with appropriate mitigations.

Files

17 files · 17.3 GBWeights 17.3 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes199 Be71f7f61bf0d538ce7957e1ba0f758301b9b269f2f1f6732452a10f80db1d3ed
README.md4.34 KB635e608dc781dd53ee002a7fddc4a4775b9e77d7c077a22be086dcf67fb5dad6
config.json3.52 KB1798906d016a625ffa0100182cad152e055bfee53fb228a45ffe25d8179b9b24
figures/DER.jpg62.7 KB7472f1f44110da44ebfc49f7926096098c8598c0c63dd837cbace3748d9256d1
figures/VibeVoice_ASR_archi.png149 KBc5973094212c6c5c9c0bba6ee274e396ddbb272d8642f86c0d96c5b9e85dd52b
figures/cpWER.jpg68.5 KBcd686c29637e4267ecb1119e68c973fe6782ef09e5b9fb136b5265b048255947
figures/language_distribution_horizontal.png888 KB1151d7587c660c7417df0194bbb7aeefe02a6be5a3ba8a89203d52a3602fa700
figures/tcpWER.jpg64.3 KB1586b7b5635a9be4f1f67f8e31db639ca4382cc6dea747adff1afe37d27d0dc0
model-00001-of-00008.safetensors2.49 GB5548c67885d423ba184bc8c33f2e9f81b582a6d119cef79907e19a274b916637
model-00002-of-00008.safetensors2.39 GB163023c61a3fb047745cbaf53ed41c1e27e515e9786a376e122bfac2ea6e687e
model-00003-of-00008.safetensors2.47 GB4e021702dfac2c52e8fdd6688de82c118be7bb7ad9b5c7988725ec63c44a64fb
model-00004-of-00008.safetensors2.47 GBb17657bb151daa117a5a4671374ac1b248acb696691a2a67ac227a1115925e30
model-00005-of-00008.safetensors2.50 GB0ed4e457268f7b02dda5cffe16b3a32614ccc2ccfe5de2db39bdd79700836406
model-00006-of-00008.safetensors2.48 GB6de8246bb042fd853b57d40995efd289ea44e4d1b611cec2e122570b8d2122bd
model-00007-of-00008.safetensors1.46 GBa2ba6960d994dc7598efc6796f85ab097da7708f4dd56095f7fccf4df8dc00e5
model-00008-of-00008.safetensors1.09 GB1b9d9b328f85a25b4efca712d31513c6eed9e178152cc8cf4a6f0c2cd2bb623f
model.safetensors.index.json120 KB1468c7b7c74fe27831d8db57871fbf15efd270c747f3f99caf689119ace658ba
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d0c9efdb8d pinned now manifest updated, same commit2026-11-14 21:23 UTC17 files · 17.3 GB
d0c9efdb8d2026-11-14 21:23 UTC17 files · 17.3 GB

Use it

$ fw get microsoft/VibeVoice-ASR
# manifest sha256 0fc7fc2599ed… · 17.3 GB · 17 files
$ fw verify ./VibeVoice-ASR microsoft/VibeVoice-ASR
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/microsoft/VibeVoice-ASR.json --dir ./VibeVoice-ASR $ python3 fw.py verify ./VibeVoice-ASR ./microsoft__VibeVoice-ASR.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/VibeVoice-ASR --revision d0c9efdb8d614685062c04425d91e01b6f37d944 --local-dir ./VibeVoice-ASR
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="microsoft/VibeVoice-ASR", revision="d0c9efdb8d614685062c04425d91e01b6f37d944") print(asr("audio.wav")["text"])
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
635e608dc781dd53ee002a7fddc4a4775b9e77d7c077a22be086dcf67fb5dad6
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: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.speechSubject: VibeVoice-ASRDate: 2026-11-14Commit: d0c9efdSigned: 2DC28CC7B26A283B ✓
Upstream
microsoft/VibeVoice-ASR
Pinned commit
d0c9efdb8d614685062c04425d91e01b6f37d944
Manifest
VibeVoice-ASR.json · .minisig
Manifest sha256
0fc7fc2599edce9de3082fdb16198638a21953e341e0a6c2ea8ece6407b9d160
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:23 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/microsoft/VibeVoice-ASR.json $ curl -O https://freeweights.allternit.com/manifests/microsoft/VibeVoice-ASR.json.minisig $ minisign -Vm VibeVoice-ASR.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/VibeVoice-ASR
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. VibeVoice-ASR.json. Provenance. Takedown history: none.
Source
huggingface.co/microsoft/VibeVoice-ASR

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