CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.speech / VibeVoice-ASR-Streaming-1.5B
From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.speechSubject:

VibeVoice-ASR-Streaming-1.5B

Date: 2026-11-15Commit: 4262d23Signed: 2DC28CC7B26A283B ✓

Automatic speech recognition model with 2.8B parameters. Safetensors weights, 5.65 GB in all. Published by microsoft under MIT.

2.8B params5.65GBVibeVoice-ASR-Streaming-1.5Bsafetensorspermissive
FactsParams2.8BSize5.65 GBFormatssafetensorsTaskautomatic speech recognitionLicenseMITFrom sourcepermissive
$ fw get microsoft/VibeVoice-ASR-Streaming-1.5B
# manifest sha256 8c672e4fbb8a… · 5.65 GB · 16 files
$ fw verify ./VibeVoice-ASR-Streaming-1.5B microsoft/VibeVoice-ASR-Streaming-1.5B
From sourceHosted (signed)microsoft/VibeVoice-ASR-Streaming-1.5BLast check: 2026-11-15 03:30 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
5.65 GB
Weights
5.63 GB (safetensors)
Parameters
2.8B
Formats
safetensors
Task
automatic speech recognition
License
MIT (permissive)
Files
16, each with a sha256
Publisher
microsoft
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 03:30 UTCpassed

Model card

From the publisher at commit 4262d23. Shown as plain text with links; images open at the publisher.

VibeVoice-ASR-Streaming-1.5B#

GitHub Live Playground

VibeVoice-ASR-Streaming is a unified streaming ASR model that transcribes Who (Speaker) said What (Content), with support for Customized Hotwords and 10 languages.

➡️ Code: microsoft/VibeVoice

➡️ Demo: VibeVoice-ASR-Streaming

Image: VibeVoice-ASR-Streaming Architecture

🔥 Key Features#

  • 📝 Streaming Speaker-Attributed Transcription: Continuously transcribes who said what as speech arrives.
  • 👤 Customized Hotwords: Users can provide customized hotwords, such as names and technical terms, to improve recognition of domain-specific content.
  • 🌍 Multilingual Support: It supports Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish.

Technical Report#

📄 VibeVoice-ASR-Streaming Technical Report

Evaluation#

Image: VibeVoice-ASR-Streaming Results

Installation and Usage#

Please refer to the GitHub repository.

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

16 files · 5.65 GBWeights 5.63 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.74 KBc50aecad5c712e61fc8e2af657385e3c108df6da345cfa324b4e6d42f520e17d
README.md2.24 KB5e4050aec9e328c5e6ef21973ee6c97660bfcd587da9610a585e028ae97f24c1
added_tokens.json714 Bd5401f76119bc71e1844d8e909826f8cb3d68e152a058fe228cc37f74603ca84
config.json2.94 KB2b46a311855872193b218bc8d4de499e3252cd3c3c06662128d16e3f9e8bc72f
figures/VibeVoice_ASR_Streaming_architecture.png192 KB2b38df286fe4d133d3ccbaf97e3195be349aca09dad011ff463b8d3b656c678f
figures/VibeVoice_ASR_Streaming_results.png623 KBfa83f98d6506ea7ed9039e0c886baa375a9614a12ad915d71009bb76b6b15535
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00003.safetensors2.50 GB788e6206a158c614e1e6777ab843baf64ca8a3f555e3cb72c26d5d79b925d4b9
model-00002-of-00003.safetensors2.49 GB4d58b3ce47ac6b0ac5d3b142d54e56f10e02a928cf016b493e9e6a3f91beb75d
model-00003-of-00003.safetensors643 MB884b560dcd3024436d8827d32c7e211c545751c099df4ee75101c1ee2196f427
model.safetensors.index.json120 KBbeac94f964e3358f8c66e7dcdbc700e5518e5cf2a7b7697a0c156ff7bcf89038
preprocessor_config.json191 B59ee0cc74687fc2ab8f5f9c2fc3b61cdf66078ebd4f34a61e1fcfc1a644ac31a
special_tokens_map.json769 B7093fea72a118fb4016ee85c13cc2f94ecd659d4600c6ce16cdcd3a2c1d96e68
tokenizer.json11.4 MBd198a051741ee47805797b744e6524c259b08a59b58d1ec159cfd7f1da5f2df7
tokenizer_config.json9.33 KBe80c7714aaff125403ba7c18a4c06da9b18eb81cb6ee4bee711143fa15d94fd6
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
4262d23d8a pinned now2026-11-15 03:30 UTC16 files · 5.65 GB

Use it

$ fw get microsoft/VibeVoice-ASR-Streaming-1.5B
# manifest sha256 8c672e4fbb8a… · 5.65 GB · 16 files
$ fw verify ./VibeVoice-ASR-Streaming-1.5B microsoft/VibeVoice-ASR-Streaming-1.5B
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-Streaming-1.5B.json --dir ./VibeVoice-ASR-Streaming-1.5B $ python3 fw.py verify ./VibeVoice-ASR-Streaming-1.5B ./microsoft__VibeVoice-ASR-Streaming-1.5B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/VibeVoice-ASR-Streaming-1.5B --revision 4262d23d8a539a6530cf64fbd0b1751ef9a30853 --local-dir ./VibeVoice-ASR-Streaming-1.5B
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-Streaming-1.5B", revision="4262d23d8a539a6530cf64fbd0b1751ef9a30853") 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. 2026-11-15
Text in
README.md
Text sha256
5e4050aec9e328c5e6ef21973ee6c97660bfcd587da9610a585e028ae97f24c1
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-ASR-Streaming-1.5BDate: 2026-11-15Commit: 4262d23Signed: 2DC28CC7B26A283B ✓
Upstream
microsoft/VibeVoice-ASR-Streaming-1.5B
Pinned commit
4262d23d8a539a6530cf64fbd0b1751ef9a30853
Manifest
VibeVoice-ASR-Streaming-1.5B.json · .minisig
Manifest sha256
8c672e4fbb8ac189b998b9839743d3bb6586b244cc4b5e799ff76e75fb0ab128
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/microsoft/VibeVoice-ASR-Streaming-1.5B.json $ curl -O https://freeweights.allternit.com/manifests/microsoft/VibeVoice-ASR-Streaming-1.5B.json.minisig $ minisign -Vm VibeVoice-ASR-Streaming-1.5B.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-Streaming-1.5B
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-Streaming-1.5B.json. Provenance. Takedown history: none.
Source
huggingface.co/microsoft/VibeVoice-ASR-Streaming-1.5B

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