VibeVoice-ASR-HF

Checkpointmicrosoft/VibeVoice-ASR-HFModel card indexedModel card

Support summary

VibeVoice-ASR-HF is a checkpoint published by Microsoft, built on the VibeVoiceAsrForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support.

vLLM documents support in 3 of 20 indexed releases, from 0.27.0 to 0.28.0.

Configured context
131,072 tokens
License
mit
Hugging Face model card
Publisher
Microsoft
Task
audio text to text
License
mit
Library
transformers
Architecture
VibeVoiceAsrForConditionalGeneration
Weight tensor elements
8.3B
Tensor types
BF16
Configured context
131,072 tokens
Languages
en, zh, es, pt, de, ja, ko, fr, ru, id, sv, it, he, nl, pl, no, tr, th, ar, hu, ca, cs, da, fa, af, hi, fi, et, aa, el, ro, vi, bg, is, sl, sk, lt, sw, uk, kl, lv, hr, ne, sr, tl, yi, ms, ur, mn, hy, jv
Weight access
Public
Repository created
2026-03-02
Source 1: microsoft/VibeVoice-ASR-HF · publisher model cardSource 2: microsoft/VibeVoice-ASR-HF · Hugging Face metadataSource 3: microsoft/VibeVoice-ASR-HF · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for VibeVoice-ASR-HF
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1