HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

VibeVoice-Realtime-0.5B-ONNX

elbruno/VibeVoice-Realtime-0.5B-ONNX

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
microsoft/VibeVoice-Realtime-0.5B
provider
elbruno
license
mit
language
en
context
—
library
onnxruntime
vRAM (GB)
—
size on disk
—
downloads
216
likes
5
created
—
last modified
2026-02-22T22:57:15+00:00 (2026)
huggingface
https://huggingface.co/elbruno/VibeVoice-Realtime-0.5B-ONNX
tags
onnxruntimeonnxvibevoice-realtime-onnxtext-to-speechttsvibevoicemicrosoftdiffusionstreamingrealtimespeech-synthesisendataset:librispeech_asrarxiv:2508.19205arxiv:2412.08635base_model:microsoft/VibeVoice-Realtime-0.5Bbase_model:quantized:microsoft/VibeVoice-Realtime-0.5Blicense:mitmodel-indexregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
Speaker SIMspeech-tts64.3low| VALL-E 2 | 2.40 | 0.643 |
WERspeech-asr2.4low| VALL-E 2 | 2.40 | 0.643 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.