HF Model & Benchmark Matrix

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

g-omnivoice

g-group-ai-lab/g-omnivoice

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
k2-fsa/OmniVoice
provider
g-group-ai-lab
license
apache-2.0
language
vi
context
—
library
omnivoice
vRAM (GB)
—
size on disk
—
downloads
769
likes
2
created
—
last modified
2026-07-06T07:08:27+00:00 (2026)
huggingface
https://huggingface.co/g-group-ai-lab/g-omnivoice
tags
omnivoicesafetensorstext-to-speechttsvoice-cloningvoice-designzero-shotvietnameseviarxiv:2604.00688base_model:Qwen/Qwen3-0.6Bbase_model:finetune:Qwen/Qwen3-0.6Blicense:apache-2.0region:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
Speaker SIMspeech-tts89.0mediumSIM 0.890
MOSspeech-tts7.71low| k2-fsa/OmniVoice | 0.0712 | 0.892 | 7.709 |
WERspeech-asr7.12low| k2-fsa/OmniVoice | 0.0712 | 0.892 | 7.709 |

Discussions (0)

none scraped.

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