HF Model & Benchmark Matrix

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

omnivoice-hakka-community-1

formospeech/omnivoice-hakka-community-1

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
k2-fsa/OmniVoice
provider
formospeech
license
cc-by-nc-4.0
language
hak
context
—
library
omnivoice
vRAM (GB)
—
size on disk
—
downloads
151
likes
1
created
—
last modified
2026-05-12T05:08:12+00:00 (2026)
huggingface
https://huggingface.co/formospeech/omnivoice-hakka-community-1
tags
omnivoicesafetensorszero-shotmultilingualvoice-cloningvoice-designtaiwanese-hakkahakkatext-to-speechhakbase_model:k2-fsa/OmniVoicebase_model:finetune:k2-fsa/OmniVoicelicense:cc-by-nc-4.0region:us

Benchmark scores (7)

benchmarkcategoryscorecontextconfevidence
Speaker SIMspeech-tts80.1low| OmniVoice Taiwanese Hakka | 2.61% | 2.29% | 0.801 | 3.65 |
Speaker SIMspeech-tts80.1SIM-omedium| SIM-o | 0.801 |
UTMOSspeech-tts3.65low| OmniVoice Taiwanese Hakka | 2.61% | 2.29% | 0.801 | 3.65 |
UTMOSspeech-tts3.65UTMOSmedium| UTMOS | 3.65 |
CERspeech-asr2.61low| OmniVoice Taiwanese Hakka | 2.61% | 2.29% | 0.801 | 3.65 |
CERspeech-asr2.61Hakka CER (Avg of sample CERs)medium| Hakka CER (Avg of sample CERs) | 2.61% |
CERspeech-asr2.29Hakka CER (Weighted)medium| Hakka CER (Weighted) | 2.29% |

Discussions (0)

none scraped.

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