HF Model & Benchmark Matrix

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

gepard-1.0

nineninesix/gepard-1.0

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
nineninesix/qwen3_5-full-attn-only-14
provider
nineninesix
license
apache-2.0
language
en, es, pt, nl
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
9,622
likes
128
created
—
last modified
2026-07-11T12:04:14+00:00 (2026)
huggingface
https://huggingface.co/nineninesix/gepard-1.0
tags
transformerssafetensorsqwen3_5_texttext-generationtext-to-speechttsspeech-synthesisvoice-cloningautoregressivevllmenesptnldataset:laion/Emoliaarxiv:2309.06180arxiv:2307.08691arxiv:2508.05835arxiv:2309.15505arxiv:2406.17957arxiv:2207.12598arxiv:2305.18290arxiv:2405.14734arxiv:2301.12597

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
Speaker SIMspeech-tts86.7low| VoxCPM2 | **0.015** | **0.867** | 2.42 | 3.97 | 3.86 | 3.96 | 4.30 |
MOSspeech-tts3.97low| VoxCPM2 | **0.015** | **0.867** | 2.42 | 3.97 | 3.86 | 3.96 | 4.30 |
UTMOSspeech-tts2.42low| VoxCPM2 | **0.015** | **0.867** | 2.42 | 3.97 | 3.86 | 3.96 | 4.30 |
WERspeech-asr1.5low| VoxCPM2 | **0.015** | **0.867** | 2.42 | 3.97 | 3.86 | 3.96 | 4.30 |

Discussions (0)

none scraped.

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