HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Models
/
Sariel00/cosyvoice2_rknn
cosyvoice2_rknn
Sariel00/cosyvoice2_rknn
kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
—
provider
Sariel00
license
apache-2.0
language
zh
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
203
likes
6
created
—
last modified
2026-07-24T11:35:37+00:00
(2026)
huggingface
https://huggingface.co/Sariel00/cosyvoice2_rknn
tags
cosyvoice
onnx
safetensors
rk3588
rknn
rkllm
text-to-speech
zh
license:apache-2.0
region:us
Benchmark scores (1)
benchmark
category
score
context
conf
evidence
RTF
speech-asr
74.59
low
| 短音频 | 5.92 s | 2.255 s | **0.7459** | 1.0210 | 1523.6 MiB |
Discussions (0)
none scraped.
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.