HF Model & Benchmark Matrix

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

CosyVoice2-0.5B

FunAudioLLM/CosyVoice2-0.5B

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
FunAudioLLM/CosyVoice2-0.5B
provider
FunAudioLLM
license
apache-2.0
language
zh, en, fr, es, ja, ko, it, ru, de
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
4,963
likes
83
created
—
last modified
2026-05-31T03:10:15+00:00 (2026)
huggingface
https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B
tags
onnxsafetensorstext-to-speechzhenfresjakoitrudearxiv:2505.17589arxiv:2412.10117arxiv:2407.05407license:apache-2.0region:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
Speaker SIMspeech-tts75.7Open-Sourcehigh| CosyVoice2 | ✅ | 0.5B | 1.45 | 75.7 | 2.57 | 65.9 | 6.83 | 72.4 |
WERspeech-asr2.57Open-Sourcehigh| CosyVoice2 | ✅ | 0.5B | 1.45 | 75.7 | 2.57 | 65.9 | 6.83 | 72.4 |
CERspeech-asr1.45Open-Sourcehigh| CosyVoice2 | ✅ | 0.5B | 1.45 | 75.7 | 2.57 | 65.9 | 6.83 | 72.4 |

Discussions (0)

none scraped.

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