Fun-CosyVoice3-0.5B-2512

Home/Models/FunAudioLLM/Fun-CosyVoice3-0.5B-2512

FunAudioLLM/Fun-CosyVoice3-0.5B-2512

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-to-speech
root model: FunAudioLLM/Fun-CosyVoice3-0.5B-2512
provider: FunAudioLLM
license: apache-2.0
language: zh, en, fr, es, ja, ko, it, ru, de
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 26,054
likes: 598
created: —
last modified: 2026-02-03T07:58:17+00:00 (2026)
huggingface: https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512
tags: onnxsafetensorstext-to-speechzhenfresjakoitrudearxiv:2505.17589arxiv:2412.10117arxiv:2407.05407license:apache-2.0region:us

benchmark	category	score	context	conf	evidence
Speaker SIM	speech-tts	78.0	Open-Source	high	`\| Fun-CosyVoice3-0.5B-2512 \| ✅ \| 0.5B \| 1.21 \| 78.0 \| 2.24 \| 71.8 \| 6.71 \| 75.8 \|`
WER	speech-asr	2.24	Open-Source	high	`\| Fun-CosyVoice3-0.5B-2512 \| ✅ \| 0.5B \| 1.21 \| 78.0 \| 2.24 \| 71.8 \| 6.71 \| 75.8 \|`
CER	speech-asr	1.21	Open-Source	high	`\| Fun-CosyVoice3-0.5B-2512 \| ✅ \| 0.5B \| 1.21 \| 78.0 \| 2.24 \| 71.8 \| 6.71 \| 75.8 \|`

none scraped.