CosyVoice-300M

Home/Models/FunAudioLLM/CosyVoice-300M

FunAudioLLM/CosyVoice-300M

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-to-speech
root model: FunAudioLLM/CosyVoice-300M
provider: FunAudioLLM
license: apache-2.0
language: zh, en, fr, es, ja, ko, it, ru, de
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 577
likes: 9
created: —
last modified: 2026-05-31T03:09:57+00:00 (2026)
huggingface: https://huggingface.co/FunAudioLLM/CosyVoice-300M
tags: onnxtext-to-speechzhenfresjakoitrudearxiv:2505.17589arxiv:2412.10117arxiv:2407.05407license:apache-2.0region:us

benchmark	category	score	context	conf	evidence
Speaker SIM	speech-tts	75.5	Open-Source	low	`\| Human \| - \| - \| 1.26 \| 75.5 \| 2.14 \| 73.4 \| - \| - \|`
WER	speech-asr	2.14	Open-Source	low	`\| Human \| - \| - \| 1.26 \| 75.5 \| 2.14 \| 73.4 \| - \| - \|`
CER	speech-asr	1.26	Open-Source	low	`\| Human \| - \| - \| 1.26 \| 75.5 \| 2.14 \| 73.4 \| - \| - \|`

none scraped.