CosyVoice · Issues· 698 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #1892
CosyVoice3推理加速优化方案：ONNX图优化、TensorRT推理调整、分桶策略与CUDA Graph
Updated Sep 18, 2026 - #1933
cosyvoice3如何利用普通话音色去微调方言模型
staleUpdated Sep 18, 2026 - #1935
这个模型只支持python=3.10么
staleUpdated Sep 18, 2026 - #1946
WER of token2text
Updated Sep 17, 2026 - #1276
求助，下载git模型的Cosyvoice2-0.5B，在comfyui运行后提示缺失文件
staleUpdated Sep 17, 2026 - #1947
https://funaudiollm.github.io/cosyvoice3页面无法打开404
Updated Sep 16, 2026 - #1051
修复cosyvoice2的flow合成前后爆音
Updated Sep 14, 2026 - #1316
利用vllm加速llm模型但是生成的是无意义的噪音
staleUpdated Sep 13, 2026 - #1653
方言微调cosyvoice2求助
Updated Sep 12, 2026 - #1931
RAM Optimize
staleUpdated Sep 12, 2026 - #1932
chat stream issue
staleUpdated Sep 12, 2026 - #1945
License clarification: using Fun-CosyVoice3 outputs to train and sell an independent real-time VC mode
Updated Sep 12, 2026 - #1944
CosyVoice2: is multi-utterance batch (B>1) inference supported or planned?
Updated Sep 10, 2026 - #1103
bistream下2.0模型的zero_shot推理结果会拼接参考音频的结尾到推理结果上，偶尔也会出现开头跳过内容的问题
Updated Sep 9, 2026 - #1308
CosyVoice 2.0 克隆模式下自然语言描述语气功能不工作
staleUpdated Sep 9, 2026