Jandown

> 你好，感谢关注~ 因为这版模型是通过续写的方式来做音色克隆的，所以如果Speech prompt有截断的话会发生续写prompt的情况。请尝试调整prompt，或者在修改generation_utils.py第13行SILENCE_DURATION = 0.0的值为0.1，避免生成音频续写prompt被截断的部分。 好的，感谢解答

> > 可以看一下 和 的版本号吗? 这个问题看起来很奇怪。`` flash_attn``transformers `` > > ## 以下是我的环境，最开始transformers 4.53.1，报错，降了版本4.30.0也还是报错 > ## (moss_ttsd) PS D:\AI\Projects\Git\AIAudio\MOSS-TTSD> pip show transformers flash-attn > Name: transformers > Version: 4.30.0 > Summary:...

> Hello , could you look at this patch in the meantime : [#11 (comment)](https://github.com/FotographerAI/ZenCtrl/issues/11#issue-3057249109) 添加了补丁依然报错 AttributeError: Can't get attribute 'PlainAQTLayout' on torchao版本是0.11.0

> sorry for the delay , we are coming back to this by tomorrow with the torchao fixes (it's the main culprit here) Thank you！

> sorry for the delay , we are coming back to this by tomorrow with the torchao fixes (it's the main culprit here) 两天过去了，还没修复吗？

The 50 series graphics card is the latest Blackwell architecture and requires torch2.7+CUDA12.8

对比了0.5，感觉0.7的音色相似度还不如0.5

> Updated the readme . Which ver of Pytorch do you have , we are running with 2.7.0 , didn't came through this error , but it seems you would...

AttributeError: Can't get attribute 'PlainAQTLayout' on

> > I have the same problem models: GFPGANv1.4 / inswapper_128_fp16 > >  > > Try to download the inswapèper_128_fp16 model again from https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/inswapper_128_fp16.onnx and substitute it with the...