CasonTsai

Results 16 issues of CasonTsai

大佬,,请问在windows安装遇到这些依赖库问题 ..\src\github.com\go-playground\validator\errors.go:9:2: cannot find package "github.com/go-playground/universal-translator" in any of: E:\CodeTool\Golang\install\src\github.com\go-playground\universal-translator (from $GOROOT) E:\Learn\Go\src\github.com\go-playground\universal-translator (from $GOPATH) ..\src\github.com\go-playground\validator\baked_in.go:23:2: cannot find package "github.com/leodido/go-urn" in any of: E:\CodeTool\Golang\install\src\github.com\leodido\go-urn (from $GOROOT) E:\Learn\Go\src\github.com\leodido\go-urn (from $GOPATH) ..\src\github.com\gmsec\micro\registry\dns_naming_register.go:16:2:...

请问大佬,我从官网下载了arcface loss的模型,然后从自己的数据用arcface loss微调,发现一开始的train acc 为0.00,但是随着训练起来,train acc逐渐上涨,请问这是正常的么?或者说这个大概是什么原因,

Thank you for this excellent work. I would like to know if DEKR is suitable for the task of single key point regression.

![image](https://user-images.githubusercontent.com/18262642/163512017-ad67c08f-e41b-42ec-a797-11b4fa7b0838.png) ![image](https://user-images.githubusercontent.com/18262642/163512037-fe42da35-5f1c-4198-bd7c-192c55a38aff.png) 是native哪块的,我排查下。。

Feel free to ask any kind of questions in the issues page, but please use English since other users may find your questions valuable. **Is your feature request related to...

enhancement

在文本生成语义token阶段,想加速,加了--compile参数,但是出现错误,去掉--compile参数就不会出错 指令如下’python tools/llama/generate.py --text "位于中国广东省深圳市南山区粤海路1006号" --prompt-text "The text corresponding to reference audio" --prompt-tokens "fake.npy" --checkpoint-path "H:\workProject\WorkProject\HangDian\dataSet\x\tts\fish-speech-1.2\checkpoints" --num-samples 2 --compile ‘,产生错误, ![image](https://github.com/user-attachments/assets/274f5e24-bd19-4921-b808-69c02b9717bd) 环境是:pytorch 2.3.1+cu121,gpu:rtx4060ti

it's a great work, is it support that generate the phoneme delayed time sequence ?or is there any tool we can get the phoneme delayed time sequence?

it's a great work, is it support that generate the phoneme delayed time sequence ?or is there any tool we can get the phoneme delayed(duration) time sequence?