Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如何解决Synthesis text segment too short (12) compared to prompt (46), may affect performance这样的性能问题? #934

Closed
huyyxy opened this issue Jan 26, 2025 · 3 comments
Labels

Comments

@huyyxy
Copy link
Contributor

huyyxy commented Jan 26, 2025

Image 我在运行过程中,会碰到上述告警,如何能提升性能呢? 我的服务器是4060ti的显卡,使用Docker镜像(镜像基模改为了nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04),上图日志是使用了TensorRT,以及fp16。没有使用jit。

另外,描述一下目前我感受到的效果:

  • load_jit=False, load_trt=False, fp16=False:
    RTF基本会大于1;
  • load_jit=False, load_trt=True, fp16=False:
    RTF大部分会小于1,有概率大于1的情况;
  • load_jit=False, load_trt=True, fp16=True:
    RTF会小于1;
  • load_jit=True
    RTF有不小的概率大于2

至于使用ttsfrd还是WeTextProcessing,感觉不到区别。

@huyyxy
Copy link
Contributor Author

huyyxy commented Jan 26, 2025

我目前的需求就是将实时输入的句子,一句一句的传入进来,也需要按照prompt固定音色,因此,输入的句子短于prompt的音频句子的。

Copy link

This issue is stale because it has been open for 30 days with no activity.

@github-actions github-actions bot added the stale label Feb 26, 2025
Copy link

This issue was closed because it has been inactive for 14 days since being marked as stale.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

1 participant