Skip to content

提取文本Bert特征5.16it/s,如何提升处理速度 #2364

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

Open
GanziPo opened this issue May 7, 2025 · 1 comment · May be fixed by #2374
Open

提取文本Bert特征5.16it/s,如何提升处理速度 #2364

GanziPo opened this issue May 7, 2025 · 1 comment · May be fixed by #2374

Comments

@GanziPo
Copy link

GanziPo commented May 7, 2025

Image

问题描述:

提取文本Bert特征5.16it/s,如何提升处理速度

配置信息:

device : cuda
is_half : True
version : v2
t2s_weights_path : GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt
vits_weights_path : GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2G2333k.pth
bert_base_path : GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
cnhuhbert_base_path : GPT_SoVITS/pretrained_models/chinese-hubert-base
并行推理模式已开启
分桶处理模式已开启

环境信息:

CPU :Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz
GPU :NVIDIA A2 16GB
MEM :64GB

部署方式:

源码运行

API访问参数:

{
'text': '中国大陆一共有31个省份啦!',
'text_lang': 'zh',
'ref_audio_path': '/tmp/renzhichu_peiqi.wav',
'aux_ref_audio_paths': [],
'prompt_text': '人之初,性本善。性相近,习相远。',
'prompt_lang': 'zh',
'top_k': 5,
'top_p': 1.0,
'temperature': 1.0,
'text_split_method': 'cut0',
'batch_size': 1,
'batch_threshold': 0.75,
'split_bucket': True,
'return_fragment': False,
'speed_factor': 1.0,
'streaming_mode': False,
'seed': -1,
'parallel_infer': True,
'repetition_penalty': 1.35
}

@wakaba0972
Copy link

同我在 #2361 回的,試試調高python.exe的優先順序

@Karyl01 Karyl01 linked a pull request May 12, 2025 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants