Comments (11)
我感觉似乎是由于并行化导致的,因为多次尝试都是在process 2 报错,参见koomri/text-segmentation#1
from so-vits-svc.
在神奇的重装了几次numpy并又重新处理了一下数据之后这个问题莫名的消失了_(:з」∠)_ 新的问题变成了训练速度似乎过于的慢。。。
from so-vits-svc.
你是不是在用 cpu 训练
Generated by koishi-plugin-github.
from so-vits-svc.
你是不是在用 cpu 训练
Generated by koishi-plugin-github.
那倒没有,不过之前gpu看功率确实跑不太满。现在在给numpy降了个级之后似乎有所好转。现在显卡功耗在2/3到3/4左右。。。虽然还是感觉有点慢。6个G的dataset跑一个epoch265秒算是慢吗。
from so-vits-svc.
什么显卡呢,看看显存占用
nvidia-smi
Generated by koishi-plugin-github.
from so-vits-svc.
from so-vits-svc.
哇。。。富哥
训练前打碎音频了么 可以尝试切碎后调大点bs
另外你的训练数据有多少啊
Generated by koishi-plugin-github.
from so-vits-svc.
倒也不是富哥qwq 主要是现在有组织qwq
已经切碎了,现在bs调的小是因为debug
我觉得慢主要是因为同样的参数在隔壁真富哥的4090上一个epoch是70多秒
训练数据的话大概能有4-5小时? (能整出来这么多自己的音频还得感谢以前的缺de老师
from so-vits-svc.
我本人只用过一次sovits。。。 炼了3.4版本原神的几个人物,一张V100的训练速度大概也是180s左右,我觉得是不是你硬盘和内存的问题,读写拉满了,内存不够放?
Generated by koishi-plugin-github.
from so-vits-svc.
看起来这是一个load已经生成的spec文件时出现的错误。
.pt文件本质上是一个压缩包,而这个压缩包之中的文件是序列化的torch实例(类似于Json),载入.pt文件相当于反序列化这个文件中的内容,这里的pickle就是执行这个序列化和反序列化的过程,不过pickle的序列化和反序列化与json不同,json使用了文本文件形式,而pickle使用了二进制形式,读写二进制形式的文件,受到其读取和写入方法的影响较大。所以很有可能是由于相关模块多个版本之间load函数不一致,而你使用的版本与之不匹配导致了这个问题。
from so-vits-svc.
查了一下存储服务器的盘是SAS的。。。4kIO应该是到头了所以速度慢。结案了。。。
from so-vits-svc.
Related Issues (20)
- ValueError: math domain error
- [mps] issue with Apple silicon compatibility HOT 1
- [Help]: 特征检索在webui推理中无法使用 HOT 8
- [Help] Where to download the latest weight? error, emb_g.weight is not in the checkpoint HOT 2
- [Help]: subprocess-exited-with-error HOT 1
- [Bug]: KL散度为负数 HOT 3
- [Bug]: ERROR: Failed building wheel for pyworld on Google Colab HOT 3
- issue about speaker embedding
- dlopen: cannot load any more object with static TLS HOT 1
- [Bug]: HOT 2
- [Bug]:ERROR: During reasoning, the final result cannot be output
- [Bug]: ValueError: array is not C-contiguous When using feature_retrieval 使用特征检索时报错 HOT 1
- [Help]: 是否有支持VITS模型ONNX的计划? HOT 1
- [Help]: 为何扩散模型生成的效果要远好於 sovits 的模型? HOT 3
- [Bug]: new Shallow diffusion bug? HOT 3
- [Bug]: Package conflict with numpy
- [Help]: OOM error on 24 GB GPU upon inference HOT 1
- [Bug]: 4.0下如果数据集过多生成F0会导致爆显存 HOT 10
- [Help]: 如何使用自己的预训练模型 HOT 2
- [Bug]: 中文文件名会出现编码错误 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from so-vits-svc.