Comments (8)
whisper is built-in, do not install it additionally, it will conflict and report an error
set working directory:
export PYTHONPATH=$PWD
from whisper-vits-svc.
whisper is built-in, do not install it additionally, it will conflict and report an error
set working directory:
export PYTHONPATH=$PWD
thank you , it works but another errors happened :
Traceback (most recent call last):
File "prepare/preprocess_ppg.py", line 62, in
pred_ppg(whisper, f"{wavPath}/{spks}/{file}.wav", f"{ppgPath}/{spks}/{file}.ppg")
File "prepare/preprocess_ppg.py", line 34, in pred_ppg
ppg = whisper.encoder(mel.unsqueeze(0)).squeeze().data.cpu().float().numpy()
File "/home/parisa/anaconda3/envs/voice/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in call_impl
return forward_call(*input, **kwargs)
File "/home/parisa/so-vits-svc-5.0/whisper/model.py", line 159, in forward
x = block(x)
File "/home/parisa/anaconda3/envs/voice/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in call_impl
return forward_call(*input, **kwargs)
File "/home/parisa/so-vits-svc-5.0/whisper/model.py", line 124, in forward
x = x + self.attn(self.attn_ln(x), mask=mask, kv_cache=kv_cache)[0]
File "/home/parisa/anaconda3/envs/voice/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in call_impl
return forward_call(*input, **kwargs)
File "/home/parisa/so-vits-svc-5.0/whisper/model.py", line 30, in forward
return super().forward(x.float()).type(x.dtype)
File "/home/parisa/anaconda3/envs/voice/lib/python3.7/site-packages/torch/nn/modules/normalization.py", line 191, in forward
input, self.normalized_shape, self.weight, self.bias, self.eps)
File "/home/parisa/anaconda3/envs/voice/lib/python3.7/site-packages/torch/nn/functional.py", line 2515, in layer_norm
return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: expected scalar type Float but found Half
from whisper-vits-svc.
you need update codes, and need a GPU.
from whisper-vits-svc.
you need update codes, and need a GPU.
i got this error after running the fifth step of inference
Traceback (most recent call last):
File "svc_inference.py", line 169, in
main(args)
File "svc_inference.py", line 51, in main
load_svc_model(args.model, model)
File "svc_inference.py", line 17, in load_svc_model
assert os.path.isfile(checkpoint_path)
AssertionError
from whisper-vits-svc.
do you downward the checkpoint of the model, and set the right path?
from whisper-vits-svc.
do you downward the checkpoint of the model, and set the right path?
Whrere are the checkpoints of the model and how to set them?
from whisper-vits-svc.
in readme
from whisper-vits-svc.
I have downloaded the model and saved it in whisper_pretrain as per readme.
But still getting this error:
#46 (comment)
from whisper-vits-svc.
Related Issues (20)
- Error but show nothing(error). HOT 2
- 推理是是否需要用分离后的人声部分进行推理 HOT 1
- 推理速度如何加快,CPU
- 5分多钟的歌,生成出来只有2分钟左右,这个是什么原因,我使用的是space中的代码 HOT 2
- Pre-training model dataset questions in SO-VITS-SVC 5.0 HOT 1
- 现在需要男歌手翻唱女声的歌曲,使用的是singer0008,因为软件没有变调功能,出来的效果不太行 HOT 2
- 模型训练之后没有best.pt,能否改进?
- 奇怪的问题,GPU推理声音有部分失真,cpu推理正常 HOT 1
- UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weig ht_norm. HOT 3
- 训练的时候GPU利用率较低
- 训练说话模型而非唱歌的问题 HOT 16
- where the Timbre Encode come from? HOT 2
- 怎么把whisper替换掉啊???可以把whisper替换为fast-whisper嘛,为什么替换掉whisper就可以实时语音转换了
- 关于版权方面 HOT 2
- Missing data perturbation code in Data preprocessing. HOT 1
- 如何推理能产出48k的音频?
- 混合说话人参数时仅输出.spk.npy,没有输出模型,混合后的说话人参数怎么用?
- sovits好像会抑制高频数据,导致输出的结果平平的,有没有参数可以调节,达到还原度最高?
- 想修改模型架构为输出48k,不知道训练底模需要成本是多少?作者是用A100 80G训练的吗?7天 80 batch_size HOT 1
- Increasing SVC inference speed HOT 3
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 whisper-vits-svc.