Comments (5)
you need do:
apt update && sudo apt install ffmpeg
pip install ffmpeg-python==0.2.0
from whisper-vits-svc.
is there more detial log info?
from whisper-vits-svc.
is there more detial log info?
it's all the error after running step 4 of data preprocessing
data_svc/waves-16k/
data_svc/whisper
Traceback (most recent call last):
File "prepare/preprocess_ppg.py", line 56, in
whisper = load_model(os.path.join("whisper_pretrain", "medium.pt"))
File "prepare/preprocess_ppg.py", line 25, in load_model
dims = ModelDimensions(**checkpoint["dims"])
TypeError: 'ModuleSpec' object is not callable
from whisper-vits-svc.
your code is different from this project, line 25 is " audln = audio.shape[0]"
from whisper-vits-svc.
your code is different from this project, line 25 is " audln = audio.shape[0]"
oh yes you're right it's different , but i cloned the repo yesterday
i don't know why it's different !
So i copied the code from the file preprocess_ppg.py but i got this error this time :/
data_svc/waves-16k/
data_svc/whisper
speaker0<<<<<<<<<<
Traceback (most recent call last):
File "/home/parisa/so-vits-svc-5.0_/whisper/audio.py", line 44, in load_audio
ffmpeg.input(file, threads=0)
AttributeError: module 'ffmpeg' has no attribute 'input'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "prepare/preprocess_ppg.py", line 58, in
pred_ppg(whisper, f"{wavPath}/{spks}/{file}.wav", f"{ppgPath}/{spks}/{file}.ppg")
File "prepare/preprocess_ppg.py", line 24, in pred_ppg
audio = load_audio(wavPath)
File "/home/parisa/so-vits-svc-5.0_/whisper/audio.py", line 48, in load_audio
except ffmpeg.Error as e:
AttributeError: module 'ffmpeg' has no attribute 'Error'
from whisper-vits-svc.
Related Issues (20)
- 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
- Does anyone know if the whisper-ppg-largev2 or v3 model can train diffusion models and use them? HOT 1
- 歌曲文件进行推理如何保留伴奏呀? 试了一下,貌似只有人声。
- silerovad 在多进程中会卡主
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.