The stellavoicechanger from sophiefy

stellavoicechanger's Introduction

Hi there 👋

🎓 I'm currently interested in speech synthesis and natural language processing.
😋 I can speak Chinese, English and Japanese.
🍵 I love Chinese Calligraphy!

Some synthesized audio clips

私はソフィーフィで、ただの通りすがりの吸血鬼だ。

intro_ja.webm

Feel free to reach me at:

stellavoicechanger's People

Contributors

Stargazers

Watchers

stellavoicechanger's Issues

Please allow us to train our own models

Hi! I want to train a model with a specific voice. My intent is to make my voice sound like this other voice. I have 15 minutes of audio on this other voice. It is in Brazilian Portuguese (as my voice).

Thank you!

HTTP接口支持

大佬有没有兴趣增加一个HTTP接口支持，在本地启动一个HTTP接口，和这个基于HTTP接口的VST插接相结合，实现DAW里的实时处理
https://github.com/zhaohui8969/VST_NetProcess-

加载模型时报错且无法转换

你好,开发者,

我在加载模型时,log输出一段报错,并且无法转换.

报错:

Welcome to Stella Voice Changer!
Please load models and corresponding configuration files!


Loading models...


Exception in thread 
Thread-3
: 
Traceback (most recent call last): 
File "threading.py", line 973, in _bootstrap_inner 
File "threading.py", line 910, in run 
File "app.py", line 438, in startInference 
File "backend\starganv2\inference.py", line 248, in voice_conversion 

starganv2.inference(source, sid_target)

File "backend\starganv2\inference.py", line 111, in inference 

out = self.generator(source.unsqueeze(1), ref, F0=f0_feat)

File "torch\nn\modules\module.py", line 1130, in _call_impl 

return forward_call(*input, **kwargs)

File "D:\StellaVoiceChanger\backend/starganv2\models_starganv2.py", line 224, in forward 

x = block(x)

File "torch\nn\modules\module.py", line 1130, in _call_impl 

return forward_call(*input, **kwargs)

File "D:\StellaVoiceChanger\backend/starganv2\models_starganv2.py", line 92, in forward 

x = self._shortcut(x) + self._residual(x)

File "D:\StellaVoiceChanger\backend/starganv2\models_starganv2.py", line 74, in _shortcut 

x = self.conv1x1(x)

File "torch\nn\modules\module.py", line 1130, in _call_impl 

return forward_call(*input, **kwargs)

File "torch\nn\modules\conv.py", line 457, in forward 

return self._conv_forward(input, self.weight, self.bias)

File "torch\nn\modules\conv.py", line 453, in _conv_forward 

return F.conv2d(input, weight, bias, self.stride,

RuntimeError
: 
[enforce fail at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\c10\core\impl\alloc_cpu.cpp:81] data. DefaultCPUAllocator: not enough memory: you tried to allocate 291553280 bytes.

Exception in threading.excepthook:

Exception ignored in thread started by
: 
>

Traceback (most recent call last): 
File "threading.py", line 930, in _bootstrap 
File "threading.py", line 975, in _bootstrap_inner 
File "threading.py", line 1257, in invoke_excepthook 
AttributeError
: 
'EmitStr' object has no attribute 'flush'

Exception ignored in sys.unraisablehook
: 


AttributeError
: 
'EmitStr' object has no attribute 'flush'