VC PROCESSING!!!! EXCEPTION!!! "slow_conv2d_cpu"
from RVC + VC Client
対応：v.1.5.1.15aにダウングレードしたらうごいた
zshVC PROCESSING!!!! EXCEPTION!!! "slow_conv2d_cpu" not implemented for 'Half'
Traceback (most recent call last):
File "voice_changer\VoiceChanger.py", line 197, in on_request
File "voice_changer\RVC\RVC.py", line 277, in inference
File "voice_changer\RVC\RVC.py", line 267, in _pyTorch_inference
File "voice_changer\RVC\custom_vc_infer_pipeline.py", line 149, in pipeline
File "voice_changer\RVC\custom_vc_infer_pipeline.py", line 86, in vc
File "fairseq\models\hubert\hubert.py", line 535, in extract_features
res = self.forward(
File "fairseq\models\hubert\hubert.py", line 437, in forward
features = self.forward_features(source)
File "fairseq\models\hubert\hubert.py", line 392, in forward_features
features = self.feature_extractor(source)
File "torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "fairseq\models\wav2vec\wav2vec2.py", line 895, in forward
x = conv(x)
File "torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "torch\nn\modules\container.py", line 204, in forward
input = module(input)
File "torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "torch\nn\modules\conv.py", line 313, in forward
return self._conv_forward(input, self.weight, self.bias)
File "torch\nn\modules\conv.py", line 309, in _conv_forward
return F.conv1d(input, weight, bias, self.stride,
RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
The error message "slow_conv2d_cpu" not implemented for 'Half' usually occurs when you try to perform convolutional operations on half-precision floating-point numbers (float16 or "Half" in PyTorch) using a CPU...
To solve this issue, you can try either of the following solutions:
Convert your inputs to a higher-precision floating-point format (e.g., float32) before performing the convolution operation.
Use a GPU for your computations instead of a CPU. GPUs are optimized for matrix operations and can handle half-precision floating-point numbers much more efficiently than CPUs.
>v.1.5.1.15b
>
> RVC(Retrieval-based-Voice-Conversion)の軽量化を行いました。精度や応答速度をわずかに落とすことでより低スペックな PC での稼働も可能になりました。
v.1.5.1.15aにしたらうごいた