RVC-Boss / GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
MIT License
30.22k stars 3.47k forks source link

when i exe onnx model which name is _vits.onnx, i got a error message "Input shape:{1,2,10,1}, requested shape:{1,2,200}" #633

Open xwan07017 opened 5 months ago

xwan07017 commented 5 months ago

I export four onnx model, the first three models is exeing successfully, but when i exeing the fourth one, i got a error message " Non-zero status code returned while running Reshape node. Name:'/vq_model/enc_p/encoder_ssl/attn_layers.0/Reshape_7' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{1,2,10,1}, requested shape:{1,2,200}".

I run the non-onnx model , it can get the result, but run the onnx model, it will get error. please help me! thanks!

obitodaitu commented 4 months ago

我也遇到了,改成cpu推理可以用。