Hello, I’m trying to compile VITS model (GitHub - jaywalnut310/vits: VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech), I got dimension mismatch I’m not able to identify from which not it is generated, I also tried to compile model dividing into parts, caused following NotImplementedError: Currently the operator ‘gather_nd’ is not supported. Does anyone faced such kind of error, any solution for this??
Model Link: vits.onnx - Google Drive