FasoCA

Dummy inputs are tensors of the size as expected by the model but filled with either random values or zeros. Did you manage to complete the onnx conversion? It seems...

@EuphoriaCelestial Much appreciated the reply. I've also been working exclusively in python so far. To get around the lack of torch.bucketize support, one can write a custom onnx operator in...

> I followed my friend's suggestion and hard fix the bucketize like below (this is the else-clause in `get_pitch_embedding` and `get_energy_embedding` ). I dont have deep knowledge in this so...