An error occurs when exporting T5G2PModel to ONNX.

[VoiceGenerationProject]

Describe the bug

An error occurs when exporting T5G2PModel to ONNX.

Steps/Code to reproduce bug

import torch
from transformers import PreTrainedTokenizerBase, AutoTokenizer

from nemo.collections.tts.g2p.models.t5 import T5G2PModel
model_name = "T5G2P.nemo"
model = T5G2PModel.restore_from(model_name, map_location=torch.device("cpu"))
model.eval()

model.export("test.onnx")

[Error]
RuntimeError: 0 INTERNAL ASSERT FAILED at "../torch/csrc/jit/ir/alias_analysis.cpp":615, please report a bug to PyTorch. We don't have an op for aten::full but it isn't a special case. Argument types: int[], bool, int, NoneType, Device, bool,

Candidates:
aten::full.names(int[] size, Scalar fill_value, *, str[]? names, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor
aten::full(SymInt[] size, Scalar fill_value, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor
aten::full.names_out(int[] size, Scalar fill_value, *, str[]? names, Tensor(a!) out) -> Tensor(a!)
aten::full.out(SymInt[] size, Scalar fill_value, *, Tensor(a!) out) -> Tensor(a!)

Environment details

If NVIDIA docker image is used you don't need to specify these.
Otherwise, please provide:

• Ubuntu 20.04
• PyTorch version - 2.3.0+cu118
• Python version - 3.10.12