Как преобразовать .pth в .pt (PyTorch.audio) ⇐ Python

[Anonymous]

Я пытаюсь понять, как преобразовать .pth (форматирование предварительно обученной голосовой библиотеки, которую я использую) в .pt (форматирование, читаемое программой C#, с которой я ее запускаю). У меня есть только нашел информацию о torchvision (для преобразования .pth визуальных моделей), поэтому буду очень признателен за любую помощь.
Я не очень хорошо осведомлен о PyTorch, и есть даже меньше документации по PyTorch.audio, так что я немного растерялся.
(Я также знаю, что .pth и .pt по сути одинаковы, но python мешает форматированию .pth).
Редактирование: это было самое близкое, что мне удалось получить, используя примеры torchvision-
pth_file_path = 'FILE/PATH/model.pth'
pt_file_path = 'FILE/PATH/model.pt'

import torch
import torchaudio
from unet import UNet
from zmq import device
model = UNet(3, 2)

model.load_state_dict(torch.load(pth_file_path, map_location=torch.device('cpu')))
model.eval()
example = torch.rand(1, 3, 320, 480)
traced_script_module = torch.jit.trace(model, example)
traced_script_module.save(pt_file_path)

Но выдает ошибку времени выполнения:
model.load_state_dict(torch.load(pth_file_path, map_location=torch.device('cpu')))
Traceback (most recent call last):
File ".\IMPORT.py", line 11, in
model.load_state_dict(torch.load(pth_file_path, map_location=torch.device('cpu')))
File "C:\Users\user\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 2215, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for UNet:
Missing key(s) in state_dict: "encoder.encoding_blocks.0.conv1.conv_layer.weight", "encoder.encoding_blocks.0.conv1.conv_layer.bias", "encoder.encoding_blocks.0.conv1.block.0.weight", "encoder.encoding_blocks.0.conv1.block.0.bias", "encoder.encoding_blocks.0.conv2.conv_layer.weight", "encoder.encoding_blocks.0.conv2.conv_layer.bias", "encoder.encoding_blocks.0.conv2.block.0.weight", "encoder.encoding_blocks.0.conv2.block.0.bias", "encoder.encoding_blocks.1.conv1.conv_layer.weight", "encoder.encoding_blocks.1.conv1.conv_layer.bias", "encoder.encoding_blocks.1.conv1.block.0.weight", "encoder.encoding_blocks.1.conv1.block.0.bias", "encoder.encoding_blocks.1.conv2.conv_layer.weight", "encoder.encoding_blocks.1.conv2.conv_layer.bias", "encoder.encoding_blocks.1.conv2.block.0.weight", "encoder.encoding_blocks.1.conv2.block.0.bias", "encoder.encoding_blocks.2.conv1.conv_layer.weight", "encoder.encoding_blocks.2.conv1.conv_layer.bias", "encoder.encoding_blocks.2.conv1.block.0.weight", "encoder.encoding_blocks.2.conv1.block.0.bias", "encoder.encoding_blocks.2.conv2.conv_layer.weight", "encoder.encoding_blocks.2.conv2.conv_layer.bias", "encoder.encoding_blocks.2.conv2.block.0.weight", "encoder.encoding_blocks.2.conv2.block.0.bias", "encoder.encoding_blocks.3.conv1.conv_layer.weight", "encoder.encoding_blocks.3.conv1.conv_layer.bias", "encoder.encoding_blocks.3.conv1.block.0.weight", "encoder.encoding_blocks.3.conv1.block.0.bias", "encoder.encoding_blocks.3.conv2.conv_layer.weight", "encoder.encoding_blocks.3.conv2.conv_layer.bias", "encoder.encoding_blocks.3.conv2.block.0.weight", "encoder.encoding_blocks.3.conv2.block.0.bias", "bottom_block.conv1.conv_layer.weight", "bottom_block.conv1.conv_layer.bias", "bottom_block.conv1.block.0.weight", "bottom_block.conv1.block.0.bias", "bottom_block.conv2.conv_layer.weight", "bottom_block.conv2.conv_layer.bias", "bottom_block.conv2.block.0.weight", "bottom_block.conv2.block.0.bias", "decoder.decoding_blocks.0.upsample.weight", "decoder.decoding_blocks.0.upsample.bias", "decoder.decoding_blocks.0.conv1.conv_layer.weight", "decoder.decoding_blocks.0.conv1.conv_layer.bias", "decoder.decoding_blocks.0.conv1.block.0.weight", "decoder.decoding_blocks.0.conv1.block.0.bias", "decoder.decoding_blocks.0.conv2.conv_layer.weight", "decoder.decoding_blocks.0.conv2.conv_layer.bias", "decoder.decoding_blocks.0.conv2.block.0.weight", "decoder.decoding_blocks.0.conv2.block.0.bias", "decoder.decoding_blocks.1.upsample.weight", "decoder.decoding_blocks.1.upsample.bias", "decoder.decoding_blocks.1.conv1.conv_layer.weight", "decoder.decoding_blocks.1.conv1.conv_layer.bias", "decoder.decoding_blocks.1.conv1.block.0.weight", "decoder.decoding_blocks.1.conv1.block.0.bias", "decoder.decoding_blocks.1.conv2.conv_layer.weight", "decoder.decoding_blocks.1.conv2.conv_layer.bias", "decoder.decoding_blocks.1.conv2.block.0.weight", "decoder.decoding_blocks.1.conv2.block.0.bias", "decoder.decoding_blocks.2.upsample.weight", "decoder.decoding_blocks.2.upsample.bias", "decoder.decoding_blocks.2.conv1.conv_layer.weight", "decoder.decoding_blocks.2.conv1.conv_layer.bias", "decoder.decoding_blocks.2.conv1.block.0.weight", "decoder.decoding_blocks.2.conv1.block.0.bias", "decoder.decoding_blocks.2.conv2.conv_layer.weight", "decoder.decoding_blocks.2.conv2.conv_layer.bias", "decoder.decoding_blocks.2.conv2.block.0.weight", "decoder.decoding_blocks.2.conv2.block.0.bias", "decoder.decoding_blocks.3.upsample.weight", "decoder.decoding_blocks.3.upsample.bias", "decoder.decoding_blocks.3.conv1.conv_layer.weight", "decoder.decoding_blocks.3.conv1.conv_layer.bias", "decoder.decoding_blocks.3.conv1.block.0.weight", "decoder.decoding_blocks.3.conv1.block.0.bias", "decoder.decoding_blocks.3.conv2.conv_layer.weight", "decoder.decoding_blocks.3.conv2.conv_layer.bias", "decoder.decoding_blocks.3.conv2.block.0.weight", "decoder.decoding_blocks.3.conv2.block.0.bias", "classifier.conv_layer.weight", "classifier.conv_layer.bias", "classifier.block.0.weight", "classifier.block.0.bias".
Unexpected key(s) in state_dict: "weight", "config", "info", "sr", "f0", "version".


Подробнее здесь: https://stackoverflow.com/questions/791 ... orch-audio