RuntimeError: Unknown qengine

[zoldaten]

tried to run on orange pi 4B ubuntu 18.04 bionic.
Linux orangepi4 4.4.179-rk3399 #2 SMP Thu May 6 10:53:22 CST 2021 aarch64 aarch64 aarch64 GNU/Linux

built everything correctly.
torch==1.10.0
onnx==1.11.0

but have problem with pickle:

Traceback (most recent call last):
  File "/home/orangepi/Desktop/speech/tts/example5.py", line 13, in <module>
    model = torch.package.PackageImporter(local_file).load_pickle("tts_models", "model")
  File "/home/orangepi/.local/lib/python3.6/site-packages/torch/package/package_importer.py", line 249, in load_pickle
    result = unpickler.load()
  File "/usr/lib/python3.6/pickle.py", line 1050, in load
    dispatch[key[0]](self)
  File "/usr/lib/python3.6/pickle.py", line 1091, in load_binpersid
    self.append(self.persistent_load(pid))
  File "/home/orangepi/.local/lib/python3.6/site-packages/torch/package/package_importer.py", line 227, in persistent_load
    loaded_reduces[reduce_id] = func(self, *args)
  File "/home/orangepi/.local/lib/python3.6/site-packages/torch/jit/_script.py", line 349, in unpackage_script_module
    script_module_id,
RuntimeError: Unknown qengine

tried this example:

# V3
import os
import torch

device = torch.device('cpu')
torch.set_num_threads(4)
local_file = 'model.pt'

if not os.path.isfile(local_file):
    torch.hub.download_url_to_file('https://models.silero.ai/models/tts/ru/ru_v3.pt',
                                   local_file)  
model = torch.package.PackageImporter(local_file).load_pickle("tts_models", "model")
model.to(device)

example_text = 'В недрах тундры выдры в г+етрах т+ырят в вёдра ядра кедров.'
sample_rate = 48000
speaker='baya'

audio_paths = model.save_wav(text=example_text,
                             speaker=speaker,
                             sample_rate=sample_rate)

i tried replace standard pickle like that:

pip install pickle5
import pickle5 as pickle

but no result (

[snakers4]

Hi,

This package contains some quantized models (accentor), that do not run without AVX2 instructions (because they are quantized).

Sometimes this helps

We did not target AMD builds explicitly (yet). Maybe in future with ONNX it will be much easier.