Applio icon indicating copy to clipboard operation
Applio copied to clipboard

⌛ · fix mismatch length in 44100.json

Open Tps-F opened this issue 1 year ago • 3 comments

Issue: #428

Tps-F avatar May 12 '24 15:05 Tps-F

That works for you? Because even with your pull request in my case training in 44k doesn't work

aitronz avatar May 15 '24 18:05 aitronz

I know and I'm sorry I forgot to convert it to the draft. I'm just helping Blaise for now-

Tps-F avatar May 16 '24 08:05 Tps-F

  loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
Process Process-1:
Traceback (most recent call last):
  File "C:\Users\X\Downloads\Applio\env\lib\multiprocessing\process.py", line 315, in _bootstrap
    self.run()
  File "C:\Users\X\Downloads\Applio\env\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\X\Downloads\Applio\rvc\train\train.py", line 258, in run
    train_and_evaluate(
  File "C:\Users\X\Downloads\Applio\rvc\train\train.py", line 465, in train_and_evaluate
    loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
  File "C:\Users\X\Downloads\Applio\env\lib\site-packages\torch\nn\functional.py", line 3297, in l1_loss
    expanded_input, expanded_target = torch.broadcast_tensors(input, target)
  File "C:\Users\X\Downloads\Applio\env\lib\site-packages\torch\functional.py", line 73, in broadcast_tensors
    return _VF.broadcast_tensors(tensors)  # type: ignore[attr-defined]
RuntimeError: The size of tensor a (23) must match the size of tensor b (13) at non-singleton dimension 2

blaisewf avatar May 20 '24 15:05 blaisewf